发表机构
Sanya Science and Education Innovation Park, Wuhan University of Technology; School of Computer Science and Artificial Intelligence, Wuhan University of Technology; School of Earth and Space Science and Technology, Wuhan University; School of Water Resources and Hydropower Engineering, Wuhan University; GNSS Research Center, Wuhan University（武汉理工大学三亚科教创新园; 武汉理工大学计算机科学与人工智能学院; 武汉大学地球空间与科学技术学院; 武汉大学水利水电学院; 武汉大学卫星导航定位技术研究中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对站点级降水临近预报的两大挑战，提出 MZ-Rain 框架，结合 moisture budget 引导建模与自适应 Tweedie 策略，在多区域实验中优于基线模型，强降水预报性能卓越。
AI 中文摘要
准确的站点级降水临近预报对农业、水资源管理和灾害预防至关重要，通常被表述为时间序列预测问题。然而，传统时间序列建模技术在处理站点级降水临近预报时面临两大核心挑战：（1）缺乏物理引导建模，即气象变量被视为同质集合，未考虑其在降水形成中的不同作用，导致预测结果偏离降水的物理过程；（2）降水存在严重的零膨胀现象，数据集中干旱区间占主导，掩盖了有意义的降水模式，使预测建模复杂化。为应对这些挑战，我们提出 MZ-Rain，这是一个用于站点级降水临近预报的 moisture-budget 引导零膨胀 sLSTM 框架。在 moisture budget 方程的引导下，MZ-Rain 将降水形成过程分解为对应 moisture 存储、moisture 输送、表面蒸发和降水持续性的特定过程路径，并通过专用 sLSTM 分支捕捉它们的时间演变。为解决降水的零膨胀特性，MZ-Rain 引入自适应 Tweedie 建模策略，该策略可自适应调节降雨均值，同时将降水发生作为辅助任务联合学习，使模型能更好地平衡干湿区分和定量降水估计。在不同地理和气候区域开展的大量实验表明，MZ-Rain 在 CSI、FAR、MSE 和 MAE 等多项评估指标上始终优于强劲的基线模型。尤其值得注意的是，该模型在预报强降水事件方面表现出卓越性能，同时得益于基于物理原理的过程建模。
英文摘要
Accurate station-level precipitation nowcasting is critical for agriculture, water resource management, and disaster prevention, which typically is formulated as a time series forecasting problem. However, conventional time-series modeling techniques face two major challenges in addressing station-level precipitation nowcasting: (1) Lack of Physics-Guided Modeling}, where meteorological variables are treated as a homogeneous set without accounting for their distinct roles in precipitation formation, leads to predictions that deviate from the physical processes governing precipitation. (2) Severe zero inflation in precipitation, where dry intervals dominate the dataset, obscuring meaningful precipitation patterns and complicating the predictive modeling. To address these challenges, we propose \textbf{MZ-Rain}, a moisture-budget-guided zero-inflated sLSTM framework for station-level precipitation nowcasting. Guided by the moisture budget equation, MZ-Rain decomposes the precipitation formation process into process-specific pathways corresponding to moisture storage, moisture transport, surface evaporation, and precipitation persistence, and captures their temporal evolution through dedicated sLSTM branches. To account for the zero-inflated nature of precipitation, MZ-Rain introduces an adaptive Tweedie modeling strategy that adaptively modulates the rainfall mean while jointly learning precipitation occurrence as an auxiliary task, enabling the model to better balance dry-wet discrimination and quantitative precipitation estimation. Extensive experiments across diverse geographical and climatic regimes demonstrate that MZ-Rain consistently outperforms strong baselines on multiple evaluation metrics, including CSI, FAR, MSE, and MAE. In particular, the model exhibits superior skill in forecasting heavy precipitation events, while benefiting from physically grounded process modeling.
Comments16 pages, 6 figures
