Water quality polluted by total suspended solids classified within an Artificial Neural Network approach

This study investigates the application of an artificial neural network (ANN) framework for analysing water pollution caused by solids. To address the challenge, we develop a convolutional neural network trained under a transfer learning strategy with AlexNet. We feed the network with pictures of samples of water with low, medium, and high concentrations of total suspended solids and achieve a high validation accuracy of 99.85% with a precision of 99.85%, which is highly competitive with other approaches. Our model demonstrates significant improvements in speed and reliability over conventional image processing methods, effectively predicting pollution levels. Our findings suggest that ANNs can serve as an effective tool for real-time monitoring and management of water pollution, facilitating proactive decision-making and policy formulation.