MODEL PREDIKSI CURAH HUJAN MENGGUNAKAN ALGORTIMA MACHINE LEARNING YANG DITINGKATKAN
DOI:
https://doi.org/10.37859/coscitech.v5i2.7629
Abstract
Curah hujan merupakan parameter meteorologi yang memiliki dampak signifikan terhadap berbagai aspek kehidupan, seperti kerusakan infrastruktur, gangguan transportasi, dan implikasi sosial-ekonomi. Prakiraan curah hujan tradisional sering kali tidak dapat mengatasi kompleksitas pola non-linear, variabilitas spasial, dan temporal curah hujan. Perkembangan teknologi seperti Internet of Things (IoT) dan penginderaan jauh membuka peluang baru dalam memperoleh data meteorologi yang kaya, namun analisis data ini memerlukan pendekatan yang lebih canggih.
Penelitian ini bertujuan untuk mengembangkan model prediksi curah hujan di Kota Pekanbaru, Riau, menggunakan algoritma Random Forest. Dataset yang digunakan merupakan data deret waktu (time series) dari Januari 2010 hingga Desember 2023. Data tambahan berasal dari citra penginderaan jauh satelit MODIS (variabel Land Surface Temperature) serta data meteorologi dari BMKG. Model ini dioptimalkan melalui hyperparameter tuning untuk meningkatkan akurasi prediksi. Evaluasi kinerja dilakukan dengan parameter statistik seperti R-squared (R²), Mean Absolute Error (MAE), dan Mean Squared Error (MSE).
Hasil penelitian menunjukkan bahwa model Random Forest memberikan kinerja prediksi yang baik dengan R-squared sebesar 0.8266, MAE sebesar 1.3948, dan MSE sebesar 4.2100. Penelitian ini diharapkan dapat memberikan kontribusi signifikan dalam peningkatan akurasi prakiraan curah hujan, yang berguna untuk mitigasi risiko, peringatan dini, dan perencanaan pengelolaan risiko bencana di wilayah urban.
Downloads
References
M. A. Abdel-Aty dan H. T. Abdelwahab, “Predicting Injury Severity Levels in Traffic Crashes: A Modeling Comparison,” J Transp Eng, vol. 130, no. 2, hlm. 204–210, 2004, doi: 10.1061/(ASCE)0733-947X(2004)130:2(204).
K. Haleem, P. Alluri, dan A. Gan, “Analyzing pedestrian crash injury severity at signalized and non-signalized locations,” Accid Anal Prev, vol. 81, hlm. 14–23, 2015, doi: https://doi.org/10.1016/j.aap.2015.04.025.
S. Ibrahim Kabeer dan J. Roche, “Analysis of Road accident in Leeds MSc Research Project Data Analytics,” 2016.
A. Iranitalab dan A. Khattak, “Comparison of four statistical and machine learning methods for crash severity prediction,” Accid Anal Prev, vol. 108, hlm. 27–36, 2017, doi: https://doi.org/10.1016/j.aap.2017.08.008.
Md. M. Rizvee, M. Amiruzzaman, dan Md. R. Islam, “Data Mining and Visualization to Understand Accident-prone Areas,” ArXiv, vol. abs/2103.09062, 2021, [Daring]. Tersedia pada: https://api.semanticscholar.org/CorpusID:232240229
M. Ijaz, L. lan, M. Zahid, dan A. Jamal, “A comparative study of machine learning classifiers for injury severity prediction of crashes involving three-wheeled motorized rickshaw,” Accid Anal Prev, vol. 154, hlm. 106094, 2021, doi: https://doi.org/10.1016/j.aap.2021.106094.
G. Baryannis, S. Dani, dan G. Antoniou, “Predicting supply chain risks using machine learning: The trade-off between performance and interpretability,” Future Gener. Comput. Syst., vol. 101, no. C, hlm. 993–1004, Des 2019, doi: 10.1016/j.future.2019.07.059.
S. Dong, A. Khattak, I. Ullah, J. Zhou, dan A. Hussain, “Predicting and Analyzing Road Traffic Injury Severity Using Boosting-Based Ensemble Learning Models with SHAPley Additive exPlanations,” Int J Environ Res Public Health, vol. 19, no. 5, 2022, doi: 10.3390/ijerph19052925.
J. P. S. S. Madushani, R. M. K. Sandamal, D. P. P. Meddage, H. R. Pasindu, dan P. I. A. Gomes, “Evaluating expressway traffic crash severity by using logistic regression and explainable & supervised machine learning classifiers,” Transportation Engineering, vol. 13, hlm. 100190, 2023, doi: https://doi.org/10.1016/j.treng.2023.100190.
L. Eboli, C. Forciniti, dan G. Mazzulla, “Factors influencing accident severity: an analysis by road accident type,” Transportation Research Procedia, vol. 47, hlm. 449–456, 2020, doi: https://doi.org/10.1016/j.trpro.2020.03.120.
D. Patil, R. Franklin, S. Deshmukh, S. Pillai, dan P. M. Nashipudimath, “ANALYSIS OF ROAD ACCIDENTS USING DATA MINING TECHNIQUES : A SURVEY,” International Research Journal of Engineering and Technology, 2020, [Daring]. Tersedia pada: www.irjet.net
M. Karla Rocha, M. José Anzanello, G. Harumi Yamashita, F. Caleffi, dan H. Cybis, “Identifying the most informative variables to discriminate between fatal and non-fatal road accidents,” Case Stud Transp Policy, vol. 14, hlm. 101093, 2023, doi: https://doi.org/10.1016/j.cstp.2023.101093.
H. Jeong, Y. Jang, P. J. Bowman, dan N. Masoud, “Classification of motor vehicle crash injury severity: A hybrid approach for imbalanced data,” Accid Anal Prev, vol. 120, hlm. 250–261, 2018, doi: https://doi.org/10.1016/j.aap.2018.08.025.
X. Wen, Y. Xie, L. Jiang, Z. Pu, dan T. Ge, “Applications of machine learning methods in traffic crash severity modelling: current status and future directions,” Transp Rev, vol. 41, no. 6, hlm. 855–879, 2021, doi: https://doi.org/10.1080/01441647.2021.1954108.
P. and S. M. K. and S. S. D. Rekha Sundari M. and Reddi, “Fatality Prediction in Road Accidents Using Neural Networks,” dalam Proceedings of International Conference on Recent Trends in Computing, S. K. and R. S. and P. P. Mahapatra Rajendra Prasad and Peddoju, Ed., Singapore: Springer Nature Singapore, 2023, hlm. 25–33.
B. H. Misheva dan J. Osterrieder, “A Hypothesis on Good Practices for AI-based Systems for Financial Time Series Forecasting: Towards Domain-Driven XAI Methods,” ArXiv, vol. abs/2311.07513, 2023, [Daring]. Tersedia pada: https://api.semanticscholar.org/CorpusID:265149899
T. Chen dan C. Guestrin, “XGBoost: A scalable tree boosting system,” dalam Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery, Agu 2016, hlm. 785–794. doi: 10.1145/2939672.2939785.
S. Nowozin dkk., “Decision jungles: Compact and rich models for classification,” 2013. [Daring]. Tersedia pada: https://www.researchgate.net/publication/289206432
C. Bentéjac, A. Csörgő, dan G. Martínez-Muñoz, “A comparative analysis of gradient boosting algorithms,” Artif Intell Rev, vol. 54, no. 3, hlm. 1937–1967, 2021, doi: 10.1007/s10462-020-09896-5.
L. Breiman, “Random Forests,” Mach Learn, vol. 45, no. 1, hlm. 5–32, 2001, doi: 10.1023/A:1010933404324.
F. Pedregosa dkk., “Scikit-learn: Machine Learning in Python,” 2011. [Daring]. Tersedia pada: http://scikit-learn.sourceforge.net.
M. T. Ribeiro, S. Singh, dan C. Guestrin, “‘Why Should I Trust You?’: Explaining the Predictions of Any Classifier,” dalam Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, dalam KDD ’16. New York, NY, USA: Association for Computing Machinery, 2016, hlm. 1135–1144. doi: 10.1145/2939672.2939778.
