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

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.

Figure 1

Study area location.

Figure 2

Flash-flood predictors: (a) Slope; (b) Topographic Wetness Index (TWI); (c) Topographic Position Index (TPI); (d) Profile curvature; (e) Convergence index; (f) Stream Power Index (SPI).

Figure 3

Flash-flood predictors: (a) Aspect; (b) Land use; (c) Hydrological soil groups; (d) Lithology.

Figure 4

Flowchart of the methodological steps applied in this research.

Figure 5

Linear Support Vector Machine (LSVM) scores assigned to flash-flood predictors.

Figure 6

Distribution of FR and WOE coefficients within the classes of flash-flood predictors.

Figure 7

DLNN based ensemble running outputs (a) Training and Validating loss of DLNN-FR; (b) Training and Validating accuracy of DLNN-FR; (c) Training and Validating loss of DLNN-WOE; (d) Training and Validating accuracy of DLNN-WOE).

Figure 8

Deep Learning Neural Network architecture.

Figure 9

Flash-flood predictors importance.

Figure 10

Flash Flood Potential Index (a) DLNN-FR; (b) DLNN-WOE; (c) ADT-FR; (d) ADT-WOE.

Figure 11

Flash-Flood Potential Index (FFPI) classes weights.

Figure 12

Optimally pruned Decision Tree Structure for ADT based ensembles ((a) ADT-FR and (b) ADT-WOE ensembles).

Figure 13

Receiver Operating Characteristic (ROC) curve (a) Success Rate; (b) Prediction Rate.