Scholarlink

This article presents multistep time-series forecasting of annual monsoon rainfall in India using nonlinear autoregressive with exogenous input (NARX) neural network. The annual monsoon rainfall data of duration from year 1901 to 2014 has been considered learning of NARX neural network. The prediction accuracy of the NARX model has been confirmed using several error indicators namely mean absolute error (MAE), root mean squared error (RMSE), mean absolute percentage error (MAPE) and mean arctangent absolute percentage error (MAAPE). The outcomes demonstrate outstanding performance of NARX neural network model giving a MAE, RMSE, MAPE, and MAAPE of 28.38 mm, 30.64 mm, 3.52% and 3.49%, respectively.

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

Nonlinear Autoregressive with Exogenous Input (NARX) Neural Network-Based Machine-Learning Model for Time-Series Application

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Ashwani Kharola,
  • Ravi Kanojia,
  • Deepak Juyal,
  • Abhishek Misra,
  • Kiran Sharma,
  • Tarun Kumar Dhiman,
  • Vishwjeet Choudhary,
  • Sankula Madhava

摘要

This article presents multistep time-series forecasting of annual monsoon rainfall in India using nonlinear autoregressive with exogenous input (NARX) neural network. The annual monsoon rainfall data of duration from year 1901 to 2014 has been considered learning of NARX neural network. The prediction accuracy of the NARX model has been confirmed using several error indicators namely mean absolute error (MAE), root mean squared error (RMSE), mean absolute percentage error (MAPE) and mean arctangent absolute percentage error (MAAPE). The outcomes demonstrate outstanding performance of NARX neural network model giving a MAE, RMSE, MAPE, and MAAPE of 28.38 mm, 30.64 mm, 3.52% and 3.49%, respectively.