Interpretable Short-Term Weather Prediction via Singular Value Decomposition and Linear System Modeling
DOI:
https://doi.org/10.63876/ijtm.v4i3.93Keywords:
Weather prediction, Short-term forecasting, Linear system modeling, Singular Value Decomposition (SVD), Matrix data analysis, Meteorological dataAbstract
Short-term weather prediction plays a critical role in supporting decision-making across sectors such as agriculture, transportation, and disaster risk management. This study proposes an interpretable and computationally efficient weather forecasting approach based on linear system modeling combined with Singular Value Decomposition (SVD). Historical meteorological data—including temperature, humidity, air pressure, and wind speed—are represented in matrix form to extract dominant patterns and construct a system of linear equations describing inter-variable relationships. The resulting model is evaluated for short-term forecasting horizons of 24–48 hours using standard performance metrics. Experimental results demonstrate that the proposed SVD-based linear system model outperforms conventional linear regression, achieving lower MAE and RMSE values and higher coefficients of determination (R² = 0.94 for temperature and 0.91 for humidity). While not intended to replace physics-based numerical weather prediction models for long-term forecasting, the proposed approach offers significant advantages in computational speed, interpretability, and applicability in data- and resource-constrained environments. These findings indicate that matrix-based linear system analysis provides a viable alternative for fast and accurate short-term weather prediction and can be further enhanced through integration with non-linear or machine learning-based methods.
Downloads
References
Z. Amiri, A. Heidari, dan N. J. Navimipour, “Comprehensive survey of artificial intelligence techniques and strategies for climate change mitigation,” Energy, vol. 308, hlm. 132827, Nov 2024, doi: https://doi.org/10.1016/j.energy.2024.132827.
M. E. F. Othman, L. M. Sidek, H. Basri, A. El-Shafie, dan A. N. Ahmed, “Climate challenges for sustainable hydropower development and operational resilience: A review,” Renewable and Sustainable Energy Reviews, vol. 209, hlm. 115108, Mar 2025, doi: https://doi.org/10.1016/j.rser.2024.115108.
Z. Shen dkk., “Current progress in subseasonal-to-decadal prediction based on machine learning,” Applied Computing and Geosciences, vol. 24, hlm. 100201, Des 2024, doi: https://doi.org/10.1016/j.acags.2024.100201.
S. Noh dan K.-H. Rhee, “Transparent and Accountable Training Data Sharing in Decentralized Machine Learning Systems,” CMC, vol. 79, no. 3, hlm. 3805–3826, 2024, doi: https://doi.org/10.32604/cmc.2024.050949.
P. Saikia, H. Bastida, dan C. E. Ugalde-Loo, “An effective predictor of the dynamic operation of latent heat thermal energy storage units based on a non-linear autoregressive network with exogenous inputs,” Applied Energy, vol. 360, hlm. 122697, Apr 2024, doi: https://doi.org/10.1016/j.apenergy.2024.122697.
Y. Qin, S. Duan, S. Achiche, Y. Zhang, dan Y. Cao, “Advanced hybrid empirical mode decomposition, convolutional neural network and long short-term memory neural network approach for predicting grain pile humidity based on meteorological inputs,” Journal of Stored Products Research, vol. 109, hlm. 102427, Des 2024, doi: https://doi.org/10.1016/j.jspr.2024.102427.
R. Yang dkk., “Interpretable machine learning for weather and climate prediction: A review,” Atmospheric Environment, vol. 338, hlm. 120797, Des 2024, doi: https://doi.org/10.1016/j.atmosenv.2024.120797.
L. D. O. Santos, T. AlSkaif, G. C. Barroso, dan P. C. M. D. Carvalho, “Photovoltaic power estimation and forecast models integrating physics and machine learning: A review on hybrid techniques,” Solar Energy, vol. 284, hlm. 113044, Des 2024, doi: https://doi.org/10.1016/j.solener.2024.113044.
J. Iglesias, I. Cuesta, C. Salueña, J. Solé, D. O. Prevatt, dan A. Fabregat, “Predictive modeling of severe weather impact on individuals and populations using Machine Learning,” International Journal of Disaster Risk Reduction, vol. 105, hlm. 104398, Apr 2024, doi: https://doi.org/10.1016/j.ijdrr.2024.104398.
N. L. Scuro, O. Beneš, S. Lorenzi, M. Krstovic, J. Krepel, dan M. H. A. Piro, “Coupled computational fluid dynamics and computational thermodynamics simulations for fission product retention and release: A molten salt fast reactor application,” Progress in Nuclear Energy, vol. 177, hlm. 105450, Des 2024, doi: https://doi.org/10.1016/j.pnucene.2024.105450.
L. Hou, Z. Yan, C. Desrosiers, dan H. Liu, “MFCPNet: Real time medical image segmentation network via multi-scale feature fusion and channel pruning,” Biomedical Signal Processing and Control, vol. 100, hlm. 107074, Feb 2025, doi: https://doi.org/10.1016/j.bspc.2024.107074.
B. Chen dkk., “High-resolution short-term prediction of the COVID-19 epidemic based on spatial-temporal model modified by historical meteorological data,” Fundamental Research, vol. 4, no. 3, hlm. 527–539, Mei 2024, doi: https://doi.org/10.1016/j.fmre.2024.02.006.
A. C. Donizette, C. D. Rocco, dan T. A. D. Queiroz, “Predicting leishmaniasis outbreaks in Brazil using machine learning models based on disease surveillance and meteorological data,” Operations Research for Health Care, vol. 44, hlm. 100453, Jun 2025, doi: https://doi.org/10.1016/j.orhc.2024.100453.
C. Cao, “How to better predict the effect of urban traffic and weather on air pollution? Norwegian evidence from machine learning approaches,” Journal of Economic Behavior & Organization, vol. 221, hlm. 544–569, Mei 2024, doi: https://doi.org/10.1016/j.jebo.2024.03.018.
Y. Biton, D. Braunstein, dan A. Rabinovitch, “New mapping algorithm SHIM (SVD, Hilbert Identifying Method) for the extraction of phase singularities and spiral waves in cardiac arrhythmias,” Biomedical Signal Processing and Control, vol. 100, hlm. 107106, Feb 2025, doi: https://doi.org/10.1016/j.bspc.2024.107106.
J. Wang, D. Gao, dan Z. Zhuang, “An optimized deep nonlinear integrated framework for wind speed forecasting and uncertainty analysis,” Applied Soft Computing, vol. 141, hlm. 110310, Jul 2023, doi: https://doi.org/10.1016/j.asoc.2023.110310.
Y. Zhang, J. Shen, J. Li, X. Yao, X. Chen, dan D. Liu, “A new lightweight framework based on knowledge distillation for reducing the complexity of multi-modal solar irradiance prediction model,” Journal of Cleaner Production, vol. 475, hlm. 143663, Okt 2024, doi: https://doi.org/10.1016/j.jclepro.2024.143663.
B. Sulkowski dan M. Collette, “A comparison of machine learning classifiers in predicting safety for a multi-component dynamic system representation of an autonomous vessel,” Applied Ocean Research, vol. 154, hlm. 104368, Jan 2025, doi: https://doi.org/10.1016/j.apor.2024.104368.
E. Fraga, A. Cortés, T. Margalef, P. Hernández, dan C. Carrillo, “Cloud-based urgent computing for forest fire spread prediction,” Environmental Modelling & Software, vol. 177, hlm. 106057, Jun 2024, doi: https://doi.org/10.1016/j.envsoft.2024.106057.
R. Maity, A. Srivastava, S. Sarkar, dan M. I. Khan, “Revolutionizing the future of hydrological science: Impact of machine learning and deep learning amidst emerging explainable AI and transfer learning,” Applied Computing and Geosciences, vol. 24, hlm. 100206, Des 2024, doi: https://doi.org/10.1016/j.acags.2024.100206.
