A Comparative Analysis of CNN-based Deep Learning Models for Landslide Detection
Published in 2024 Asian Conference on Intelligent Technologies (ACOIT), 2024
Abstract: Landslides inflict substantial societal and economic damage. The purpose of this work is to investigate CNNs’ potential in more detail. We compared four traditional semantic segmentation models (U-Net, LinkNet, PSPNet, and FPN) utilizing a ResNet50 backbone. According to the experimental results, LinkNet gave the best results among the four models having an Accuracy of 97.49% and a F1-score of 85.7%.
Dataset Samples: 
Recommended citation: O. Oak, R. Nazre, S. Naigaonkar, S. Sawant, H. Vaidya. (2024). "A Comparative Analysis of CNN-based Deep Learning Models for Landslide Detection." IEEE ACOIT 2024.
Download Paper