Application of Machine Learning Models in Water Quality Classification in Lake Maninjau: Random Forest as the Optimal Solution

Abdurrahman Niarman; Reni Kurnia; Iswandi Iswandi

The PDF file you selected should load here if your Web browser has a PDF reader plug-in installed (for example, a recent version of Adobe Acrobat Reader).

If you would like more information about how to print, save, and work with PDFs, Highwire Press provides a helpful Frequently Asked Questions about PDFs.

Alternatively, you can download the PDF file directly to your computer, from where it can be opened using a PDF reader. To download the PDF, click the Download link above.

Fullscreen Fullscreen Off

Abstract

This research develops a machine learning model to classify water quality in Lake Maninjau using data from the Ministry of Environment and Forestry's Onlimo application. The dataset includes parameters such as temperature, pH, DO, conductivity, TDS, salinity, turbidity, nitrate and ammonium. Four machine learning algorithms were tested: Logistic Regression, SVM, Gradient Boosting, and Random Forest. As a result, Random Forest shows the best performance with an average accuracy of 87.33% and a standard deviation of 6.97%, and a test accuracy of 90.63%. This model is effective in monitoring and managing water quality, supporting authorities in water resource management decision making. This research also shows how the integration of machine learning and IoT can provide practical solutions in environmental monitoring.