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

2025-10-29

AI Summary

Manual habitat mapping in alpine ecosystems is costly, and conventional methods underperform in scenarios involving ambiguous boundaries and class imbalance. Method: This study pioneers the application of geospatial foundation models (Prithvi-EO-2.0 and Clay v1.0) to multi-temporal land cover change detection in Alpine protected areas. We systematically compare post-classification change detection versus direct change detection paradigms, integrating RGB, near-infrared (NIR), LiDAR, and topographic data; notably, we innovatively leverage LiDAR to enhance semantic segmentation. Results: Clay v1.0 achieves 51% overall accuracy in multi-class change detection—outperforming U-Net by 10 percentage points—and attains an IoU of 0.53 and binary classification accuracy of 67% under the direct change detection framework. It demonstrates markedly superior cross-year generalization compared to supervised models. Moreover, LiDAR integration boosts segmentation accuracy from 30% to 50%, confirming its critical role in improving fine-grained habitat delineation.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• Detecting habitat changes in alpine protected areas
• Comparing AI architectures for environmental change detection
• Addressing class imbalance in complex natural landscapes

Innovation

• Compared post-classification and direct change detection paradigms
• Evaluated geospatial foundation models against U-Net baselines
• Integrated multimodal data including LiDAR and terrain attributes