The classification of water quality status is the first step towards ensuring safe water for agricultural fields, manufacturing, and daily consumption, including drinking water. Water quality is essential for the survival of humans, animals, and plants. Recently, artificial intelligence techniques, particularly supervised machine learning, have been utilized to develop predictive water quality models. In this paper, we propose a method based on supervised learning that employs a 20-dimensional feature vector along with several supervised machine learning classifiers. Eight classifiers are included in this study: Non-Linear Support Vector Machine (Non-SVM), Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), K-Nearest Neighbors (KNN), Decision Tree (DT), Multilayer Perceptron Neural Networks (MLP-NN), AdaBoost, and Random Forest (RF). The 20-dimensional feature vector, which encodes relevant information, is used to train each classifier for binary classification. Additionally, three different cross-validation strategies are employed in the evaluation process. The proposed method is tested using publicly available datasets, and the experimental results—both visual and quantitative—demonstrate the robustness of the approach