Flooding is one of the most damaging natural hazards globally. During the past three years, floods have claimed hundreds of lives and millions of dollars of damage in Iran. In this study, we detected flood locations and mapped areas susceptible to floods using time series satellite data analysis as well as a new model of bagging ensemble-based alternating decision trees, namely, bag-ADTree. We used Sentinel-1 data for flood detection and time series analysis. We employed twelve conditioning parameters of elevation, normalized difference’s vegetation index, slope, topographic wetness index, aspect, curvature, stream power index, lithology, drainage density, proximities to river, soil type, and rainfall for mapping areas susceptible to floods. ADTree and bag-ADTree models were used for flood susceptibility mapping. We used software of Sentinel application platform, Waikato Environment for Knowledge Analysis, ArcGIS, and Statistical Package for the Social Sciences for preprocessing, processing, and postprocessing of the data. We extracted 199 locations as flooded areas, which were tested using a global positioning system to ensure that flooded areas were detected correctly. Root mean square error, accuracy, and the area under the ROC curve were used to validate the models. Findings showed that root mean square error was 0.31 and 0.3 for ADTree and bag-ADTree techniques, respectively. More findings illustrated that accuracy was obtained as 86.61 for bag-ADTree model, while it was 85.44 for ADTree method. Based on AUC, success and prediction rates were 0.736 and 0.786 for bag-ADTree algorithm, in order, while these proportions were 0.714 and 0.784 for ADTree. This study can be a good source of information for crisis management in the study area.

中文翻译：

---

使用Sentinel-1时间序列，备用决策树和Bag-ADTree模型进行洪水检测和敏感性映射

洪水是全球最具破坏力的自然灾害之一。在过去三年中，洪水在伊朗夺走了数百人的生命，并造成了数百万美元的损失。在这项研究中，我们使用时间序列卫星数据分析以及基于装袋集成的交替决策树的新模型（bag-ADTree）来检测洪水位置和易受洪水侵袭的区域。我们将Sentinel-1数据用于洪水检测和时间序列分析。我们使用了十二个条件参数，分别是海拔，归一化差异的植被指数，坡度，地形湿度指数，纵横比，曲率，水流功率指数，岩性，排水密度，邻近河流，土壤类型和降雨，以绘制易受洪水侵袭的地区。ADTree和bag-ADTree模型用于洪水敏感性地图绘制。我们使用Sentinel应用程序平台软件，怀卡托知识分析环境，ArcGIS和社会科学统计软件包对数据进行预处理，处理和后处理。我们提取了199个位置作为洪水区，并使用全球定位系统对其进行了测试，以确保正确检测到洪水区。均方根误差，准确性和ROC曲线下的面积用于验证模型。结果表明，ADTree和bag-ADTree技术的均方根误差分别为0.31和0.3。更多发现表明，对于bag-ADTree模型，准确度为86.61，而对于ADTree方法，准确度为85.44。基于AUC，bag-ADTree算法的成功率和预测率依次为0.736和0.786，而ADTree的成功率和预测率分别为0.714和0.784。