A Comparative Analysis of CNN-based Deep Learning Models for Landslide Detection

TL;DR

This paper compares four CNN-based semantic segmentation models for landslide detection, demonstrating that LinkNet achieves the highest accuracy and F1-score among them, highlighting the effectiveness of deep learning in natural disaster analysis.

Contribution

The study provides a detailed comparison of four CNN models with hyperparameter tuning for landslide detection, identifying the most effective architecture for this task.

Findings

LinkNet achieved 97.49% accuracy and 85.7% F1-score.

Hyperparameter tuning improved model performance.

Deep learning models outperform traditional algorithms in landslide detection.

Abstract

Landslides inflict substantial societal and economic damage, underscoring their global significance as recurrent and destructive natural disasters. Recent landslides in northern parts of India and Nepal have caused significant disruption, damaging infrastructure and posing threats to local communities. Convolutional Neural Networks (CNNs), a type of deep learning technique, have shown remarkable success in image processing. Because of their sophisticated architectures, advanced CNN-based models perform better in landslide detection than conventional algorithms. The purpose of this work is to investigate CNNs' potential in more detail, with an emphasis on comparison of CNN based models for better landslide detection. We compared four traditional semantic segmentation models (U-Net, LinkNet, PSPNet, and FPN) and utilized the ResNet50 backbone encoder to implement them. Moreover, we have experimented with the hyperparameters such as learning rates, batch sizes, and regularization techniques to fine-tune the models. We have computed the confusion matrix for each model and used performance metrics including precision, recall and f1-score to evaluate and compare the deep learning models. 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% (with 84.49% precision, 87.07% recall). We have also presented a comprehensive comparison of all pixel-wise confusion matrix results and the time taken to train each model.