Bayesian Inference for Quantifying Parameter Uncertainty in Disinfectant Decay Models

<p dir="ltr">This paper applies Bayesian inference to quantify parameter uncertainty in disinfectant decay models. Specifically, we obtain posterior distributions of unknown decay coefficients by updating prior beliefs with observed data. The posteriors are efficiently computed using Markov chain Monte Carlo (MCMC) sampling with a Gaussian process (GP) emulator of EPANET’s water quality solver. We demonstrate the Bayesian approach on a real-world distribution network using continuous sensing data.</p><p dir="ltr">This paper was presented at the 21st Computing and Control in the Water Industry Conference (CCWI 2025) at the University of Sheffield (1st - 3rd September 2025).</p>