Articles | Volume 21, issue 4
Research article 06 Apr 2021
Research article | 06 Apr 2021
Online urban-waterlogging monitoring based on a recurrent neural network for classification of microblogging text
Hui Liu et al.
Related subject area
Databases, GIS, Remote Sensing, Early Warning Systems and Monitoring TechnologiesPredicting power outages caused by extratropical stormsNear-real-time automated classification of seismic signals of slope failures with continuous random forestsAssessing the accuracy of remotely sensed fire datasets across the southwestern Mediterranean BasinLong-term magnetic anomalies and its possible relationship to the latest Greater Chilean earthquakes in the context of the seismo-electromagnetic theoryResponses to severe weather warnings and affective decision-makingThe object-specific flood damage database HOWAS 21A spaceborne SAR-based procedure to support the detection of landslidesGIS-based DRASTIC and composite DRASTIC indices for assessing groundwater vulnerability in the Baghin aquifer, Kerman, IranOpportunities and Risks of Disaster Data from Social Media: A Systematic Review of Incident InformationReview article: The spatial dimension in the assessment of urban socio-economic vulnerability related to geohazardsHazMapper: A global open-source natural hazard mapping application in Google Earth EngineDesign and implementation of a mobile device app for network-based earthquake early warning systems (EEWSs): application to the PRESTo EEWS in southern ItalyCCAF-DB: the Caribbean and Central American active fault databaseEvaluation of a combined drought indicator and its potential for agricultural drought prediction in southern SpainStudy on real-time correction of site amplification factorThree-dimensional rockfall shape back analysis: methods and implicationsEffects of high-resolution geostationary satellite imagery on the predictability of tropical thunderstorms over Southeast AsiaInSAR technique applied to the monitoring of the Qinghai–Tibet RailwayUnderstanding the spatiotemporal development of human settlement in hurricane-prone areas on the US Atlantic and Gulf coasts using nighttime remote sensingPre-disaster mapping with drones: an urban case study in Victoria, British Columbia, CanadaNew approaches to modelling of local seismic amplification susceptibility using direct characteristics of influencing criteria: case study of Bam City, IranSMC-Flood database: a high-resolution press database on flood cases for the Spanish Mediterranean coast (1960–2015)Statistical analysis for satellite-index-based insurance to define damaged pasture thresholdsMonitoring the seasonal dynamics of soil salinization in the Yellow River delta of China using Landsat dataTowards early warning of gravitational slope failure with co-detection of microseismic activity: the case of an active rock glacierDangerous degree forecast of soil loss on highway slopes in mountainous areas of the Yunnan–Guizhou Plateau (China) using the Revised Universal Soil Loss EquationAssessment of geodetic velocities using GPS campaign measurements over long baseline lengthsResponse time to flood events using a social vulnerability index (ReTSVI)Delimitation of flood areas based on a calibrated a DEM and geoprocessing: case study on the Uruguay River, Itaqui, southern BrazilIdentification and classification of urban micro-vulnerabilities in tsunami evacuation routes for the city of Iquique, ChileUsability of aerial video footage for 3-D scene reconstruction and structural damage assessmentUsing kites for 3-D mapping of gullies at decimetre-resolution over several square kilometres: a case study on the Kamech catchment, TunisiaA new approach for land degradation and desertification assessment using geospatial techniquesActive tectonics of the onshore Hengchun Fault using UAS DSM combined with ALOS PS-InSAR time series (Southern Taiwan)Geomorphological evolution of landslides near an active normal fault in northern Taiwan, as revealed by lidar and unmanned aircraft system dataSlope stability and rockfall assessment of volcanic tuffs using RPAS with 2-D FEM slope modellingUse of a remotely piloted aircraft system for hazard assessment in a rocky mining area (Lucca, Italy)A method for using unmanned aerial vehicles for emergency investigation of single geo-hazards and sample applications of this methodBrief communication: Vehicle routing problem and UAV application in the post-earthquake scenarioMultiple remote-sensing assessment of the catastrophic collapse in Langtang Valley induced by the 2015 Gorkha earthquakeGB-InSAR monitoring of slope deformations in a mountainous area affected by debris flow eventsBig data managing in a landslide early warning system: experience from a ground-based interferometric radar applicationApplication of UAV-SfM photogrammetry and aerial lidar to a disastrous flood: repeated topographic measurement of a newly formed crevasse splay of the Kinu River, central JapanApplication of Landsat-8 and ALOS-2 data for structural and landslide hazard mapping in Kelantan, MalaysiaDirect local building inundation depth determination in 3-D point clouds generated from user-generated flood imagesSignal frequency distribution and natural-time analyses from acoustic emission monitoring of an arched structure in the Castle of RacconigiProbabilistic flood extent estimates from social media flood observationsCoseismic displacements of the 14 November 2016 Mw 7.8 Kaikoura, New Zealand, earthquake using the Planet optical cubesat constellationTESSA: design and implementation of a platform for situational sea awarenessA multi-service data management platform for scientific oceanographic products
Roope Tervo, Ilona Láng, Alexander Jung, and Antti Mäkelä
Nat. Hazards Earth Syst. Sci., 21, 607–627,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,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,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.
Enrique Guillermo Cordaro, Patricio Venegas-Aravena, and David Laroze
Nat. Hazards Earth Syst. Sci. Discuss.,
Revised manuscript under review for NHESSShort summary
We developed a methodology that generate free-externally disturbed magnetic variations in ground magnetometers close to the Chilean convergent margin. Spectral analysis (~ mHZ) and magnetic anomalies increased prior large Chilean earthquakes (Maule 2010 Mw8.8, Iquique 2014 Mw8.2 and Illapel 2015 Mw8.3). These findings are related to micro cracks within lithosphere due changes in the stress states. These physical evidence should be thought as a last stage of earthquake preparation process.
Philippe Weyrich, Anna Scolobig, Florian Walther, and Anthony Patt
Nat. Hazards Earth Syst. Sci., 20, 2811–2821,
Patric Kellermann, Kai Schröter, Annegret H. Thieken, Sören-Nils Haubrock, and Heidi Kreibich
Nat. Hazards Earth Syst. Sci., 20, 2503–2519,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,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.
Mohammad Malakootian and Majid Nozari
Nat. Hazards Earth Syst. Sci., 20, 2351–2363,Short summary
The present study estimated the Kerman–Baghin aquifer vulnerability using DRASTIC and composite DRASTIC (CDRASTIC) indices with the aid of geographic information system (GIS) techniques. The aquifer vulnerability maps indicated very similar results, identifying the north-west parts of the aquifer as areas with high to very high vulnerability. According to the results, parts of the studied aquifer have a high vulnerability and require protective measures.
Matti Wiegmann, Jens Kersten, Hansi Senaratne, Martin Potthast, Friederike Klan, and Benno Stein
Nat. Hazards Earth Syst. Sci. Discuss.,
Revised manuscript accepted for NHESS
Diana Contreras, Alondra Chamorro, and Sean Wilkinson
Nat. Hazards Earth Syst. Sci., 20, 1663–1687,Short summary
The socio-economic condition of the population determines their vulnerability to earthquakes, tsunamis, volcanic eruptions, landslides, soil erosion and land degradation. This condition is estimated mainly from population censuses. The lack to access to basic services, proximity to hazard zones, poverty and population density highly influence the vulnerability of communities. Mapping the location of this vulnerable population makes it possible to prevent and mitigate their risk.
Corey M. Scheip and Karl W. Wegmann
Nat. Hazards Earth Syst. Sci. Discuss.,
Revised manuscript accepted for NHESSShort 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, allows researchers and the scientific-curious public a web-accessible cloud-based tool to perform similar analysis. We intend for the tool to be used both in scientific research and to provide rapid response to global natural disasters like landslides, wildfires, and volcanic eruptions.
Simona Colombelli, Francesco Carotenuto, Luca Elia, and Aldo Zollo
Nat. Hazards Earth Syst. Sci., 20, 921–931,Short summary
We developed a mobile app for Android devices which receives the alerts generated by a network-based early warning system, predicts the expected ground-shaking intensity and the available lead time at the user position, and provides customized messages to inform the user about the proper reaction to the alert. The app represents a powerful tool for informing in real time a wide audience of end users and stakeholders about the potential damaging shaking in the occurrence of an earthquake.
Richard Styron, Julio García-Pelaez, and Marco Pagani
Nat. Hazards Earth Syst. Sci., 20, 831–857,Short summary
The Caribbean and Central American region is both tectonically active and densely populated, leading to a large population that is exposed to earthquake hazards. Until now, no comprehensive fault data covering the region have been available. We present a new public fault database for Central America and the Caribbean that synthesizes published studies with new mapping from remote sensing to provide fault sources for the CCARA seismic hazard and risk analysis project and to aid future research.
María del Pilar Jiménez-Donaire, Ana Tarquis, and Juan Vicente Giráldez
Nat. Hazards Earth Syst. Sci., 20, 21–33,Short summary
A new combined drought indicator (CDI) is proposed that integrates rainfall, soil moisture and vegetation dynamics. The performance of this indicator was evaluated against crop damage data from agricultural insurance schemes in five different areas in SW Spain. Results show that this indicator was able to predict important droughts in 2004–2005 and 2011–2012, marked by crop damage of between 70 % and 95 % of the total insured area. This opens important applications for improving insurance schemes.
Quancai Xie, Qiang Ma, Jingfa Zhang, and Haiying Yu
Nat. Hazards Earth Syst. Sci., 19, 2827–2839,Short summary
This paper evaluates a new method for modeling the site amplification factor. Through implementing this method and making simulations for different cases, we find that this method shows better performance than the previous method and JMA report. We better understand the advantages and disadvantages of this method, although there are some problems that need to be considered carefully and solved; it shows good potential to be used in future earthquake early warning systems.
David A. Bonneau, D. Jean Hutchinson, Paul-Mark DiFrancesco, Melanie Coombs, and Zac Sala
Nat. Hazards Earth Syst. Sci., 19, 2745–2765,Short summary
In mountainous regions around the world rockfalls pose a hazard to infrastructure and society. To aid in our understanding and management of these complex hazards, an inventory can be compiled. Three-dimensional remote sensing data can be used to locate the source zones of these events and generate models of areas which detached. We address the way in which the shape of a rockfall object can be measured. The shape of a rockfall has implications for forward modelling of potential runout zones.
Kwonmin Lee, Hye-Sil Kim, and Yong-Sang Choi
Nat. Hazards Earth Syst. Sci., 19, 2241–2248,Short summary
This study examined the advances in the predictability of thunderstorms using geostationary satellite imageries. Our present results show that by using the latest geostationary satellite data (with a resolution of 2 km and 10 min), thunderstorms can be predicted 90–180 min ahead of their mature state. These data can capture the rapidly growing cloud tops before the cloud moisture falls as precipitation and enable prompt preparation and the mitigation of hazards.
Qingyun Zhang, Yongsheng Li, Jingfa Zhang, and Yi Luo
Nat. Hazards Earth Syst. Sci., 19, 2229–2240,Short summary
Before the opening of the railway, the deformation of the Qinghai–Tibet Railway was very small and considered stable. After opening, the overall stability of the railway section was good. The main deformation areas are concentrated in the areas where railway lines turn and geological disasters are concentrated. In order to ensure the safety of railway operation, it is necessary to carry out long-term time series observation along the Qinghai–Tibet Railway.
Xiao Huang, Cuizhen Wang, and Junyu Lu
Nat. Hazards Earth Syst. Sci., 19, 2141–2155,Short summary
This study examined the spatiotemporal dynamics of nighttime satellite-derived human settlement in response to different levels of hurricane proneness in a period from 1992 to 2013. It confirms the
Snow Belt-to-Sun BeltUS population shift trend. The results also suggest that hurricane-exposed human settlement has grown in extent and area, as more hurricane exposure has experienced a larger increase rate in settlement intensity.
Maja Kucharczyk and Chris H. Hugenholtz
Nat. Hazards Earth Syst. Sci., 19, 2039–2051,Short summary
We performed pre-disaster 3-D mapping with a drone in downtown Victoria, BC, Canada. This was the first drone mapping mission over a Canadian city approved by Canada’s aviation authority. We were legally constrained to using a specific drone. The goal was to assess the quality of the 3-D map. Results indicate that the spatial accuracies achieved with this drone would allow for sub-meter building collapse detection, but the non-tilting camera was insufficient for mapping buildings in 3-D.
Reza Hassanzadeh, Mehdi Honarmand, Mahdieh Hossienjani Zadeh, and Farzin Naseri
Nat. Hazards Earth Syst. Sci., 19, 1989–2009,Short summary
This paper proposes a new model for evaluating local seismic amplification susceptibility by considering direct characteristics of influencing criteria and dealing with uncertainty of modelling through production of fuzzy membership functions and GIS. This model helps planners and decision makers easily produce local seismic amplification susceptibility to be incorporated in designing development plans of urban areas and to evaluate safety measures of existing infrastructure.
Salvador Gil-Guirado, Alfredo Pérez-Morales, and Francisco Lopez-Martinez
Nat. Hazards Earth Syst. Sci., 19, 1955–1971,Short summary
In this study the SMC-Flood database for the municipalities of the Mediterranean coast of mainland Spain is presented. This database has enabled the reconstruction of 3008 cases of flooding on a municipal scale between 1960 and 2015. The data analysis reveals a growing trend in the frequency and area affected by flood cases. The main novelty lies in the fact that we have detected a clear latitudinal gradient of growing intensity and severity of flood cases with a north–south direction.
Juan José Martín-Sotoca, Antonio Saa-Requejo, Rubén Moratiel, Nicolas Dalezios, Ioannis Faraslis, and Ana María Tarquis
Nat. Hazards Earth Syst. Sci., 19, 1685–1702,Short summary
Vegetation indices based on satellite images, such as the normalized difference vegetation index (NDVI), have been used for damaged pasture insurance. The occurrence of damage is usually defined by NDVI thresholds mainly based on normal statistics. In this work a pasture area in Spain was delimited by MODIS images. A statistical analysis of NDVI was applied to search for alternative distributions. Results show that generalized extreme value distributions present a better fit than normal ones.
Hongyan Chen, Gengxing Zhao, Yuhuan Li, Danyang Wang, and Ying Ma
Nat. Hazards Earth Syst. Sci., 19, 1499–1508,Short summary
Using Landsat data, the inversion model of soil salt content (SSC) for different seasons was determined in the Kenli District in the Yellow River Delta region of China. The SSC exhibited a gradual increasing trend from the southwest to northeast. The SSC accumulated in spring, decreased in summer, increased in autumn and reached its peak at the the end of winter. The results can provide data for the control of soil salt hazards and utilization of saline–alkali soil.
Jérome Faillettaz, Martin Funk, Jan Beutel, and Andreas Vieli
Nat. Hazards Earth Syst. Sci., 19, 1399–1413,Short summary
We developed a new strategy for real-time early warning of gravity-driven slope failures (such as landslides, rockfalls, glacier break-off, etc.). This method enables us to investigate natural slope stability based on continuous monitoring and interpretation of seismic waves generated by the potential instability. Thanks to a pilot experiment, we detected typical patterns of precursory events prior to slide events, demonstrating the potential of this method for real-word applications.
Yue Li, Shi Qi, Bin Liang, Junming Ma, Baihan Cheng, Cong Ma, Yidan Qiu, and Qinyan Chen
Nat. Hazards Earth Syst. Sci., 19, 757–774,Short summary
This study fully considers the characteristics of expressways in mountain areas. The catchment area is considered a prediction unit. The method of slope division is improved, and a method of improving the parameters in the model is proposed. Comparison and analysis with actual observation data show that the method of soil and water loss prediction adopted in this paper has less error and higher prediction accuracy than other models and can satisfy prediction requirements.
Huseyin Duman and Dogan Ugur Sanli
Nat. Hazards Earth Syst. Sci., 19, 571–582,Short summary
Research has been done to assess the performance of relative positioning over long baseline lengths in determining the accuracy of site velocities from GPS campaign measurements. GPS campaign measurements were generated from the IGS data, and the results were compared with PPP-derived findings. A major outcome of this study is that relative positioning over long baseline lengths produces similar accuracies to PPP. A newly proposed refinement method also improves the available PPP accuracy.
Alvaro Hofflinger, Marcelo A. Somos-Valenzuela, and Arturo Vallejos-Romero
Nat. Hazards Earth Syst. Sci., 19, 251–267,Short summary
In this work, we propose a novel methodology (ReTSVI) to integrate a social vulnerability index into flood hazard methodologies. ReTSVI combines a series of modules that are pieces of information that interact during an evacuation, such as evacuation rate curves, mobilization, inundation models, and social vulnerability indexes, to create an integrated map of the evacuation rate in a given location.
Paulo Victor N. Araújo, Venerando E. Amaro, Robert M. Silva, and Alexandre B. Lopes
Nat. Hazards Earth Syst. Sci., 19, 237–250,Short summary
This paper aims to map flood hazard areas under the influence of the Uruguay River, Itaqui (southern Brazil), using a calibrated digital elevation model (DEM), historic river level data and geoprocessing techniques. Assessment of the areas that can potentially be flooded can help to reduce the negative impact of flood events by supporting the process of land-use planning in areas exposed to flood hazards.
Gonzalo Álvarez, Marco Quiroz, Jorge León, and Rodrigo Cienfuegos
Nat. Hazards Earth Syst. Sci., 18, 2027–2039,Short summary
Evacuation planning has been recognized as one of the best tools for safeguarding the population against tsunami hazards. In this work we develop a novel methodology to identify and classify urban micro-vulnerabilities that may difficult pedestrian evacuation processes resulting from problems in urban design or informal uses of the public space. The correct identification and correction of these issues could make the difference in saving lives when the available time for evacuation is short.
Johnny Cusicanqui, Norman Kerle, and Francesco Nex
Nat. Hazards Earth Syst. Sci., 18, 1583–1598,Short summary
Aerial multi-perspective images can be used for the effective assessment of post-disaster structural damage. Alternatively, rapidly available video data can be processed for the same purpose. However, video quality characteristics are different than those of images taken with still cameras. The use of video data in post-disaster damage assessment has not been demonstrated. Based on a comparative assessment, our findings support the application of video data in post-disaster damage assessment.
Denis Feurer, Olivier Planchon, Mohamed Amine El Maaoui, Abir Ben Slimane, Mohamed Rached Boussema, Marc Pierrot-Deseilligny, and Damien Raclot
Nat. Hazards Earth Syst. Sci., 18, 1567–1582,Short summary
We present a method for acquiring very-high-resolution images for 3-D mapping of gullies over kilometre-square areas using kites. Kites used in appropriate conditions can be an advantageous alternative to light unmanned aircraft when local regulations or weather conditions hamper their use. We proved that kites can acquire images, allowing for high-quality 3-D coverage of large areas. We automatically detected and mapped gullies from a decimetre kite DEM with 74 % accuracy of the length.
Masoud Masoudi, Parviz Jokar, and Biswajeet Pradhan
Nat. Hazards Earth Syst. Sci., 18, 1133–1140,Short summary
The paper attempts to create a new technique for assessing the current state of land degradation. Assessment of land degradation is difficult, because it includes a complex process. This assessment, using RS and GIS seems to be more realistic in finding the degree of degradation, because it is more related to its impact on land productivity. It is hoped that this attempt, which is the first attempt of its kind in the world, will be found applicable for other regions.
Benoit Deffontaines, Kuo-Jen Chang, Johann Champenois, Kuan-Chuan Lin, Chyi-Tyi Lee, Rou-Fei Chen, Jyr-Ching Hu, and Samuel Magalhaes
Nat. Hazards Earth Syst. Sci., 18, 829–845,Short summary
To better settle the location and quantify the activity of the Hengchun Fault, we integrate UAS for geomorphologic data acquisitions, photograph and morphotectonic interpretation. Then PS-InSAR results, validated with GPS and leveling data, allow characterizing and quantifying the surface displacements. We confirm the geometry, characterization and quantification of the active sinistral transpressive Hengchun fault. The potential hazards are worthy of further investigation.
Kuo-Jen Chang, Yu-Chang Chan, Rou-Fei Chen, and Yu-Chung Hsieh
Nat. Hazards Earth Syst. Sci., 18, 709–727,Short summary
Several remote sensing techniques, i.e., aerial photographs, drone images, and airborne lidar, were used in this study to decipher the morphological features of obscure landslides in volcanic regions and how the observed features may be used for understanding landslide occurrence, subsequent geomorphological evolution, and potential hazards. Two large-scale landslides were characterized and quantified in this study.
Ákos Török, Árpád Barsi, Gyula Bögöly, Tamás Lovas, Árpád Somogyi, and Péter Görög
Nat. Hazards Earth Syst. Sci., 18, 583–597,Short summary
The present study demonstrates the application of drones and terrestrial laser scanner in stability assessment of steep, hardly accessible rock slopes that can endanger human lives. These technologies can be deployed very quickly, but data processing requires time. For reliable hazard evaluation, besides these techniques, engineering geological field work, laboratory tests of the mechanical properties of rocks and computer simulations are also necessary.
Riccardo Salvini, Giovanni Mastrorocco, Giuseppe Esposito, Silvia Di Bartolo, John Coggan, and Claudio Vanneschi
Nat. Hazards Earth Syst. Sci., 18, 287–302,Short summary
Remotely Piloted Aircraft System was used for the engineering geological investigation of a marble mine area in Italy. High resolution images were processed by using SfM techniques for obtaining an accurate and detailed three-dimensional model of the area. Geological and geometrical information was used for a preliminary stability analysis with focus on investigating the contribution of potential rock bridges of two large blocks that pose a potential hazard issue for the workforce.
Haifeng Huang, Jingjing Long, Wu Yi, Qinglin Yi, Guodong Zhang, and Bangjun Lei
Nat. Hazards Earth Syst. Sci., 17, 1961–1979,Short summary
Unmanned aerial vehicles are widely used in the emergency investigations of major natural hazards in a large area, but less commonly for single geo-hazards. Based on a number of successful practices in the Three Gorges Reservoir area, China, a complete UAV-based emergency investigation method of single geo-hazards is concluded. It can not only greatly reduce the time, strength and risks, but can also provide high-accuracy, high-definition valuable information to support emergency responses.
Marco Cannioto, Antonino D'Alessandro, Giosuè Lo Bosco, Salvatore Scudero, and Giovanni Vitale
Nat. Hazards Earth Syst. Sci., 17, 1939–1946,Short summary
Immediately after an earthquake it is crucial to perform the fastest recognition of the damaged area to rescue as much people is possible and to assess and map the damage scenario. We apply the vehicle routing problem (VRP) to a fleet of unmanned aerial vehicles (UAVs) to find the shortest routes and the best take-off sites. The simulation, performed with different autonomy ranges, is carried out in the town of Acireale (Italy), where a real-time accelerometric network has been installed.
Hiroto Nagai, Manabu Watanabe, Naoya Tomii, Takeo Tadono, and Shinichi Suzuki
Nat. Hazards Earth Syst. Sci., 17, 1907–1921,Short summary
We demonstrated an assessment of the sediments caused by a catastrophic avalanche, induced by the main shock of the 2015 Gorkha Earthquake in Nepal. A Japanese space-borne sensor, PALSAR-2, have a high potential for delineating the hazardous zone. Comparison of pre- and post-high-resolution topographic data estimates the avalanche-induced sediment volume as 5.51 × 106 m3. High-resolution satellite imagery revealed that it has multiple layers of sediment with different physical properties.
William Frodella, Teresa Salvatici, Veronica Pazzi, Stefano Morelli, and Riccardo Fanti
Nat. Hazards Earth Syst. Sci., 17, 1779–1793,Short summary
A local scale GB-InSAR system was implemented for mapping and monitoring slope landslide residual deformations and for early warning purposes in case of landslide reactivations, with the aim of assuring the safety of the valley inhabitants and the personnel involved in the post-event recovery phase. The here presented methodology could represent a useful contribution to a better understanding of landslide phenomena and decision making process during the post-emergency management activities.
Emanuele Intrieri, Federica Bardi, Riccardo Fanti, Giovanni Gigli, Francesco Fidolini, Nicola Casagli, Sandra Costanzo, Antonio Raffo, Giuseppe Di Massa, Giovanna Capparelli, and Pasquale Versace
Nat. Hazards Earth Syst. Sci., 17, 1713–1723,Short summary
Landslides are a threat not only to people but also to important infrastructure, like highways. Nowadays there are several monitoring systems that are able to detect slope displacements in order to give prompt alarms. On the other hand, such instruments produce a huge amount of information, which is often not totally used and which can also represent an issue for data storage and transmission. In this paper we explain how we dealt with the large quantity of data provided by one of these tools.
Atsuto Izumida, Shoichiro Uchiyama, and Toshihiko Sugai
Nat. Hazards Earth Syst. Sci., 17, 1505–1519,Short summary
Geomorphic impact of the 2015 flood of the Kinu River, which created a new crevasse splay on its floodplain, was quantified by volumetric calculations using three topographic data obtained by aerial laser scanning (ALS) and UAV photogrammetry. Topographic changes on the order of 0.1 m were detected, and the erosive character of the crevasse splay was revealed. The results suggest that a combination of ALS and UAV is useful for quantification of sudden topographic changes through disasters.
Amin Beiranvand Pour and Mazlan Hashim
Nat. Hazards Earth Syst. Sci., 17, 1285–1303,Short summary
L-band SAR remote sensing data are used for identification of high potential risk and susceptible zones for natural hazards of geological origin in tropical environments. Results of this investigation have great potential in terms of a solution to flood disaster management in tropical environments by providing important information to assess the natural hazards of geological origin.
Luisa Griesbaum, Sabrina Marx, and Bernhard Höfle
Nat. Hazards Earth Syst. Sci., 17, 1191–1201,Short summary
This study provides a new method for flood documentation based on user-generated flood images. We demonstrate how flood elevation and building inundation depth can be derived from photographs by means of 3-D reconstruction of the scene. With an accuracy of 0.13 m ± 0.10 m, the derived building inundation depth can be used to facilitate damage assessment.
Gianni Niccolini, Amedeo Manuello, Elena Marchis, and Alberto Carpinteri
Nat. Hazards Earth Syst. Sci., 17, 1025–1032,Short summary
An architectural element of the Royal Castle of Racconigi (northwestern Italy, 17th century) is subjected to nondestructive testing for structural integrity evaluation. It is found that the so-called acoustic emissions – high-frequency vibrations emitted as tiny cracks that develop inside stone and concrete – correlate with those of small nearby earthquakes, suggesting new approaches to monitoring gradual damage accumulation inflicted by such earthquakes on architectural heritage and monuments.
Tom Brouwer, Dirk Eilander, Arnejan van Loenen, Martijn J. Booij, Kathelijne M. Wijnberg, Jan S. Verkade, and Jurjen Wagemaker
Nat. Hazards Earth Syst. Sci., 17, 735–747,Short summary
The increasing number and severity of floods, driven by e.g. urbanization, subsidence and climate change, create a growing need for accurate and timely flood maps. At the same time social media is a source of much real-time data that is still largely untapped in flood disaster management. This study illustrates that inherently uncertain data from social media can be used to derive information about flooding.
Andreas Kääb, Bas Altena, and Joseph Mascaro
Nat. Hazards Earth Syst. Sci., 17, 627–639,Short summary
We evaluate for the first time a new class of optical satellite images for measuring Earth surface displacements due to earthquakes – images from cubesats. The PlanetScope cubesats used in this study are 10 cm × 10 cm × 30 cm small and standardized satellites. Around 120 of these cubesats orbit around Earth and are about to provide daily 2–4 m resolution images of the entire land surface of the Earth.
Mario Scalas, Palmalisa Marra, Luca Tedesco, Raffaele Quarta, Emanuele Cantoro, Antonio Tumolo, Davide Rollo, and Marco Spagnulo
Nat. Hazards Earth Syst. Sci., 17, 185–196,
Alessandro D'Anca, Laura Conte, Paola Nassisi, Cosimo Palazzo, Rita Lecci, Sergio Cretì, Marco Mancini, Alessandra Nuzzo, Maria Mirto, Gianandrea Mannarini, Giovanni Coppini, Sandro Fiore, and Giovanni Aloisio
Nat. Hazards Earth Syst. Sci., 17, 171–184,Short summary
Updated situational sea awareness requires an advanced technological system to make data available for decision makers, improving the capacity of intervention and supporting users in managing emergency situations due to natural hazards. The TESSA data platform meets the request of near-real-time access to heterogeneous data with different accuracy, resolution or degrees of aggregation providing efficient and secure data access and strong support to operational oceanographic high-level services.
Anselmo, V., Galeati, G., Palmieri, S., Rossi, U., and Todini, E.: Flood risk assessment using an integrated hydrological and hydraulic modelling approach: a case study, J. Hydrol., 175, 533–554, https://doi.org/10.1016/S0022-1694(96)80023-0, 1996.
Barker, J., Barker, J. L. P., and Macleod, C. J. A.: Development of a national-scale real-time Twitter data mining pipeline for social geodata on the potential impacts of flooding on communities, Environ. Model. Softw., 115, 213–227, https://doi.org/10.1016/j.envsoft.2018.11.013, 2019.
Chawla, N., Japkowicz, N., and Kolcz, A.: Editorial: Special issue on learning from imbalanced data sets, ACM SIGKDD Explor., 6, 1–6, https://doi.org/10.1145/1007730.1007733, 2004.
Cheng, X., Han, G. F., Zhao, Y. F., and Li, L.: Evaluating social media response to urban flood disaster: Case study on an East Asian City (Wuhan, China), Sustainability, 11, 1–18, https://doi.org/10.3390/su11195330, 2019.
de Bruijn, J. A., de Model, H., Jongman, B., Wagemaker, J., and Aerts, J. C. J. H.: TAGGS: Grouping tweets to improve global geoparsing for disaster response, J. Geovisual. Spat. Anal., 2, 2, https://doi.org/10.1007/s41651-017-0010-6, 2018.
de Bruijn, J. A., de Model, H., Jongman, B., de Ruiter, M. C., Wagemaker, J., and Aerts, J. C. J. H.: A global database of historic and real-time flood events based on social media, Sci. Data, 6, 311, https://doi.org/10.1038/s41597-019-0326-9, 2019.
Feng, H., Li, M., Hou, X., and Xu, Z.: Study of network intrusion detection method based on SMOTE and GBDT, Appl. Res. Comput., 34, 3745–3748, https://doi.org/10.3969/j.issn.1001-3695.2017.12.051, 2017.
Feng, Y. and Sester, M.: Extraction of pluvial flood relevant volunteered geographic information (VGI) by deep learning from user generated texts and photos, ISPRS Int. J. Geo-Inf., 7, 39–64, https://doi.org/10.3390/ijgi7020039, 2018.
Friedman, J. H.: Greedy function approximation a gradient boosting machine, Ann. Stat., 29, 1189–1232, 2000.
García, S. and Herrera, F.: Evolutionary undersampling for classification with imbalanced datasets: Proposals and taxonomy, Evolution. Comput., 17, 275–306, https://doi.org/10.1162/evco.2009.17.3.275, 2009.
Gensim: Gensim topic modelling for humans: Word2vec embeddings, available at: https://radimrehurek.com/gensim/models/word2vec.html, last access: 4 September 2020.
Guan, Q., Deng, S., and Wang, H.: Chinese stopwords for text clustering: A comparative study, Data Anal. Knowled. Discov., 1, 72–80, 2017.
Hochreiter, S. and Schmidhuber, J.: Long short-term memory, Neural Comput., 9, 1735–1780, https://doi.org/10.1162/neco.1918.104.22.1685, 1997.
Hu, X., Liu, L., and Qiu, N.: A novel spam categorization algorithm based on active learning method and negative selection algorithm, Acta Electron. Sin., 46, 203–209, https://doi.org/10.3969/j.issn.0372-2112.2018.01.028, 2018.
Kang, A., Zhang, K., Liang, J., and Yan, B.: Applying the dynamic critical precipitation method for flash flood early warning, J. Environ. Stud., 28, 1727–1733, https://doi.org/10.15244/pjoes/83731, 2019.
Kim, Y.: Convolutional neural networks for sentence classification, in: Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, 2014.
Kuklicke, C. and Demeritt, D.: Adaptive and risk-based approaches to climate change and the management of uncertainly and institutional risk: The case of future flooding in England, Global Environ. Change, 37, 56–68, https://doi.org/10.1016/j.gloenvcha.2016.01.007, 2016.
LeCun, Y., Bengio, Y., and Hinton, G.: Deep learning, Nature, 521, 436–444, 2015.
Li, S. and Chen, D.: Recurrent neural network using attention model for sentiment analysis, J. Huaqiao Univers. (Nat. Sci.), 39, 252–255, https://doi.org/10.11830/ISSN.1000-5013.201606123, 2018.
Liu, H.: hliu2016/waterlogging: urban waterlogging (Version v1.0), Zenodo, https://doi.org/10.5281/zenodo.4646972, 2021.
Liang, L.: Application of rising rate analysis method in flood warning and forecast, Guangxi Water Resour. Hydropow. Eng., 2, 29–32, https://doi.org/10.16014/j.cnki.1003-1510.2019.02.008, 2019.
Liang, Z., Tang, T., Li, B., Wang, J., and Hu, Y.: Research and application of comprehensive evaluation method for flood early warning, Yellow River, 41, 82–86, 2019.
Lima, C., Lall, U., Troy, T. J., and Devineni, N.: A climate informed model for nonstationary flood risk prediction: Application to Negro River at Manaus, Amazonia, J. Hydrol., 522, 594–602, https://doi.org/10.1016/j.jhydrol.2015.01.009, 2015.
Liu, P., Qiu, X., and Huang, X.: Recurrent neural network for text classification with multi-task learning, Computer Science, arxiv: preprint, available at: https://arxiv.org/abs/1605.05101 (last access: 29 July 2020), 2016.
Liu, T., Zhu, W., and Liu, G.: Advances in deep learning based on text classification, Elect. Power Inform. Commun. Tech., 16, 1–7, https://doi.org/10.16543/j.2095-641x.electric.power.ict.2018.03.000, 2018.
Liu, X. Y., Wu, J., and Zhou, Z. H.: Exploratory undersampling for class-imbalance learning, IEEE T. Syst. Man Cybernet. Pt. B, 39, 539–550, https://doi.org/10.1109/TSMCB.2008.2007853, 2008.
Mikolov, T., Chen, K., Corrado, G.,and Dean, J.: Efficient estimation of word representations in vector space, Computer Science, arxiv: preprint, available at: https://arxiv.org/abs/1301.3781 (last access: 13 May 2020), 2013.
Niu, C., Zhan, G., and Li, Z.: Chinese Weibo sentiment analysis based on deep neural network, Comput. Syst. Appl., 27, 205–210, https://doi.org/10.15888/j.cnki.csa.006645, 2018.
Receiver: Receiver operating characteristic: Receiver operating characteristic, available at: https://en.wikipedia.org/wiki/Receiver_operating_characteristic/, last access: 21 August 2020.
Robinson, B., Bai, H., Power, R., and Lin, X. G.: Research on social media disaster detection for Sina Weibo, in: International Symposium on Emergency Management 2014, 25 November 2014, Shenzhen, China, 2014.
Salton, G. and Buckley, B.: Term-weighting approaches in automatic text retrieval, Inform. Process. Manage., 24, 513–523, https://doi.org/10.1016/0306-4573(88)90021-0, 1998.
Singh, N., Roy, N., and Gangopadhyay, A.: Localized flood detection with minimal labeled social media data using transfer learning, arXiv: preprint, available at: https://arxiv.org/abs/2003.04973, last access: 15 June 2020.
Sofia, G., Roder, G., Dalla Fontana, G., and Tarolli, P.: Flood dynamics in urbanised landscapes: 100 years of climate and humans' interaction, Sci. Rep., 7, 40527, https://doi.org/10.1038/srep40527, 2017.
Tan, G. and Ding, H.: Improvement of SVM method in text categorization, Inform. Technol., 1, 83–85, 2008.
Tawatchai, T. and Mohammed, F. K.: Flood hazard and risk analysis in the southwest region of Bangladesh, Hydrol. Process., 19, 2055–2069, https://doi.org/10.1002/hyp.5666, 2005.
Tharwat, A.: Classification assessment methods, Appl. Comput. Inform., 17, 168–192, https://doi.org/10.1016/j.aci.2018.08.003, 2018.
Wadawadagi, R. and Pagi, V.: Disaster severity analysis from micro-blog texts using Deep-NN, Evolution in Computational Intelligence, Springer, Singapore, 1176, 145–157, https://doi.org/10.1007/978-981-15-5788-0_14, 2020.
Wang, H., Yang, L., and Lin, H. F.: Hot event analysis of Japan earthquake on microblog, J. Chinese Inform. Process., 26, 7–14, 2012.
Wang, J., Luo, L., and Wang, D.: Research on Chinese short text classification based on Word2Vec, Comput. Syst. Appl., 27, 209–215, 2018.
Wheater, H. and Evans, E.: Land use, water management and future flood risk, Land Use Policy, 26, 251–264, https://doi.org/10.1016/j.landusepol.2009.08.019, 2009.
Xiao, Z., Liang, Z., Li, B., Hu, Y., and Wang, J.: New flood early warning and forecasting method based on similarity theory, J. Hydrol. Eng., 24, 04019023, https://doi.org/10.1061/(ASCE)HE.1943-5584.0001811, 2019.
Xiong, Z., Li, G., Chen, X., and Chen, W.: Improvement and application to weighting terms based on text classification, Comput. Eng. Appl., 44, 187–189, 2008.
Yu, H. and Zhai, H.: Applying a subspace clustering algorithm in multi-label text classification, Comput. Appl. Softw., 31, 288–303, 2014.
Yu, W., Nakakita, E., Kim, S., and Yamaguchi, K.: Improvement of rainfall and flood forecasts by blending ensemble NWP rainfall with radar prediction considering orographic rainfall, J. Hydrol., 531, 494–507, https://doi.org/10.1016/j.jhydrol.2015.04.055, 2015.
Zhang, Y. and Wang, J. C.: On the problems and countermeasures of government information release mechanism in emergency – based on the case study of 2015 Shanghai Bund Stampede Incident, J. Intellig., 34, 111–117, 2015.
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.
We trained a recurrent neural network model to classify microblogging posts related to urban...