Automating global landslide detection with heterogeneous ensemble deep-learning classification

TL;DR

This paper develops an ensemble deep-learning approach combining multiple segmentation models and satellite data to improve global landslide detection accuracy, addressing data scarcity and model sensitivity issues.

Contribution

It introduces a heterogeneous ensemble model that leverages diverse deep learning segmentation architectures and multispectral satellite data for enhanced landslide mapping.

Findings

Ensemble model achieved F1-score of 0.69 with combined Sentinel-1 and Sentinel-2 data.

Ensemble size of 20 yielded an average improvement of 6.87%.

Sentinel-2 data alone achieved an F1 score of 0.61 with a 14.59% improvement.

Abstract

With changing climatic conditions, we are already seeing an increase in extreme weather events and their secondary consequences, including landslides. Landslides threaten infrastructure, including roads, railways, buildings, and human life. Hazard-based spatial planning and early warning systems are cost-effective strategies to reduce the risk to society from landslides. However, these both rely on data from previous landslide events, which is often scarce. Many deep learning (DL) models have recently been applied for landside mapping using medium- to high-resolution satellite images as input. However, they often suffer from sensitivity problems, overfitting, and low mapping accuracy. This study addresses some of these limitations by using a diverse global landslide dataset, using different segmentation models, such as Unet, Linknet, PSP-Net, PAN, and DeepLab and based on their performances, building an ensemble model. The ensemble model achieved the highest F1-score (0.69) when combining both Sentinel-1 and Sentinel-2 bands, with the highest average improvement of 6.87 % when the ensemble size was 20. On the other hand, Sentinel-2 bands only performed very well, with an F1 score of 0.61 when the ensemble size is 20 with an improvement of 14.59 % when the ensemble size is 20. This result shows considerable potential in building a robust and reliable monitoring system based on changes in vegetation index dNDVI only.