Flash-Flood Potential Mapping Using Deep Learning, Alternating Decision Trees and Data Provided by Remote Sensing Sensors

Romulus Costache; Alireza Arabameri; Thomas Blaschke; Quoc Bao Pham; Binh Thai Pham; Manish Pandey; Aman Arora; Nguyen Thi Thuy Linh; Iulia Costache

doi:10.3390/s21010280

Flash-Flood Potential Mapping Using Deep Learning, Alternating Decision Trees and Data Provided by Remote Sensing Sensors

Sensors (Basel). 2021 Jan 4;21(1):280. doi: 10.3390/s21010280.

Authors

Romulus Costache^{1

2}, Alireza Arabameri³, Thomas Blaschke⁴, Quoc Bao Pham^{5

6}, Binh Thai Pham⁷, Manish Pandey^{8

9}, Aman Arora¹⁰, Nguyen Thi Thuy Linh^{11

12}, Iulia Costache¹³

Affiliations

¹ Research Institute of the University of Bucharest, 90-92 Sos. Panduri, 5th District, 050663 Bucharest, Romania.
² National Institute of Hydrology and Water Management, București-Ploiești Road, 97E, 1st District, 013686 Bucharest, Romania.
³ Department of Geomorphology, Tarbiat Modares University, Tehran 36581-17994, Iranmailto.
⁴ Department of Geoinformatics-Z_GIS, University of Salzburg, 5020 Salzburg, Austria.
⁵ Environmental Quality, Atmospheric Science and Climate Change Research Group, Ton Duc Thang University, Ho Chi Minh City 700000, Vietnam.
⁶ Faculty of Environment and Labour Safety, Ton Duc Thang University, Ho Chi Minh City 700000, Vietnam.
⁷ Geotechnical Engineering Deparment, University of Transport Technology, Hanoi 100000, Vietnam.
⁸ University Center for Research & Development (UCRD), Chandigarh University, Punjab 140413, India.
⁹ Department of Civil Engineering, University Institute of Engineering, Chandigarh University, Punjab 140413, India.
¹⁰ Department of Geography, Faculty of Natural Sciences, Jamia Millia Islamia, New Delhi 110025, India.
¹¹ Institute of Research and Development, Duy Tan University, Danang 550000, Vietnam.
¹² Faculty of Environmental and Chemical Engineering, Duy Tan University, Danang 550000, Vietnam.
¹³ Faculty of Geography, University of Bucharest, Bd. Nicolae Bălcescu No 1, 1st District, 010041 Bucharest, Romania.

Abstract

There is an evident increase in the importance that remote sensing sensors play in the monitoring and evaluation of natural hazards susceptibility and risk. The present study aims to assess the flash-flood potential values, in a small catchment from Romania, using information provided remote sensing sensors and Geographic Informational Systems (GIS) databases which were involved as input data into a number of four ensemble models. In a first phase, with the help of high-resolution satellite images from the Google Earth application, 481 points affected by torrential processes were acquired, another 481 points being randomly positioned in areas without torrential processes. Seventy percent of the dataset was kept as training data, while the other 30% was assigned to validating sample. Further, in order to train the machine learning models, information regarding the 10 flash-flood predictors was extracted in the training sample locations. Finally, the following four ensembles were used to calculate the Flash-Flood Potential Index across the Bâsca Chiojdului river basin: Deep Learning Neural Network-Frequency Ratio (DLNN-FR), Deep Learning Neural Network-Weights of Evidence (DLNN-WOE), Alternating Decision Trees-Frequency Ratio (ADT-FR) and Alternating Decision Trees-Weights of Evidence (ADT-WOE). The model's performances were assessed using several statistical metrics. Thus, in terms of Sensitivity, the highest value of 0.985 was achieved by the DLNN-FR model, meanwhile the lowest one (0.866) was assigned to ADT-FR ensemble. Moreover, the specificity analysis shows that the highest value (0.991) was attributed to DLNN-WOE algorithm, while the lowest value (0.892) was achieved by ADT-FR. During the training procedure, the models achieved overall accuracies between 0.878 (ADT-FR) and 0.985 (DLNN-WOE). K-index shows again that the most performant model was DLNN-WOE (0.97). The Flash-Flood Potential Index (FFPI) values revealed that the surfaces with high and very high flash-flood susceptibility cover between 46.57% (DLNN-FR) and 59.38% (ADT-FR) of the study zone. The use of the Receiver Operating Characteristic (ROC) curve for results validation highlights the fact that FFPI_DLNN-WOE is characterized by the most precise results with an Area Under Curve of 0.96.

Keywords: alternating decision trees; bivariate statistics; deep learning neural network; ensemble models; flash-flood potential index; remote sensing sensors.