A Novel Runoff Network Synchronous Prediction Model Based on Distribution Similarity Analyzing and Sparse Matrix Mapping.
Saved in:
| Title: | A Novel Runoff Network Synchronous Prediction Model Based on Distribution Similarity Analyzing and Sparse Matrix Mapping. |
|---|---|
| Authors: | Liu, Ling1,2 (AUTHOR) liul@zuwe.edu.cn, Wang, Jujie3 (AUTHOR) jujiewang@nuist.edu.cn, Li, Jianping4 (AUTHOR) ljp@ucas.ac.cn, Hao, Jun4,5 (AUTHOR) haojun@ucas.ac.cn, Yao, Yinhong6 (AUTHOR) yaoyinhong@cueb.edu.cn |
| Source: | Water Resources Management. Jun2026, Vol. 40 Issue 8, p1-19. 19p. |
| Subject Terms: | *Runoff analysis, *Sparse matrices, *Statistical correlation, *Forecasting, *Water management, *Spatiotemporal processes, *Flood warning systems |
| Abstract: | Accurate runoff forecasting is critical for effective water resources planning and management. However, it remains challenging due to the complex spatiotemporal dynamics of hydrological networks. Here, we propose a novel runoff network synchronous prediction model that integrates a new sparse matrix mapping technique to capture spatial dependencies efficiently. This matrix comprises several sub-matrices derived from the distribution similarity analysis, effectively capturing disparities between sub-matrices as well as internal similarities. Ten benchmark models are used to evaluate the efficacy of the proposed methods. Results show that the proposed model has the best predictive performance, with mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), and Nash-Sutcliffe Efficiency Coefficient (NSE) values of 6.875, 12.381, 0.272, and 0.769, respectively. These findings offer practical implications for real-time flood warning systems. [ABSTRACT FROM AUTHOR] |
| Database: | Energy & Power Source |
Be the first to leave a comment!
