Flood susceptibility mapping using AutoML and a deep learning framework with evolutionary algorithms for hyperparameter optimization

• Published in: Applied soft computing 2023-11, Vol.148, p.110846, Article 110846
• Main Authors: Vincent, Amala Mary, K.S.S., Parthasarathy, Jidesh, P.
• Format: Article
• Language: English
• Subjects: AutoML; Bayesian optimization; Convolutional neural network; Flood susceptibility mapping; HPO; Kerala
• ISSN: 1568-4946; 1872-9681
• DOI: 10.1016/j.asoc.2023.110846

Flooding is one of the most common natural hazards that have extremely detrimental consequences. Understanding which areas are vulnerable to flooding is crucial to addressing these effects. In this work, we use machine learning models and Automated machine learning (AutoML) systems for flood susceptibility mapping in Kerala, India. In particular, we used a three-dimensional convolutional neural network (CNN) architecture for this purpose. The CNN model was assisted with hyperparameter optimization techniques that combine Bayesian optimization with evolutionary algorithms like differential evolution and covariance matrix adaptation evolutionary strategies. The performances of all models are compared in terms of cross-entropy loss, accuracy, precision, recall, area under the curve (AUC) and kappa score. The CNN model shows better performance than the AutoML models. Evolutionary algorithm-assisted hyperparameter optimization methods improved the efficiency of the CNN model by 4 and 9 percent in terms of accuracy and by 0.0265 and 0.0497 with reference to the AUC score. [Display omitted] •A 3D CNN model is proposed to assess flood susceptibility.•Model performance is compared with state-of-the-art machine learning and AutoML models.•A novel hyperparameter optimization model designed for the 3D CNN model.•The model is further improvised by using the evolutionary algorithms-assisted Bayesian optimization technique.