Spatial Mapping of Flood Susceptibility Using Decision Tree–Based Machine Learning Models for the Vembanad Lake System in Kerala, India

Floods have claimed the lives of countless people and caused significant property damage in many countries, putting their livelihoods in the jeopardy. The Vembanad lake system (VLS) in Kerala, India, has faced adverse mishappening during 2018, 2019, and 2021 floods in the state due to torrential rainfall. The goal of this research is to construct effective decision tree–based machine learning models such as adaptive boosting (AdaBoost), random forest (RF), gradient boosting machines (GBMs), and extreme gradient boosting (XGBoost) for integrating data, processing, and generating flood susceptibility maps. There are 18 conditioning parameters considered, which include seven categories and 11 numerical data. These seven categorical data were converted to numerical data, bringing the total amount of input data to 61. The recursive feature elimination (RFE) was utilized as the feature selection technique, and a total of 22 layers were chosen to feed into the machine learning models to generate the flood susceptibility maps. The efficiencies of the models were evaluated using receiver operating characteristic (ROC)–area under the ROC curve (AUC), F1 score, accuracy, and kappa. According to the results, the performance of all four models demonstrated their practical application; however, XGBoost fared well in terms of the model’s metrics. For the testing data set, the ROC-AUC values of XGBoost, GBM, and AdaBoost are 0.90, whereas it was 0.89 for RF. The accuracy varied significantly among the four models, with XGBoost scoring 0.92, followed by GBM (0.88), RF (0.87), and AdaBoost (0.87). As a result, this map may be utilized for early mitigation actions during future floods, as well as for land-use planners and emergency managers, assisting in the reduction of flood risk in regions prone to this hazard.

The parameters used in the current methodology can be used to develop a flood susceptibility model for rainfall-induced flooding. The machine learning models used are some of the most widely accepted models, and they perform well in terms of accuracy and model reliability. This study will be extremely useful to the government and nongovernmental organizations in terms of risk assessment and mitigation during times of crisis, as well as early people rescue and worthwhile preparation. The focus of risk evaluation and prevention efforts is no longer on controlling floods, but rather on local governments’ obligations to lessen flood impacts. Residents in flood-prone areas should be warned about the hazards and possibilities. Land-use planners and government entities are obligated to inform local communities about the most recent flood susceptibility evaluations and the rules prohibiting new projects in areas with a high risk of flooding. Using maps of flood-prone areas and the severity of the damage, a possible rescue route during difficult times can be planned.