arXiv：cs.LG· Mohammad A. Farmani, Hoshin V. Gupta, Ali Behrangi, Muhammad Jawad, Sadaf Moghisi, Guo-Yue Niu·· 7 小时前AI 评分33
保质量神经网络框架 MCP 如何用文过程约束做降雨径流建模
Process-Aware AI for Rainfall-Runoff Modeling: A Mass-Conserving Neural Framework with Hydrological Process Constraints
AI 导读
Mass-Conserving Perceptron（MCP）通过逐步嵌入有界土壤蓄水、状态依赖导水率、可变孔隙度、入渗能力、地表积水、垂直排水和非线性地下水位动态等水文过程约束，在美国本土五大水文气候区 15 个流域的日径流预测中普遍提升性能。
正文
Abstract:Machine learning models can achieve high predictive accuracy in hydrological applications but often lack physical interpretability. The Mass-Conserving Perceptron (MCP) provides a physics-aware artificial intelligence (AI) framework that enforces conservation principles while allowing hydrological process relationships to be learned from data. In this study, we investigate how progressively embedding physically meaningful representations of hydrological processes within a single MCP storage unit improves predictive skill and interpretability in rainfall-runoff modeling. Starting from a minimal MCP formulation, we sequentially introduce bounded soil storage, state-dependent conductivity, variable porosity, infiltration capacity, surface ponding, vertical drainage, and nonlinear water-table dynamics. The resulting hierarchy of process-aware MCP models is evaluated across 15 catchments spanning five hydroclimatic regions of the continental United States using daily streamflow prediction as the target. Results show that progressively augmenting the internal physical structure of the MCP unit generally improves predictive performance. The influence of these process representations is strongly hydroclimate dependent: vertical drainage substantially improves model skill in arid and snow-dominated basins but reduces performance in rainfall-dominated regions, while surface ponding has comparatively small effects. The best-performing MCP configurations approach the predictive skill of a Long Short-Term Memory benchmark while maintaining explicit physical interpretability. These results demonstrate that embedding hydrological process constraints within AI architectures provides a promising pathway toward interpretable and process-aware rainfall-runoff modeling.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2603.25093 [cs.LG] |
| (or arXiv:2603.25093v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2603.25093 arXiv-issued DOI via DataCite |
Submission history
From: Mohammad Farmani [view email]
[v1]
Thu, 26 Mar 2026 06:58:31 UTC (2,634 KB)
[v2]
Mon, 31 Aug 2026 19:11:08 UTC (6,121 KB)
[v3]
Tue, 6 Oct 2026 16:21:32 UTC (5,145 KB)
来源：arXiv：cs.LG · arxiv.org