2026-10-14T22:07:54Z https://www.scidb.cn/oai

10.57760/sciencedb.12069 2024-09-26T19:40:04Z

2024-09-26 Harnessing Deep Learning Techniques and Open-source Datasets to Analyze Possible Effects of Flooding on Land-cover, Population and Critical Facilities of the Nam Ngum River Basin, Lao PDR doi:10.57760/sciencedb.12069 en Flood susceptibility mapping is critical for disaster risk management in flood-prone regions, particularly the Nam Ngum River Basin in Lao PDR, which faces annual flooding due to monsoons and rainstorms. This study combines point-based data from publicly available open-source earth system datasets, historical flood observation datasets, Google’s cloud computing platform, and advanced remote sensing and deep learning techniques to create detailed flood susceptibility maps. Key datasets include digital elevation model (DEM), satellite-observed rainfall data, land use/land cover, and remote sensing image-derived indices such as NDVI and Sentinel-1 SAR imagery. The assessment employs various deep learning models, including Artificial Neural Networks (ANN), Long Short-Term Memory (LSTM), and Deep Neural Networks (DNN), to analyze hydro-meteorological and geomorphological parameters. These models were trained and tested using eleven flood conditioning variables and samples divided into training and testing datasets in a 70:30 ratio. Performance metrics such as accuracy, precision, and the area under the curve of Receiver Operating Characteristics (AUROC) were used to evaluate the models. The resulting flood susceptibility maps identify critical zones within the Nam Ngum River Basin at high risk of flooding, revealing that 36-53 % of the basin area is highly susceptible, especially in low-elevation and low-slope regions.Additionally, 85-93 % of the population is highly vulnerable to flooding within 261 to 296 km² of built-up area. Almost all of the critical facilities for health and education lie within the area, which is highly susceptible to flooding. The results of this study show the alarming situation of flood risk management. The study thus offers valuable insights for local authorities and stakeholders, enhancing flood risk management, emergency planning, and mitigation strategies. The findings provide essential information for policymakers, aiding disaster risk reduction and facilitating sustainable development planning in Lao PDR. Flood susceptibility; Deep learning algorithm; Open-source Datasets; Critical Facilities; Nam Ngum River Basin; Laos MANGKHASEUM Sackdavong Sunil Duwal Yogesh Bhattarai Akitoshi Hanazawa PUBLIC https://creativecommons.org/licenses/by/4.0/ dataset http://www.doi.org/10.52202/083081-0091 Science Data Bank