基于扩散的概率建模用于小时尺度径流预测与同化
Diffusion-Based Probabilistic Modeling for Hourly Streamflow Prediction and Assimilation
AI总结：
针对小时尺度径流预测，提出基于去噪扩散概率模型的h-Diffusion方法，以日径流为条件生成小时过程线，优于LSTM基线，并利用修复技术实现数据同化以提升洪水预报。
摘要：
小时尺度预测对于发布洪水预警至关重要，因为小时尺度的洪峰可能明显高于相应的日尺度洪峰。目前一种流行的小时尺度数据驱动预测方案是多时间尺度长短期记忆网络（MTS-LSTM），但此类模型在概率预测或整合可用观测数据方面面临挑战。扩散人工智能（AI）模型代表了一种预测高分辨率信息（如小时尺度径流）的有前景的方法。在此，我们开发了一种去噪扩散概率模型（h-Diffusion），用于小时尺度径流预测，该模型以水文模型观测或模拟的日径流为条件，生成小时尺度水文过程线。该模型在CAMELS小时数据集上，与创纪录的MTS-LSTM和多频LSTM（MF-LSTM）基线进行了基准测试。结果表明，h-Diffusion在总体性能和极端指标方面均优于基线。此外，h-Diffusion模型可以利用图像修复技术和近期观测数据进行数据同化，从而大幅提升洪水预报性能。这些进展可以大大降低洪水预报的不确定性，并为小时尺度的降尺度、预测和数据同化提供统一的概率框架，代表了日尺度模型无法捕捉的风险。
英文摘要：
Hourly predictions are critical for issuing flood warnings as the flood peaks on the hourly scale can be distinctly higher than the corresponding daily ones. Currently a popular hourly data-driven prediction scheme is multi-time-scale long short-term memory (MTS-LSTM), yet such models face challenges in probabilistic forecasts or integrating observations when available. Diffusion artificial intelligence (AI) models represent a promising method to predict high-resolution information, e.g., hourly streamflow. Here we develop a denoising diffusion probabilistic model (h-Diffusion) for hourly streamflow prediction that conditions on either observed or simulated daily discharge from hydrologic models to generate hourly hydrographs. The model is benchmarked on the CAMELS hourly dataset against record-holding MTS-LSTM and multi-frequency LSTM (MF-LSTM) baselines. Results show that h-Diffusion outperforms baselines in terms of general performance and extreme metrics. Furthermore, the h-Diffusion model can utilize the inpainting technique and recent observations to accomplish data assimilation that largely improves flood forecasting performance. These advances can greatly reduce flood forecasting uncertainty and provide a unified probabilistic framework for downscaling, prediction, and data assimilation at the hourly scale, representing risks where daily models cannot.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
