Habitat and Land Cover Change Detection in Alpine Protected Areas: A Comparison of AI Architectures

TL;DR

This study compares AI architectures for habitat change detection in alpine ecosystems, demonstrating that advanced models like Clay v1.0 and ChangeViT outperform traditional methods in accuracy, especially when integrating multimodal data.

Contribution

It evaluates and compares the performance of geospatial foundation models and deep learning architectures for habitat change detection in complex alpine environments, highlighting their robustness and potential improvements.

Findings

Clay v1.0 achieves 51% accuracy in multi-class habitat change detection.

Direct change detection with ChangeViT yields higher IoU (0.53) than U-Net.

LiDAR data integration improves semantic segmentation accuracy from 30% to 50%.

Abstract

Rapid climate change and other disturbances in alpine ecosystems demand frequent habitat monitoring, yet manual mapping remains prohibitively expensive for the required temporal resolution. We employ deep learning for change detection using long-term alpine habitat data from Gesaeuse National Park, Austria, addressing a major gap in applying geospatial foundation models (GFMs) to complex natural environments with fuzzy class boundaries and highly imbalanced classes. We compare two paradigms: post-classification change detection (CD) versus direct CD. For post-classification CD, we evaluate GFMs Prithvi-EO-2.0 and Clay v1.0 against U-Net CNNs; for direct CD, we test the transformer ChangeViT against U-Net baselines. Using high-resolution multimodal data (RGB, NIR, LiDAR, terrain attributes) covering 4,480 documented changes over 15.3 km2, results show Clay v1.0 achieves 51% overall accuracy versus U-Net's 41% for multi-class habitat change, while both reach 67% for binary change detection. Direct CD yields superior IoU (0.53 vs 0.35) for binary but only 28% accuracy for multi-class detection. Cross-temporal evaluation reveals GFM robustness, with Clay maintaining 33% accuracy on 2020 data versus U-Net's 23%. Integrating LiDAR improves semantic segmentation from 30% to 50% accuracy. Although overall accuracies are lower than in more homogeneous landscapes, they reflect realistic performance for complex alpine habitats. Future work will integrate object-based post-processing and physical constraints to enhance applicability.