Swarm‐based optimizer for convolutional neural network: An application for flood susceptibility mapping
Tien‐Yin Chou, Thanh Van Hoang, Yao‐Min Fang, Quoc‐Huy Nguyen, Tuan Anh Lai, Van‐Manh Pham, Van‐Manh Vu, Quang‐Thanh Bui
Abstract
Abstract This article investigates the use of the galactic swarm optimization algorithm in searching for parameters of a convolutional neural network for flood susceptibility mapping. Ha Giang province, the mountainous area of Vietnam, was chosen as a case study because of the frequent occurrence of floods. From this study area, 11 predictor variables and historical flood locations were selected to build up the training datasets, in which each sample is prepared in the 3D form of (height × width × channels or variables) = (5 × 5 × 11), (7 × 7 × 11), and (9 × 9 × 11), respectively for three experiments. The model performance was assessed by root mean square error, area under the receiver operating characteristic (AUC), and overall accuracy (OA). The results showed that the examined model significantly improved the classification accuracies: OA = 83.093, AUC = 0.917; OA = 83.726, AUC = 0.923; and OA = 82.791, AUC = 0.908 for the three training datasets in comparison to benchmarked classifiers, and this model can be considered as an alternative solution for flood susceptibility mapping.