Scholarlink

<p>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.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Novel Runoff Network Synchronous Prediction Model Based on Distribution Similarity Analyzing and Sparse Matrix Mapping

  • 期刊论文

  • 发表日期：

    2026年5月16日

查看全文
  • Ling Liu,
  • Jujie Wang,
  • Jianping Li,
  • Jun Hao,
  • Yinhong Yao

摘要

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.