Advanced water quality classification with support vector machines

Clean water is important for all living beings yet is always at risk of contamination due to human activities. Traditional assessments of the Water Quality Index (WQI) require substantial human effort, are time-consuming, and sometimes lead to human error. To overcome these limitations, this research presents an automated classification framework utilising Support Vector Machines (SVM) to evaluate water quality. The model uses a dataset of physical and chemical parameters, including pH, dissolved oxygen (DO), biochemical oxygen demand (BOD), chemical oxygen demand (COD), ammonia nitrogen (AN), and total suspended solids (TSS). The proposed SVM model was trained and validated based on standard WQI metrics. Model performance was evaluated using accuracy, precision, recall, and F1 score. The SVM algorithm achieved a classification accuracy of up to 95%. These results demonstrate that the SVM model provides a reliable, scalable, and automated approach for real-time environmental monitoring and water resource management.