发表机构
Skolkovo Institute of Science and Technology; Trofimuk Institute of Petroleum Geology and Geophysics SB RAS; King Fahd University of Petroleum and Minerals; Tyumen Industrial University; Huawei Russian Research Institute（斯科尔科沃科学技术研究所; 俄罗斯科学院西伯利亚分院特罗菲穆克石油天然气地质与地球物理研究所; 法赫德国王石油与矿产大学; 秋明工业大学; 华为俄罗斯研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出端到端多模态洪水监测框架，对比U-Net++与AnySat两种水面检测策略，结合多模态卫星数据估算洪水影响，在2019年图伦洪水监测中表现良好，为跨区域大规模洪水监测提供可行方案。
AI 中文摘要
有效的洪水监测对于最大限度降低洪水灾害对人口和基础设施的影响至关重要。然而，在广阔且环境多样的区域开展可靠的遥感洪水监测仍面临挑战，因为大多数分割算法缺乏大规模应用所需的泛化能力，且带标注的洪水数据稀缺且分布不均。本研究提出了一种用于俄罗斯联邦领土可持续洪水监测与灾害评估的端到端多模态框架，该框架基于合成孔径雷达数据、多光谱影像及数字高程模型及其衍生数据，形成21通道输入。利用涵盖俄罗斯七个地区的自建多模态数据集，对比了有限数据条件下的两种水面检测策略：监督式U-Net++模型与针对分割任务进行预训练和微调的自监督AnySat架构。在本研究的数据条件下，监督学习表现更优，而基于AnySat的方法稳定性更强，且在推理阶段预期存在更多未标注数据或缺失模态的场景中具有优势。最佳洪水区域预测结果用于估算城市地区的洪水影响，涉及受影响面积、物质损失、人员伤亡及生态与农业影响，估算依据俄罗斯紧急情况部的官方方法开展。将该框架应用于2019年图伦洪水时，所得结果与官方评估高度吻合，仅物质损失因使用开源数据库存在差异。研究结果表明，深度学习与多模态卫星数据集成在环境多样且数据有限的条件下，具备实现可扩展、可靠洪水监测的潜力。
英文摘要
Effective flood monitoring is critical for minimizing the impacts of flood disasters on populations and infrastructure. Yet reliable remote sensing across extensive and environmentally diverse regions remains challenging, as most segmentation algorithms lack the generalisation capacity required for large-scale application, while annotated flood data are scarce and unevenly distributed. This study presents an end-to-end multimodal framework for Russian Federation territories sustainable flood monitoring and damage assessment based on synthetic aperture radar data, multispectral imagery, and digital elevation models with their derivatives, forming a 21-channel input. Using a self-collected multimodal dataset covering seven Russian regions, two strategies for water surface detection under limited data conditions were compared: a supervised U-Net++ model and the self-supervised AnySat architecture pre-trained and fine-tuned for the segmentation task. Under the data conditions of this study, supervised learning proved more effective, while the AnySat-based approach offered greater stability and retains advantages for settings where larger unlabelled data or missing modalities at inference are expected. The best flood area predictions were used to estimate flood impact in urban areas in terms of the area affected, material damage, casualties, and ecological and agricultural impact. The estimations were conducted following the official methodology of the Russian Ministry of Emergency Situations. Applied to the 2019 Tulun flood, the obtained results closely matched official assessments, except for material damage, due to the open-source databases usage. The results demonstrate the potential of deep learning and multimodal satellite data integration for scalable, reliable flood monitoring across diverse environmental and data-limited conditions.
Comments37 pages, 11 figures, 9 tables. Preprint submitted to Earth Systems and Environment. This version has not been peer reviewed
