Research Institute of the University of Bucharest, 90-92 Sos. Panduri, 5th District, 050663 Bucharest, Romania.
National Institute of Hydrology and Water Management, București-Ploiești Road, 97E, 1st District, 013686 Bucharest, Romania.
Sensors (Basel). 2021 Jan 4;21(1):280. doi: 10.3390/s21010280.
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 is characterized by the most precise results with an Area Under Curve of 0.96.
遥感传感器在监测和评估自然灾害易感性和风险方面的重要性明显增加。本研究旨在利用遥感传感器和地理信息系统（GIS）数据库提供的信息，评估罗马尼亚一个小流域的山洪暴发潜力值，这些信息被用作多个集成模型的输入数据。在第一阶段，借助谷歌地球应用程序的高分辨率卫星图像，获取了 481 个受激流影响的点，另外 481 个点随机分布在没有激流的区域。数据集的 70%被保留为训练数据，而其余的 30%被分配给验证样本。此外，为了训练机器学习模型，在训练样本位置提取了 10 个山洪暴发预测因子的信息。最后，使用以下四个集成来计算 Bâsca Chiojdului 河流域的山洪暴发潜力指数：深度学习神经网络-频率比（DLNN-FR）、深度学习神经网络-证据权重（DLNN-WOE）、交替决策树-频率比（ADT-FR）和交替决策树-证据权重（ADT-WOE）。使用多个统计指标评估模型的性能。因此，在灵敏度方面，DLNN-FR 模型达到了最高值 0.985，而 ADT-FR 模型的最低值为 0.866。此外，特异性分析表明，DLNN-WOE 算法的最高值为 0.991，而 ADT-FR 模型的最低值为 0.892。在训练过程中，模型的整体准确率在 0.878（ADT-FR）和 0.985（DLNN-WOE）之间。K 指数再次表明，表现最好的模型是 DLNN-WOE（0.97）。山洪暴发潜力指数（FFPI）值表明，高和极高山洪暴发易感性的表面覆盖了研究区域的 46.57%（DLNN-FR）到 59.38%（ADT-FR）。使用接收者操作特征（ROC）曲线对结果进行验证突出表明，FFPI 的特点是具有 0.96 的曲线下面积的最精确结果。
