Sequential Feature Selection for Efficient Landslide Segmentation from Multi-Spectral Data

TL;DR

This paper introduces a sequential feature selection method for landslide segmentation from multispectral satellite data, reducing input channels while maintaining or improving model performance and enhancing interpretability.

Contribution

It proposes an explainable, systematic channel selection framework using SFFS and a lightweight model, revealing key features for landslide detection and improving input efficiency.

Findings

Selected 8 channels that match or outperform models with 30 channels.

Identified spectral and topographic features crucial for landslide prediction.

Demonstrated the interpretability benefits of the feature selection process.

Abstract

Landslide detection from satellite imagery has advanced through deep learning, yet most models rely on large, highly correlated spectral-topographic inputs whose contributions remain poorly understood. The question of which channels are actually necessary has received surprisingly little attention. This matters: redundant or correlated inputs obscure physical interpretability, inflate computational overhead, and can actively degrade model performance through the Hughes Phenomenon. We present a systematic, explainable channel-selection framework for the Landslide4Sense benchmark, combining Sentinel-2 multispectral and ALOS PALSAR terrain data with 16 engineered spectral and structural indices. Rather than relying on conventional single-band drop tests, which evaluate channels in isolation and miss interaction effects, we apply Sequential Forward Floating Selection (SFFS) to iteratively build and prune a candidate feature pool using a lightweight U-Net++ proxy model. Beyond identifying a compact 8-channel subset that matches or exceeds the segmentation F1 of configurations using up to 30 channels, we use the selection process itself to interrogate which spectral and topographic features landslide models genuinely rely on, and what this reveals about the physical cues driving their predictions. We argue that SFFS represents a principled feature selection approach to input design in Earth observation, in contrast to the prevailing practice of appending every available band and hoping the model learns what to ignore.