arXiv Computer Vision

From Landslide Conditioning Factors to Satellite Embeddings: Evaluating the Utilisation of Google AlphaEarth for Landslide Susceptibility Mapping using Deep Learning

arXiv Computer Vision
Aug 27

Synergising Local Geo-Environmental Characteristics with Spatial Context for Enhancing Landslide Susceptibility Mapping

The paper introduces a Local-Geo and Spatial Context Fusion (LGSCF) strategy that combines point-based geo-environmental features with surrounding spatial context using a feature-wise modulation mechanism. Applied to nine CNN models over a 2644 km² area in Taiwan, LGSCF consistently outperforms baseline models, achieving F1-scores up to 87.09% and AUC values up to 0.9472. The resulting susceptibility maps more accurately concentrate known landslides in high-risk zones with fewer misclassifications.

By Yusen Cheng, Lei Fan, Qinfeng Zhu, Cheng Zhang, Yangyang Li, Ron Mahabir
Hugging Face Trending Papers
Aug 10

GeoPhysAdapter: Scale-Matched Geophysical Adaptation for Cross-Domain Landslide Mapping with Vision Foundation Models

Newly triggered landslides rarely carry immediate annotations, so cross-domain transferability determines the value of landslide mapping for emergency response and regional risk assessment. Vision foundation models have strengthened representational transfer, yet on unseen regions, events, and data sources they still generate high-confidence false alarms.

Hugging Face Trending Papers
Aug 20

SAGE-XGBoost: Spatially Augmented Graph Embeddings--Machine Learning Framework for Natural Hazards Susceptibility Mapping under Data Scarcity

Natural hazard susceptibility mapping is often constrained by limited labeled data, reducing the generalizability of conventional machine learning and limiting the applicability of complex deep learning models. This study proposes SAGE (Spatially Augmented Graph Embeddings), a structurally informed feature-engineering framework that combines controlled noise-based data augmentation with neighborhood-based graph embeddings to improve prediction under data-scarce conditions.

arXiv Computer Vision
Sep 1

Multi-Sensor Mapping of Vulnerable Urban Settlements Using SAR, Multispectral, and Hyperspectral Imagery: A Case Study in C\'ordoba, Argentina

The paper introduces a multi‑sensor deep learning framework for mapping informal settlements in Córdoba, Argentina, using high‑resolution PlanetScope multispectral imagery, COSMO‑SkyMed SAR data, and medium‑resolution PRISMA hyperspectral observations. It compares SAR‑only, MS‑only, and various fusion strategies (early, middle, late) and finds that late fusion with hyperspectral data (LF+HS) delivers the best balance of classification accuracy and spatial precision. The study also demonstrates that detections outside official polygons align with broader municipal vulnerability layers and that identified settlements show higher surface temperatures during a heatwave, highlighting localized heat amplification.

By Luigi Russo, Anabella Ferral, Silvia Liberata Ullo, Paolo Gamba