Articles | Volume 24, issue 3
https://doi.org/10.5194/nhess-24-823-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/nhess-24-823-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
08 Mar 2024
Research article |
| 08 Mar 2024
| 08 Mar 2024
Space–time landslide hazard modeling via Ensemble Neural Networks
Ashok Dahal
Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente, P.O. Box 217, Enschede, AE 7500, the Netherlands
Hakan Tanyas
Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente, P.O. Box 217, Enschede, AE 7500, the Netherlands
Cees van Westen
Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente, P.O. Box 217, Enschede, AE 7500, the Netherlands
Mark van der Meijde
Faculty of Geo-Information Science and Earth Observation (ITC), University of Twente, P.O. Box 217, Enschede, AE 7500, the Netherlands
Paul Martin Mai
Physical Science and Engineering (PSE) Division, King Abdullah University of Science and Technology (KAUST), Thuwal 23955-6900, Saudi Arabia
Raphaël Huser
Statistics Program, Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, King Abdullah University of Science and Technology (KAUST), Thuwal 23955-6900, Saudi Arabia
Luigi Lombardo
Physical Science and Engineering (PSE) Division, King Abdullah University of Science and Technology (KAUST), Thuwal 23955-6900, Saudi Arabia
Related authors
No articles found.
Hunter N. Jimenez, Erkan Istanbulluoglu, Tolga Gorum, Thomas A. Stanley, Pukar M. Amatya, Hakan Tanyas, Mehmet C. Demirel, Aykut Akgun, and Deniz Bozkurt
EGUsphere, https://doi.org/10.5194/egusphere-2025-3011, https://doi.org/10.5194/egusphere-2025-3011, 2025
This preprint is open for discussion and under review for Natural Hazards and Earth System Sciences (NHESS).
Short summary
Short summary
After a major earthquake struck near the Türkiye/Syria border in February 2023, a powerful storm brought intense rainfall to the region, triggering additional landslides. We used satellite data and a physics-based model to map probabilistic landslide hazard using both coseismic and hydrologic drivers. We also explored how the sequence of these disasters affected landslide risk. Finally, we offer a method for seasonal forecasting of landslide hazard in at-risk areas using the historic climate.
Fabio Cammarano, Henrique Berger Roisenberg, Alessio Conclave, Islam Fadel, and Mark van der Meijde
Solid Earth, 16, 135–154, https://doi.org/10.5194/se-16-135-2025, https://doi.org/10.5194/se-16-135-2025, 2025
Short summary
Short summary
Sardinia and Corsica separated and have been drifting in the Mediterranean Sea for 35 Myr due to the retreat of the Ionian plate beneath the Tyrrhenian Sea. Using in-house and public data, we measured and interpreted receiver functions based on prior geophysical and petrological studies. Our findings indicate that the islands' ancient continental structure remains mostly unchanged. Alpine orogenesis about 50 million years ago influenced Corsica's crust, enriching it with water-bearing minerals.
Ionut Cristi Nicu, Letizia Elia, Lena Rubensdotter, Hakan Tanyaş, and Luigi Lombardo
Earth Syst. Sci. Data, 15, 447–464, https://doi.org/10.5194/essd-15-447-2023, https://doi.org/10.5194/essd-15-447-2023, 2023
Short summary
Short summary
Thaw slumps and thermo-erosion gullies are cryospheric hazards that are widely encountered in Nordenskiöld Land, the largest and most compact ice-free area of the Svalbard Archipelago. By statistically analysing the landscape characteristics of locations where these processes occurred, we can estimate where they may occur in the future. We mapped 562 thaw slumps and 908 thermo-erosion gullies and used them to create the first multi-hazard susceptibility map in a high-Arctic environment.
Bastian van den Bout, Chenxiao Tang, Cees van Westen, and Victor Jetten
Nat. Hazards Earth Syst. Sci., 22, 3183–3209, https://doi.org/10.5194/nhess-22-3183-2022, https://doi.org/10.5194/nhess-22-3183-2022, 2022
Short summary
Short summary
Natural hazards such as earthquakes, landslides, and flooding do not always occur as stand-alone events. After the 2008 Wenchuan earthquake, a co-seismic landslide blocked a stream in Hongchun. Two years later, a debris flow breached the material, blocked the Min River, and resulted in flooding of a small town. We developed a multi-process model that captures the full cascade. Despite input and process uncertainties, probability of flooding was high due to topography and trigger intensities.
Robert Emberson, Dalia B. Kirschbaum, Pukar Amatya, Hakan Tanyas, and Odin Marc
Nat. Hazards Earth Syst. Sci., 22, 1129–1149, https://doi.org/10.5194/nhess-22-1129-2022, https://doi.org/10.5194/nhess-22-1129-2022, 2022
Short summary
Short summary
Understanding where landslides occur in mountainous areas is critical to support hazard analysis as well as understand landscape evolution. In this study, we present a large compilation of inventories of landslides triggered by rainfall, including several that are described here for the first time. We analyze the topographic characteristics of the landslides, finding consistent relationships for landslide source and deposition areas, despite differences in the inventories' locations.
Nan Wang, Luigi Lombardo, Marj Tonini, Weiming Cheng, Liang Guo, and Junnan Xiong
Nat. Hazards Earth Syst. Sci., 21, 2109–2124, https://doi.org/10.5194/nhess-21-2109-2021, https://doi.org/10.5194/nhess-21-2109-2021, 2021
Short summary
Short summary
This study exploits 66 years of flash flood disasters across China.
The conclusions are as follows. The clustering procedure highlights distinct spatial and temporal patterns of flash flood disasters at different scales. There are distinguished seasonal, yearly and even long-term persistent flash flood behaviors of flash flood disasters. Finally, the decreased duration of clusters in the recent period indicates a possible activation induced by short-duration extreme rainfall events.
Bastian van den Bout, Theo van Asch, Wei Hu, Chenxiao X. Tang, Olga Mavrouli, Victor G. Jetten, and Cees J. van Westen
Geosci. Model Dev., 14, 1841–1864, https://doi.org/10.5194/gmd-14-1841-2021, https://doi.org/10.5194/gmd-14-1841-2021, 2021
Short summary
Short summary
Landslides, debris flows and other types of dense gravity-driven flows threaten livelihoods around the globe. Understanding the mechanics of these flows can be crucial for predicting their behaviour and reducing disaster risk. Numerical models assume that the solids and fluids of the flow are unstructured. The newly presented model captures the internal structure during movement. This important step can lead to more accurate predictions of landslide movement.
Lina Hao, Rajaneesh A., Cees van Westen, Sajinkumar K. S., Tapas Ranjan Martha, Pankaj Jaiswal, and Brian G. McAdoo
Earth Syst. Sci. Data, 12, 2899–2918, https://doi.org/10.5194/essd-12-2899-2020, https://doi.org/10.5194/essd-12-2899-2020, 2020
Short summary
Short summary
Kerala in India was subjected to an extreme rainfall event in the monsoon season of 2018 which triggered extensive floods and landslides. In order to study whether the landslides were related to recent land use changes, we generated an accurate and almost complete landslide inventory based on two existing datasets and the detailed interpretation of images from the Google Earth platform. The final dataset contains 4728 landslides with attributes of land use in 2010 and land use in 2018.
Chenxiao Tang, Xinlei Liu, Yinghua Cai, Cees Van Westen, Yu Yang, Hai Tang, Chengzhang Yang, and Chuan Tang
Nat. Hazards Earth Syst. Sci., 20, 1163–1186, https://doi.org/10.5194/nhess-20-1163-2020, https://doi.org/10.5194/nhess-20-1163-2020, 2020
Short summary
Short summary
Recovering from major earthquakes is a challenge due to a destablized environment. Over 11 years, we monitored a region hit by the Wenchuan earthquake, finding the loss caused by postseismic hazards was more than that caused by the earthquake. The main reason was a rush in reconstruction without proper hazard and risk assessment. It was concluded that postseismic recovery should consider not only spatial but also temporal dynamics of hazards as well as possible interaction among hazards.
Saad Khan, Mark van der Meijde, Harald van der Werff, and Muhammad Shafique
Nat. Hazards Earth Syst. Sci., 20, 399–411, https://doi.org/10.5194/nhess-20-399-2020, https://doi.org/10.5194/nhess-20-399-2020, 2020
Short summary
Short summary
On 8 October 2005 the region of Kashmir was struck by a devastating earthquake of magnitude 7.6. Northern Pakistan and the region of Kashmir were severely damaged. The official death toll according to the Pakistani government was 87 350. It was thought that the terrain could have played a crucial role in the damage caused by the earthquake directly or indirectly. In this article we found that the terrain played a crucial role in intensifying the devastation of the earthquake.
Jianqiang Zhang, Cees J. van Westen, Hakan Tanyas, Olga Mavrouli, Yonggang Ge, Samjwal Bajrachary, Deo Raj Gurung, Megh Raj Dhital, and Narendral Raj Khanal
Nat. Hazards Earth Syst. Sci., 19, 1789–1805, https://doi.org/10.5194/nhess-19-1789-2019, https://doi.org/10.5194/nhess-19-1789-2019, 2019
Short summary
Short summary
The aim of this study is to investigate the differences in the mappable characteristics of earthquake-triggered and rainfall triggered landslides in terms of their frequency–area relationships, spatial distributions and relation with causal factors, as well as to evaluate whether separate susceptibility maps generated for specific landslide size and triggering mechanism are better than a generic landslide susceptibility assessment including all landslide sizes and triggers.
Hugo Cruz-Jiménez, Guotu Li, Paul Martin Mai, Ibrahim Hoteit, and Omar M. Knio
Geosci. Model Dev., 11, 3071–3088, https://doi.org/10.5194/gmd-11-3071-2018, https://doi.org/10.5194/gmd-11-3071-2018, 2018
Short summary
Short summary
One of the most important challenges seismologists and earthquake engineers face is reliably estimating ground motion in an area prone to large damaging earthquakes. This study aimed at better understanding the relationship between characteristics of geological faults (e.g., hypocenter location, rupture size/location, etc.) and resulting ground motion, via statistical analysis of a rupture simulation model. This study provides important insight on ground-motion responses to geological faults.
Chenxiao Tang, Cees J. Van Westen, Hakan Tanyas, and Victor G. Jetten
Nat. Hazards Earth Syst. Sci., 16, 2641–2655, https://doi.org/10.5194/nhess-16-2641-2016, https://doi.org/10.5194/nhess-16-2641-2016, 2016
Short summary
Short summary
Post-seismic landslides highlighted the need for more research to provide critical information for reconstruction. By mapping detailed landslide inventories, our work shows that most of the landslide activities were concentrated within the first 3 years after the earthquake, and they are majorly determined by vegetation regrowth, available volumes of loose materials, and extreme rainfall events. The landslide activity will continue to decay, but it may be halted if extreme rainfall occurs.
Z. C. Aye, M. Jaboyedoff, M. H. Derron, C. J. van Westen, H. Y. Hussin, R. L. Ciurean, S. Frigerio, and A. Pasuto
Nat. Hazards Earth Syst. Sci., 16, 85–101, https://doi.org/10.5194/nhess-16-85-2016, https://doi.org/10.5194/nhess-16-85-2016, 2016
Short summary
Short summary
This paper presents the development and application of a prototype web-GIS tool for risk analysis, in particular for floods and landslides, based on open-source software and web technologies. The aim is to assist experts (risk managers) in analysing the impacts and consequences of a certain hazard event in a considered region, contributing to open-source and research community in natural hazards and risk assessment. The tool is demonstrated using a regional data set of Fella River basin, Italy.
W. T. Yang, M. Wang, N. Kerle, C. J. Van Westen, L. Y. Liu, and P. J. Shi
Nat. Hazards Earth Syst. Sci., 15, 817–825, https://doi.org/10.5194/nhess-15-817-2015, https://doi.org/10.5194/nhess-15-817-2015, 2015
T. Turkington, J. Ettema, C. J. van Westen, and K. Breinl
Nat. Hazards Earth Syst. Sci., 14, 1517–1530, https://doi.org/10.5194/nhess-14-1517-2014, https://doi.org/10.5194/nhess-14-1517-2014, 2014
Related subject area
Landslides and Debris Flows Hazards
Landslide activation during deglaciation in a fjord-dominated landscape: observations from southern Alaska (1984–2022)
Brief communication: Weak correlation between building damage and loss of life from landslides
Comparative analysis of μ(I) and Voellmy-type grain flow rheologies in geophysical mass flows: insights from theoretical and real case studies
Exploring implications of input parameter uncertainties in glacial lake outburst flood (GLOF) modelling results using the modelling code r.avaflow
From rockfall source area identification to susceptibility zonation: a proposed workflow tested on El Hierro (Canary Islands, Spain)
Brief communication: Visualizing uncertainties in landslide susceptibility modelling using bivariate mapping
Constraining landslide frequency across the United States to inform county-level risk reduction
Topographic controls on landslide mobility: modeling hurricane-induced landslide runout and debris-flow inundation in Puerto Rico
Characterizing the scale of regional landslide triggering from storm hydrometeorology
A participatory approach to determine the use of road cut slope design guidelines in Nepal to lessen landslides
An integrated method for assessing vulnerability of buildings caused by debris flows in mountainous areas
Identifying unrecognised risks to life from debris flows
Predicting the thickness of shallow landslides in Switzerland using machine learning
Unraveling landslide failure mechanisms with seismic signal analysis for enhanced pre-survey understanding
The Parraguirre ice-rock avalanche 1987, semi-arid Andes, Chile – A holistic revision
Comparison of conditioning factor classification criteria in large-scale statistically based landslide susceptibility models
Invited perspectives: Integrating hydrologic information into the next generation of landslide early warning systems
Predicting deep-seated landslide displacement on Taiwan's Lushan through the integration of convolutional neural networks and the Age of Exploration-Inspired Optimizer
Limit analysis of earthquake-induced landslides considering two strength envelopes
The vulnerability of buildings to a large-scale debris flow and outburst flood hazard cascade that occurred on 30 August 2020 in Ganluo, southwest China
Optimizing rainfall-triggered landslide thresholds for daily landslide hazard warning in the Three Gorges Reservoir area
Is higher resolution always better? Open-access DEM comparison for Slope Units delineation and regional landslide prediction
Brief communication: Monitoring impending slope failure with very high-resolution spaceborne synthetic aperture radar
Size scaling of large landslides from incomplete inventories
InSAR-informed in situ monitoring for deep-seated landslides: insights from El Forn (Andorra)
Brief Communication: AI-driven rapid landslides mapping following the 2024 Hualien City Earthquake in Taiwan
A coupled hydrological and hydrodynamic modeling approach for estimating rainfall thresholds of debris-flow occurrence
More than one landslide per road kilometer – surveying and modeling mass movements along the Rishikesh–Joshimath (NH-7) highway, Uttarakhand, India
Transformations in Exposure to Debris Flows in Post-Earthquake Sichuan, China
Large-scale assessment of rainfall-induced landslide hazard based on hydrometeorological information: application to Partenio Massif (Italy)
Shaping shallow landslide susceptibility as a function of rainfall events
Temporal clustering of precipitation for detection of potential landslides
Shallow-landslide stability evaluation in loess areas according to the Revised Infinite Slope Model: a case study of the 7.25 Tianshui sliding-flow landslide events of 2013 in the southwest of the Loess Plateau, China
Probabilistic assessment of postfire debris-flow inundation in response to forecast rainfall
Evaluating post-wildfire debris-flow rainfall thresholds and volume models at the 2020 Grizzly Creek Fire in Glenwood Canyon, Colorado, USA
Addressing class imbalance in soil movement predictions
Assessing the impact of climate change on landslides near Vejle, Denmark, using public data
Analysis of three-dimensional slope stability combined with rainfall and earthquake
Assessing landslide damming susceptibility in Central Asia
Assessing locations susceptible to shallow landslide initiation during prolonged intense rainfall in the Lares, Utuado, and Naranjito municipalities of Puerto Rico
Evaluation of debris-flow building damage forecasts
Characteristics of debris-flow-prone watersheds and debris-flow-triggering rainstorms following the Tadpole Fire, New Mexico, USA
Morphological characteristics and conditions of drainage basins contributing to the formation of debris flow fans: an examination of regions with different rock strength using decision tree analysis
Comparison of debris flow observations, including fine-sediment grain size and composition and runout model results, at Illgraben, Swiss Alps
Simulation analysis of 3D stability of a landslide with a locking segment: a case study of the Tizicao landslide in Maoxian County, southwest China
Optimization strategy for flexible barrier structures: investigation and back analysis of a rockfall disaster case in southwestern China
Numerical-model-derived intensity–duration thresholds for early warning of rainfall-induced debris flows in a Himalayan catchment
Slope Unit Maker (SUMak): an efficient and parameter-free algorithm for delineating slope units to improve landslide modeling
Probabilistic Hydrological Estimation of LandSlides (PHELS): global ensemble landslide hazard modelling
A new analytical method for stability analysis of rock blocks with basal erosion in sub-horizontal strata by considering the eccentricity effect
Jane Walden, Mylène Jacquemart, Bretwood Higman, Romain Hugonnet, Andrea Manconi, and Daniel Farinotti
Nat. Hazards Earth Syst. Sci., 25, 2045–2073, https://doi.org/10.5194/nhess-25-2045-2025, https://doi.org/10.5194/nhess-25-2045-2025, 2025
Short summary
Short summary
We studied eight glacier-adjacent landslides in Alaska and found that slope movement increased at four sites as the glacier retreated past the landslide area. Movement at other sites may be due to heavy precipitation or increased glacier thinning, and two sites showed little to no motion. We suggest that landslides near waterbodies may be especially vulnerable to acceleration, which we guess is due to faster retreat rates of water-terminating glaciers and changing water flow in the slope.
Maximillian Van Wyk de Vries, Alexandre Dunant, Amy L. Johnson, Erin L. Harvey, Sihan Li, Katherine Arrell, Jeevan Baniya, Dipak Basnet, Gopi K. Basyal, Nyima Dorjee Bhotia, Simon J. Dadson, Alexander L. Densmore, Tek Bahadur Dong, Mark E. Kincey, Katie Oven, Anuradha Puri, and Nick J. Rosser
Nat. Hazards Earth Syst. Sci., 25, 1937–1942, https://doi.org/10.5194/nhess-25-1937-2025, https://doi.org/10.5194/nhess-25-1937-2025, 2025
Short summary
Short summary
Mapping exposure to landslides is necessary to mitigate risk and reduce vulnerability. In this study, we show that there is a poor correlation between building damage and deaths from landslides, such that the deadliest landslides do not always destroy the most buildings and vice versa. This has important implications for our management of landslide risk.
Yu Zhuang, Brian W. McArdell, and Perry Bartelt
Nat. Hazards Earth Syst. Sci., 25, 1901–1912, https://doi.org/10.5194/nhess-25-1901-2025, https://doi.org/10.5194/nhess-25-1901-2025, 2025
Short summary
Short summary
The experimentally based μ(I) rheology, widely used for gravitational mass flows, is reinterpreted as a Voellmy-type relationship to highlight its link to grain flow theory. Through block modeling and case studies, we establish its equivalence to μ(R) rheology. μ(I) models shear thinning but fails to capture acceleration and deceleration processes and deposit structure. Incorporating fluctuation energy in μ(R) improves accuracy, refining mass flow modeling and revealing practical challenges.
Sonam Rinzin, Stuart Dunning, Rachel Joanne Carr, Ashim Sattar, and Martin Mergili
Nat. Hazards Earth Syst. Sci., 25, 1841–1864, https://doi.org/10.5194/nhess-25-1841-2025, https://doi.org/10.5194/nhess-25-1841-2025, 2025
Short summary
Short summary
We modelled multiple glacial lake outburst flood (GLOF) scenarios (84 simulations) and tested the effect of nine key input parameters on the modelling results using r.avaflow. Our results highlight that GLOF modelling results are subject to uncertainty from the multiple input parameters. The variation in the volume of mass movement entering the lake causes the highest uncertainty in the modelled GLOF, followed by the DEM dataset and the origin of mass movement.
Roberto Sarro, Mauro Rossi, Paola Reichenbach, and Rosa María Mateos
Nat. Hazards Earth Syst. Sci., 25, 1459–1479, https://doi.org/10.5194/nhess-25-1459-2025, https://doi.org/10.5194/nhess-25-1459-2025, 2025
Short summary
Short summary
This study proposes a novel systematic workflow that integrates source area identification, deterministic runout modelling, the classification of runout outputs to derive susceptibility zonation, and robust procedures for validation and comparison. The proposed approach enables the integration and comparison of different modelling, introducing a robust and consistent workflow/methodology that allows us to derive and verify rockfall susceptibility zonation, considering different steps.
Matthias Schlögl, Anita Graser, Raphael Spiekermann, Jasmin Lampert, and Stefan Steger
Nat. Hazards Earth Syst. Sci., 25, 1425–1437, https://doi.org/10.5194/nhess-25-1425-2025, https://doi.org/10.5194/nhess-25-1425-2025, 2025
Short summary
Short summary
Communicating uncertainties is a crucial yet challenging aspect of spatial modelling – especially in applied research, where results inform decisions. In disaster risk reduction, susceptibility maps for natural hazards guide planning and risk assessment, yet their uncertainties are often overlooked. We present a new type of landslide susceptibility map that visualizes both susceptibility and associated uncertainty alongside guidelines for creating such maps using free and open-source software.
Lisa V. Luna, Jacob B. Woodard, Janice L. Bytheway, Gina M. Belair, and Benjamin B. Mirus
EGUsphere, https://doi.org/10.5194/egusphere-2025-947, https://doi.org/10.5194/egusphere-2025-947, 2025
Short summary
Short summary
Landslide frequency (how often landslides occur) is needed to assess landslide hazard and risk but has rarely been quantified at near continental scales. Here, we used statistical models to estimate landslide frequency across the United States while addressing gaps in landslide reporting. Our results showed strong variations in landslide frequency that followed topography, earthquake probability, and ecological region and highlighted areas with potential for widespread landsliding.
Dianne L. Brien, Mark E. Reid, Collin Cronkite-Ratcliff, and Jonathan P. Perkins
Nat. Hazards Earth Syst. Sci., 25, 1229–1253, https://doi.org/10.5194/nhess-25-1229-2025, https://doi.org/10.5194/nhess-25-1229-2025, 2025
Short summary
Short summary
Landslide runout zones are the areas downslope or downstream of landslide initiation. People often live and work in these areas, leading to property damage and deaths. Landslide runout may occur on hillslopes or in channels, requiring different modeling approaches. We develop methods to identify potential runout zones and apply these methods to identify susceptible areas for three municipalities in Puerto Rico.
Jonathan Perkins, Nina S. Oakley, Brian D. Collins, Skye C. Corbett, and W. Paul Burgess
Nat. Hazards Earth Syst. Sci., 25, 1037–1056, https://doi.org/10.5194/nhess-25-1037-2025, https://doi.org/10.5194/nhess-25-1037-2025, 2025
Short summary
Short summary
Rainfall-induced landslides result in deaths and economic losses annually across the globe. However, it is unclear how storm severity relates to landslide severity across large regions. Here we develop a method to dynamically map landslide-affected areas, and we compare this to meteorological estimates of storm severity. We find that preconditioning by earlier storms and the location of rainfall bursts, rather than atmospheric storm strength, dictate landslide magnitude and pattern.
Ellen B. Robson, Bhim Kumar Dahal, and David G. Toll
Nat. Hazards Earth Syst. Sci., 25, 949–973, https://doi.org/10.5194/nhess-25-949-2025, https://doi.org/10.5194/nhess-25-949-2025, 2025
Short summary
Short summary
Slopes excavated alongside roads in Nepal frequently fail (a landslide), resulting in substantial losses. Our participatory approach study with road engineers aimed to assess how road slope design guidelines in Nepal can be improved. Our study revealed inconsistent guideline adherence due to a lack of user-friendliness and inadequate training. We present general recommendations to enhance road slope management, as well as technical recommendations to improve the guidelines.
Chenchen Qiu and Xueyu Geng
Nat. Hazards Earth Syst. Sci., 25, 709–726, https://doi.org/10.5194/nhess-25-709-2025, https://doi.org/10.5194/nhess-25-709-2025, 2025
Short summary
Short summary
We propose an integrated method using a combination of a physical vulnerability matrix and a machine learning model to estimate the potential physical damage and associated economic loss caused by future debris flows based on collected historical data on the Qinghai–Tibet Plateau region.
Mark Bloomberg, Tim Davies, Elena Moltchanova, Tom Robinson, and David Palmer
Nat. Hazards Earth Syst. Sci., 25, 647–656, https://doi.org/10.5194/nhess-25-647-2025, https://doi.org/10.5194/nhess-25-647-2025, 2025
Short summary
Short summary
Debris flows occur infrequently, with average recurrence intervals (ARIs) ranging from decades to millennia. Consequently, they pose an underappreciated hazard. We describe how to make a preliminary identification of debris-flow-susceptible catchments, estimate threshold ARIs for debris flows that pose an unacceptable risk to life, and identify the “window of non-recognition” where debris flows are infrequent enough that their hazard is unrecognised yet frequent enough to pose a risk to life.
Christoph Schaller, Luuk Dorren, Massimiliano Schwarz, Christine Moos, Arie C. Seijmonsbergen, and E. Emiel van Loon
Nat. Hazards Earth Syst. Sci., 25, 467–491, https://doi.org/10.5194/nhess-25-467-2025, https://doi.org/10.5194/nhess-25-467-2025, 2025
Short summary
Short summary
We developed a machine-learning-based approach to predict the potential thickness of shallow landslides to generate improved inputs for slope stability models. We selected 21 explanatory variables, including metrics on terrain, geomorphology, vegetation height, and lithology, and used data from two Swiss field inventories to calibrate and test the models. The best-performing machine learning model consistently reduced the mean average error by at least 20 % compared to previous models.
Jui-Ming Chang, Che-Ming Yang, Wei-An Chao, Chin-Shang Ku, Ming-Wan Huang, Tung-Chou Hsieh, and Chi-Yao Hung
Nat. Hazards Earth Syst. Sci., 25, 451–466, https://doi.org/10.5194/nhess-25-451-2025, https://doi.org/10.5194/nhess-25-451-2025, 2025
Short summary
Short summary
The study on the Cilan landslide (CL) demonstrates the utilization of seismic analysis results as preliminary data for geologists during field surveys. Spectrograms revealed that the first event of CL consisted of four sliding failures accompanied by a gradual reduction in landslide volume. The second and third events were minor toppling and rockfalls. Then combining the seismological-based knowledge and field survey results, the spatiotemporal variation in landslide evolution is proposed.
Johannes Jakob Fürst, David Farías-Barahona, Thomas Bruckner, Lucia Scaff, Martin Mergili, Santiago Montserrat, and Humberto Peña
EGUsphere, https://doi.org/10.5194/egusphere-2024-3103, https://doi.org/10.5194/egusphere-2024-3103, 2025
Short summary
Short summary
The 1987 Parraguirre ice-rock avalanche developed into a devastating debris-flow causing loss of many lives and inflicting severe damage near Santiago, Chile. Here, we revise this event combining various observational records with modelling techniques. In this year, important snow cover coincided with warm days in spring. We further quantify the total solid volume, and forward important upward corrections for the trigger and flood volumes. Finally, river damming was key for high flow mobility.
Marko Sinčić, Sanja Bernat Gazibara, Mauro Rossi, and Snježana Mihalić Arbanas
Nat. Hazards Earth Syst. Sci., 25, 183–206, https://doi.org/10.5194/nhess-25-183-2025, https://doi.org/10.5194/nhess-25-183-2025, 2025
Short summary
Short summary
The paper focuses on classifying continuous landslide conditioning factors for susceptibility modelling, which resulted in 54 landslide susceptibility models that tested 11 classification criteria in combination with 5 statistical methods. The novelty of the research is that using stretched landslide conditioning factor values results in models with higher accuracy and that certain statistical methods are more sensitive to the landslide conditioning factor classification criteria than others.
Benjamin B. Mirus, Thom Bogaard, Roberto Greco, and Manfred Stähli
Nat. Hazards Earth Syst. Sci., 25, 169–182, https://doi.org/10.5194/nhess-25-169-2025, https://doi.org/10.5194/nhess-25-169-2025, 2025
Short summary
Short summary
Early warning of increased landslide potential provides situational awareness to reduce landslide-related losses from major storm events. For decades, landslide forecasts relied on rainfall data alone, but recent research points to the value of hydrologic information for improving predictions. In this paper, we provide our perspectives on the value and limitations of integrating subsurface hillslope hydrologic monitoring data and mathematical modeling for more accurate landslide forecasts.
Jui-Sheng Chou, Hoang-Minh Nguyen, Huy-Phuong Phan, and Kuo-Lung Wang
Nat. Hazards Earth Syst. Sci., 25, 119–146, https://doi.org/10.5194/nhess-25-119-2025, https://doi.org/10.5194/nhess-25-119-2025, 2025
Short summary
Short summary
This study enhances landslide prediction using advanced machine learning, including new algorithms inspired by historical explorations. The research accurately forecasts landslide movements by analyzing 8 years of data from Taiwan's Lushan, improving early warning and potentially saving lives and infrastructure. This integration marks a significant advancement in environmental risk management.
Di Wu, Yuke Wang, and Xin Chen
Nat. Hazards Earth Syst. Sci., 24, 4617–4630, https://doi.org/10.5194/nhess-24-4617-2024, https://doi.org/10.5194/nhess-24-4617-2024, 2024
Short summary
Short summary
This paper proposes a 3D limit analysis for seismic stability of soil slopes to address the influence of earthquakes on slope stabilities with nonlinear and linear criteria. Comparison results illustrate that the use of a linear envelope leads to the non-negligible overestimation of steep-slope stability, and this overestimation will be significant with increasing earthquakes. Earthquakes have a smaller influence on slope slip surfaces with a nonlinear envelope than those with a linear envelope.
Li Wei, Kaiheng Hu, Shuang Liu, Lan Ning, Xiaopeng Zhang, Qiyuan Zhang, and Md. Abdur Rahim
Nat. Hazards Earth Syst. Sci., 24, 4179–4197, https://doi.org/10.5194/nhess-24-4179-2024, https://doi.org/10.5194/nhess-24-4179-2024, 2024
Short summary
Short summary
The damage patterns of the buildings were classified into three types: (I) buried by primary debris flow, (II) inundated by secondary dam-burst flood, and (III) sequentially buried by debris flow and inundated by dam-burst flood. The threshold of the impact pressures in Zones (II) and (III) where vulnerability is equal to 1 is 84 kPa and 116 kPa, respectively. Heavy damage occurs at an impact pressure greater than 50 kPa, while slight damage occurs below 30 kPa.
Bo Peng and Xueling Wu
Nat. Hazards Earth Syst. Sci., 24, 3991–4013, https://doi.org/10.5194/nhess-24-3991-2024, https://doi.org/10.5194/nhess-24-3991-2024, 2024
Short summary
Short summary
Our research enhances landslide prevention using advanced machine learning to forecast heavy-rainfall-triggered landslides. By analyzing regions and employing various models, we identified optimal ways to predict high-risk rainfall events. Integrating multiple factors and models, including a neural network, significantly improves landslide predictions. Real data validation confirms our approach's reliability, aiding communities in mitigating landslide impacts and safeguarding lives and property.
Mahnoor Ahmed, Giacomo Titti, Sebastiano Trevisani, Lisa Borgatti, and Mirko Francioni
Nat. Hazards Earth Syst. Sci. Discuss., https://doi.org/10.5194/nhess-2024-211, https://doi.org/10.5194/nhess-2024-211, 2024
Revised manuscript accepted for NHESS
Short summary
Short summary
Elevation models are compared with a true dataset for terrain characteristics which selects a better ranking model to test with different parameters for partitioning the terrain. The partitioning of the terrain is measured by how well a partitioned unit can support the mapped landslide area and number of landslides. The effect of this relationship is reflected with different metrics in the susceptibility maps.
Andrea Manconi, Yves Bühler, Andreas Stoffel, Johan Gaume, Qiaoping Zhang, and Valentyn Tolpekin
Nat. Hazards Earth Syst. Sci., 24, 3833–3839, https://doi.org/10.5194/nhess-24-3833-2024, https://doi.org/10.5194/nhess-24-3833-2024, 2024
Short summary
Short summary
Our research reveals the power of high-resolution satellite synthetic-aperture radar (SAR) imagery for slope deformation monitoring. Using ICEYE data over the Brienz/Brinzauls instability, we measured surface velocity and mapped the landslide event with unprecedented precision. This underscores the potential of satellite SAR for timely hazard assessment in remote regions and aiding disaster mitigation efforts effectively.
Oliver Korup, Lisa V. Luna, and Joaquin V. Ferrer
Nat. Hazards Earth Syst. Sci., 24, 3815–3832, https://doi.org/10.5194/nhess-24-3815-2024, https://doi.org/10.5194/nhess-24-3815-2024, 2024
Short summary
Short summary
Catalogues of mapped landslides are useful for learning and forecasting how frequently they occur in relation to their size. Yet, rare and large landslides remain mostly uncertain in statistical summaries of these catalogues. We propose a single, consistent method of comparing across different data sources and find that landslide statistics disclose more about subjective mapping choices than trigger types or environmental settings.
Rachael Lau, Carolina Seguí, Tyler Waterman, Nathaniel Chaney, and Manolis Veveakis
Nat. Hazards Earth Syst. Sci., 24, 3651–3661, https://doi.org/10.5194/nhess-24-3651-2024, https://doi.org/10.5194/nhess-24-3651-2024, 2024
Short summary
Short summary
This work examines the use of interferometric synthetic-aperture radar (InSAR) alongside in situ borehole measurements to assess the stability of deep-seated landslides for the case study of El Forn (Andorra). Comparing InSAR with borehole data suggests a key trade-off between accuracy and precision for various InSAR resolutions. Spatial interpolation with InSAR informed how many remote observations are necessary to lower error in a remote sensing re-creation of ground motion over the landslide.
Lorenzo Nava, Alessandro Novellino, Chengyong Fang, Kushanav Bhuyan, Kathryn Leeming, Itahisa Gonzalez Alvarez, Claire Dashwood, Sophie Doward, Rahul Chahel, Emma McAllister, Sansar Raj Meena, and Filippo Catani
Nat. Hazards Earth Syst. Sci. Discuss., https://doi.org/10.5194/nhess-2024-146, https://doi.org/10.5194/nhess-2024-146, 2024
Revised manuscript accepted for NHESS
Short summary
Short summary
On April 2, 2024, a Mw 7.4 earthquake hit Taiwan’s eastern coast, causing extensive landslides and damage. We used automated methods combining Earth Observation (EO) data with Artificial Intelligence (AI) to quickly inventory the landslides. This approach identified 7,090 landslides over 75 km2 within 3 hours of acquiring the EO imagery. The study highlights AI’s role in improving landslide detection and understanding earthquake-landslide interactions for better hazard mitigation.
Zhen Lei Wei, Yue Quan Shang, Qiu Hua Liang, and Xi Lin Xia
Nat. Hazards Earth Syst. Sci., 24, 3357–3379, https://doi.org/10.5194/nhess-24-3357-2024, https://doi.org/10.5194/nhess-24-3357-2024, 2024
Short summary
Short summary
The initiation of debris flows is significantly influenced by rainfall-induced hydrological processes. We propose a novel framework based on an integrated hydrological and hydrodynamic model and aimed at estimating intensity–duration (ID) rainfall thresholds responsible for triggering debris flows. In comparison to traditional statistical approaches, this physically based framework is particularly suitable for application in ungauged catchments where historical debris flow data are scarce.
Jürgen Mey, Ravi Kumar Guntu, Alexander Plakias, Igo Silva de Almeida, and Wolfgang Schwanghart
Nat. Hazards Earth Syst. Sci., 24, 3207–3223, https://doi.org/10.5194/nhess-24-3207-2024, https://doi.org/10.5194/nhess-24-3207-2024, 2024
Short summary
Short summary
The Himalayan road network links remote areas, but fragile terrain and poor construction lead to frequent landslides. This study on the NH-7 in India's Uttarakhand region analyzed 300 landslides after heavy rainfall in 2022 . Factors like slope, rainfall, rock type and road work influence landslides. The study's model predicts landslide locations for better road maintenance planning, highlighting the risk from climate change and increased road use.
Isabelle Utley, Tristram Hales, Ekbal Hussain, and Xuanmei Fan
EGUsphere, https://doi.org/10.5194/egusphere-2024-2277, https://doi.org/10.5194/egusphere-2024-2277, 2024
Short summary
Short summary
We analysed debris flows in Sichuan, China, using satellite data and simulations to assess check dam efficacy. Our study found whilst check dams can mitigate smaller flows, they may increase exposure to extreme events, with up to 40 % of structures in some areas affected. Urban development and reliance on check dams can create a false sense of security, raising exposure during large debris flows and highlights the need for risk management and infrastructure planning in hazard-prone areas.
Daniel Camilo Roman Quintero, Pasquale Marino, Abdullah Abdullah, Giovanni Francesco Santonastaso, and Roberto Greco
EGUsphere, https://doi.org/10.5194/egusphere-2024-2329, https://doi.org/10.5194/egusphere-2024-2329, 2024
Short summary
Short summary
Local thresholds for landslide forecasting, combining hydrologic predisposing factors and rainfall features, are developed from a physically based model of a slope. To extend their application to a wide area, uncertainty due to spatial variability of geomorphological and hydrologic variables is introduced. The obtained hydrometeorological thresholds, integrating root zone soil moisture and aquifer water level with rainfall depth, outperform thresholds based on rain intensity and duration.
Micol Fumagalli, Alberto Previati, Paolo Frattini, and Giovanni B. Crosta
Nat. Hazards Earth Syst. Sci. Discuss., https://doi.org/10.5194/nhess-2024-140, https://doi.org/10.5194/nhess-2024-140, 2024
Revised manuscript accepted for NHESS
Short summary
Short summary
Shallow landslides are mass movements of limited thickness, mainly triggered by extreme rainfalls, that can pose a serious risk to the population. This study uses statistical methods to analyse and simulate the relationship between shallow landslides and rainfalls, showing that in the studied area shallow landslides are modulated by rainfall but controlled by lithology. A new classification method considering the costs associated with a misclassification of the susceptibility is also proposed.
Fabiola Banfi, Emanuele Bevacqua, Pauline Rivoire, Sérgio C. Oliveira, Joaquim G. Pinto, Alexandre M. Ramos, and Carlo De Michele
Nat. Hazards Earth Syst. Sci., 24, 2689–2704, https://doi.org/10.5194/nhess-24-2689-2024, https://doi.org/10.5194/nhess-24-2689-2024, 2024
Short summary
Short summary
Landslides are complex phenomena causing important impacts in vulnerable areas, and they are often triggered by rainfall. Here, we develop a new approach that uses information on the temporal clustering of rainfall, i.e. multiple events close in time, to detect landslide events and compare it with the use of classical empirical rainfall thresholds, considering as a case study the region of Lisbon, Portugal. The results could help to improve the prediction of rainfall-triggered landslides.
Jianqi Zhuang, Jianbing Peng, Chenhui Du, Yi Zhu, and Jiaxu Kong
Nat. Hazards Earth Syst. Sci., 24, 2615–2631, https://doi.org/10.5194/nhess-24-2615-2024, https://doi.org/10.5194/nhess-24-2615-2024, 2024
Short summary
Short summary
The Revised Infinite Slope Model (RISM) is proposed using the equal differential unit method and correcting the deficiency of the safety factor increasing with the slope increasing when the slope is larger than 40°, as calculated using the Taylor slope infinite model. The intensity–duration (I–D) prediction curve of the rainfall-induced shallow loess landslides with different slopes was constructed and can be used in forecasting regional shallow loess landslides.
Alexander B. Prescott, Luke A. McGuire, Kwang-Sung Jun, Katherine R. Barnhart, and Nina S. Oakley
Nat. Hazards Earth Syst. Sci., 24, 2359–2374, https://doi.org/10.5194/nhess-24-2359-2024, https://doi.org/10.5194/nhess-24-2359-2024, 2024
Short summary
Short summary
Fire can dramatically increase the risk of debris flows to downstream communities with little warning, but hazard assessments have not traditionally included estimates of inundation. We unify models developed by the scientific community to create probabilistic estimates of inundation area in response to rainfall at forecast lead times (≥ 24 h) needed for decision-making. This work takes an initial step toward a near-real-time postfire debris-flow inundation hazard assessment product.
Francis K. Rengers, Samuel Bower, Andrew Knapp, Jason W. Kean, Danielle W. vonLembke, Matthew A. Thomas, Jaime Kostelnik, Katherine R. Barnhart, Matthew Bethel, Joseph E. Gartner, Madeline Hille, Dennis M. Staley, Justin K. Anderson, Elizabeth K. Roberts, Stephen B. DeLong, Belize Lane, Paxton Ridgway, and Brendan P. Murphy
Nat. Hazards Earth Syst. Sci., 24, 2093–2114, https://doi.org/10.5194/nhess-24-2093-2024, https://doi.org/10.5194/nhess-24-2093-2024, 2024
Short summary
Short summary
Every year the U.S. Geological Survey produces 50–100 postfire debris-flow hazard assessments using models for debris-flow likelihood and volume. To refine these models they must be tested with datasets that clearly document rainfall, debris-flow response, and debris-flow volume. These datasets are difficult to obtain, but this study developed and analyzed a postfire dataset with more than 100 postfire storm responses over a 2-year period. We also proposed ways to improve these models.
Praveen Kumar, Priyanka Priyanka, Kala Venkata Uday, and Varun Dutt
Nat. Hazards Earth Syst. Sci., 24, 1913–1928, https://doi.org/10.5194/nhess-24-1913-2024, https://doi.org/10.5194/nhess-24-1913-2024, 2024
Short summary
Short summary
Our study focuses on predicting soil movement to mitigate landslide risks. We develop machine learning models with oversampling techniques to address the class imbalance in monitoring data. The dynamic ensemble model with K-means SMOTE (synthetic minority oversampling technique) achieves high precision, high recall, and a high F1 score. Our findings highlight the potential of these models with oversampling techniques to improve soil movement predictions in landslide-prone areas.
Kristian Svennevig, Julian Koch, Marie Keiding, and Gregor Luetzenburg
Nat. Hazards Earth Syst. Sci., 24, 1897–1911, https://doi.org/10.5194/nhess-24-1897-2024, https://doi.org/10.5194/nhess-24-1897-2024, 2024
Short summary
Short summary
In our study, we analysed publicly available data in order to investigate the impact of climate change on landslides in Denmark. Our research indicates that the rising groundwater table due to climate change will result in an increase in landslide activity. Previous incidents of extremely wet winters have caused damage to infrastructure and buildings due to landslides. This study is the first of its kind to exclusively rely on public data and examine landslides in Denmark.
Jiao Wang, Zhangxing Wang, Guanhua Sun, and Hongming Luo
Nat. Hazards Earth Syst. Sci., 24, 1741–1756, https://doi.org/10.5194/nhess-24-1741-2024, https://doi.org/10.5194/nhess-24-1741-2024, 2024
Short summary
Short summary
With a simplified formula linking rainfall and groundwater level, the rise of the phreatic surface within the slope can be obtained. Then, a global analysis method that considers both seepage and seismic forces is proposed to determine the safety factor of slopes subjected to the combined effect of rainfall and earthquakes. By taking a slope in the Three Gorges Reservoir area as an example, the safety evolution of the slope combined with both rainfall and earthquake is also examined.
Carlo Tacconi Stefanelli, William Frodella, Francesco Caleca, Zhanar Raimbekova, Ruslan Umaraliev, and Veronica Tofani
Nat. Hazards Earth Syst. Sci., 24, 1697–1720, https://doi.org/10.5194/nhess-24-1697-2024, https://doi.org/10.5194/nhess-24-1697-2024, 2024
Short summary
Short summary
Central Asia regions are marked by active tectonics, high mountains with glaciers, and strong rainfall. These predisposing factors make large landslides a serious threat in the area and a source of possible damming scenarios, which endanger the population. To prevent this, a semi-automated geographic information system (GIS-)based mapping method, centered on a bivariate correlation of morphometric parameters, was applied to give preliminary information on damming susceptibility in Central Asia.
Rex L. Baum, Dianne L. Brien, Mark E. Reid, William H. Schulz, and Matthew J. Tello
Nat. Hazards Earth Syst. Sci., 24, 1579–1605, https://doi.org/10.5194/nhess-24-1579-2024, https://doi.org/10.5194/nhess-24-1579-2024, 2024
Short summary
Short summary
We mapped potential for heavy rainfall to cause landslides in part of the central mountains of Puerto Rico using new tools for estimating soil depth and quasi-3D slope stability. Potential ground-failure locations correlate well with the spatial density of landslides from Hurricane Maria. The smooth boundaries of the very high and high ground-failure susceptibility zones enclose 75 % and 90 %, respectively, of observed landslides. The maps can help mitigate ground-failure hazards.
Katherine R. Barnhart, Christopher R. Miller, Francis K. Rengers, and Jason W. Kean
Nat. Hazards Earth Syst. Sci., 24, 1459–1483, https://doi.org/10.5194/nhess-24-1459-2024, https://doi.org/10.5194/nhess-24-1459-2024, 2024
Short summary
Short summary
Debris flows are a type of fast-moving landslide that start from shallow landslides or during intense rain. Infrastructure located downstream of watersheds susceptible to debris flows may be damaged should a debris flow reach them. We present and evaluate an approach to forecast building damage caused by debris flows. We test three alternative models for simulating the motion of debris flows and find that only one can forecast the correct number and spatial pattern of damaged buildings.
Luke A. McGuire, Francis K. Rengers, Ann M. Youberg, Alexander N. Gorr, Olivia J. Hoch, Rebecca Beers, and Ryan Porter
Nat. Hazards Earth Syst. Sci., 24, 1357–1379, https://doi.org/10.5194/nhess-24-1357-2024, https://doi.org/10.5194/nhess-24-1357-2024, 2024
Short summary
Short summary
Runoff and erosion increase after fire, leading to a greater likelihood of floods and debris flows. We monitored debris flow activity following a fire in western New Mexico, USA, and observed 16 debris flows over a <2-year monitoring period. Rainstorms with recurrence intervals of approximately 1 year were sufficient to initiate debris flows. All debris flows initiated during the first several months following the fire, indicating a rapid decrease in debris flow susceptibility over time.
Ken'ichi Koshimizu, Satoshi Ishimaru, Fumitoshi Imaizumi, and Gentaro Kawakami
Nat. Hazards Earth Syst. Sci., 24, 1287–1301, https://doi.org/10.5194/nhess-24-1287-2024, https://doi.org/10.5194/nhess-24-1287-2024, 2024
Short summary
Short summary
Morphological conditions of drainage basins that classify the presence or absence of debris flow fans were analyzed in areas with different rock strength using decision tree analysis. The relief ratio is the most important morphological factor regardless of the geology. However, the thresholds of morphological parameters needed for forming debris flow fans differ depending on the geology. Decision tree analysis is an effective tool for evaluating the debris flow risk for each geology.
Daniel Bolliger, Fritz Schlunegger, and Brian W. McArdell
Nat. Hazards Earth Syst. Sci., 24, 1035–1049, https://doi.org/10.5194/nhess-24-1035-2024, https://doi.org/10.5194/nhess-24-1035-2024, 2024
Short summary
Short summary
We analysed data from the Illgraben debris flow monitoring station, Switzerland, and we modelled these flows with a debris flow runout model. We found that no correlation exists between the grain size distribution, the mineralogical composition of the matrix, and the debris flow properties. The flow properties rather appear to be determined by the flow volume, from which most other parameters can be derived.
Yuntao Zhou, Xiaoyan Zhao, Guangze Zhang, Bernd Wünnemann, Jiajia Zhang, and Minghui Meng
Nat. Hazards Earth Syst. Sci., 24, 891–906, https://doi.org/10.5194/nhess-24-891-2024, https://doi.org/10.5194/nhess-24-891-2024, 2024
Short summary
Short summary
We developed three rock bridge models to analyze 3D stability and deformation behaviors of the Tizicao landslide and found that the contact surface model with high strength parameters combines advantages of the intact rock mass model in simulating the deformation of slopes with rock bridges and the modeling advantage of the Jennings model. The results help in choosing a rock bridge model to simulate landslide stability and reveal the influence laws of rock bridges on the stability of landslides.
Li-Ru Luo, Zhi-Xiang Yu, Li-Jun Zhang, Qi Wang, Lin-Xu Liao, and Li Peng
Nat. Hazards Earth Syst. Sci., 24, 631–649, https://doi.org/10.5194/nhess-24-631-2024, https://doi.org/10.5194/nhess-24-631-2024, 2024
Short summary
Short summary
We performed field investigations on a rockfall near Jiguanshan National Forest Park, Chengdu. Vital information was obtained from an unmanned aerial vehicle survey. A finite element model was created to reproduce the damage evolution. We found that the impact kinetic energy was below the design protection energy. Improper member connections prevent the barrier from producing significant deformation to absorb energy. Damage is avoided by improving the ability of the nets and ropes to slide.
Sudhanshu Dixit, Srikrishnan Siva Subramanian, Piyush Srivastava, Ali P. Yunus, Tapas Ranjan Martha, and Sumit Sen
Nat. Hazards Earth Syst. Sci., 24, 465–480, https://doi.org/10.5194/nhess-24-465-2024, https://doi.org/10.5194/nhess-24-465-2024, 2024
Short summary
Short summary
Rainfall intensity–duration (ID) thresholds can aid in the prediction of natural hazards. Large-scale sediment disasters like landslides, debris flows, and flash floods happen frequently in the Himalayas because of their propensity for intense precipitation events. We provide a new framework that combines the Weather Research and Forecasting (WRF) model with a regionally distributed numerical model for debris flows to analyse and predict intense rainfall-induced landslides in the Himalayas.
Jacob B. Woodard, Benjamin B. Mirus, Nathan J. Wood, Kate E. Allstadt, Benjamin A. Leshchinsky, and Matthew M. Crawford
Nat. Hazards Earth Syst. Sci., 24, 1–12, https://doi.org/10.5194/nhess-24-1-2024, https://doi.org/10.5194/nhess-24-1-2024, 2024
Short summary
Short summary
Dividing landscapes into hillslopes greatly improves predictions of landslide potential across landscapes, but their scaling is often arbitrarily set and can require significant computing power to delineate. Here, we present a new computer program that can efficiently divide landscapes into meaningful slope units scaled to best capture landslide processes. The results of this work will allow an improved understanding of landslide potential and can help reduce the impacts of landslides worldwide.
Anne Felsberg, Zdenko Heyvaert, Jean Poesen, Thomas Stanley, and Gabriëlle J. M. De Lannoy
Nat. Hazards Earth Syst. Sci., 23, 3805–3821, https://doi.org/10.5194/nhess-23-3805-2023, https://doi.org/10.5194/nhess-23-3805-2023, 2023
Short summary
Short summary
The Probabilistic Hydrological Estimation of LandSlides (PHELS) model combines ensembles of landslide susceptibility and of hydrological predictor variables to provide daily, global ensembles of hazard for hydrologically triggered landslides. Testing different hydrological predictors showed that the combination of rainfall and soil moisture performed best, with the lowest number of missed and false alarms. The ensemble approach allowed the estimation of the associated prediction uncertainty.
Xushan Shi, Bo Chai, Juan Du, Wei Wang, and Bo Liu
Nat. Hazards Earth Syst. Sci., 23, 3425–3443, https://doi.org/10.5194/nhess-23-3425-2023, https://doi.org/10.5194/nhess-23-3425-2023, 2023
Short summary
Short summary
A 3D stability analysis method is proposed for biased rockfall with external erosion. Four failure modes are considered according to rockfall evolution processes, including partial damage of underlying soft rock and overall failure of hard rock blocks. This method is validated with the biased rockfalls in the Sichuan Basin, China. The critical retreat ratio from low to moderate rockfall susceptibility is 0.33. This method could facilitate rockfall early identification and risk mitigation.
Cited articles
Abraham, N. and Khan, N. M.: A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation, CoRR, abs/1810.07842, arXiv [preprint], https://doi.org/10.48550/arXiv.1810.07842, 2018. a, b
Alvioli, M., Marchesini, I., Reichenbach, P., Rossi, M., Ardizzone, F., Fiorucci, F., and Guzzetti, F.: Automatic delineation of geomorphological slope units with <tt>r.slopeunits v1.0</tt> and their optimization for landslide susceptibility modeling, Geosci. Model Dev., 9, 3975–3991, https://doi.org/10.5194/gmd-9-3975-2016, 2016. a
Amit, S. N. K. B. and Aoki, Y.: Disaster detection from aerial imagery with convolutional neural network, in: 2017 international electronics symposium on knowledge creation and intelligent computing (IES-KCIC), Surabaya, Indonesia, 26–27 September, IEEE, 239–245, https://doi.org/10.1109/KCIC.2017.8228593, 2017. a
Ardizzone, F., Cardinali, M., Carrara, A., Guzzetti, F., and Reichenbach, P.: Impact of mapping errors on the reliability of landslide hazard maps, Nat. Hazards Earth Syst. Sci., 2, 3–14, https://doi.org/10.5194/nhess-2-3-2002, 2002. a
Bout, B., Lombardo, L., van Westen, C., and Jetten, V.: Integration of two-phase solid fluid equations in a catchment model for flashfloods, debris flows and shallow slope failures, Environ. Modell. Softw., 105, 1–16, https://doi.org/10.1016/j.envsoft.2018.03.017, 2018. a
Brenning, A.: Statistical geocomputing combining R and SAGA: The example of landslide susceptibility analysis with generalized additive models, Hamburger Beiträge zur Physischen Geographie und Landschaftsökologie, 19, 23–32, 2008. a
Brock, J., Schratz, P., Petschko, H., Muenchow, J., Micu, M., and Brenning, A.: The performance of landslide susceptibility models critically depends on the quality of digital elevation models, Geomat. Nat. Haz. Risk, 11, 1075–1092, 2020. a
Burton, A. and Bathurst, J.: Physically based modelling of shallow landslide sediment yield at a catchment scale, Environ. Geol., 35, 89–99, 1998. a
Catani, F.: Landslide detection by deep learning of non-nadiral and crowdsourced optical images, Landslides, 18, 1025–1044, 2021. a
Catani, F., Casagli, N., Ermini, L., Righini, G., and Menduni, G.: Landslide hazard and risk mapping at catchment scale in the Arno River basin, Landslides, 2, 329–342, 2005. a
Catani, F., Tofani, V., and Lagomarsino, D.: Spatial patterns of landslide dimension: a tool for magnitude mapping, Geomorphology, 273, 361–373, 2016. a
Cisneros, D., Richards, J., Dahal, A., Lombardo, L., and Huser, R.: Deep graphical regression for jointly moderate and extreme Australian wildfires, arXiv [preprint], arXiv:2308.14547, 2023. a
Clinton, B. D.: Light, temperature, and soil moisture responses to elevation, evergreen understory, and small canopy gaps in the southern Appalachians, Forest Ecol. Manag., 186, 243–255, 2003. a
Corominas, J., van Westen, C., Frattini, P., Cascini, L., Malet, J.-P., Fotopoulou, S., Catani, F., Van Den Eeckhaut, M., Mavrouli, O., Agliardi, F., Pitilakis, K., Winter, M. G., Pastor, M., Ferlisi, S., Tofani, V., Hervás, J., and Smith, J. T.: Recommendations for the quantitative analysis of landslide risk, B. Eng. Geol. Environ., 73, 209–263, 2014. a
Dahal, A., Castro-Cruz, D. A., Tanyaş, H., Fadel, I., Mai, P. M., van der Meijde, M., van Westen, C., Huser, R., and Lombardo, L.: From ground motion simulations to landslide occurrence prediction, Geomorphology, 441, 108898, 2023. a
Dahal, A.: ashokdahal/LandslideHazard: v1.0.0, Zenodo [data set and code], https://doi.org/10.5281/zenodo.10765925, 2024.
Davison, A. and Huser, R.: Statistics of Extremes, Annu. Rev. Stat. Appl., 2, 203–235, https://doi.org/10.1146/annurev-statistics-010814-020133, 2015. a
Dhital, M. R.: An overview of landslide hazard mapping and rating systems in Nepal, Journal of Nepal Geological Society, 22, 533–538, 2000. a
Di Napoli, M., Tanyas, H., Castro-Camilo, D., Calcaterra, D., Cevasco, A., Di Martire, D., Pepe, G., Brandolini, P., and Lombardo, L.: On the estimation of landslide intensity, hazard and density via data-driven models, Nat. Hazards, 119, 1513–1530, 2023. a
Fan, X., Scaringi, G., Korup, O., West, A. J., van Westen, C. J., Tanyas, H., Hovius, N., Hales, T. C., Jibson, R. W., Allstadt, K. E., and Zhang, L.: Earthquake-Induced Chains of Geologic Hazards: Patterns, Mechanisms, and Impacts, Rev. Geophys., 57, 421–503, 2019. a
Fang, Z., Wang, Y., van Westen, C., and Lombardo, L.: Space–Time Landslide Susceptibility Modeling Based on Data-Driven Methods, Math. Geosci., 55, 1–20, 2023. a
Fawcett, T.: An introduction to ROC analysis, Pattern Recogn. Lett., 27, 861–874, https://doi.org/10.1016/j.patrec.2005.10.010, 2006. a
Fell, R., Corominas, J., Bonnard, C., Cascini, L., Leroi, E., and Savage, W. Z.: Guidelines for landslide susceptibility, hazard and risk zoning for land-use planning, Eng. Geol., 102, 99–111, 2008. a
Formetta, G., Capparelli, G., and Versace, P.: Evaluating performance of simplified physically based models for shallow landslide susceptibility, Hydrol. Earth Syst. Sci., 20, 4585–4603, https://doi.org/10.5194/hess-20-4585-2016, 2016. a
Frattini, P., Crosta, G., and Carrara, A.: Techniques for evaluating the performance of landslide susceptibility models, Eng. Geol., 111, 62–72, https://doi.org/10.1016/j.enggeo.2009.12.004, 2010. a
Ghorbanzadeh, O., Meena, S. R., Abadi, H. S. S., Piralilou, S. T., Zhiyong, L., and Blaschke, T.: Landslide Mapping Using Two Main Deep-Learning Convolution Neural Network Streams Combined by the Dempster–Shafer Model, IEEE J. Sel. Top. Appl., 14, 452–463, 2020. a
Glenn, N. F., Streutker, D. R., Chadwick, D. J., Thackray, G. D., and Dorsch, S. J.: Analysis of LiDAR-derived topographic information for characterizing and differentiating landslide morphology and activity, Geomorphology, 73, 131–148, 2006. a
Glorot, X. and Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks, in: Proceedings of the thirteenth international conference on artificial intelligence and statistics, JMLR Workshop and Conference Proceedings, Sardinia, Italy, 13–15 May 2010, 249–256, https://proceedings.mlr.press/v9/glorot10a.html (last access: 2 March 2024), 2010. a
Gomez, H. and Kavzoglu, T.: Assessment of shallow landslide susceptibility using artificial neural networks in Jabonosa River Basin, Venezuela, Eng. Geol., 78, 11–27, 2005. a
Grelle, G., Soriano, M., Revellino, P., Guerriero, L., Anderson, M., Diambra, A., Fiorillo, F., Esposito, L., Diodato, N., and Guadagno, F.: Space–time prediction of rainfall-induced shallow landslides through a combined probabilistic/deterministic approach, optimized for initial water table conditions, Bull. Eng. Geol. Environ., 73, 877–890, 2014. a
Guzzetti, F., Carrara, A., Cardinali, M., and Reichenbach, P.: Landslide Hazard Evaluation: A Review of Current Techniques and Their Application in a Multi-Scale Study, Central Italy, Geomorphology, 31, 181–216, https://doi.org/10.1016/S0169-555X(99)00078-1, 1999. a, b, c, d
Guzzetti, F., Cardinali, M., Reichenbach, P., and Carrara, A.: Comparing Landslide Maps: A Case Study in the Upper Tiber River Basin, Central Italy, Environ. Manage., 25, 247–263, https://doi.org/10.1007/s002679910020, 00000, 2000. a
He, K., Zhang, X., Ren, S., and Sun, J.: Deep Residual Learning for Image Recognition, CoRR, abs/1512.03385, arXiv [preprint], http://arxiv.org/abs/1512.03385 (last access: 2 March 2024), 2015. a
Horton, J. B.: Parametric insurance as an alternative to liability for compensating climate harms, Carbon & Climate Law Review, 12, 285–296, 2018. a
Hosmer, D. W. and Lemeshow, S.: Applied Logistic Regression, 2nd ed. edn., Wiley, New York, https://doi.org/10.1002/9781118548387, 2000. a, b
Hough, S. E., Martin, S. S., Gahalaut, V., Joshi, A., Landes, M., and Bossu, R.: A comparison of observed and predicted ground motions from the 2015 Mw 7.8 Gorkha, Nepal, earthquake, Nat. Hazards, 84, 1661–1684, 2016. a
Huang, Y., Tang, Z., Chen, D., Su, K., and Chen, C.: Batching soft IoU for training semantic segmentation networks, IEEE Signal Proc. Let., 27, 66–70, 2019. a
Intrieri, E., Gigli, G., Mugnai, F., Fanti, R., and Casagli, N.: Design and implementation of a landslide early warning system, Eng. Geol., 147, 124–136, 2012. a
Ioffe, S. and Szegedy, C.: Batch normalization: Accelerating deep network training by reducing internal covariate shift, in: International conference on machine learning, Lille, France, 7–9 July 2015, pmlr, 448–456, https://doi.org/10.48550/arXiv.1502.03167, 2015b. a, b, c, d
Johnson, J. M. and Khoshgoftaar, T. M.: Survey on deep learning with class imbalance, Journal of Big Data, 6, 1–54, 2019. a
Jones, J. N., Boulton, S. J., Bennett, G. L., Stokes, M., and Whitworth, M. R.: Temporal variations in landslide distributions following extreme events: Implications for landslide susceptibility modeling, J. Geophys. Res.-Earth, 126, e2021JF006067, https://doi.org/10.1029/2021JF006067, 2021. a
Ju, N., Huang, J., He, C., Van Asch, T., Huang, R., Fan, X., Xu, Q., Xiao, Y., and Wang, J.: Landslide early warning, case studies from Southwest China, Eng. Geol., 279, 105917, https://doi.org/10.1016/j.enggeo.2020.105917, 2020. a
Kargel, J. S., Leonard, G. J., Shugar, D. H., Haritashya, U. K., Bevington, A., Fielding, E., Fujita, K., Geertsema, M., Miles, E., Steiner, J., and Anderson, E.: Geomorphic and geologic controls of geohazards induced by Nepal's 2015 Gorkha earthquake, Science, 351, aac8353, https://doi.org/10.1126/science.aac8353, 2016. a
Kincey, M. E., Rosser, N. J., Robinson, T. R., Densmore, A. L., Shrestha, R., Pujara, D. S., Oven, K. J., Williams, J. G., and Swirad, Z. M.: Evolution of coseismic and post-seismic landsliding after the 2015 Mw 7.8 Gorkha earthquake, Nepal, J. Geophys. Res.-Earth, 126, e2020JF005803, https://doi.org/10.1029/2020JF005803, 2021. a, b, c, d, e, f, g, h, i, j, k, l
Kingma, D. P. and Ba, J.: Adam: A Method for Stochastic Optimization, arXiv [preprint], https://doi.org/10.48550/ARXIV.1412.6980 (last access: 2 March 2024), 2014. a
Kirschbaum, D. and Stanley, T.: Satellite-Based Assessment of Rainfall-Triggered Landslide Hazard for Situational Awareness, Earths Future, 6, 505–523, 2018. a
Lee, S., Ryu, J.-H., Won, J.-S., and Park, H.-J.: Determination and application of the weights for landslide susceptibility mapping using an artificial neural network, Eng. Geol., 71, 289–302, 2004. a
Li, M., Zhang, X., Thrampoulidis, C., Chen, J., and Oymak, S.: AutoBalance: Optimized Loss Functions for Imbalanced Data, CoRR, abs/2201.01212, arXiv [preprint], https://arxiv.org/abs/2201.01212 (last access: 2 March 2024), 2022. a
Loche, M., Scaringi, G., Yunus, A. P., Catani, F., Tanyaş, H., Frodella, W., Fan, X., and Lombardo, L.: Surface temperature controls the pattern of post-earthquake landslide activity, Sci. Rep.-UK, 12, 1–11, 2022. a
Lombardo, L. and Tanyas, H.: Chrono-validation of near-real-time landslide susceptibility models via plug-in statistical simulations, Eng. Geol., 278, 105818, https://doi.org/10.1016/j.enggeo.2020.105818, 2020. a
Lombardo, L., Bakka, H., Tanyas, H., van Westen, C., Mai, P. M., and Huser, R.: Geostatistical modeling to capture seismic-shaking patterns from earthquake-induced landslides, J. Geophys. Res.-Earth, 124, 1958–1980, https://doi.org/10.1029/2019JF005056, 2019. a
Lombardo, L., Opitz, T., Ardizzone, F., Guzzetti, F., and Huser, R.: Space–time landslide predictive modelling, Earth-Sci. Rev., 209, 103318, https://doi.org/10.1016/j.earscirev.2020.103318, 2020. a
Lombardo, L., Tanyas, H., Huser, R., Guzzetti, F., and Castro-Camilo, D.: Landslide size matters: A new data-driven, spatial prototype, Eng. Geol., 293, 106288, https://doi.org/10.1016/j.enggeo.2021.106288, 2021. a, b, c
Maufroy, E., Cruz-Atienza, V. M., Cotton, F., and Gaffet, S.: Frequency-scaled curvature as a proxy for topographic site-effect amplification and ground-motion variability, B. Seismol. Soc. Am., 105, 354–367, 2015. a
McAdoo, B. G., Quak, M., Gnyawali, K. R., Adhikari, B. R., Devkota, S., Rajbhandari, P. L., and Sudmeier-Rieux, K.: Roads and landslides in Nepal: how development affects environmental risk, Nat. Hazards Earth Syst. Sci., 18, 3203–3210, https://doi.org/10.5194/nhess-18-3203-2018, 2018. a
Monaco, S., Pasini, A., Apiletti, D., Colomba, L., Garza, P., and Baralis, E.: Improving wildfire severity classification of deep learning U-nets from satellite images, in: 2020 IEEE International Conference on Big Data (Big Data), Atlanta, Georgia, USA and Virtual Conference, 10–13 December 2020, IEEE, 5786–5788, https://doi.org/10.1109/BigData50022.2020.9377867, 2020. a
Montrasio, L., Valentino, R., Corina, A., Rossi, L., and Rudari, R.: A prototype system for space–time assessment of rainfall-induced shallow landslides in Italy, Nat. Hazards, 74, 1263–1290, 2014. a
Nava, L., Bhuyan, K., Meena, S. R., Monserrat, O., and Catani, F.: Rapid Mapping of Landslides on SAR Data by Attention U-Net, Remote Sens.-Basel, 14, 1449, https://doi.org/10.3390/rs14061449, 2022. a
Neaupane, K. M. and Achet, S. H.: Use of backpropagation neural network for landslide monitoring: a case study in the higher Himalaya, Eng. Geol., 74, 213–226, 2004. a
Neaupane, K. M. and Piantanakulchai, M.: Analytic network process model for landslide hazard zonation, Eng. Geol., 85, 281–294, 2006. a
Nocentini, N., Rosi, A., Segoni, S., and Fanti, R.: Towards landslide space–time forecasting through machine learning: the influence of rainfall parameters and model setting, Front. Earth Sci., 11, 1152130, https://doi.org/10.3389/feart.2023.1152130, 2023. a
Nowicki Jessee, M., Hamburger, M., Allstadt, K., Wald, D., Robeson, S., Tanyas, H., Hearne, M., and Thompson, E.: A Global Empirical Model for Near-Real-Time Assessment of Seismically Induced Landslides, J. Geophys. Res.-Earth, 123, 1835–1859, 2018. a
Ohlmacher, G. C.: Plan curvature and landslide probability in regions dominated by earth flows and earth slides, Eng. Geol., 91, 117–134, https://doi.org/10.1016/j.enggeo.2007.01.005, 2007. a
Ozturk, U.: Geohazards explained 10: Time-dependent landslide susceptibility, Geology Today, 38, 117–120, 2022. a
Ozturk, U., Pittore, M., Behling, R., Roessner, S., Andreani, L., and Korup, O.: How robust are landslide susceptibility estimates?, Landslides, 18, 681–695, 2021. a
Ozturk, U., Bozzolan, E., Holcombe, E. A., Shukla, R., Pianosi, F., and Wagener, T.: How climate change and unplanned urban sprawl bring more landslides, Nature, 608, 262–265, https://doi.org/10.1038/d41586-022-02141-9, 2022. a
Pearson, K.: Note on Regression and Inheritance in the Case of Two Parents, P. R. Soc. London, 58, 240–242, http://www.jstor.org/stable/115794 (last access: 2 March 2024), 1895. a
Prabhakar, S., Srinivasan, A., and Shaw, R.: Climate change and local level disaster risk reduction planning: need, opportunities and challenges, Mitig. Adapt. Strat. Gl., 14, 7–33, 2009. a
Prakash, N., Manconi, A., and Loew, S.: A new strategy to map landslides with a generalized convolutional neural network, Sci. Rep.-UK, 11, 9722, https://doi.org/10.1038/s41598-021-89015-8, 2021. a
Qi, J., Du, J., Siniscalchi, S. M., Ma, X., and Lee, C.-H.: On mean absolute error for deep neural network based vector-to-vector regression, IEEE Signal Proc. Let., 27, 1485–1489, 2020. a
Rana, K., Ozturk, U., and Malik, N.: Landslide geometry reveals its trigger, Geophys. Res. Lett., 48, e2020GL090848, https://doi.org/10.1029/2020GL090848, 2021. a
Reichenbach, P., Rossi, M., Malamud, B. D., Mihir, M., and Guzzetti, F.: A Review of Statistically-Based Landslide Susceptibility Models, Earth-Sci. Rev., 180, 60–91, https://doi.org/10.1016/j.earscirev.2018.03.001, 2018. a
Richards, J., Huser, R., Bevacqua, E., and Zscheischler, J.: Insights into the drivers and spatiotemporal trends of extreme mediterranean wildfires with statistical deep learning, Artificial Intelligence for the Earth Systems, 2, e220095, https://doi.org/10.1175/AIES-D-22-0095.1, 2023. a
Roback, K., Clark, M. K., West, A. J., Zekkos, D., Li, G., Gallen, S. F., Chamlagain, D., and Godt, J. W.: The size, distribution, and mobility of landslides caused by the 2015 Mw7.8 Gorkha earthquake, Nepal, Geomorphology, 301, 121–138, 2018. a
Ronneberger, O., Fischer, P., and Brox, T.: U-Net: Convolutional Networks for Biomedical Image Segmentation, CoRR, abs/1505.04597, arXiv [preprint], http://arxiv.org/abs/1505.04597 (last access: 2 March 2024), 2015. a
Rosser, N., Kincey, M., Oven, K., Densmore, A., Robinson, T., Pujara, D. S., Shrestha, R., Smutny, J., Gurung, K., Lama, S., and Dhital, M. R.: Changing significance of landslide Hazard and risk after the 2015 Mw 7.8 Gorkha, Nepal Earthquake, Progress in Disaster Science, 10, 100159, https://doi.org/10.1016/j.pdisas.2021.100159, 2021. a
Samia, J., Temme, A. J., Bregt, A., Wallinga, J., Fausto Guzzetti, Ardizzone, F., and Rossi, M.: Characterization and Quantification of Path Dependency in Landslide Susceptibility, Geomorphology, 292, 16–24, https://doi.org/10.1016/j.geomorph.2017.04.039, 2017. a
Samia, J., Temme, A., Bregt, A., Wallinga, J., Guzzetti, F., and Ardizzone, F.: Dynamic path-dependent landslide susceptibility modelling, Nat. Hazards Earth Syst. Sci., 20, 271–285, https://doi.org/10.5194/nhess-20-271-2020, 2020. a
Scarselli, F., Gori, M., Tsoi, A. C., Hagenbuchner, M., and Monfardini, G.: The graph neural network model, IEEE T. Neural Networ., 20, 61–80, 2008. a
Schlögel, R., Marchesini, I., Alvioli, M., Reichenbach, P., Rossi, M., and Malet, J.-P.: Optimizing landslide susceptibility zonation: Effects of DEM spatial resolution and slope unit delineation on logistic regression models, Geomorphology, 301, 10–20, https://doi.org/10.1016/j.geomorph.2017.10.018, 2018. a
Shou, K.-J. and Lin, J.-F.: Evaluation of the extreme rainfall predictions and their impact on landslide susceptibility in a sub-catchment scale, Eng. Geol., 265, 105434, https://doi.org/10.1016/j.enggeo.2019.105434, 2020. a
Sørensen, R., Zinko, U., and Seibert, J.: On the calculation of the topographic wetness index: evaluation of different methods based on field observations, Hydrol. Earth Syst. Sci., 10, 101–112, https://doi.org/10.5194/hess-10-101-2006, 2006. a
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R.: Dropout: A Simple Way to Prevent Neural Networks from Overfitting, J. Mach. Learn. Res., 15, 1929–1958, http://jmlr.org/papers/v15/srivastava14a.html (last access: 2 March 2024), 2014a. a
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting, J. Mach. Learn. Res., 15, 1929–1958, 2014b. a
Steger, S., Brenning, A., Bell, R., and Glade, T.: The propagation of inventory-based positional errors into statistical landslide susceptibility models, Nat. Hazards Earth Syst. Sci., 16, 2729–2745, https://doi.org/10.5194/nhess-16-2729-2016, 2016. a, b
Steger, S., Mair, V., Kofler, C., Pittore, M., Zebisch, M., and Schneiderbauer, S.: Correlation does not imply geomorphic causation in data-driven landslide susceptibility modelling–Benefits of exploring landslide data collection effects, Sci. Total Environ., 776, 145935, https://doi.org/10.1016/j.scitotenv.2021.145935, 2021. a
Tanyaş, H., Allstadt, K. E., and van Westen, C. J.: An updated method for estimating landslide-event magnitude, Earth Surf. Proc. Land., 43, 1836–1847, https://doi.org/10.1002/esp.4359, 2018. a
Tanyaş, H., Hill, K., Mahoney, L., Fadel, I., and Lombardo, L.: The world's second-largest, recorded landslide event: Lessons learnt from the landslides triggered during and after the 2018 Mw 7.5 Papua New Guinea earthquake, Eng. Geol., 297, 106504, https://doi.org/10.1016/j.enggeo.2021.106504, 2022. a
Tanyaş, H., Kirschbaum, D., Görüm, T., van Westen, C. J., Tang, C., and Lombardo, L.: A closer look at factors governing landslide recovery time in post-seismic periods, Geomorphology, 391, 107912, https://doi.org/10.1016/j.geomorph.2021.107912, 2021a. a
Tanyaş, H., Kirschbaum, D., and Lombardo, L.: Capturing the footprints of ground motion in the spatial distribution of rainfall-induced landslides, B. Eng. Geol. Environ., 80, 4323–4345, 2021b. a
Tanyaş, H., Görüm, T., Kirschbaum, D., and Lombardo, L.: Could road constructions be more hazardous than an earthquake in terms of mass movement?, Nat. Hazards, 112, 639–663, https://doi.org/10.1007/s11069-021-05199-2, 2022a. a
Tanyaş, H., Hill, K., Mahoney, L., Fadel, I., and Lombardo, L.: The world's second-largest, recorded landslide event: Lessons learnt from the landslides triggered during and after the 2018 Mw 7.5 Papua New Guinea earthquake, Eng. Geol., 297, 106504, 2022b. a
Taylor, D. W.: Fundamentals of Soil Mechanics, John Wiley & Sons, Wisconsin, USA, ISBN 978-1258768928, 1948. a
Titti, G., van Westen, C., Borgatti, L., Pasuto, A., and Lombardo, L.: When Enough Is Really Enough? On the Minimum Number of Landslides to Build Reliable Susceptibility Models, Geosciences, 11, 469, https://doi.org/10.3390/geosciences11110469, 2021. a
Titti, G., Sarretta, A., Lombardo, L., Crema, S., Pasuto, A., and Borgatti, L.: Mapping susceptibility with open-source tools: a new plugin for QGIS, Front. Earth Sci., 229, 842425, https://doi.org/10.3389/feart.2022.842425, 2022. a
Upreti, B. N: The Physiographic and Geology of Nepal and Their Bearing on the Landslide Problem, in: Landslide Hazard Mitigation in the Hindu Kush-Himalaya, edited by: Upreti, B. N., Tianchi, L., and Chalise, S. R. Kathmandu, International Centre for Integrated Mountain Development, 31–49, https://doi.org/10.53055/ICIMOD.374, 2001. a, b
van den Bout, B., Lombardo, L., Chiyang, M., van Westen, C., and Jetten, V.: Physically-based catchment-scale prediction of slope failure volume and geometry, Eng. Geol., 284, 105942, https://doi.org/10.1016/j.enggeo.2020.105942, 2021a. a
van den Bout, B., van Asch, T., Hu, W., Tang, C. X., Mavrouli, O., Jetten, V. G., and van Westen, C. J.: Towards a model for structured mass movements: the OpenLISEM hazard model 2.0a, Geosci. Model Dev., 14, 1841–1864, https://doi.org/10.5194/gmd-14-1841-2021, 2021b. a
Van Westen, C., Van Asch, T. W., and Soeters, R.: Landslide hazard and risk zonation—why is it still so difficult?, B. Eng. Geol. Environ., 65, 167–184, 2006. a
Van Westen, C. J., Castellanos, E., and Kuriakose, S. L.: Spatial data for landslide susceptibility, hazard, and vulnerability assessment: An overview, Eng. Geol., 102, 112–131, 2008. a
Vasiliev, I. R.: Visualization of spatial dependence: an elementary view of spatial autocorrelation, in: Practical handbook of spatial statistics, edited by: Arlinghaus, S., CRC Press, Boca Raton, 17–30, https://doi.org/10.1201/9781003067689, 2020. a
von Specht, S., Ozturk, U., Veh, G., Cotton, F., and Korup, O.: Effects of finite source rupture on landslide triggering: the 2016 Mw 7.1 Kumamoto earthquake, Solid Earth, 10, 463–486, https://doi.org/10.5194/se-10-463-2019, 2019. a
Wang, H., Xu, W., and Xu, R.: Slope stability evaluation using back propagation neural networks, Eng. Geol., 80, 302–315, 2005. a
Wang, N., Cheng, W., Marconcini, M., Bachofer, F., Liu, C., Xiong, J., and Lombardo, L.: Space–time susceptibility modeling of hydro-morphological processes at the Chinese national scale, Eng. Geol., 301, 106586, https://doi.org/10.1016/j.enggeo.2022.106586, 2022. a
Wang, T., Dahal, A., Fang, Z., van Westen, C., Yin, K., and Lombardo, L.: From spatio-temporal landslide susceptibility to landslide risk forecast, Geosci. Front., 15, 101765, https://doi.org/10.1016/j.gsf.2023.101765, 2023. a
Wang, X., Chen, Y., and Zhu, W:. A survey on curriculum learning, IEEE T. Pattern Anal., 44, 4555–4576, 2021. a
Weng, T.-W., Zhang, H., Chen, P.-Y., Yi, J., Su, D., Gao, Y., Hsieh, C.-J., and Daniel, L.: Evaluating the robustness of neural networks: An extreme value theory approach, arXiv [preprint], arXiv:1801.10578, 2018. a
Whiteley, J., Chambers, J., Uhlemann, S., Wilkinson, P. B., and Kendall, J.: Geophysical monitoring of moisture-induced landslides: a review, Rev. Geophys., 57, 106–145, 2019. a
Worden, C. and Wald, D.: ShakeMap manual online: Technical manual, user's guide, and software guide, US Geol. Surv., Reston, Virginia, USA, 1–156, https://doi.org/10.3133/tm12A1, 2016. a, b, c
Yeon, Y.-K., Han, J.-G., and Ryu, K. H.: Landslide susceptibility mapping in Injae, Korea, using a decision tree, Eng. Geol., 116, 274–283, 2010. a
Yesilnacar, E. and Topal, T.: Landslide susceptibility mapping: a comparison of logistic regression and neural networks methods in a medium scale study, Hendek region (Turkey), Eng. Geol., 79, 251–266, 2005. a
Zapata, M. M., Steger, S., Tanyas, H., and Lombardo, L.: Modeling the area of co-seismic landslides via data-driven models: The Kaikōura example, Eng. Geol., 320, 107121, https://doi.org/10.1016/j.enggeo.2023.107121, 2023. a, b
Zevenbergen, L. W. and Thorne, C. R.: Quantitative analysis of land surface topography, Earth Surf. Proc. Land., 12, 47–56, 1987. a
Zhang, Y., Chen, G., Zheng, L., Li, Y., and Wu, J.: Effects of near-fault seismic loadings on run-out of large-scale landslide: a case study, Eng. Geol., 166, 216–236, 2013. a
Short summary
We propose a modeling approach capable of recognizing slopes that may generate landslides, as well as how large these mass movements may be. This protocol is implemented, tested, and validated with data that change in both space and time via an Ensemble Neural Network architecture.
We propose a modeling approach capable of recognizing slopes that may generate landslides, as...
Altmetrics
Final-revised paper
Preprint