A New Hybrid Firefly-PSO Optimized Random Subspace Tree Intelligence for Torrential Rainfall-Induced Flash Flood Susceptible Mapping

Nhu, Viet-Ha1,2; Thi Ngo, Phuong-Thao3; Pham, Tien Dat4; Dou, Jie5,6; Song, Xuan7; Hoang, Nhat-Duc8; Tran, Dang An9; Cao, Duong Phan10,11; Aydilek, Ibrahim Berkan12; Amiri, Mahdis13; Costache, Romulus14; Hoa, Pham Viet15; Tien Bui, Dieu16

2020-09

10.3390/rs12172688

Remote Sensing   影响因子和分区

2072-4292

2072-4292

Flash flood is one of the most dangerous natural phenomena because of its high magnitudes and sudden occurrence, resulting in huge damages for people and properties. Our work aims to propose a state-of-the-art model for susceptibility mapping of the flash flood using the decision tree random subspace ensemble optimized by hybrid firefly-particle swarm optimization (HFPS), namely the HFPS-RSTree model. In this work, we used data from a flood inventory map consisting of 1866 polygons derived from Sentinel-1 C-band synthetic aperture radar (SAR) data and a field survey conducted in the northwest mountainous area of the Van Ban district, Lao Cai Province in Vietnam. A total of eleven flooding conditioning factors (soil type, geology, rainfall, river density, elevation, slope, aspect, topographic wetness index (TWI), normalized difference vegetation index (NDVI), plant curvature, and profile curvature) were used as explanatory variables. These indicators were compiled from a geological and mineral resources map, soil type map, and topographic map, ALOS PALSAR DEM 30 m, and Landsat-8 imagery. The HFPS-RSTree model was trained and verified using the inventory map and the eleven conditioning variables and then compared with four machine learning algorithms, i.e., the support vector machine (SVM), the random forests (RF), the C4.5 decision trees (C4.5 DT), and the logistic model trees (LMT) models. We employed a range of statistical standard metrics to assess the predictive performance of the proposed model. The results show that the HFPS-RSTree model had the best predictive performance and achieved better results than those of other benchmarks with the ability to predict flash flood, reaching an overall accuracy of over 90%. It can be concluded that the proposed approach provides new insights into flash flood prediction in mountainous regions.

flood modeling firefly Particle Swarm Optimization flash flood GIS remote sensing rainfall

SCI ; EI

英语

其他

Remote Sensing

Remote Sensing

WOS:000570373900001

MDPI

20203709161790

Landsat ; Rain ; Bioluminescence ; Decision trees ; Geology ; Particle swarm optimization (PSO) ; Support vector machines ; Vegetation mapping ; Learning algorithms ; Synthetic aperture radar ; Benchmarking ; Floods ; Maps

Surveying:405.3 ; Precipitation:443.3 ; Geology:481.1 ; Satellites:655.2 ; Radar Systems and Equipment:716.2 ; Computer Software, Data Handling and Applications:723 ; Machine Learning:723.4.2 ; Light/Optics:741.1 ; Combinatorial Mathematics, Includes Graph Theory, Set Theory:921.4 ; Optimization Techniques:921.5 ; Systems Science:961

Web of Science

1.Ton Duc Thang Univ, Geog Informat Sci Res Grp, Ho Chi Minh City 700000, Vietnam
2.Ton Duc Thang Univ, Fac Environm & Labour Safety, Ho Chi Minh City 700000, Vietnam
3.Duy Tan Univ, Inst Res & Dev, Da Nang 550000, Vietnam
4.Vietnam Natl Univ Agr VNUA, Ctr Agr Res & Ecol Studies CARES, Hanoi 100000, Vietnam
5.China Univ Geosci, Minist Educ, Three Gorges Res Ctr Geohazards, Wuhan 430074, Peoples R China
6.Nagaoka Univ Technol, Dept Civil & Environm Engn, Nagaoka, Niigata 16031, Japan
7.Southern Univ Sci & Technol SUSTech, Dept Comp Sci & Engn, SUSTech UTokyo Joint Res Ctr Super Smart City, Shenzhen 518055, Peoples R China
8.Duy Tan Univ, Inst Res & Dev, Fac Civil Engn, Da Nang 550000, Vietnam
9.Thuyloi Univ, Fac Water Resources Engn, 175 Tay Son, Hanoi 100000, Vietnam
10.Univ Tsukuba, Grad Sch Life & Environm Sci, Tennoudai 1-1-1, Tsukuba, Ibaraki 3058572, Japan
11.Vietnam Acad Water Resources, Hydraul Construct Inst, 3,Alley 95,Chua Boc St, Hanoi 116765, Vietnam
12.Harran Univ, Fac Engn, Dept Comp Engn, TR-63050 Sanliurfa, Turkey
13.Gorgan Univ Agr Sci & Nat Resources, Dept Watershed & Arid Zone Management, Gorgan 4913815739, Golestan, Iran
14.Univ Bucharest, Res Inst, 90-92 Sos Panduri,5th Dist, Bucharest 050663, Romania
15.Vietnam Acad Sci & Technol, Ho Chi Minh City Inst Resources Geog, Mac Dinh Chi 1,Ben Nghe,1 Dist, Ho Chi Minh City 700000, Vietnam
16.Univ Southeast Norway, Dept Business & IT, GIS Grp, Gullbringvegen 36, N-3800 Bo I Telemark, Norway

Nhu, Viet-Ha,Thi Ngo, Phuong-Thao,Pham, Tien Dat,et al. A New Hybrid Firefly-PSO Optimized Random Subspace Tree Intelligence for Torrential Rainfall-Induced Flash Flood Susceptible Mapping[J]. Remote Sensing,2020,12(17).

Nhu, Viet-Ha.,Thi Ngo, Phuong-Thao.,Pham, Tien Dat.,Dou, Jie.,Song, Xuan.,...&Tien Bui, Dieu.(2020).A New Hybrid Firefly-PSO Optimized Random Subspace Tree Intelligence for Torrential Rainfall-Induced Flash Flood Susceptible Mapping.Remote Sensing,12(17).

Nhu, Viet-Ha,et al."A New Hybrid Firefly-PSO Optimized Random Subspace Tree Intelligence for Torrential Rainfall-Induced Flash Flood Susceptible Mapping".Remote Sensing 12.17(2020).