Application of ResNet and Autoencoder models for anomaly detection in wastewater networks data: A Comparative study of supervised and unsupervised approaches

Artificial intelligence (AI) enhances data validation for urban wastewater networks by addressing inaccuracies in sensor-generated data from harsh environments. Traditional manual validation methods are labor-intensive and prone to human error, necessitating automated solutions. The performance of two AI-driven models— a supervised ResNet model and an unsupervised Autoencoder—was compared on turbidity data issued from an urban wastewater network. The ResNet model showed improved accuracy when the classification threshold was optimized using the Precison-Recall curve but required rigorous data validation to manage learning bias and class imbalance. The Autoencoder achieved an F1 score of 0.96, demonstrating its efficacy in detecting anomalies when trained on valid data sequences. Hence, AI models significantly reduce the workload of manual data validation, enhance the reliability of water management systems, and allow stakeholders to focus on more critical tasks. • Machine Learning models improve the accuracy of data validation in urban wastewater networks, reducing manual labour and human error. • Expert intervention is crucial during model training, to ensure accurate annotations and evaluate models’ validation results. • Comparison of deep learning approaches reveals Autoencoder's superiority for anomaly detection, with an F1 score of 0.96. • The results of the ResNet model in a supervised approach depend on the quality of the ground-truth validation and class imbalance.