Diffusion-based Time Series Forecasting for Sewerage Systems

We introduce a novel deep learning approach that harnesses the power of generative artificial intelligence to enhance the accuracy of contextual forecasting in sewerage systems. By developing a diffusion - based model that processes multivariate time series data, our system exce ls at capturing complex correlations across diverse environmental signals, enabling robust prediction s even during extreme weather events. To strengthen the model's reliability, we further calibrate its predictions with a conformal inference technique, tailored for probabilistic time series data, ensuring that the resulting prediction intervals are statistically reliable and cover the true target va lues with a desired confidence level . Our empirical tests on real sewerage system data confirm the model's exceptional capability to deliver reliable contextual predictions, maintaining accuracy even under severe weather conditions.