Enhancing Water Quality Classification in Agriculture Using a Voting Classifier Ensemble Approach

Water quality plays a critical role in agriculture, affecting crop yields, livestock health, and overall farm productivity. Traditional assessment methods are slow and resource-intensive, making them impractical for large-scale monitoring. This study explores the application of machine learning in water quality classification, leveraging a voting classifier that integrates Gradient Boosting, CatBoost, and AdaBoost to enhance accuracy and scalability. The dataset, pre-processed and augmented for robustness, was used to train and evaluate the model, achieving an accuracy of 92.03% on the test set. Results indicate that ensemble learning significantly improves prediction reliability over individual models. By providing a scalable and efficient approach to water quality monitoring, this research contributes to sustainable agriculture and better resource management. Future work will focus on expanding datasets, integrating environmental variables, and developing real-time IoT-based monitoring systems for enhanced decision-making.