Analisis Performa Model Random Forest dan Support Vector Regression  untuk Prediksi Suhu Maksimum Harian di Kota Jambi

R. Zaevan Khazafi Putra; Riza Pahlevi; Ronald Naibaho; Agus Nugroho

doi:10.61132/prosemnasproit.v2i2.103

Authors

R. Zaevan Khazafi Putra Universitas Dinamika Bangsa
Riza Pahlevi Universitas Dinamika Bangsa
Ronald Naibaho Universitas Dinamika Bangsa
Agus Nugroho Universitas Dinamika Bangsa

DOI:

https://doi.org/10.61132/prosemnasproit.v2i2.103

Keywords:

Feature Engineering, Prediksi Cuaca, Random Forest, Suhu Maksimum, Support Vector Regression

Abstract

The dynamic changes in weather patterns in Jambi City require an accurate temperature prediction
system, thus this study aims to compare the performance of Random Forest and Support Vector Regression (SVR)
algorithms in predicting daily maximum temperatures using weather data from 2020–2024 obtained from Open
Meteo with the application of Feature Engineering including lag and rolling window features. The test results
indicate that the SVR model with a Radial Basis Function (RBF) kernel optimized using Grid Search (C=10,
epsilon=0.2, gamma=0.01) significantly outperforms Random Forest based on a statistical Paired T-test (p-value
< 0.05), yielding an R-squared (R²) value of 87.46%, Mean Absolute Error (MAE) of 0.3818 °C, and Root Mean
Squared Error (RMSE) of 0.4964 °C compared to Random Forest's R² of 84.05%, where the previous day's
temperature (lag) and three-day rolling average were identified as the most dominant predictors, leading to the
recommendation of SVR as the more effective method for temperature prediction in the study area.

References

Béland, H. K. & Sun, Y. (2021). Machine Learning in Atmospheric Science: A Review. Atmosphere, 12(8). https://doi.org/10.3390/atmos12080988

Breiman, L. (2001). Random Forests. Machine Learning, 45(1), 5–32.

Brownlee, J. (2020). Machine Learning Mastery With Python. Machine Learning Mastery.

Gupta, A., Maji, S. & Debnath, R. (2022). Machine Learning Approaches for Weather Prediction: An Overview. Environmental Modelling & Software, 152. https://doi.org/10.1016/j.envsoft.2022.105360

Indrasari, W. & Suhendar, H. (n.d.). ANALISIS MODEL PREDIKSI CUACA MENGGUNAKAN SUPPORT VECTOR MACHINE, GRADIENT BOOSTING, RANDOM FOREST, DAN DECISION TREE. Prosiding Seminar Nasional Fisika (E-Journal), XII. https://doi.org/10.21009/03.1201.FA18

Kumar, V. & others. (2021). A Review on Numerical Weather Prediction Models and Their Applications. Earth-Science Reviews, 221. https://doi.org/10.1016/j.earscirev.2021.103774

Li, Y., Li, T., Lv, W., Liang, Z. & Wang, J. (2023). Prediction of Daily Temperature Based on the Robust Machine Learning Algorithms. Sustainability (Switzerland), 15(12). https://doi.org/10.3390/su15129289

Pal, M. & Foody, D. (2022). Applications of Support Vector Machines in the Prediction of Environmental Parameters. Environmental Modelling & Software, 150. https://doi.org/10.1016/j.envsoft.2022.105296

Plevris, V., Solorzano, G., Bakas, N. P. & Ben Seghier, M. E. A. (2022). INVESTIGATION OF PERFORMANCE METRICS IN REGRESSION ANALYSIS AND MACHINE LEARNING-BASED PREDICTION MODELS. World Congress in Computational Mechanics and ECCOMAS Congress. https://doi.org/10.23967/eccomas.2022.155

Smaili, A., Seridi, H. & Sandli, F. E. (2022). Support Vector Regression Models for Nonlinear System Modeling: A Comprehensive Review. Neural Computing and Applications, 34, 10341–10363. https://doi.org/10.1007/s00521-021-06735-w

Smola, A. J. & Schölkopf, B. (2004). A Tutorial on Support Vector Regression. Statistics and Computing, 14(3), 199–222.

Xu, W. & others. (2022). Trends and Perspectives in Artificial Intelligence and Machine Learning for Environmental Data Analysis. Environmental Science & Technology, 56(12), 8197–8212. https://doi.org/10.1021/acs.est.1c08499

Zhang, G., Bateni, S. M., Jun, C., Khoshkam, H., Band, S. S. & Mosavi, A. (2022). Feasibility of Random Forest and Multivariate Adaptive Regression Splines for Predicting Long-Term Mean Monthly Dew Point Temperature. Frontiers in Environmental Science, 10. https://doi.org/10.3389/fenvs.2022.826165