A probabilistic framework for urban wastewater flow forecasting

Abstract

Sewer flow forecasting is critical for managing the performance of sewer networks and their treatment plants. While simulators have been used in modelling the sewer flow for years, data-driven emulators recently have gained attention in making predictions with a higher computational speed and feasibility. In this research, a framework is proposed based on multi-input single-output Gaussian Processes for predicting sewer flow using time and rainfall as inputs. The predictions are presented as Gaussian distributions, showing the confidence levels. The results of the GPR on the data of a sewer system in this study demonstrated a robust performance of the model with 93.6% coverage of the predictions in the 95% credible interval, and 89.5 L/s of RMSE.