Klasifikasi Kualitas Air Sungai menggunakan Random Forest, SVC Dan Logistic Regression
Article Sidebar
Read Counter : 9
Download : 4
Main Article Content
Abstract
Studi ini bertujuan untuk mengklasifikasikan kualitas air sungai menggunakan tiga algoritma machine learning: Random Forest, Support Vector Classifier (SVC), dan Logistic Regression. Tujuan dari penelitian ini adalah untuk membandingkan kinerja ketiga algoritma tersebut berdasarkan accuracy, precision, recall, dan F1-score guna menentukan model yang paling sesuai untuk pemantauan kualitas air. Dataset yang digunakan diperoleh dari portal Satu Data Jakarta, yang berisi pengukuran kualitas air dari 23 sungai berdasarkan parameter fisik dan kimia seperti pH, dissolved oxygen (DO), biochemical oxygen demand (BOD), total dissolved solids (TDS), suhu, dan kekeruhan. Data tersebut melalui proses preprocessing melalui pembersihan, categorical encoding, dan feature scaling sebelum digunakan untuk pelatihan dan pengujian model. Hasil penelitian menunjukkan bahwa algoritma Random Forest mencapai accuracy tertinggi (93,33%) dan F1-score sebesar 0,87, diikuti oleh SVC dan Logistic Regression. Logistic Regression menghasilkan precision tertinggi, sementara Random Forest memberikan keseimbangan terbaik antara precision dan recall. Temuan ini menunjukkan bahwa Random Forest merupakan algoritma yang paling efektif dan adaptif untuk klasifikasi kualitas air sungai, menawarkan kinerja yang andal untuk mendukung pemantauan lingkungan dan pengelolaan air yang berkelanjutan.
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This work is licensed under a Jurnal Komunikasi Creative Commons Attribution-ShareAlike 4.0 International License.
How to Cite
References
[1] A. Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow (3rd ed.). O’Reilly Media, 2023.
[2] A. W. Saputra, F. H. Arifianto, and R. H. Putra, “Application of Machine Learning Models in Water Quality Classification in Lake Maninjau: Random Forest as the Optimal Solution,” E-Tech J. Ilm. Teknol. Elektro, vol. 10, no. 2, pp. 45–54, 2023.
[3] A. P. Singh and M. N. Islam, “Optimization of Machine Learning Algorithms for River Water Quality Prediction,” Environ. Monit. Assess., vol. 196, no. 3, pp. 1–15, 2024.
[4] J. K. Nair and A. Thomas, “Comparative Evaluation of Ensemble Learning Techniques for Surface Water Quality Classification,” Water Resour. Manag., vol. 37, no. 4, pp. 1103–1118, 2023.
[5] S. Li and X. Zheng, “Cryptanalysis of a Chaotic Image Encryption Method,” in Proceedings IEEE – ISACS, Scottsdale, Arizona, 2002.
[6] Y. Mao and G. Chen, “Chaos-Based Image Encryption BT - Handbook of Computational Geometry for Pattern Recognition, Computer Vision, Neural Computing and Robotics,” Berlin: Springer, 2003.
[7] S. Khan, R. Kumar, and P. Mehta, “Water Quality Assessment Through Predictive Modeling Employing Machine Learning Methods,” J. Comput. Biomed. Informatics, vol. 3, no. 1, pp. 33–42, 2024.
[8] M. A. Yildiz and B. Kaya, “Prediction of Water Quality’s pH Value Using Random Forest and LightGBM Algorithms,” MEMBA J. Water Sci., vol. 6, no. 2, pp. 120–130, 2025.
[9] T. Y. Nguyen, H. Pham, and N. Tran, “Deep Learning-Based Framework for Water Quality Forecasting in Urban Rivers,” J. Environ. Manage., vol. 339, p. 118112, 2023.
[10] F. M. Rahman and M. Chowdhury, “Comparative Study of Machine Learning Techniques for Predicting Water Quality in Developing Regions,” Heliyon, vol. 9, no. 1, p. e13211, 2023.
[11] A. Elbeltagi, M. E. Salah, and H. E. Abdelrahman, “Random Forest and Logistic Regression Algorithms for Prediction of Groundwater Contamination Using Ammonia Concentration,” Arab. J. Geosci., vol. 15, no. 12, pp. 1–15, 2022.
[12] N. Hassan, M. Salleh, and A. Rahman, “Predicting Kereh River’s Water Quality: A Comparative Study of Machine Learning Models,” Environ. Proc. J., vol. 7, no. 21, pp. 49–56, 2022.
[13] L. Chen, X. Zhao, and Y. Fang, “Improved Random Forest Model for Water Quality Index Prediction,” Environ. Sci. Pollut. Res., vol. 31, no. 1, pp. 87–99, 2024.
[14] D. P. Patel, A. Mishra, and R. Shah, “Performance Analysis of Supervised Machine Learning Algorithms for River Water Quality Prediction,” Sustainability, vol. 14, no. 6, pp. 1–12, 2022.
[15] H. Zhang and J. Li, “Predicting River Water Quality Using Hybrid Random Forest and Gradient Boosting Models,” Environ. Model. Softw., vol. 172, p. 106233, 2025.
[16] D. Sharma and R. Joshi, “Evaluation of Water Quality Classification Using Random Forest and SVM: A Case Study of Ganga River Basin,” Sci. Rep., vol. 12, no. 2113, pp. 1–10, 2024.
[17] K. R. Castleman, Digital Image Processing. New Jersey: Prentice Hall, 1998.
[18] B. Wiv, C. Liv, and B. Jonathan, “Statistics Review 14: Logistic Regression,” Natl. Libr. Med., 2005.
[19] L. Breiman, “Random Forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001.
[20] C. Jair, F. García-Lamont, L. Rodríguez-Mazahua, and A. López, “A Comprehensive Survey on Support Vector Machine Classification: Applications, Challenges and Trends,” Appl. Comput. Informatics, vol. 17, no. 1, pp. 1–22, 2020.