Scholarlink

Accurate weather forecasting holds paramount significance across a multitude of sectors, encompassing vital industries such as agriculture, transportation, and disaster management, where precise predictions can greatly influence operational efficiency and safety. Although traditional Numerical Weather Prediction (NWP) models furnish essential insights into meteorological phenomena, they frequently present challenges related to significant computational expense and exhibit difficulty in effectively capturing the complex non-linear dynamics that are inherently present within atmospheric systems. This research undertakes a comprehensive examination of various deep learning models, alongside conducting an extensive comparative analysis between these distinct methodologies to ascertain their individual strengths and weaknesses. The performance of these models are meticulously evaluated through the application of standard error metrics, which include Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE), to rigorously assess their predictive accuracy and robustness in the realm of meteorological predictions.

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 Comparative Study of Temperature Prediction Using Deep Learning Models

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Sudha Prakriti,
  • Pathan Muskan,
  • Makkapati Poojitha,
  • Gajavalli Pallavi,
  • Naba Krushna Sabat

摘要

Accurate weather forecasting holds paramount significance across a multitude of sectors, encompassing vital industries such as agriculture, transportation, and disaster management, where precise predictions can greatly influence operational efficiency and safety. Although traditional Numerical Weather Prediction (NWP) models furnish essential insights into meteorological phenomena, they frequently present challenges related to significant computational expense and exhibit difficulty in effectively capturing the complex non-linear dynamics that are inherently present within atmospheric systems. This research undertakes a comprehensive examination of various deep learning models, alongside conducting an extensive comparative analysis between these distinct methodologies to ascertain their individual strengths and weaknesses. The performance of these models are meticulously evaluated through the application of standard error metrics, which include Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE), to rigorously assess their predictive accuracy and robustness in the realm of meteorological predictions.