Deep Learning Based Monthly Temperature Prediction for Jilin Province: A Multi Model Comparative Study 2000 2026

Abstract

Jilin Province, a core commercial grain production base in China with a mid-temperate continental monsoon climate and significant temperature fluctuations, relies heavily on temperature for agricultural production and ecological security. Existing temperature prediction studies focus mostly on national/southeastern coastal regions, with few targeting Jilin's specific climatic characteristics, and most models fail to integrate local temperature's spatiotemporal differentiation and seasonal periodicity, limiting prediction accuracy. Using 1 km $\times$ 1 km monthly mean temperature raster data (2000--2024) of Jilin Province, we analyzed regional temperature's spatiotemporal variation and constructed a multi-model comparison system including four deep learning models (LSTM, GRU, BiLSTM, Transformer) and five traditional machine learning models (Ridge/Lasso Regression, SVR, Random Forest, Gradient Boosting). Model performance was evaluated via RMSE, MAE, and $R^2$. Results show Jilin's temperature has obvious latitudinal zonal distribution, significant warming trend, strong seasonal periodicity, and high temporal autocorrelation. The LSTM model achieved optimal performance (test set RMSE=2.26 ${}^{\circ }$C, MAE=1.83 ${}^{\circ }$C, $R^2$=0.9655), outperforming traditional models and Transformer. Predictions for 2025--2026 indicate stable seasonal temperature fluctuations with an annual mean of ~4.9 ${}^{\circ }$C. This study enriches mid-latitude cold region temperature prediction research, verifies LSTM's applicability for Jilin's monthly temperature prediction, and provides scientific support for agricultural planning, frost disaster warning, and extreme temperature risk prevention.