GEOID-Flood：大规模多模态洪水分割基准数据集

摘要

地理空间基础模型旨在学习可跨区域和传感器迁移的表征，然而在特定任务上评估这些模型，需要大规模、高质量、多模态的基准数据集，以衡量此类模型从数据中提取价值的能力。就洪水制图而言，现有数据集很少能在较大规模上同时提供双时相SAR与配准的光学影像，导致基础模型在该下游任务中的价值在很大程度上未经测试。我们提出了GEOID-Flood，一个大规模多模态洪水分割基准，其数据来源于哥白尼应急管理服务（Copernicus Emergency Management Service）的启动任务，涵盖十年间65个国家的219起事件。该数据集提供超过14,000个图块，包含配准的哨兵一号（Sentinel-1）事件前后影像（GRD与RTC格式）、事件前哨兵二号（Sentinel-2）合成影像以及DEM，并附带人工验证的标注，可将背景与永久性水体和洪水水体区分开来。基于该基准，我们评估了基础模型与常规编码器在单影像、多时相和多模态协议下的表现。我们报告三项主要发现：基础模型提供了一致但适度的优势；光学与SAR融合结合微调最能解决瞬时洪水识别问题；在GEOID-Flood上训练的模型向未见事件的迁移能力优于在现有数据集上训练的模型。数据集和代码可在 https://github.com/links-ads/geoid-flood 获取。

English

Geospatial foundation models aim to learn representations that transfer across regions and sensors, yet evaluating them on specific tasks requires large, high-quality, multi-modal benchmarks that measure how well such models extract value from data. Concerning flood mapping, existing datasets rarely combine bi-temporal SAR and co-registered optical imagery at scale, leaving the value of foundation models for this downstream task largely untested. We introduce GEOID-Flood, a large-scale multi-modal flood segmentation benchmark, derived from Copernicus Emergency Management Service activations, spanning 219 events across 65 countries over ten years. The dataset provides more than 14,000 tiles with co-registered pre- and post-event Sentinel-1, in GRD and RTC format, pre-event Sentinel-2 composite, and DEM, including manually validated labels that separate background from permanent water and flooded water. Using this benchmark, we evaluate foundation models against conventional encoders across single-image, multi-temporal, and multi-modal protocols. We report three main findings: foundation models offer a consistent but modest advantage; optical-SAR fusion with finetuning best resolves transient flooding; and models trained on GEOID-Flood transfer to unseen events better than those trained on existing datasets. Dataset and code available at https://github.com/links-ads/geoid-flood.