August 16, 2025Natural HazardsOpen Access

Flood susceptibility mapping of urban flood risk: comparing autoencoder multilayer perceptron and logistic regression models in Ubon Ratchathani, Thailand

View Full Paper

Ask AI

Bookmark

Authors

Discussion

Evaluation reveals AE-MLP outperforms logistic regression for flood susceptibility mapping, suggesting improved urban planning strategies.

The AE-MLP model predicted flood risks more accurately than logistic regression, significantly enhancing urban planning.
AUC for the AE-MLP model reached 0.950, while logistic regression achieved only 0.860, indicating superior predictive performance.
Assessment used various metrics such as F1-score and accuracy, illustrating comprehensive model evaluation for flood risks.
Implementing the AE-MLP model could improve urban resilience by effectively identifying high-risk flood areas.

Tsumita et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

Evaluation reveals AE-MLP outperforms logistic regression for flood susceptibility mapping, suggesting improved urban planning strategies.