首页|Flood susceptibility mapping using a novel integration of multi-temporal sentinel-1 data and eXtreme deep learning model

Flood susceptibility mapping using a novel integration of multi-temporal sentinel-1 data and eXtreme deep learning model

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
Flash floods(FFs)are amongst the most devastating hazards in arid regions in response to climate change and can cause the loss of agricultural land,human lives and infrastructure.One of the major challenges is the high-intensity rainfall events affecting low-lying areas that are vulnerable to FF.Several works in this field have been conducted using ensemble machine learning models and geohydrological models.However,the current advancement of eXtreme deep learning,which is named eXtreme deep factorisa-tion machine(xDeepFM),for FF susceptibility mapping(FSM)is lacking in the literature.The current study introduces a new model and employs a previously unapplied approach to enhance FSM for captur-ing the severity of floods.The proposed approach has three main objectives:(ⅰ)During-and after-flood effects are assessed through flood detection techniques using Sentinel-1 data.(ⅱ)Flood inventory is updated using remote sensing-based methods.The derived flood effects are implemented in the next step.(ⅲ)An FSM map is generated using an xDeepFM model.Therefore,this study aims to apply xDeepFM to estimate susceptible areas using 13 factors in the emirates of Fujairah,UAE.The performance metrics show a recall of 0.9488),an F1-score of 0.9107),precision of(0.8756)and an overall accuracy of 90.41％.The accuracy of the applied xDeepFM model is compared with that of traditional machine learn-ing models,specifically the deep neural network(78％),support vector machine(85.4％)and random for-est(88.75％).Random forest achieves high accuracy,which is due to its strong performance that depends on factors contribution,dataset size and quality,and available computational resources.Comparatively,the xDeepFM model works efficiently for complicated prediction problems having high non-collinearity and huge datasets.The obtained map denotes that the narrow basins,lowland coastal areas and riverbank areas up to 5 km(Fujairah)are highly prone to FF,whilst the alluvial plains in Al Dhaid and hilly regions in Fujairah show low probability.The coastal city areas are bounded by high-rise steep hills and the Gulf of Oman,which can elevate the water levels during heavy rainfall.Four major synchronised influencing factors,namely,rainfall,elevation,drainage density,distance from drainage and geomorphology,account for nearly 50％of the total factors contributing to a very high flood susceptibility.This study offers a plat-form for planners and decision makers to take timely actions on potential areas in mitigating the effects of FF.

Flood susceptibility mappingeXtreme Deep Factorisation MachineSentinel-1Remote sensing

Rami Al-Ruzouq、Abdallah Shanableh、Ratiranjan Jena、Mohammed Barakat A.Gibril、Nezar Atalla Hammouri、Fouad Lamghari

展开 >

GIS & Remote Sensing Center,Research Institute of Sciences and Engineering,University of Sharjah,Sharjah 27272,United Arab Emirates

Civil and Environmental Engineering Department,University of Sharjah,Sharjah 27272,United Arab Emirates

Department of Earth and Environmental Sciences,Prince El-Hassan bin Tolal Faculty for Natural Resources & Environment,The Hashemite University,Zarqa,Jordan

Fujairah Research Centre,Fujairah City,Al Hilal Tower,Al Hilal City,Fujairah,United Arab Emirates

展开 >

funds received by the University of Sharjah and Fujairah Research Centre

1902041134-P

2024

10.1016/j.gsf.2024.101780

地学前缘(英文版)
中国地质大学（北京） 北京大学

地学前缘(英文版)

CSTPCD
影响因子：0.576
ISSN：1674-9871
年,卷(期)：2024.15(3)
  • 66