A Comparative Study on Deep Learning-Based: Temperature Prediction Models: Performance Evaluation of CNN, Transformer and Random Forest

Qingyang Feng

doi:10.54254/2755-2721/2025.LD27822

Applied and Computational EngineeringOpen access

A Comparative Study on Deep Learning-Based: Temperature Prediction Models: Performance Evaluation of CNN, Transformer and Random Forest

Research Article

Open Access

A Comparative Study on Deep Learning-Based: Temperature Prediction Models: Performance Evaluation of CNN, Transformer and Random Forest

Qingyang Feng ^1*

¹ Department of Mathematics and Statistics, University of Toronto, City, Country, Toronto, Canada

^*Corresponding author: fqy10987@163.com

Published on 14 October 2025

ACE Vol.191

ISSN (Print): 2755-273X

ISSN (Online): 2755-2721

ISBN (Print): 978-1-80590-184-6

ISBN (Online): 978-1-80590-129-7

Download Cover

Abstract

Accurate short-term temperature prediction is of great significance in fields such as agricultural production and disaster prevention and mitigation. This study aims to explore the performance differences among three models—Convolutional Neural Network (CNN), Transformer, and Random Forest (RF)—in short-term temperature prediction tasks, providing a reference for model selection and optimization in meteorological forecasting. Based on the Beijing PM2.5 dataset, the research constructs supervised learning samples through data preprocessing (using the temperature sequence of the past 24 hours as input to predict the temperature at the 25th hour) and trains and evaluates the three models under unified experimental configurations. The results show that all three models can achieve high-precision predictions. Among them, Random Forest performs the best , with significant advantages in error control, noise resistance, and high training efficiency. CNN follows and excels at capturing local short-term fluctuation features. Transformer , although capable of modeling long-range dependencies, performs slightly inferior with the current dataset. The study reveals that traditional machine learning models still have practical value in resource-constrained scenarios, while deep learning models can further improve accuracy when sufficient data is available. Model fusion and the introduction of multiple factors may be future optimization directions.

Keywords:

Short-term temperature prediction, CNN, Transformer, Random Forest, machine learning

View PDF

References

[1]. J. Ahn, J. Kim, and Y. Park, "Deep learning approaches for weather forecasting: A review, " Atmosphere, vol. 15, no. 1, p. 123, 2024. doi: 10.3390/atmos15010123.

[2]. C. Wen, Z. Fu, Y. Guo, and Q. Zhou, "Deep learning for weather and climate prediction: A survey, " Artif. Intell. Rev., vol. 55, no. 8, pp. 5977–6006, 2022. doi: 10.1007/s10462-021-10083-1.

[3]. P. Hewage, A. Behera, M. Trovati, and E. Pereira, "Machine learning approaches for weather and climate modelling, " Neurocomputing, vol. 461, pp. 237–256, 2021. doi: 10.1016/j.neucom.2021.07.045.

[4]. M. Reichstein, G. Camps-Valls, B. Stevens, M. Jung, J. Denzler, N. Carvalhais, and P. Prabhat, "Deep learning and process understanding for data-driven Earth system science, " Nature, vol. 566, no. 7743, pp. 195–204, 2019. doi: 10.1038/s41586-019-0912-1.

[5]. A. Krizhevsky, I. Sutskever, and G. E. Hinton, "ImageNet classification with deep convolutional neural networks, " Adv. Neural Inf. Process. Syst., vol. 25, pp. 1097–1105, 2012.

[6]. K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition, " Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), pp. 770–778, 2016. doi: 10.1109/CVPR.2016.90.

[7]. A. Vaswani et al., "Attention is all you need, " Adv. Neural Inf. Process. Syst., vol. 30, pp. 5998–6008, 2017.

[8]. H. Zhou, S. Zhang, J. Peng, S. Zhang, J. Li, H. Xiong, and W. Zhang, "Informer: Beyond efficient transformer for long sequence time-series forecasting, " Proc. AAAI Conf. Artif. Intell., vol. 35, no. 12, pp. 11106–11115, 2023.

[9]. L. Breiman, "Random forests, " Machine Learn., vol. 45, no. 1, pp. 5–32, 2001. doi: 10.1023/A: 1010933404324.

[10]. X. Li and Y. Qian, "CNN-based approaches for short-term weather prediction, " J. Appl. Meteorol. Climatol., vol. 63, no. 2, pp. 245–260, 2024.

[11]. Y. Li, H. Zhang, and J. Wang, "Application of random forests in meteorological forecasting, " Theor. Appl. Climatol., vol. 157, no. 3–4, pp. 789–803, 2024.

[12]. J. A. Weyn, D. R. Durran, and R. Caruana, "Can machines learn to predict weather? Using deep learning to predict gridded 500-hPa geopotential height from historical weather data, " J. Adv. Modeling Earth Syst., vol. 11, no. 8, pp. 2680–2693, 2019. doi: 10.1029/2019MS001705.

[13]. S. Wang, Y. Liu, X. Chen, and J. Zhu, "Hybrid models for weather prediction combining deep learning and physical approaches, " Clim. Dyn., vol. 60, no. 1–2, pp. 55–70, 2023. doi: 10.1007/s00382-022-06410-7.

[14]. J. Chen, L. Zhao, and Y. Huang, "Evaluation of error metrics in weather forecasting models, " Environ. Model. Softw., vol. 162, p. 105589, 2023. doi: 10.1016/j.envsoft.2023.105589.

[15]. R. J. Hyndman and A. B. Koehler, "Another look at measures of forecast accuracy, " Int. J. Forecasting, vol. 22, no. 4, pp. 679–688, 2006. doi: 10.1016/j.ijforecast.2006.03.001.

[16]. R. Lam, Q. He, and T. Zhang, "Explainable AI in weather forecasting: Current progress and future directions, " Expert Syst. Appl., vol. 213, p. 118957, 2023. doi: 10.1016/j.eswa.2022.118957.

[17]. P. D. Dueben and P. Bauer, "Challenges and design choices for global weather and climate models based on machine learning, " Geosci. Model Dev., vol. 11, no. 10, pp. 3999–4009, 2018. doi: 10.5194/gmd-11-3999-2018.

[18]. S. Rasp, P. D. Dueben, S. Scher, J. A. Weyn, S. Mouatadid, and N. Thuerey, "WeatherBench: A benchmark dataset for data-driven weather forecasting, " J. Adv. Modeling Earth Syst., vol. 12, no. 11, e2020MS002203, 2020. doi: 10.1029/2020MS002203.

[19]. K. Bi, Z. Sun, and X. Zhao, "Robust weather forecasting models using ensemble deep learning, " Appl. Intell., vol. 53, no. 5, pp. 5431–5445, 2023. doi: 10.1007/s10489-022-04077-8.

[20]. Y. Liu, T. Xu, X. Chen, and W. Zhang, "Transformer-based models for weather forecasting: A comprehensive study, " IEEE Trans. Geosci. Remote Sens., vol. 60, pp. 1–15, 2022. doi: 10.1109/TGRS.2021.3137264.