Articles | Volume 22, issue 12
https://doi.org/10.5194/nhess-22-3859-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Special issue:
https://doi.org/10.5194/nhess-22-3859-2022
© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
01 Dec 2022
Research article |
| 01 Dec 2022
| 01 Dec 2022
Comparison of machine learning techniques for reservoir outflow forecasting
Centro de Investigación Mariña, Universidade de Vigo,
Environmental Physics Laboratory (CIM-EPhysLab), Campus Auga, 32004 Ourense, Spain
Water and Environmental Engineering Group, Department of Civil
Engineering, Universidade da Coruña, 15071 A Coruña, Spain
José González-Cao
Centro de Investigación Mariña, Universidade de Vigo,
Environmental Physics Laboratory (CIM-EPhysLab), Campus Auga, 32004 Ourense, Spain
Diego Fernández-Nóvoa
Centro de Investigación Mariña, Universidade de Vigo,
Environmental Physics Laboratory (CIM-EPhysLab), Campus Auga, 32004 Ourense, Spain
Instituto Dom Luiz (IDL), Faculdade de Ciências da Universidade de Lisboa, 1749-016 Lisbon, Portugal
Gonzalo Astray Dopazo
Departamento de Química Física, Facultade de Ciencias, Universidade de Vigo, 32004 Ourense, Spain
Moncho Gómez-Gesteira
Centro de Investigación Mariña, Universidade de Vigo,
Environmental Physics Laboratory (CIM-EPhysLab), Campus Auga, 32004 Ourense, Spain
Related authors
Diego Fernández-Nóvoa, Alexandre M. Ramos, José González-Cao, Orlando García-Feal, Cristina Catita, Moncho Gómez-Gesteira, and Ricardo M. Trigo
Nat. Hazards Earth Syst. Sci., 24, 609–630, https://doi.org/10.5194/nhess-24-609-2024, https://doi.org/10.5194/nhess-24-609-2024, 2024
Short summary
Short summary
The present study focuses on an in-depth analysis of floods in the lower section of the Tagus River from a hydrodynamic perspective by means of the Iber+ numerical model and on the development of dam operating strategies to mitigate flood episodes using the exceptional floods of February 1979 as a benchmark. The results corroborate the model's capability to evaluate floods in the study area and confirm the effectiveness of the proposed strategies to reduce flood impact in the lower Tagus valley.
Diego Fernández-Nóvoa, Orlando García-Feal, José González-Cao, Maite deCastro, and Moncho Gómez-Gesteira
Nat. Hazards Earth Syst. Sci., 22, 3957–3972, https://doi.org/10.5194/nhess-22-3957-2022, https://doi.org/10.5194/nhess-22-3957-2022, 2022
Short summary
Short summary
A multiscale analysis, where the historical and future precipitation data from the CORDEX project were used as input in a hydrological model (HEC-HMS) that, in turn, feeds a 2D hydraulic model (Iber+), was applied to the case of the Miño-Sil basin (NW Spain), specifically to Ourense city, in order to analyze future changes in flood hazard. Detailed flood maps indicate an increase in the frequency and intensity of future floods, implying an increase in flood hazard in important areas of the city.
José González-Cao, Orlando García-Feal, Diego Fernández-Nóvoa, José Manuel Domínguez-Alonso, and Moncho Gómez-Gesteira
Nat. Hazards Earth Syst. Sci., 19, 2583–2595, https://doi.org/10.5194/nhess-19-2583-2019, https://doi.org/10.5194/nhess-19-2583-2019, 2019
Short summary
Short summary
An early-warning system (EWS) for flood prediction was developed in the upper reach of the Miño River and the city of Lugo (NW Spain). This EWS can provide accurate results in less than 1 h, for a forecast horizon of 3 d, and report an alert situation to decision makers in order to mitigate the consequences of floods. In addition, this EWS can be easily adapted for any area of the world since the required input data and software are freely available.
Brieuc Thomas, Jose Carlos Fernández-Alvarez, Xurxo Costoya, Maite deCastro, Raquel Nieto, David Carvalho, Luis Gimeno, and Moncho Gómez-Gesteira
EGUsphere, https://doi.org/10.5194/egusphere-2025-1339, https://doi.org/10.5194/egusphere-2025-1339, 2025
This preprint is open for discussion and under review for Geoscientific Model Development (GMD).
Short summary
Short summary
Understanding climate change is crucial, but global models lack fine detail for local assessments. Regional climate models improve accuracy by simulating climate at higher resolution. This study compares two approaches: one continuous and one resetting daily to reduce errors and speed up processing. Both perform well and similarly, but the reinitialized method is 30 times more efficient. Its lower cost makes it a promising option for high-resolution climate modelling and regional predictions.
Diego Fernández-Nóvoa, Alexandre M. Ramos, José González-Cao, Orlando García-Feal, Cristina Catita, Moncho Gómez-Gesteira, and Ricardo M. Trigo
Nat. Hazards Earth Syst. Sci., 24, 609–630, https://doi.org/10.5194/nhess-24-609-2024, https://doi.org/10.5194/nhess-24-609-2024, 2024
Short summary
Short summary
The present study focuses on an in-depth analysis of floods in the lower section of the Tagus River from a hydrodynamic perspective by means of the Iber+ numerical model and on the development of dam operating strategies to mitigate flood episodes using the exceptional floods of February 1979 as a benchmark. The results corroborate the model's capability to evaluate floods in the study area and confirm the effectiveness of the proposed strategies to reduce flood impact in the lower Tagus valley.
Diego Fernández-Nóvoa, Orlando García-Feal, José González-Cao, Maite deCastro, and Moncho Gómez-Gesteira
Nat. Hazards Earth Syst. Sci., 22, 3957–3972, https://doi.org/10.5194/nhess-22-3957-2022, https://doi.org/10.5194/nhess-22-3957-2022, 2022
Short summary
Short summary
A multiscale analysis, where the historical and future precipitation data from the CORDEX project were used as input in a hydrological model (HEC-HMS) that, in turn, feeds a 2D hydraulic model (Iber+), was applied to the case of the Miño-Sil basin (NW Spain), specifically to Ourense city, in order to analyze future changes in flood hazard. Detailed flood maps indicate an increase in the frequency and intensity of future floods, implying an increase in flood hazard in important areas of the city.
José González-Cao, Orlando García-Feal, Diego Fernández-Nóvoa, José Manuel Domínguez-Alonso, and Moncho Gómez-Gesteira
Nat. Hazards Earth Syst. Sci., 19, 2583–2595, https://doi.org/10.5194/nhess-19-2583-2019, https://doi.org/10.5194/nhess-19-2583-2019, 2019
Short summary
Short summary
An early-warning system (EWS) for flood prediction was developed in the upper reach of the Miño River and the city of Lugo (NW Spain). This EWS can provide accurate results in less than 1 h, for a forecast horizon of 3 d, and report an alert situation to decision makers in order to mitigate the consequences of floods. In addition, this EWS can be easily adapted for any area of the world since the required input data and software are freely available.
Related subject area
Databases, GIS, Remote Sensing, Early Warning Systems and Monitoring Technologies
Prediction of the volume of shallow landslides due to rainfall using data-driven models
Monitoring snow depth variations in an avalanche release area using low-cost lidar and optical sensors
Satellite-based data for agricultural index insurance: a systematic quantitative literature review
A methodology to compile multi-hazard interrelationships in a data-scarce setting: an application to the Kathmandu Valley, Nepal
An automated approach for developing geohazard inventories using news: Integrating NLP, machine learning, and mapping
Review article: Physical vulnerability database for critical infrastructure hazard risk assessments – a systematic review and data collection
Exploring drought hazard, vulnerability, and related impacts on agriculture in Brandenburg
Dynamical changes in seismic properties prior to, during, and after the 2014–2015 Holuhraun eruption, Iceland
The World Wide Lightning Location Network (WWLLN) over Spain
Automated Rapid Estimation of Flood Depth using Digital Elevation Model and EOS-04 Satellite derived Flood inundation
AscDAMs: advanced SLAM-based channel detection and mapping system
Shoreline and land use–land cover changes along the 2004-tsunami-affected South Andaman coast: understanding changing hazard susceptibility
What can we learn from global disaster records about multi-hazards and their risk dynamics?
Insights into the development of a landslide early warning system prototype in an informal settlement: the case of Bello Oriente in Medellín, Colombia
Tsunami hazard perception and knowledge of alert: early findings in five municipalities along the French Mediterranean coastlines
Exploiting radar polarimetry for nowcasting thunderstorm hazards using deep learning
Machine-learning-based nowcasting of the Vögelsberg deep-seated landslide: why predicting slow deformation is not so easy
Fixed photogrammetric systems for natural hazard monitoring with high spatio-temporal resolution
A neural network model for automated prediction of avalanche danger level
Brief communication: Landslide activity on the Argentinian Santa Cruz River mega dam works confirmed by PSI DInSAR
Impact of topography on in situ soil wetness measurements for regional landslide early warning – a case study from the Swiss Alpine Foreland
Earthquake building damage detection based on synthetic-aperture-radar imagery and machine learning
Assessing riverbank erosion in Bangladesh using time series of Sentinel-1 radar imagery in the Google Earth Engine
Quantifying unequal urban resilience to rainfall across China from location-aware big data
Development of black ice prediction model using GIS-based multi-sensor model validation
Forecasting vegetation condition with a Bayesian auto-regressive distributed lags (BARDL) model
A dynamic hierarchical Bayesian approach for forecasting vegetation condition
Using a single remote-sensing image to calculate the height of a landslide dam and the maximum volume of a lake
Enhancing disaster risk resilience using greenspace in urbanising Quito, Ecuador
Gridded flood depth estimates from satellite-derived inundations
ProbFire: a probabilistic fire early warning system for Indonesia
Index establishment and capability evaluation of space–air–ground remote sensing cooperation in geohazard emergency response
Brief communication: Monitoring a soft-rock coastal cliff using webcams and strain sensors
Multiscale analysis of surface roughness for the improvement of natural hazard modelling
EUNADICS-AV early warning system dedicated to supporting aviation in the case of a crisis from natural airborne hazards and radionuclide clouds
Are sirens effective tools to alert the population in France?
UAV survey method to monitor and analyze geological hazards: the case study of the mud volcano of Villaggio Santa Barbara, Caltanissetta (Sicily)
Timely prediction potential of landslide early warning systems with multispectral remote sensing: a conceptual approach tested in the Sattelkar, Austria
CHILDA – Czech Historical Landslide Database
Review article: Detection of actionable tweets in crisis events
Long-term magnetic anomalies and their possible relationship to the latest greater Chilean earthquakes in the context of the seismo-electromagnetic theory
HazMapper: a global open-source natural hazard mapping application in Google Earth Engine
Opportunities and risks of disaster data from social media: a systematic review of incident information
Online urban-waterlogging monitoring based on a recurrent neural network for classification of microblogging text
Predicting power outages caused by extratropical storms
Near-real-time automated classification of seismic signals of slope failures with continuous random forests
Assessing the accuracy of remotely sensed fire datasets across the southwestern Mediterranean Basin
Responses to severe weather warnings and affective decision-making
The object-specific flood damage database HOWAS 21
A spaceborne SAR-based procedure to support the detection of landslides
Jérémie Tuganishuri, Chan-Young Yune, Gihong Kim, Seung Woo Lee, Manik Das Adhikari, and Sang-Guk Yum
Nat. Hazards Earth Syst. Sci., 25, 1481–1499, https://doi.org/10.5194/nhess-25-1481-2025, https://doi.org/10.5194/nhess-25-1481-2025, 2025
Short summary
Short summary
To reduce the consequences of landslides due to rainfall, such as loss of life, economic losses, and disruption to daily living, this study describes the process of building a machine learning model which can help to estimate the volume of landslide material that can occur in a particular region, taking into account antecedent rainfall, soil characteristics, type of vegetation, etc. The findings can be useful for land use management, infrastructure design, and rainfall disaster management.
Pia Ruttner, Annelies Voordendag, Thierry Hartmann, Julia Glaus, Andreas Wieser, and Yves Bühler
Nat. Hazards Earth Syst. Sci., 25, 1315–1330, https://doi.org/10.5194/nhess-25-1315-2025, https://doi.org/10.5194/nhess-25-1315-2025, 2025
Short summary
Short summary
Snow depth variations caused by wind are an important factor in avalanche danger, but detailed and up-to-date information is rarely available. We propose a monitoring system, using lidar and optical sensors, to measure the snow depth distribution at high spatial and temporal resolution. First results show that we can quantify snow depth changes with an accuracy on the low decimeter level, or better, and can identify events such as avalanches or displacement of snow during periods of strong winds.
Thuy T. Nguyen, Shahbaz Mushtaq, Jarrod Kath, Thong Nguyen-Huy, and Louis Reymondin
Nat. Hazards Earth Syst. Sci., 25, 913–927, https://doi.org/10.5194/nhess-25-913-2025, https://doi.org/10.5194/nhess-25-913-2025, 2025
Short summary
Short summary
We reviewed the use of satellite-based data in designing agricultural index-based insurance (IBI) products, an effective tool for managing climate risk and promoting sustainable development. Despite the increasing number of studies since 2010 to present, the review revealed a gap in applying the approach to perennial crops in developing countries. We also highlighted the growing importance of satellite data for index insurance, employing high-resolution datasets to reduce basis risk.
Harriet E. Thompson, Joel C. Gill, Robert Šakić Trogrlić, Faith E. Taylor, and Bruce D. Malamud
Nat. Hazards Earth Syst. Sci., 25, 353–381, https://doi.org/10.5194/nhess-25-353-2025, https://doi.org/10.5194/nhess-25-353-2025, 2025
Short summary
Short summary
We present a methodology to compile single hazards and multi-hazard interrelationships in data-scarce urban settings, which we apply to the Kathmandu Valley, Nepal. Using blended sources, we collate evidence of 21 single natural hazard types and 83 multi-hazard interrelationships that could impact the Kathmandu Valley. We supplement these exemplars with multi-hazard scenarios developed by practitioner stakeholders, emphasising the need for inclusive disaster preparedness and response approaches.
Aydoğan Avcıoğlu, Ogün Demir, and Tolga Görüm
EGUsphere, https://doi.org/10.5194/egusphere-2025-7, https://doi.org/10.5194/egusphere-2025-7, 2025
Short summary
Short summary
Here we demonstrate an approach for the development of inventories from internet sources to geolocalized geohazard incidents. We created a tool that autonomously gets news, processes it using NLP and machine learning, and maps using Open Street Map. Consequently, we present spatiotemporal inventories for geohazards resulting in a total of 13940 incidents between 1997 and 2023 in Türkiye. Our alternative and easy-to-implement development inventory method aids geohazard management and resilience.
Sadhana Nirandjan, Elco E. Koks, Mengqi Ye, Raghav Pant, Kees C. H. Van Ginkel, Jeroen C. J. H. Aerts, and Philip J. Ward
Nat. Hazards Earth Syst. Sci., 24, 4341–4368, https://doi.org/10.5194/nhess-24-4341-2024, https://doi.org/10.5194/nhess-24-4341-2024, 2024
Short summary
Short summary
Critical infrastructures (CIs) are exposed to natural hazards, which may result in significant damage and burden society. Vulnerability is a key determinant for reducing these risks, yet crucial information is scattered in the literature. Our study reviews over 1510 fragility and vulnerability curves for CI assets, creating a unique publicly available physical vulnerability database that can be directly used for hazard risk assessments, including floods, earthquakes, windstorms, and landslides.
Fabio Brill, Pedro Henrique Lima Alencar, Huihui Zhang, Friedrich Boeing, Silke Hüttel, and Tobia Lakes
Nat. Hazards Earth Syst. Sci., 24, 4237–4265, https://doi.org/10.5194/nhess-24-4237-2024, https://doi.org/10.5194/nhess-24-4237-2024, 2024
Short summary
Short summary
Droughts are a threat to agricultural crops, but different factors influence how much damage occurs. This is important to know to create meaningful risk maps and to evaluate adaptation options. We investigate the years 2013–2022 in Brandenburg, Germany, and find in particular the soil quality and meteorological drought in June to be statistically related to the observed damage. Measurement of crop health from satellites is also related to soil quality and not necessarily to anomalous yields.
Maria R. P. Sudibyo, Eva P. S. Eibl, Sebastian Hainzl, and Matthias Ohrnberger
Nat. Hazards Earth Syst. Sci., 24, 4075–4089, https://doi.org/10.5194/nhess-24-4075-2024, https://doi.org/10.5194/nhess-24-4075-2024, 2024
Short summary
Short summary
We assessed the performance of permutation entropy (PE), phase permutation entropy (PPE), and instantaneous frequency (IF), which are estimated from a single seismic station, to detect changes before, during, and after the 2014–2015 Holuhraun eruption in Iceland. We show that these three parameters are sensitive to the pre-eruptive and eruptive processes. Finally, we discuss their potential and limitations in eruption monitoring.
Enrique A. Navarro, Jorge A. Portí, Alfonso Salinas, Sergio Toledo-Redondo, Jaume Segura-García, Aida Castilla, Víctor Montagud-Camps, and Inmaculada Albert
Nat. Hazards Earth Syst. Sci., 24, 3925–3943, https://doi.org/10.5194/nhess-24-3925-2024, https://doi.org/10.5194/nhess-24-3925-2024, 2024
Short summary
Short summary
The World Wide Lightning Location Network (WWLLN) operates a globally distributed network of stations that detect lightning signals at a planetary scale. A detection efficiency of 29 % with a location accuracy of between 2 and 3 km is obtained for the area of Spain by comparing WWLLN data with those of the Spanish State Meteorological Agency. The network's capability to resolve convective-storm cells generated in a cutoff low-pressure system is also demonstrated in the west Mediterranean Sea.
Lakshmi Amani Chimata, Suresh Babu Anuvala Setty Venkata, Shashi Vardhan Reddy Patlolla, Durga Rao Korada Hari Venkata, Sreenivas Kandrika, and Prakash Chauhan
EGUsphere, https://doi.org/10.5194/egusphere-2024-2278, https://doi.org/10.5194/egusphere-2024-2278, 2024
Short summary
Short summary
Fast flood assessments are important for providing effective help during emergencies and planning for future floods. This study presents a new automated way to quickly measure flood depth. By using satellite images and digital elevation models, this method makes it easier to get real-time flood information. We applied this new method in several flood-prone areas in India and found that it provides more accurate results than existing flood measurement tools.
Tengfei Wang, Fucheng Lu, Jintao Qin, Taosheng Huang, Hui Kong, and Ping Shen
Nat. Hazards Earth Syst. Sci., 24, 3075–3094, https://doi.org/10.5194/nhess-24-3075-2024, https://doi.org/10.5194/nhess-24-3075-2024, 2024
Short summary
Short summary
Harsh environments limit the use of drone, satellite, and simultaneous localization and mapping technology to obtain precise channel morphology data. We propose AscDAMs, which includes a deviation correction algorithm to reduce errors, a point cloud smoothing algorithm to diminish noise, and a cross-section extraction algorithm to quantitatively assess the morphology data. AscDAMs solves the problems and provides researchers with more reliable channel morphology data for further analysis.
Vikas Ghadamode, Aruna Kumari Kondarathi, Anand K. Pandey, and Kirti Srivastava
Nat. Hazards Earth Syst. Sci., 24, 3013–3033, https://doi.org/10.5194/nhess-24-3013-2024, https://doi.org/10.5194/nhess-24-3013-2024, 2024
Short summary
Short summary
In 2004-tsunami-affected South Andaman, tsunami wave propagation, arrival times, and run-up heights at 13 locations are computed to analyse pre- and post-tsunami shoreline and land use–land cover changes to understand the evolving hazard scenario. The LULC changes and dynamic shoreline changes are observed in zones 3, 4, and 5 owing to dynamic population changes, infrastructural growth, and gross state domestic product growth. Economic losses would increase 5-fold for a similar tsunami.
Wiebke S. Jäger, Marleen C. de Ruiter, Timothy Tiggeloven, and Philip J. Ward
Nat. Hazards Earth Syst. Sci. Discuss., https://doi.org/10.5194/nhess-2024-134, https://doi.org/10.5194/nhess-2024-134, 2024
Revised manuscript under review for NHESS
Short summary
Short summary
Multiple hazards, occurring at the same time or shortly after one another, can have more extreme impacts than single hazards. We examined the disaster records in the global emergency events database EM-DAT to better understand this phenomenon. We developed a method to identify such multi-hazards and analyzed their reported impacts using statistics. Multi-hazards have accounted for a disproportionate amount of the overall impacts, but there are different patterns in which the impacts compound.
Christian Werthmann, Marta Sapena, Marlene Kühnl, John Singer, Carolina Garcia, Tamara Breuninger, Moritz Gamperl, Bettina Menschik, Heike Schäfer, Sebastian Schröck, Lisa Seiler, Kurosch Thuro, and Hannes Taubenböck
Nat. Hazards Earth Syst. Sci., 24, 1843–1870, https://doi.org/10.5194/nhess-24-1843-2024, https://doi.org/10.5194/nhess-24-1843-2024, 2024
Short summary
Short summary
Early warning systems (EWSs) promise to decrease the vulnerability of self-constructed (informal) settlements. A living lab developed a partially functional prototype of an EWS for landslides in a Medellín neighborhood. The first findings indicate that technical aspects can be manageable, unlike social and political dynamics. A resilient EWS for informal settlements has to achieve sufficient social and technical redundancy to maintain basic functionality in a reduced-support scenario.
Johnny Douvinet, Noé Carles, Pierre Foulquier, and Matthieu Peroche
Nat. Hazards Earth Syst. Sci., 24, 715–735, https://doi.org/10.5194/nhess-24-715-2024, https://doi.org/10.5194/nhess-24-715-2024, 2024
Short summary
Short summary
This study provided an opportunity to assess both the perception of the tsunami hazard and the knowledge of alerts in five municipalities located along the French Mediterranean coastlines. The age and location of the respondents explain several differences between the five municipalities surveyed – more so than gender or residence status. This study may help local authorities to develop future tsunami awareness actions and to identify more appropriate strategies to be applied in the short term.
Nathalie Rombeek, Jussi Leinonen, and Ulrich Hamann
Nat. Hazards Earth Syst. Sci., 24, 133–144, https://doi.org/10.5194/nhess-24-133-2024, https://doi.org/10.5194/nhess-24-133-2024, 2024
Short summary
Short summary
Severe weather such as hail, lightning, and heavy rainfall can be hazardous to humans and property. Dual-polarization weather radars provide crucial information to forecast these events by detecting precipitation types. This study analyses the importance of dual-polarization data for predicting severe weather for 60 min using an existing deep learning model. The results indicate that including these variables improves the accuracy of predicting heavy rainfall and lightning.
Adriaan L. van Natijne, Thom A. Bogaard, Thomas Zieher, Jan Pfeiffer, and Roderik C. Lindenbergh
Nat. Hazards Earth Syst. Sci., 23, 3723–3745, https://doi.org/10.5194/nhess-23-3723-2023, https://doi.org/10.5194/nhess-23-3723-2023, 2023
Short summary
Short summary
Landslides are one of the major weather-related geohazards. To assess their potential impact and design mitigation solutions, a detailed understanding of the slope is required. We tested if the use of machine learning, combined with satellite remote sensing data, would allow us to forecast deformation. Our results on the Vögelsberg landslide, a deep-seated landslide near Innsbruck, Austria, show that the formulation of such a machine learning system is not as straightforward as often hoped for.
Xabier Blanch, Marta Guinau, Anette Eltner, and Antonio Abellan
Nat. Hazards Earth Syst. Sci., 23, 3285–3303, https://doi.org/10.5194/nhess-23-3285-2023, https://doi.org/10.5194/nhess-23-3285-2023, 2023
Short summary
Short summary
We present cost-effective photogrammetric systems for high-resolution rockfall monitoring. The paper outlines the components, assembly, and programming codes required. The systems utilize prime cameras to generate 3D models and offer comparable performance to lidar for change detection monitoring. Real-world applications highlight their potential in geohazard monitoring which enables accurate detection of pre-failure deformation and rockfalls with a high temporal resolution.
Vipasana Sharma, Sushil Kumar, and Rama Sushil
Nat. Hazards Earth Syst. Sci., 23, 2523–2530, https://doi.org/10.5194/nhess-23-2523-2023, https://doi.org/10.5194/nhess-23-2523-2023, 2023
Short summary
Short summary
Snow avalanches are a natural hazard that can cause danger to human lives. This threat can be reduced by accurate prediction of the danger levels. The development of mathematical models based on past data and present conditions can help to improve the accuracy of prediction. This research aims to develop a neural-network-based model for correlating complex relationships between the meteorological variables and the profile variables.
Guillermo Tamburini-Beliveau, Sebastián Balbarani, and Oriol Monserrat
Nat. Hazards Earth Syst. Sci., 23, 1987–1999, https://doi.org/10.5194/nhess-23-1987-2023, https://doi.org/10.5194/nhess-23-1987-2023, 2023
Short summary
Short summary
Landslides and ground deformation associated with the construction of a hydropower mega dam in the Santa Cruz River in Argentine Patagonia have been monitored using radar and optical satellite data, together with the analysis of technical reports. This allowed us to assess the integrity of the construction, providing a new and independent dataset. We have been able to identify ground deformation trends that put the construction works at risk.
Adrian Wicki, Peter Lehmann, Christian Hauck, and Manfred Stähli
Nat. Hazards Earth Syst. Sci., 23, 1059–1077, https://doi.org/10.5194/nhess-23-1059-2023, https://doi.org/10.5194/nhess-23-1059-2023, 2023
Short summary
Short summary
Soil wetness measurements are used for shallow landslide prediction; however, existing sites are often located in flat terrain. Here, we assessed the ability of monitoring sites at flat locations to detect critically saturated conditions compared to if they were situated at a landslide-prone location. We found that differences exist but that both sites could equally well distinguish critical from non-critical conditions for shallow landslide triggering if relative changes are considered.
Anirudh Rao, Jungkyo Jung, Vitor Silva, Giuseppe Molinario, and Sang-Ho Yun
Nat. Hazards Earth Syst. Sci., 23, 789–807, https://doi.org/10.5194/nhess-23-789-2023, https://doi.org/10.5194/nhess-23-789-2023, 2023
Short summary
Short summary
This article presents a framework for semi-automated building damage assessment due to earthquakes from remote-sensing data and other supplementary datasets including high-resolution building inventories, while also leveraging recent advances in machine-learning algorithms. For three out of the four recent earthquakes studied, the machine-learning framework is able to identify over 50 % or nearly half of the damaged buildings successfully.
Jan Freihardt and Othmar Frey
Nat. Hazards Earth Syst. Sci., 23, 751–770, https://doi.org/10.5194/nhess-23-751-2023, https://doi.org/10.5194/nhess-23-751-2023, 2023
Short summary
Short summary
In Bangladesh, riverbank erosion occurs every year during the monsoon and affects thousands of households. Information on locations and extent of past erosion can help anticipate where erosion might occur in the upcoming monsoon season and to take preventive measures. In our study, we show how time series of radar satellite imagery can be used to retrieve information on past erosion events shortly after the monsoon season using a novel interactive online tool based on the Google Earth Engine.
Jiale Qian, Yunyan Du, Jiawei Yi, Fuyuan Liang, Nan Wang, Ting Ma, and Tao Pei
Nat. Hazards Earth Syst. Sci., 23, 317–328, https://doi.org/10.5194/nhess-23-317-2023, https://doi.org/10.5194/nhess-23-317-2023, 2023
Short summary
Short summary
Human activities across China show a similar trend in response to rains. However, urban resilience varies significantly by region. The northwestern arid region and the central underdeveloped areas are very fragile, and even low-intensity rains can trigger significant human activity anomalies. By contrast, even high-intensity rains might not affect residents in the southeast.
Seok Bum Hong, Hong Sik Yun, Sang Guk Yum, Seung Yeop Ryu, In Seong Jeong, and Jisung Kim
Nat. Hazards Earth Syst. Sci., 22, 3435–3459, https://doi.org/10.5194/nhess-22-3435-2022, https://doi.org/10.5194/nhess-22-3435-2022, 2022
Short summary
Short summary
This study advances previous models through machine learning and multi-sensor-verified results. Using spatial and meteorological data from the study area (Suncheon–Wanju Highway in Gurye-gun), the amount and location of black ice were modelled based on system dynamics to predict black ice and then simulated with the geographic information system (m2). Based on the model results, multiple sensors were buried at four selected points in the study area, and the model was compared with sensor data.
Edward E. Salakpi, Peter D. Hurley, James M. Muthoka, Adam B. Barrett, Andrew Bowell, Seb Oliver, and Pedram Rowhani
Nat. Hazards Earth Syst. Sci., 22, 2703–2723, https://doi.org/10.5194/nhess-22-2703-2022, https://doi.org/10.5194/nhess-22-2703-2022, 2022
Short summary
Short summary
The devastating effects of recurring drought conditions are mostly felt by pastoralists that rely on grass and shrubs as fodder for their animals. Using historical information from precipitation, soil moisture, and vegetation health data, we developed a model that can forecast vegetation condition and the probability of drought occurrence up till a 10-week lead time with an accuracy of 74 %. Our model can be adopted by policymakers and relief agencies for drought early warning and early action.
Edward E. Salakpi, Peter D. Hurley, James M. Muthoka, Andrew Bowell, Seb Oliver, and Pedram Rowhani
Nat. Hazards Earth Syst. Sci., 22, 2725–2749, https://doi.org/10.5194/nhess-22-2725-2022, https://doi.org/10.5194/nhess-22-2725-2022, 2022
Short summary
Short summary
The impact of drought may vary in a given region depending on whether it is dominated by trees, grasslands, or croplands. The differences in impact can also be the agro-ecological zones within the region. This paper proposes a hierarchical Bayesian model (HBM) for forecasting vegetation condition in spatially diverse areas. Compared to a non-hierarchical model, the HBM proved to be a more natural method for forecasting drought in areas with different land covers and
agro-ecological zones.
Weijie Zou, Yi Zhou, Shixin Wang, Futao Wang, Litao Wang, Qing Zhao, Wenliang Liu, Jinfeng Zhu, Yibing Xiong, Zhenqing Wang, and Gang Qin
Nat. Hazards Earth Syst. Sci., 22, 2081–2097, https://doi.org/10.5194/nhess-22-2081-2022, https://doi.org/10.5194/nhess-22-2081-2022, 2022
Short summary
Short summary
Landslide dams are secondary disasters caused by landslides, which can cause great damage to mountains. We have proposed a procedure to calculate the key parameters of these dams that uses only a single remote-sensing image and a pre-landslide DEM combined with landslide theory. The core of this study is a modeling problem. We have found the bridge between the theory of landslide dams and the requirements of disaster relief.
C. Scott Watson, John R. Elliott, Susanna K. Ebmeier, María Antonieta Vásquez, Camilo Zapata, Santiago Bonilla-Bedoya, Paulina Cubillo, Diego Francisco Orbe, Marco Córdova, Jonathan Menoscal, and Elisa Sevilla
Nat. Hazards Earth Syst. Sci., 22, 1699–1721, https://doi.org/10.5194/nhess-22-1699-2022, https://doi.org/10.5194/nhess-22-1699-2022, 2022
Short summary
Short summary
We assess how greenspaces could guide risk-informed planning and reduce disaster risk for the urbanising city of Quito, Ecuador, which experiences earthquake, volcano, landslide, and flood hazards. We use satellite data to evaluate the use of greenspaces as safe spaces following an earthquake. We find disparities regarding access to and availability of greenspaces. The availability of greenspaces that could contribute to community resilience is high; however, many require official designation.
Seth Bryant, Heather McGrath, and Mathieu Boudreault
Nat. Hazards Earth Syst. Sci., 22, 1437–1450, https://doi.org/10.5194/nhess-22-1437-2022, https://doi.org/10.5194/nhess-22-1437-2022, 2022
Short summary
Short summary
The advent of new satellite technologies improves our ability to study floods. While the depth of water at flooded buildings is generally the most important variable for flood researchers, extracting this accurately from satellite data is challenging. The software tool presented here accomplishes this, and tests show the tool is more accurate than competing tools. This achievement unlocks more detailed studies of past floods and improves our ability to plan for and mitigate disasters.
Tadas Nikonovas, Allan Spessa, Stefan H. Doerr, Gareth D. Clay, and Symon Mezbahuddin
Nat. Hazards Earth Syst. Sci., 22, 303–322, https://doi.org/10.5194/nhess-22-303-2022, https://doi.org/10.5194/nhess-22-303-2022, 2022
Short summary
Short summary
Extreme fire episodes in Indonesia emit large amounts of greenhouse gasses and have negative effects on human health in the region. In this study we show that such burning events can be predicted several months in advance in large parts of Indonesia using existing seasonal climate forecasts and forest cover change datasets. A reliable early fire warning system would enable local agencies to prepare and mitigate the worst of the effects.
Yahong Liu and Jin Zhang
Nat. Hazards Earth Syst. Sci., 22, 227–244, https://doi.org/10.5194/nhess-22-227-2022, https://doi.org/10.5194/nhess-22-227-2022, 2022
Short summary
Short summary
Through a comprehensive analysis of the current remote sensing technology resources, this paper establishes the database to realize the unified management of heterogeneous sensor resources and proposes a capability evaluation method of remote sensing cooperative technology in geohazard emergencies, providing a decision-making basis for the establishment of remote sensing cooperative observations in geohazard emergencies.
Diego Guenzi, Danilo Godone, Paolo Allasia, Nunzio Luciano Fazio, Michele Perrotti, and Piernicola Lollino
Nat. Hazards Earth Syst. Sci., 22, 207–212, https://doi.org/10.5194/nhess-22-207-2022, https://doi.org/10.5194/nhess-22-207-2022, 2022
Short summary
Short summary
In the Apulia region (southeastern Italy) we are monitoring a soft-rock coastal cliff using webcams and strain sensors. In this urban and touristic area, coastal recession is extremely rapid and rockfalls are very frequent. In our work we are using low-cost and open-source hardware and software, trying to correlate both meteorological information with measures obtained from crack meters and webcams, aiming to recognize potential precursor signals that could be triggered by instability phenomena.
Natalie Brožová, Tommaso Baggio, Vincenzo D'Agostino, Yves Bühler, and Peter Bebi
Nat. Hazards Earth Syst. Sci., 21, 3539–3562, https://doi.org/10.5194/nhess-21-3539-2021, https://doi.org/10.5194/nhess-21-3539-2021, 2021
Short summary
Short summary
Surface roughness plays a great role in natural hazard processes but is not always well implemented in natural hazard modelling. The results of our study show how surface roughness can be useful in representing vegetation and ground structures, which are currently underrated. By including surface roughness in natural hazard modelling, we could better illustrate the processes and thus improve hazard mapping, which is crucial for infrastructure and settlement planning in mountainous areas.
Hugues Brenot, Nicolas Theys, Lieven Clarisse, Jeroen van Gent, Daniel R. Hurtmans, Sophie Vandenbussche, Nikolaos Papagiannopoulos, Lucia Mona, Timo Virtanen, Andreas Uppstu, Mikhail Sofiev, Luca Bugliaro, Margarita Vázquez-Navarro, Pascal Hedelt, Michelle Maree Parks, Sara Barsotti, Mauro Coltelli, William Moreland, Simona Scollo, Giuseppe Salerno, Delia Arnold-Arias, Marcus Hirtl, Tuomas Peltonen, Juhani Lahtinen, Klaus Sievers, Florian Lipok, Rolf Rüfenacht, Alexander Haefele, Maxime Hervo, Saskia Wagenaar, Wim Som de Cerff, Jos de Laat, Arnoud Apituley, Piet Stammes, Quentin Laffineur, Andy Delcloo, Robertson Lennart, Carl-Herbert Rokitansky, Arturo Vargas, Markus Kerschbaum, Christian Resch, Raimund Zopp, Matthieu Plu, Vincent-Henri Peuch, Michel Van Roozendael, and Gerhard Wotawa
Nat. Hazards Earth Syst. Sci., 21, 3367–3405, https://doi.org/10.5194/nhess-21-3367-2021, https://doi.org/10.5194/nhess-21-3367-2021, 2021
Short summary
Short summary
The purpose of the EUNADICS-AV (European Natural Airborne Disaster Information and Coordination System for Aviation) prototype early warning system (EWS) is to develop the combined use of harmonised data products from satellite, ground-based and in situ instruments to produce alerts of airborne hazards (volcanic, dust, smoke and radionuclide clouds), satisfying the requirement of aviation air traffic management (ATM) stakeholders (https://cordis.europa.eu/project/id/723986).
Johnny Douvinet, Anna Serra-Llobet, Esteban Bopp, and G. Mathias Kondolf
Nat. Hazards Earth Syst. Sci., 21, 2899–2920, https://doi.org/10.5194/nhess-21-2899-2021, https://doi.org/10.5194/nhess-21-2899-2021, 2021
Short summary
Short summary
This study proposes to combine results of research regarding the spatial inequalities due to the siren coverage, the political dilemma of siren activation, and the social problem of siren awareness and trust for people in France. Surveys were conducted using a range of complementary methods (GIS analysis, statistical analysis, questionnaires, interviews) through different scales. Results show that siren coverage in France is often determined by population density but not risks or disasters.
Fabio Brighenti, Francesco Carnemolla, Danilo Messina, and Giorgio De Guidi
Nat. Hazards Earth Syst. Sci., 21, 2881–2898, https://doi.org/10.5194/nhess-21-2881-2021, https://doi.org/10.5194/nhess-21-2881-2021, 2021
Short summary
Short summary
In this paper we propose a methodology to mitigate hazard in a natural environment in an urbanized context. The deformation of the ground is a precursor of paroxysms in mud volcanoes. Therefore, through the analysis of the deformation supported by a statistical approach, this methodology was tested to reduce the hazard around the mud volcano. In the future, the goal is that this dangerous area will become both a naturalistic heritage and a source of development for the community of the area.
Doris Hermle, Markus Keuschnig, Ingo Hartmeyer, Robert Delleske, and Michael Krautblatter
Nat. Hazards Earth Syst. Sci., 21, 2753–2772, https://doi.org/10.5194/nhess-21-2753-2021, https://doi.org/10.5194/nhess-21-2753-2021, 2021
Short summary
Short summary
Multispectral remote sensing imagery enables landslide detection and monitoring, but its applicability to time-critical early warning is rarely studied. We present a concept to operationalise its use for landslide early warning, aiming to extend lead time. We tested PlanetScope and unmanned aerial system images on a complex mass movement and compared processing times to historic benchmarks. Acquired data are within the forecasting window, indicating the feasibility for landslide early warning.
Michal Bíl, Pavel Raška, Lukáš Dolák, and Jan Kubeček
Nat. Hazards Earth Syst. Sci., 21, 2581–2596, https://doi.org/10.5194/nhess-21-2581-2021, https://doi.org/10.5194/nhess-21-2581-2021, 2021
Short summary
Short summary
The online landslide database CHILDA (Czech Historical Landslide Database) summarises information about landslides which occurred in the area of Czechia (the Czech Republic). The database is freely accessible via the https://childa.cz/ website. It includes 699 records (spanning the period of 1132–1989). Overall, 55 % of all recorded landslide events occurred only within 15 years of the extreme landslide incidence.
Anna Kruspe, Jens Kersten, and Friederike Klan
Nat. Hazards Earth Syst. Sci., 21, 1825–1845, https://doi.org/10.5194/nhess-21-1825-2021, https://doi.org/10.5194/nhess-21-1825-2021, 2021
Short summary
Short summary
Messages on social media can be an important source of information during crisis situations. This article reviews approaches for the reliable detection of informative messages in a flood of data. We demonstrate the varying goals of these approaches and present existing data sets. We then compare approaches based (1) on keyword and location filtering, (2) on crowdsourcing, and (3) on machine learning. We also point out challenges and suggest future research.
Enrique Guillermo Cordaro, Patricio Venegas-Aravena, and David Laroze
Nat. Hazards Earth Syst. Sci., 21, 1785–1806, https://doi.org/10.5194/nhess-21-1785-2021, https://doi.org/10.5194/nhess-21-1785-2021, 2021
Short summary
Short summary
We developed a methodology that generates free externally disturbed magnetic variations in ground magnetometers close to the Chilean convergent margin. Spectral analysis (~ mHz) and magnetic anomalies increased prior to large Chilean earthquakes (Maule 2010, Mw 8.8; Iquique 2014, Mw 8.2; Illapel 2015, Mw 8.3). These findings relate to microcracks within the lithosphere due to stress state changes. This physical evidence should be thought of as a last stage of the earthquake preparation process.
Corey M. Scheip and Karl W. Wegmann
Nat. Hazards Earth Syst. Sci., 21, 1495–1511, https://doi.org/10.5194/nhess-21-1495-2021, https://doi.org/10.5194/nhess-21-1495-2021, 2021
Short summary
Short summary
For many decades, natural disasters have been monitored by trained analysts using multiple satellite images to observe landscape change. This approach is incredibly useful, but our new tool, HazMapper, offers researchers and the scientifically curious public a web-accessible
cloud-based tool to perform similar analysis. We intend for the tool to both be used in scientific research and provide rapid response to global natural disasters like landslides, wildfires, and volcanic eruptions.
Matti Wiegmann, Jens Kersten, Hansi Senaratne, Martin Potthast, Friederike Klan, and Benno Stein
Nat. Hazards Earth Syst. Sci., 21, 1431–1444, https://doi.org/10.5194/nhess-21-1431-2021, https://doi.org/10.5194/nhess-21-1431-2021, 2021
Short summary
Short summary
In this paper, we study when social media is an adequate source to find metadata about incidents that cannot be acquired by traditional means. We identify six major use cases: impact assessment and verification of model predictions, narrative generation, recruiting citizen volunteers, supporting weakly institutionalized areas, narrowing surveillance areas, and reporting triggers for periodical surveillance.
Hui Liu, Ya Hao, Wenhao Zhang, Hanyue Zhang, Fei Gao, and Jinping Tong
Nat. Hazards Earth Syst. Sci., 21, 1179–1194, https://doi.org/10.5194/nhess-21-1179-2021, https://doi.org/10.5194/nhess-21-1179-2021, 2021
Short summary
Short summary
We trained a recurrent neural network model to classify microblogging posts related to urban waterlogging and establish an online monitoring system of urban waterlogging caused by flood disasters. We manually curated more than 4400 waterlogging posts to train the RNN model so that it can precisely identify waterlogging-related posts of Sina Weibo to timely determine urban waterlogging.
Roope Tervo, Ilona Láng, Alexander Jung, and Antti Mäkelä
Nat. Hazards Earth Syst. Sci., 21, 607–627, https://doi.org/10.5194/nhess-21-607-2021, https://doi.org/10.5194/nhess-21-607-2021, 2021
Short summary
Short summary
Predicting the number of power outages caused by extratropical storms is a key challenge for power grid operators. We introduce a novel method to predict the storm severity for the power grid employing ERA5 reanalysis data combined with a forest inventory. The storms are first identified from the data and then classified using several machine-learning methods. While there is plenty of room to improve, the results are already usable, with support vector classifier providing the best performance.
Michaela Wenner, Clément Hibert, Alec van Herwijnen, Lorenz Meier, and Fabian Walter
Nat. Hazards Earth Syst. Sci., 21, 339–361, https://doi.org/10.5194/nhess-21-339-2021, https://doi.org/10.5194/nhess-21-339-2021, 2021
Short summary
Short summary
Mass movements constitute a risk to property and human life. In this study we use machine learning to automatically detect and classify slope failure events using ground vibrations. We explore the influence of non-ideal though commonly encountered conditions: poor network coverage, small number of events, and low signal-to-noise ratios. Our approach enables us to detect the occurrence of rare events of high interest in a large data set of more than a million windowed seismic signals.
Luiz Felipe Galizia, Thomas Curt, Renaud Barbero, and Marcos Rodrigues
Nat. Hazards Earth Syst. Sci., 21, 73–86, https://doi.org/10.5194/nhess-21-73-2021, https://doi.org/10.5194/nhess-21-73-2021, 2021
Short summary
Short summary
This paper aims to provide a quantitative evaluation of three remotely sensed fire datasets which have recently emerged as an important resource to improve our understanding of fire regimes. Our findings suggest that remotely sensed fire datasets can be used to proxy variations in fire activity on monthly and annual timescales; however, caution is advised when drawing information from smaller fires (< 100 ha) across the Mediterranean region.
Philippe Weyrich, Anna Scolobig, Florian Walther, and Anthony Patt
Nat. Hazards Earth Syst. Sci., 20, 2811–2821, https://doi.org/10.5194/nhess-20-2811-2020, https://doi.org/10.5194/nhess-20-2811-2020, 2020
Patric Kellermann, Kai Schröter, Annegret H. Thieken, Sören-Nils Haubrock, and Heidi Kreibich
Nat. Hazards Earth Syst. Sci., 20, 2503–2519, https://doi.org/10.5194/nhess-20-2503-2020, https://doi.org/10.5194/nhess-20-2503-2020, 2020
Short summary
Short summary
The flood damage database HOWAS 21 contains object-specific flood damage data resulting from fluvial, pluvial and groundwater flooding. The datasets incorporate various variables of flood hazard, exposure, vulnerability and direct tangible damage at properties from several economic sectors. This paper presents HOWAS 21 and highlights exemplary analyses to demonstrate the use of HOWAS 21 flood damage data.
Giuseppe Esposito, Ivan Marchesini, Alessandro Cesare Mondini, Paola Reichenbach, Mauro Rossi, and Simone Sterlacchini
Nat. Hazards Earth Syst. Sci., 20, 2379–2395, https://doi.org/10.5194/nhess-20-2379-2020, https://doi.org/10.5194/nhess-20-2379-2020, 2020
Short summary
Short summary
In this article, we present an automatic processing chain aimed to support the detection of landslides that induce sharp land cover changes. The chain exploits free software and spaceborne SAR data, allowing the systematic monitoring of wide mountainous regions exposed to mass movements. In the test site, we verified a general accordance between the spatial distribution of seismically induced landslides and the detected land cover changes, demonstrating its potential use in emergency management.
Cited articles
Adaramola, M.: Climate Change And The Future Of Sustainability: The Impact
on Renewable Resources, CRC Press, 1–336, https://doi.org/10.1201/9781315366050, 2016.
Alcamo, J., Dronin, N., Endejan, M., Golubev, G., and Kirilenko, A.: A new
assessment of climate change impacts on food production shortfalls and water
availability in Russia, Global Environ. Change, 17, 429–444,
https://doi.org/10.1016/j.gloenvcha.2006.12.006, 2007.
Amirkhani, S., Tootchi, A., and Chaibakhsh, A.: Fault detection and isolation of gas turbine using series–parallel NARX model, ISA Trans., 120, 205–221, https://doi.org/10.1016/j.isatra.2021.03.019, 2022.
Arnell, N. W. and Gosling, S. N.: The impacts of climate change on river flood risk at the global scale, Climatic Change, 134, 387–401,
https://doi.org/10.1007/s10584-014-1084-5, 2016.
Baba, A., Tsatsanifos, C., el Gohary, F., Palerm, J., Khan, S., Mahmoudian, S. A., Ahmed, A. T., Tayfur, G., Dialynas, Y. G., and Angelakis, A. N.: Developments in water dams and water harvesting systems throughout history
in different civilizations, Int. J. Hydrol., 2, 155–171,
https://doi.org/10.15406/ijh.2018.02.00064, 2018.
Berga, L.: The Role of Hydropower in Climate Change Mitigation and Adaptation: A Review, Engineering, 2, 313–318, https://doi.org/10.1016/J.ENG.2016.03.004, 2016.
Berghuijs, W. R., Aalbers, E. E., Larsen, J. R., Trancoso, R., and Woods, R.
A.: Recent changes in extreme floods across multiple continents, Environ. Res. Lett., 12, 114035, https://doi.org/10.1088/1748-9326/aa8847, 2017.
Booth, D. B. and Bledsoe, B. P.: Streams and urbanization, in: The Water
Environment of Cities, edited by: Baker, L. A., Springer US, Boston, MA,
93–123, https://doi.org/10.1007/978-0-387-84891-4_6, 2009.
Bradshaw, C. J. A., Sodhi, N. S., Peh, K. S. H., and Brook, B. W.: Global
evidence that deforestation amplifies flood risk and severity in the developing world, Global Change Biol., 13, 2379–2395,
https://doi.org/10.1111/j.1365-2486.2007.01446.x, 2007.
Castelletti, A., Pianosi, F., and Soncini-Sessa, R.: Water reservoir control
under economic, social and environmental constraints, Automatica, 44,
1595–1607, https://doi.org/10.1016/j.automatica.2008.03.003, 2008.
Confederación Hidrográfica del Miño-Sil: Plan hidrológico de
la parte española de la Demarcación Hidrográfica del
Miño-Sil, 2015–2021,
https://www.chminosil.es/images/planificacion/proyecto-ph-2015-2021-vca/DOCUMENTO_DE_SINTESIS.pdf
(last access: 29 November 2022), 2016.
de la Paix, M. J., Lanhai, L., Xi, C., Ahmed, S., and Varenyam, A.: Soil
degradation and altered flood risk as a consequence of deforestation, Land
Degrad. Dev., 24, 478–485, https://doi.org/10.1002/ldr.1147, 2013.
Dozat, T.: Incorporating Nesterov Momentum into Adam, in: ICLR Workshop,
2–4 May 2016, San Juan, Puerto Rico, 2013–2016,
https://openreview.net/forum?id=OM0jvwB8jIp57ZJjtNEZ (last access: 29 November 2022), 2016.
Elliott, J., Deryng, D., Müller, C., Frieler, K., Konzmann, M., Gerten,
D., Glotter, M., Flörke, M., Wada, Y., Best, N., Eisner, S., Fekete, B.
M., Folberth, C., Foster, I., Gosling, S. N., Haddeland, I., Khabarov, N.,
Ludwig, F., Masaki, Y., Olin, S., Rosenzweig, C., Ruane, A. C., Satoh, Y.,
Schmid, E., Stacke, T., Tang, Q., and Wisser, D.: Constraints and potentials
of future irrigation water availability on agricultural production under
climate change, P. Natl. Acad. Sci. USA, 111, 3239–3244, https://doi.org/10.1073/pnas.1222474110, 2014.
Emami, S. and Parsa, J.: Comparative evaluation of imperialist competitive
algorithm and artificial neural networks for estimation of reservoirs storage capacity, Appl. Water Sci., 10, 177, https://doi.org/10.1007/s13201-020-01259-3, 2020.
Farizawani, A., Puteh, M., Marina, Y., and Rivaie, A.: A review of artificial neural network learning rule based on multiple variant of conjugate gradient approaches, J. Phys.: Conf. Ser., 1529, 022–040, https://doi.org/10.1088/1742-6596/1529/2/022040, 2020.
Fernández-Nóvoa, D., deCastro, M., Des, M., Costoya, X., Mendes, R.,
and Gómez-Gesteira, M.: Characterization of Iberian turbid plumes by
means of synoptic patterns obtained through MODIS imagery, J. Sea Res., 126, 12–25, https://doi.org/10.1016/j.seares.2017.06.013, 2017.
Field, C. B., Barros, V., Stocker, T. F., Dahe, Q., Jon Dokken, D., Ebi, K.
L., Mastrandrea, M. D., Mach, K. J., Plattner, G. K., Allen, S. K., Tignor,
M., and Midgley, P. M.: Managing the risks of extreme events and disasters
to advance climate change adaptation: Special report of the intergovernmental panel on climate change, Cambridge University Press, 1–582, https://doi.org/10.1017/CBO9781139177245, 2012.
Géron, A.: Hands-on machine learning with Scikit-Learn, Keras and
TensorFlow: concepts, tools, and techniques to build intelligent systems,
O'Reilly Media, Inc., 851 pp., ISBN 9781492032649, 2019.
Ghorbani, M. A., Deo, R. C., Karimi, V., Kashani, M. H., and Ghorbani, S.:
Design and implementation of a hybrid MLP-GSA model with multi-layer perceptron-gravitational search algorithm for monthly lake water level
forecasting, Stoch. Environ. Res. Risk A., 33, 125–147, https://doi.org/10.1007/s00477-018-1630-1, 2019.
Guzman, S. M., Paz, J. O., and Tagert, M. L. M.: The Use of NARX Neural Networks to Forecast Daily Groundwater Levels, Water Resour. Manage., 31, 1591–1603, https://doi.org/10.1007/s11269-017-1598-5, 2017.
Hallegatte, S.: A Cost Effective Solution to Reduce Disaster Losses in
Developing Countries: HydroMeteorological Services, Early Warning and Evacuation, World Bank policy research paper No. 6058, The World Bank, Washington, DC, https://doi.org/10.1596/1813-9450-6058, 2012.
Hochreiter, S. and Schmidhuber, J.: Long Short-Term Memory, Neural Comput., 9, 1735–1780, https://doi.org/10.1162/neco.1997.9.8.1735, 1997.
Jeuland, M., Baker, J., Bartlett, R., and Lacombe, G.: The costs of uncoordinated infrastructure management in multi-reservoir river basins,
Environ. Res. Lett., 9, 105006, https://doi.org/10.1088/1748-9326/9/10/105006, 2014.
Jonkman, S. N.: Global perspectives on loss of human life caused by floods,
Nat. Hazards, 34, 151–175, https://doi.org/10.1007/s11069-004-8891-3, 2005.
Kingma, D. P. and Ba, J.: Adam: A Method for Stochastic Optimization,
ARXIV: preprint, https://doi.org/10.48550/ARXIV.1412.6980, 2014.
Kratzert, F., Klotz, D., Brenner, C., Schulz, K., and Herrnegger, M.:
Rainfall-runoff modelling using Long Short-Term Memory (LSTM) networks,
Hydrol. Earth Syst. Sci., 22, 6005–6022, https://doi.org/10.5194/hess-22-6005-2018, 2018.
Le, X. H., Ho, H. V., Lee, G., and Jung, S.: Application of Long Short-Term
Memory (LSTM) neural network for flood forecasting, Water, 11, 1387, https://doi.org/10.3390/w11071387, 2019.
Lee, S.-Y., Hamlet, A. F., Fitzgerald, C. J., and Burges, S. J.: Optimized
Flood Control in the Columbia River Basin for a Global Warming Scenario, J. Water Resour. Plan. Manage., 135, 440–450, https://doi.org/10.1061/(asce)0733-9496(2009)135:6(440), 2009.
Lee, W. K. and Tuan Resdi, T. A.: Simultaneous hydrological prediction at
multiple gauging stations using the NARX network for Kemaman catchment,
Terengganu, Malaysia, Hydrolog. Sci. J., 61, 2930–2945, https://doi.org/10.1080/02626667.2016.1174333, 2016.
Lin, T., Horne, B. G., Tiňo, P., and Giles, C. L.: Learning long-term
dependencies in NARX recurrent neural networks, IEEE T. Neural Netw., 7, 1329–1338, https://doi.org/10.1109/72.548162, 1996.
Liu, C., Guo, L., Ye, L., Zhang, S., Zhao, Y., and Song, T.: A review of
advances in China's flash flood early-warning system, Nat. Hazards, 92,
619–634, https://doi.org/10.1007/s11069-018-3173-7, 2018.
Livingstone, D. J., Manallack, D. T., and Tetko, I. v.: Data modelling with
neural networks: Advantages and limitations, J. Comput.-Aid. Molec. Design, 11, 135–142, https://doi.org/10.1023/A:1008074223811, 1997.
Markham, I. S. and Rakes, T. R.: The effect of sample size and variability
of data on the comparative performance of artificial neural networks and
regression, Comput. Operat. Res., 25, 251–263, https://doi.org/10.1016/S0305-0548(97)00074-9, 1998.
Marques, G. F. and Tilmant, A.: The economic value of coordination in large-scale multireservoir systems: The Parana River case, Water Resour. Res., 49, 7546–7557, https://doi.org/10.1002/2013WR013679, 2013.
Masters, D. and Luschi, C.: Revisiting Small Batch Training for Deep Neural
Networks, ARXIV: preprint, https://doi.org/10.48550/ARXIV.1804.07612, 2018.
MathWorks Inc.: Design Time Series NARX Feedback Neural Networks – MATLAB & Simulink,
https://es.mathworks.com/help/deeplearning/ug/design-time-series-narx-feedback-neural-networks.html,
last access: 29 November 2022.
Moriasi, D. N., Arnold, J. G., van Liew, M. W., Bingner, R. L., Harmel, R. D., and Veith, T. L.: Model Evaluation Guidelines for Systematic Quantification of Accuracy in Watershed Simulations, T. ASABE, 50, 885–900, https://doi.org/10.13031/2013.23153, 2007.
Narendra, K. S. and Parthasarathy, K.: Identification and Control of Dynamical Systems Using Neural Networks, IEEE T. Neural Netw., 1, 4–27, https://doi.org/10.1109/72.80202, 1990.
Nash, J. E. and Sutcliffe, J. V.: River flow forecasting through conceptual
models part I – A discussion of principles, J. Hydrol., 10, 282–290, https://doi.org/10.1016/0022-1694(70)90255-6, 1970.
O'Malley, T., Bursztein, E., Long, J., Chollet, F., Jin, H., Invernizzi, L.,
and others: KerasTuner, GitHub [software], https://github.com/keras-team/keras-tuner (last access: 29 November 2022), 2019.
Passerotti, G., Massazza, G., Pezzoli, A., Bigi, V., Zsótér, E., and
Rosso, M.: Hydrological model application in the Sirba river: Early warning
system and GloFAS improvements, Water, 12, 620, https://doi.org/10.3390/w12030620, 2020.
Quinn, J. D., Reed, P. M., Giuliani, M., and Castelletti, A.: What Is Controlling Our Control Rules? Opening the Black Box of Multireservoir
Operating Policies Using Time-Varying Sensitivity Analysis, Water Resour. Res., 55, 5962–5984, https://doi.org/10.1029/2018WR024177, 2019.
RapidMiner Inc.: Neural Net – RapidMiner Documentation,
https://docs.rapidminer.com/latest/studio/operators/modeling/predictive/neural_nets/neural_net.html,
last access: 29 November 2022.
Rashidi, H. H., Tran, N. K., Betts, E. V., Howell, L. P., and Green, R.:
Artificial Intelligence and Machine Learning in Pathology: The Present
Landscape of Supervised Methods, Academic Pathol., 6, 2374289519873088,
https://doi.org/10.1177/2374289519873088, 2019.
Rjeily, Y. A., Abbas, O., Sadek, M., Shahrour, I., and Chehade, F. H.: Flood
forecasting within urban drainage systems using NARX neural network, Water
Sci. Technol., 76, 2401–2412, https://doi.org/10.2166/wst.2017.409, 2017.
Rosburg, T. T., Nelson, P. A., and Bledsoe, B. P.: Effects of Urbanization
on Flow Duration and Stream Flashiness: A Case Study of Puget Sound Streams,
Western Washington, USA, J. Am. Water Resour. Assoc., 53, 493–507, https://doi.org/10.1111/1752-1688.12511, 2017.
Rougé, C., Reed, P. M., Grogan, D. S., Zuidema, S., Prusevich, A., Glidden, S., Lamontagne, J. R., and Lammers, R. B.: Coordination and control-limits in standard representations of multi-reservoir operations in
hydrological modeling, Hydrol. Earth Syst. Sci., 25, 1365–1388,
https://doi.org/10.5194/hess-25-1365-2021, 2021.
Sammen, S. S., Mohamed, T. A., Ghazali, A. H., El-Shafie, A. H., and Sidek,
L. M.: Generalized Regression Neural Network for Prediction of Peak Outflow
from Dam Breach, Water Resour. Manage., 31, 549–562, https://doi.org/10.1007/s11269-016-1547-8, 2017.
Solomatine, D. P. and Ostfeld, A.: Data-driven modelling: Some past experiences and new approaches, J. Hydroinform., 10, 3–22,
https://doi.org/10.2166/hydro.2008.015, 2008.
Sutskever, I., Vinyals, O., and Le, Q. V.: Sequence to Sequence Learning with
Neural Networks, in: Advances in Neural Information Processing Systems,
Curran Associates, Inc., ISBN 9781510800410, https://proceedings.neurips.cc/paper/2014/file/a14ac55a4f27472c5d894ec1c3c743d2-Paper.pdf
(last access: 29 November 2022), 2014.
Taghi Sattari, M., Yurekli, K., and Pal, M.: Performance evaluation of
artificial neural network approaches in forecasting reservoir inflow, Appl. Math. Model., 36, 2649–2657, https://doi.org/10.1016/j.apm.2011.09.048, 2012.
TensorFlow Developers: TensorFlow, Zenodo [software], https://doi.org/10.5281/ZENODO.4724125, 2022.
Wallemacq, P., House, R., Below, R., and McLean, D.: Economic losses,
poverty & disasters: 1998–2017, Brussels, Belgium, https://www.undrr.org/publication/economic-losses-poverty-disasters-1998-2017
(last access: 29 November 2022) 2018.
Xiang, Z., Yan, J., and Demir, I.: A Rainfall-Runoff Model With LSTM-Based
Sequence-to-Sequence Learning, Water Resour. Res., 56, e2019WR02532, https://doi.org/10.1029/2019WR025326, 2020.
Xie, H., Tang, H., and Liao, Y. H.: Time series prediction based on narx
neural networks: An advanced approach, in: Proceedings of the 2009 International Conference on Machine Learning and Cybernetics, 12–15 July 2009, Baoding, Hebei, China, 1275–1279, https://doi.org/10.1109/ICMLC.2009.5212326, 2009.
Xiong, W., Conway, D., Lin, E., Xu, Y., Ju, H., Jiang, J., Holman, I., and
Li, Y.: Future cereal production in China: The interaction of climate change, water availability and socio-economic scenarios, Global Environ. Change, 19, 34–44, https://doi.org/10.1016/j.gloenvcha.2008.10.006, 2009.
Yang, S., Yang, D., Chen, J., and Zhao, B.: Real-time reservoir operation
using recurrent neural networks and inflow forecast from a distributed
hydrological model, J. Hydrol., 579, 124229, https://doi.org/10.1016/j.jhydrol.2019.124229, 2019.
Zhang, D., Lin, J., Peng, Q., Wang, D., Yang, T., Sorooshian, S., Liu, X.,
and Zhuang, J.: Modeling and simulating of reservoir operation using the
artificial neural network, support vector regression, deep learning algorithm, J. Hydrol., 565, 720–736, https://doi.org/10.1016/j.jhydrol.2018.08.050, 2018.
Short summary
Extreme events have increased in the last few decades; having a good estimation of the outflow of a reservoir can be an advantage for water management or early warning systems. This study analyzes the efficiency of different machine learning techniques to predict reservoir outflow. The results obtained showed that the proposed models provided a good estimation of the outflow of the reservoirs, improving the results obtained with classical approaches.
Extreme events have increased in the last few decades; having a good estimation of the outflow...
Special issue
Altmetrics
Final-revised paper
Preprint