Journal of Fujian Normal University(Natural Science Edition), Volume. 41, Issue 4, 11(2025)

Deep Learning-Based Forecast of the 30-Day Average Temperature

ZHANG Yujie1,2,3, CHEN Xueying1,2,3、*, LUO Haifeng1,2,3, WENG Bin1,2,3, HUANG Liqing1,2,3, and YOU Lijun4
Author Affiliations
  • 1College of Computer and Cyber Security, Fujian Normal University, Fuzhou 350117, China
  • 2Digital Fujian Big Data Security Technology Institute, Fuzhou 350117, China
  • 3Fujian Provincial Engineering Research Center of Public Service Big Data Analysis and Application, Fuzhou 350117, China
  • 4Fujian Meteorological Information Center, Fujian Key Laboratory of Severe Weather, Fuzhou 350025, China
  • show less

    Existing global numerical weather prediction models typically provide large-scale, low-resolution forecasts, which are insufficient to meet the requirements of localized, fine-scale meteorological prediction. This study focuses on forecasting the 30-day average temperature in Fujian Province and proposes two deep learning approaches based on a multi-layer perceptron (MLP) and a convolutional neural network (CNN). Experimental results show that the independently trained CNN model with a 5×5 grid input achieves the best performance, reducing the mean absolute error (MAE) and mean squared error (MSE) by 65.3% and 86.7%, respectively, and increasing the correlation coefficient by 4.4%, compared to the baseline provided by the European Centre for Medium-Range Weather Forecasts (ECMWF). These findings demonstrate that selecting appropriate grid scales and model architectures can substantially improve the accuracy of temperature forecasts in specific regions.

    Tools

    Get Citation

    Copy Citation Text

    ZHANG Yujie, CHEN Xueying, LUO Haifeng, WENG Bin, HUANG Liqing, YOU Lijun. Deep Learning-Based Forecast of the 30-Day Average Temperature[J]. Journal of Fujian Normal University(Natural Science Edition), 2025, 41(4): 11

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Received: Nov. 7, 2024

    Accepted: Aug. 21, 2025

    Published Online: Aug. 21, 2025

    The Author Email: CHEN Xueying (qsx20231335@student.fjnu.edu.cn)

    DOI:10.12046/j.issn.1000-5277.2024110015

    Topics