Comparing Machine Learning Methods for Offline Applications with Short Lookback and Limited Input

Hongyi Lai

doi:10.54254/2753-8818/2025.DL27105

Theoretical and Natural ScienceOpen access

Comparing Machine Learning Methods for Offline Applications with Short Lookback and Limited Input

Research Article

Open Access

Comparing Machine Learning Methods for Offline Applications with Short Lookback and Limited Input

Hongyi Lai ^1*

¹ University of California - Santa Barbara

^*Corresponding author: hongyilai@ucsb.edu

Published on 24 September 2025

TNS Vol.132

ISSN (Print): 2753-8826

ISSN (Online): 2753-8818

ISBN (Print): 978-1-80590-305-5

ISBN (Online): 978-1-80590-306-2

Download Cover

Abstract

This study focuses on a comparative study of machine learning methods on offline weather forecasting with short lookback windows and limited computational resources. Using 90 days of single-station GSOD inputs, models predict 15-day horizons for temperature, precipitation, wind speed, and visibility. Evaluation with Nash–Sutcliffe efficiency, RMSE, and inference time shows that Linear Regression is a surprisingly strong and stable baseline, excelling in wind speed and remaining competitive across variables. Transformer models perform best for temperature by capturing long-range dependencies, while sequence-to-sequence GRUs outperform others on precipitation and visibility. In contrast, XGBoost and persistence baselines consistently underperform in this constrained setup. In inference time, LR outperform all other methods due to its simplicity. The results indicate that simple linear models can excel in this scenario compare to deep learning approaches, while specialized neural architectures provide targeted gains, suggesting a combination of models could be the most effective for practical low-resource forecasting.

Keywords:

Weather forecast, Machine learning, Transformer, Linear regression, Comparative Study

View PDF

References

[1]. Chhetri, M., Kumar, S., Roy, P. P., & Kim, B.-G. (2020). Deep BLSTM-GRU model for monthly rainfall prediction: A case study of Simtokha, Bhutan. Remote Sensing, 12(19), 3174.

[2]. Chen, L., Zhong, X., Zhang, F., Cheng, Y., Xu, Y., Qi, Y., & Li, H. (2023). FuXi: A cascade machine learning forecasting system for 15-day global weather forecast. npj Climate and Atmospheric Science, 6, 190.

[3]. Eka Setiawan, K., Elwirehardja, G. N., & Pardamean, B. (2023). Indoor Climate Prediction Using Attention-Based Sequence-to-Sequence Neural Network. Civil Engineering Journal, 9(5), 1105–1120.

[4]. Bojesomo, A., Al Marzouqi, H., & Liatsis, P. (2024). A novel transformer network with shifted window cross-attention for spatiotemporal weather forecasting. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 17, 45–55.

[5]. Deng, X., Ye, A., Zhong, J., Xu, D., Yang, W., Song, Z., Zhang, Z., Guo, J., Wang, T., Tian, Y., Pan, H., Zhang, Z., Wang, H., Wu, C., Shao, J., & Chen, X. (2022). Bagging–XGBoost algorithm-based extreme weather identification and short-term load forecasting model. Energy Reports, 8, 8661–8674.

[6]. Yu, Y., Cao, J., & Zhu, J. (2019). An LSTM short-term solar irradiance forecasting under complicated weather conditions. IEEE Access, 7, 145651–145666.

[7]. Sherstinsky, A. (2020). Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D: Nonlinear Phenomena, 404, 132306.

[8]. Chicco, D., Warrens, M. J., & Jurman, G. (2021). The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. Peerj computer science, 7, e623.

References

[1]. Chhetri, M., Kumar, S., Roy, P. P., & Kim, B.-G. (2020). Deep BLSTM-GRU model for monthly rainfall prediction: A case study of Simtokha, Bhutan. Remote Sensing, 12(19), 3174.

[3]. Eka Setiawan, K., Elwirehardja, G. N., & Pardamean, B. (2023). Indoor Climate Prediction Using Attention-Based Sequence-to-Sequence Neural Network. Civil Engineering Journal, 9(5), 1105–1120.

[6]. Yu, Y., Cao, J., & Zhu, J. (2019). An LSTM short-term solar irradiance forecasting under complicated weather conditions. IEEE Access, 7, 145651–145666.

[7]. Sherstinsky, A. (2020). Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D: Nonlinear Phenomena, 404, 132306.

Cite this article

Lai,H. (2025). Comparing Machine Learning Methods for Offline Applications with Short Lookback and Limited Input. Theoretical and Natural Science,132,33-42.

Data availability

The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.

About volume

Volume title: Proceedings of CONF-APMM 2025 Symposium: Simulation and Theory of Differential-Integral Equation in Applied Physics

ISBN: 978-1-80590-305-5(Print) / 978-1-80590-306-2(Online)

Editor: Marwan Omar, Shuxia Zhao

Conference website: https://www.confapmm.org/dalian.html

Conference date: 27 September 2025

Series: Theoretical and Natural Science

Volume number: Vol.132

ISSN: 2753-8818(Print) / 2753-8826(Online)

© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license. Authors who publish this series agree to the following terms:

1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.

2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.

3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open access policy for details).