Scholarlink

<p>Lakes play a crucial role in the water cycle, and accurately modeling their water level fluctuation is vital for managing water resources, ecosystems, and flood control. The current study aims to develop a novel emotional artificial neural network optimized by genetic algorithm (GA-EANN), weighted average model stacking (WAE) and neural network-based stacking (NNE) that combines the outputs of emotional artificial neural network (EANN) and artificial neural network (ANN) for modeling the water level of four lakes of Rift Valley Lakes Basin (RVLB) in Ethiopia. Ten years of daily hydrological and weather data were used for model training and testing. The efficiencies of the employed algorithms were compared using graphical and statistical metrics such as root mean square error (RMSE), mean absolute error (MAE), Nash Sutcliffe Efficiency (NSE) and coefficient of determination (R<sup>2</sup>). The modeling result demonstrated that the NNE method provided the best prediction accuracy at Hawassa Lake (RMSE = 0.056&#xa0;m, NSE = 0.972 and R<sup>2</sup> = 0.972), Langano Lake (RMSE = 0.059&#xa0;m, NSE = 0.978 and R<sup>2</sup> = 0.978) and Abiyata lake (RMSE = 0.052&#xa0;m, NSE = 0.987and R<sup>2</sup> = 0.987) in the testing set. At Ziway Lake, the hybrid GA-EANN model surpassed other models with R<sup>2</sup> value of 0.976 in testing set. Generally, the NNE and optimized hybrid modeling (GA-EANN) significantly improved the performance of water level prediction.</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

Hybrid emotional neural networks and novel multi-model stacking algorithms for multi-lake water level fluctuation modeling

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年2月15日

查看全文
  • Gebre Gelete,
  • Tagesse Gichamo,
  • Tesfalem Abraham,
  • Huseyin Gokcekus

摘要

Lakes play a crucial role in the water cycle, and accurately modeling their water level fluctuation is vital for managing water resources, ecosystems, and flood control. The current study aims to develop a novel emotional artificial neural network optimized by genetic algorithm (GA-EANN), weighted average model stacking (WAE) and neural network-based stacking (NNE) that combines the outputs of emotional artificial neural network (EANN) and artificial neural network (ANN) for modeling the water level of four lakes of Rift Valley Lakes Basin (RVLB) in Ethiopia. Ten years of daily hydrological and weather data were used for model training and testing. The efficiencies of the employed algorithms were compared using graphical and statistical metrics such as root mean square error (RMSE), mean absolute error (MAE), Nash Sutcliffe Efficiency (NSE) and coefficient of determination (R2). The modeling result demonstrated that the NNE method provided the best prediction accuracy at Hawassa Lake (RMSE = 0.056 m, NSE = 0.972 and R2 = 0.972), Langano Lake (RMSE = 0.059 m, NSE = 0.978 and R2 = 0.978) and Abiyata lake (RMSE = 0.052 m, NSE = 0.987and R2 = 0.987) in the testing set. At Ziway Lake, the hybrid GA-EANN model surpassed other models with R2 value of 0.976 in testing set. Generally, the NNE and optimized hybrid modeling (GA-EANN) significantly improved the performance of water level prediction.