用基础模型提升滑坡制图泛化能力，解决数据少、传感器多变难题。
Landslide Hazard Mapping with Geospatial Foundation Models: Geographical Generalizability, Data Scarcity, and Band Adaptability
- 构建三轴适配框架，提升模型跨传感器、区域和标签稀缺场景下的表现
- 在多个数据集上优于专用CNN与视觉变压器模型，尤其在小样本下保持高精度
- 适合灾害监测、环境评估等需要跨区域部署的科研与应用团队
滑坡对生命、基础设施和环境造成严重破坏，精准及时的制图对防灾减灾至关重要。然而，传统深度学习模型在不同传感器、区域或训练数据有限时表现不佳。本文针对普里蒂维-EO-2.0（Prithvi-EO-2.0）地理空间基础模型（GeoFMs），提出涵盖传感器、标签与领域三个维度的适配分析框架。通过系列实验表明，该模型在多个滑坡数据集上均显著优于专用卷积网络（如U-Net、U-Net++）、视觉变压器（Segformer、SwinV2-B）及其他基础模型（TerraMind、SatMAE）。其基于全球预训练、自监督学习与可调微调机制，在光谱变化、标签稀缺及跨地域场景中仍保持高鲁棒性与泛化能力。同时指出计算成本高与可复用AI友好型训练数据稀缺等挑战。研究证明GeoFMs是实现更稳健、可扩展滑坡风险防控与环境监测的重要方向。
原文摘要 · Abstract (English)
Landslides cause severe damage to lives, infrastructure, and the environment, making accurate and timely mapping essential for disaster preparedness and response. However, conventional deep learning models often struggle when applied across different sensors, regions, or under conditions of limited training data. To address these challenges, we present a three-axis analytical framework of sensor, label, and domain for adapting geospatial foundation models (GeoFMs), focusing on Prithvi-EO-2.0 for landslide mapping. Through a series of experiments, we show that it consistently outperforms task-specific CNNs (U-Net, U-Net++), vision transformers (Segformer, SwinV2-B), and other GeoFMs (TerraMind, SatMAE). The model, built on global pretraining, self-supervision, and adaptable fine-tuning, proved resilient to spectral variation, maintained accuracy under label scarcity, and generalized more reliably across diverse datasets and geographic settings. Alongside these strengths, we also highlight remaining challenges such as computational cost and the limited availability of reusable AI-ready training data for landslide research. Overall, our study positions GeoFMs as a step toward more robust and scalable approaches for landslide risk reduction and environmental monitoring.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。