Using GIS, Remote Sensing, and Machine Learning to Highlight the Correlation between the Land-Use/Land-Cover Changes and Flash-Flood Potential

被引：47

作者：

Costache, Romulus ^{[1
,2
]}

Quoc Bao Pham ^{[3
,4
]}

Corodescu-Rosca, Ema ^{[5
]}

Cimpianu, Catalin ^{[5
]}

Hong, Haoyuan ^{[6
,7
,8
]}

Nguyen Thi Thuy Linh ^{[9
]}

Fai, Chow Ming ^{[10
]}

Ahmed, Ali Najah ^{[11
]}

Vojtek, Matej ^{[12
]}

Pandhiani, Siraj Muhammed ^{[13
]}

Minea, Gabriel ^{[2
]}

Ciobotaru, Nicu ^{[2
,14
]}

Popa, Mihnea Cristian ^{[14
,15
]}

Diaconu, Daniel Constantin ^{[15
,16
]}

Binh Thai Pham ^{[17
]}

机构：

[1] Univ Bucharest, Res Inst, 90-92 Sos Panduri,5th Dist, Bucharest, Romania

[2] Natl Inst Hydrol & Water Management, 97E Sos Bucuresti Ploiesti,1st Dist, Bucharest 013686, Romania

[3] Ton Duc Thang Univ, Environm Qual Atmospher Sci & Climate Change Res, Ho Chi Minh City 70000, Vietnam

[4] Ton Duc Thang Univ, Fac Environm & Labour Safety, Ho Chi Minh City 70000, Vietnam

[5] Alexandru Ioan Cuza Univ, Fac Geog & Geol, Dept Geog, Iasi 700505, Romania

[6] Nanjing Normal Univ, Minist Educ, Key Lab Virtual Geog Environm, Nanjing 210023, Peoples R China

[7] State Key Lab Cultivat Base Geog Environm Evolut, Nanjing 210023, Peoples R China

[8] Jiangsu Ctr Collaborat Innovat Geog Informat Reso, Nanjing 210023, Peoples R China

[9] Thuyloi Univ, Fac Water Resource Engn, 175 Tay Son, Hanoi 100000, Vietnam

[10] Univ Tenaga Nas, Inst Sustainable Energy ISE, Kajang 43000, Selangor, Malaysia

[11] Univ Tenaga Nas, Coll Engn, Inst Energy Infrastruct IEI, Civil Engn Dept, Kajang 43000, Selangor, Malaysia

[12] Constantine Philosopher Univ Nitra, Fac Nat Sci, Dept Geog & Reg Dev, Nitra 94974, Slovakia

[13] Jubail Univ Coll, Dept Gen Studies, Royal Commiss Jubail, Jubail Ind City 31961, Saudi Arabia

[14] Univ Bucharest, Simion Mehedinti Nat & Sustainable Dev Doctoral S, Bucharest 010041, Romania

[15] Univ Bucharest, Ctr Integrated Anal & Terr Management, Bucharest 010041, Romania

[16] Univ Bucharest, Fac Geog, Bucharest 010041 1, Romania

[17] Duy Tan Univ, Inst Res & Dev, Da Nang 550000, Vietnam

来源：

REMOTE SENSING | 2020年 / 12卷 / 09期

关键词：

Zbala; Landsat images; multilayer perceptron; total relative difference-synthetic dynamic land-use index; flash-flood potential index; geographically weighted regression; MULTICRITERIA DECISION-MAKING; ARTIFICIAL NEURAL-NETWORK; SUPPORT VECTOR MACHINE; BIOGEOGRAPHY-BASED OPTIMIZATION; WEIGHTS-OF-EVIDENCE; SUSCEPTIBILITY ASSESSMENT; SPATIAL PREDICTION; RIVER CATCHMENT; SURFACE RUNOFF; QUANTITATIVE ESTIMATION;

D O I：

10.3390/rs12091422

中图分类号：

X [环境科学、安全科学];

学科分类号：

08 ; 0830 ;

摘要：

The aim of the present study was to explore the correlation between the land-use/land cover change and the flash-flood potential changes in Zbala catchment (Romania) between 1989 and 2019. In this regard, the efficiency of GIS, remote sensing and machine learning techniques in detecting spatial patterns of the relationship between the two variables was tested. The paper elaborated upon an answer to the increase in flash flooding frequency across the study area and across the earth due to the occurred land-use/land-cover changes, as well as due to the present climate change, which determined the multiplication of extreme meteorological phenomena. In order to reach the above-mentioned purpose, two land-uses/land-covers (for 1989 and 2019) were obtained using Landsat image processing and were included in a relative evolution indicator (total relative difference-synthetic dynamic land-use index), aggregated at a grid-cell level of 1 km(2). The assessment of runoff potential was made with a multilayer perceptron (MLP) neural network, which was trained for 1989 and 2019 with the help of 10 flash-flood predictors, 127 flash-flood locations, and 127 non-flash-flood locations. For the year 1989, the high and very high surface runoff potential covered around 34% of the study area, while for 2019, the same values accounted for approximately 46%. The MLP models performed very well, the area under curve (AUC) values being higher than 0.837. Finally, the land-use/land-cover change indicator, as well as the relative evolution of the flash flood potential index, was included in a geographically weighted regression (GWR). The results of the GWR highlights that high values of the Pearson coefficient (r) occupied around 17.4% of the study area. Therefore, in these areas of the Zbala river catchment, the land-use/land-cover changes were highly correlated with the changes that occurred in flash-flood potential.

引用

页数：30

共 127 条

[11] Sensitivity of the hydrological response to the variability of rainfall fields and soils for the Gard 2002 flash-flood event [J].