用物理约束生成模型，实时预测洪水深度。
PIFF: A Physics-Informed Generative Flow Model for Real-Time Flood Depth Mapping
- 基于流形生成网络，结合地形与降雨数据预测洪水深度。
- 在台湾台南26平方公里区域测试，182组降雨场景下实现近实时输出。
- 融合水文物理规律，替代昂贵仿真，适合应急响应使用。
洪水映射对评估和减轻洪灾影响至关重要，但传统方法如数值模拟和航空摄影在效率与可靠性方面存在局限。为此，我们提出PIFF，一种基于物理信息的流式生成神经网络，用于近实时洪水深度估计。该模型基于图像到图像的生成框架，高效将数字高程模型（DEM）映射为洪水深度预测结果。模型通过简化淹没模型（SPM）嵌入水动力先验知识，并引入基于Transformer的降雨编码器以捕捉降水的时间依赖性。结合物理约束与数据驱动学习，PIFF能够刻画降雨、地形、SPM与洪水之间的因果关系，以高精度实现近实时洪水地图生成，取代耗时的数值模拟。在台湾台南26平方公里区域，针对182种降雨情景（24–720 mm/24小时）进行验证，结果表明PIFF是一种高效、数据驱动的洪水预测与响应新范式。
原文摘要 · Abstract (English)
Flood mapping is crucial for assessing and mitigating flood impacts, yet traditional methods like numerical modeling and aerial photography face limitations in efficiency and reliability. To address these challenges, we propose PIFF, a physics-informed, flow-based generative neural network for near real-time flood depth estimation. Built on an image-to-image generative framework, it efficiently maps Digital Elevation Models (DEM) to flood depth predictions. The model is conditioned on a simplified inundation model (SPM) that embeds hydrodynamic priors into the training process. Additionally, a transformer-based rainfall encoder captures temporal dependencies in precipitation. Integrating physics-informed constraints with data-driven learning, PIFF captures the causal relationships between rainfall, topography, SPM, and flooding, replacing costly simulations with accurate, real-time flood maps. Using a 26 km study area in Tainan, Taiwan, with 182 rainfall scenarios ranging from 24 mm to 720 mm over 24 hours, our results demonstrate that PIFF offers an effective, data-driven alternative for flood prediction and response.
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。