Novel Ensembles of Deep Learning Neural Network and Statistical Learning for Flash-Flood Susceptibility Mapping DOI Open Access
Romulus Costache, Phuong Thao Thi Ngo, Dieu Tien Bui

et al.

Water, Journal Year: 2020, Volume and Issue: 12(6), P. 1549 - 1549

Published: May 29, 2020

This study aimed to assess flash-flood susceptibility using a new hybridization approach of Deep Neural Network (DNN), Analytical Hierarchy Process (AHP), and Frequency Ratio (FR). A catchment area in south-eastern Romania was selected for this proposed approach. In regard, geospatial database the flood with 178 locations 10 predictors prepared used AHP FR were processing coding into numeric format, whereas DNN, which is powerful state-of-the-art probabilistic machine leaning, employed build an inference model. The reliability models verified help Receiver Operating Characteristic (ROC) Curve, Area Under Curve (AUC), several statistical measures. result shows that two ensemble models, DNN-AHP DNN-FR, are capable predicting future areas accuracy higher than 92%; therefore, they tool studies.

Language: Английский

GIS-based comparative assessment of flood susceptibility mapping using hybrid multi-criteria decision-making approach, naïve Bayes tree, bivariate statistics and logistic regression: A case of Topľa basin, Slovakia DOI Creative Commons
Sk Ajim Ali, Farhana Parvin, Quoc Bao Pham

et al.

Ecological Indicators, Journal Year: 2020, Volume and Issue: 117, P. 106620 - 106620

Published: June 21, 2020

Flood is a devastating natural hazard that may cause damage to the environment infrastructure, and society. Hence, identifying susceptible areas flood an important task for every country prevent such dangerous consequences. The present study developed framework flood-prone of Topľa river basin, Slovakia using geographic information system (GIS), multi-criteria decision making approach (MCDMA), bivariate statistics (Frequency Ratio (FR), Statistical Index (SI)) machine learning (Naïve Bayes Tree (NBT), Logistic Regression (LR)). To reach goal, different physical-geographical factors (criteria) were integrated mapped. access relationship interdependences among criteria, decision-making trial evaluation laboratory (DEMATEL) analytic network process (ANP) used. Based on experts' decisions, DEMATEL-ANP model was used compute relative weights criteria GIS-based linear combination performed derive susceptibility index. Separately, index computation through NBT-FR NBT-SI hybrid models assumed, in first stage, estimation weight each class/category conditioning factor SI FR integration these values NBT algorithm. application LR stand-alone required calculation by analysing their spatial relation with location historical events. revealed very high classes covered between 20% 47% area, respectively. validation results, past points, highlighted most performant Area Under ROC curve higher than 0.97, accuracy 0.922 value HSS 0.844. presented methodological identification can serve as alternative updating preliminary risk assessment based EU Floods Directive.

Language: Английский

Citations

264
Linking the Remote Sensing of Geodiversity and Traits Relevant to Biodiversity—Part II: Geomorphology, Terrain and Surfaces DOI Creative Commons
Angela Lausch, Michael E. Schaepman, Andrew K. Skidmore

et al.

Remote Sensing, Journal Year: 2020, Volume and Issue: 12(22), P. 3690 - 3690

Published: Nov. 10, 2020

The status, changes, and disturbances in geomorphological regimes can be regarded as controlling regulating factors for biodiversity. Therefore, monitoring geomorphology at local, regional, global scales is not only necessary to conserve geodiversity, but also preserve biodiversity, well improve biodiversity conservation ecosystem management. Numerous remote sensing (RS) approaches platforms have been used the past enable a cost-effective, increasingly freely available, comprehensive, repetitive, standardized, objective of characteristics their traits. This contribution provides state-of-the-art review RS-based these traits, by presenting examples aeolian, fluvial, coastal landforms. Different crucial discipline geodiversity using RS are provided, discussing implementation technologies such LiDAR, RADAR, multi-spectral hyperspectral sensor technologies. Furthermore, data products that could future introduced. use spectral traits (ST) trait variation (STV) with geomorphic diversity monitored. We focus on requirements specifically aimed overcoming some key limitations ecological modeling, namely: linking in-situ, close-range, air- spaceborne technologies, science components better understanding impacts complex ecosystems. paper aims impart multidimensional information obtained improved utilization monitoring.

Language: Английский

Citations

262
Application of remote sensing and machine learning algorithms for forest fire mapping in a Mediterranean area DOI Creative Commons
Meriame Mohajane, Romulus Costache, Firoozeh Karimi

et al.

Ecological Indicators, Journal Year: 2021, Volume and Issue: 129, P. 107869 - 107869

Published: June 7, 2021

Forest fire disaster is currently the subject of intense research worldwide. The development accurate strategies to prevent potential impacts and minimize occurrence disastrous events as much possible requires modeling forecasting severe conditions. In this study, we developed five new hybrid machine learning algorithms namely, Frequency Ratio-Multilayer Perceptron (FR-MLP), Ratio-Logistic Regression (FR-LR), Ratio-Classification Tree (FR-CART), Ratio-Support Vector Machine (FR-SVM), Ratio-Random (FR-RF), for mapping forest susceptibility in north Morocco. To end, a total 510 points historic fires inventory map 10 independent causal factors including elevation, slope, aspect, distance roads, residential areas, land use, normalized difference vegetation index (NDVI), rainfall, temperature, wind speed were used. area under receiver operating characteristics (ROC) curves (AUC) was computed assess effectiveness models. results conducting proposed models indicated that RF-FR achieved highest performance (AUC = 0.989), followed by SVM-FR 0.959), MLP-FR 0.858), CART-FR 0.847), LR-FR 0.809) fire. outcome prediction risk areas can provide crucial support management Mediterranean ecosystems. Moreover, demonstrate these novel increase accuracy studies approach be applied other areas.

Language: Английский

Citations

262
Flash-flood susceptibility mapping based on XGBoost, random forest and boosted regression trees DOI

Rahebeh Abedi,

Romulus Costache, Hossein Shafizadeh‐Moghadam

et al.

Geocarto International, Journal Year: 2021, Volume and Issue: 37(19), P. 5479 - 5496

Published: April 23, 2021

Historical exploration of flash flood events and producing flash-flood susceptibility maps are crucial steps for decision makers in disaster management. In this article, classification regression tree (CART) methodology its ensemble models random forest (RF), boosted trees (BRT) extreme gradient boosting (XGBoost) were implemented to create a map the Bâsca Chiojdului River Basin, one areas Romania that is constantly exposed floods. The torrential including 962 delineated from orthophotomaps field observations. Furthermore, set conditioning forces explain floods was constructed which included aspect, land use cover (LULC), hydrological soil groups lithology, slope, topographic wetness index (TWI), position (TPI), profile curvature, convergence stream power (SPI). All indicated slope as most important factor triggering occurrence. highest area under curve (AUC) achieved by RF model (AUC = 0.956), followed BRT 0.899), XGBoost 0.892) CART 0.868), respectively. results showed central part river basin, covers approximately 30% study area, more susceptible flooding.

Language: Английский

Citations

204
Flood susceptibility modeling in Teesta River basin, Bangladesh using novel ensembles of bagging algorithms DOI
Swapan Talukdar,

Bonosri Ghose,

Shahfahad

et al.

Stochastic Environmental Research and Risk Assessment, Journal Year: 2020, Volume and Issue: 34(12), P. 2277 - 2300

Published: Sept. 4, 2020

Language: Английский

Citations

184
Optimization of state-of-the-art fuzzy-metaheuristic ANFIS-based machine learning models for flood susceptibility prediction mapping in the Middle Ganga Plain, India DOI
Aman Arora, Alireza Arabameri, Manish Pandey

et al.

The Science of The Total Environment, Journal Year: 2020, Volume and Issue: 750, P. 141565 - 141565

Published: Aug. 13, 2020

Language: Английский

Citations

179
Urban flood susceptibility assessment based on convolutional neural networks DOI
Gang Zhao, Bo Pang, Zongxue Xu

et al.

Journal of Hydrology, Journal Year: 2020, Volume and Issue: 590, P. 125235 - 125235

Published: June 27, 2020

Language: Английский

Citations

145
Assessment of long and short-term flood risk using the multi-criteria analysis model with the AHP-Entropy method in Poyang Lake basin DOI

Jinru Wu,

Xiaoling Chen,

Jianzhong Lu

et al.

International Journal of Disaster Risk Reduction, Journal Year: 2022, Volume and Issue: 75, P. 102968 - 102968

Published: April 17, 2022

Language: Английский

Citations

129
Comprehensive Overview of Flood Modeling Approaches: A Review of Recent Advances DOI Creative Commons
Vijendra Kumar, Kul Vaibhav Sharma, Tommaso Caloiero

et al.

Hydrology, Journal Year: 2023, Volume and Issue: 10(7), P. 141 - 141

Published: June 30, 2023

As one of nature’s most destructive calamities, floods cause fatalities, property destruction, and infrastructure damage, affecting millions people worldwide. Due to its ability accurately anticipate successfully mitigate the effects floods, flood modeling is an important approach in control. This study provides a thorough summary modeling’s current condition, problems, probable future directions. The includes models based on hydrologic, hydraulic, numerical, rainfall–runoff, remote sensing GIS, artificial intelligence machine learning, multiple-criteria decision analysis. Additionally, it covers heuristic metaheuristic techniques employed evaluation examines advantages disadvantages various models, evaluates how well they are able predict course impacts floods. constraints data, unpredictable nature model, complexity model some difficulties that must overcome. In study’s conclusion, prospects for development advancement field discussed, including use advanced technologies integrated models. To improve risk management lessen society, report emphasizes necessity ongoing research modeling.

Language: Английский

Citations

110
Flash-flood hazard using deep learning based on H2O R package and fuzzy-multicriteria decision-making analysis DOI
Romulus Costache,

Tran Trung Tin,

Alireza Arabameri

et al.

Journal of Hydrology, Journal Year: 2022, Volume and Issue: 609, P. 127747 - 127747

Published: March 24, 2022

Language: Английский

Citations

74