Scholarlink

<p>Precise rainfall forecasting is essential for efficient water resource management and disaster preparedness, especially in areas vulnerable to severe weather conditions. This study presents an integrated approach, combining machine learning techniques and statistical models, to predict rainfall patterns in Bangladesh's southwestern and northwestern regions. To complete this study, the method employs an Evidential Neural Network with the Gaussian Random Fuzzy Numbers (EVNN-GRFN) model, integrated with the Broyden-Fletcher-Goldfarb-Shanno (BFGS) algorithm and the Autoregressive Moving Average (ARMA) model. Analyzing 41&#xa0;years of data from four stations, the research demonstrates superior performance of EVNN-GRFN-M2 for Dinajpur and EVNN-GRFN-M1 for other stations. Results show R2 values over 70% and correlation values above 0.737 during calibration and validation, with RMSE and MAPE confirming model robustness. These findings offer valuable insights for water management, agricultural practices, and disaster mitigation in regions prone to extreme weather, enabling more informed decision-making.</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

EVNN-GRFN integrated with BFGS-ARMA for rainfall prediction in Bangladesh

  • 期刊论文

  • 发表日期：

    2025年2月4日

查看全文
  • Sujit Kumar Roy,
  • Sagiru Mati,
  • Md Zidanur Rahman Zidan,
  • Billal Hossen,
  • Dilber Uzun Ozsahin,
  • Mohamed Abioui

摘要

Precise rainfall forecasting is essential for efficient water resource management and disaster preparedness, especially in areas vulnerable to severe weather conditions. This study presents an integrated approach, combining machine learning techniques and statistical models, to predict rainfall patterns in Bangladesh's southwestern and northwestern regions. To complete this study, the method employs an Evidential Neural Network with the Gaussian Random Fuzzy Numbers (EVNN-GRFN) model, integrated with the Broyden-Fletcher-Goldfarb-Shanno (BFGS) algorithm and the Autoregressive Moving Average (ARMA) model. Analyzing 41 years of data from four stations, the research demonstrates superior performance of EVNN-GRFN-M2 for Dinajpur and EVNN-GRFN-M1 for other stations. Results show R2 values over 70% and correlation values above 0.737 during calibration and validation, with RMSE and MAPE confirming model robustness. These findings offer valuable insights for water management, agricultural practices, and disaster mitigation in regions prone to extreme weather, enabling more informed decision-making.