Combined Sewer Overflows (CSOs) are a major source of pollution and urban flooding, spilling untreated wastewater directly into water bodies and the surrounding environment. If overflows can be predicted sufficiently in advance, then techniques are available for mitigation. This paper presents a novel bi-model committee evolutionary artificial neural network (CEANN) designed to forecast water level in a CSO chamber from 15 min to 6 h ahead using inputs of past/current CSO level data, radar rainfall data and forecast forecasted rainfall data. The model is composed of two evolutionary artificial neural network (EANN) models. The two models are trained and optimised for wet and dry weather conditions respectively and their results combined into a single response using a non-linear weighted averaging approach. An evolutionary strategy algorithm is employed to automatically select the optimal artificial neural network (ANN) structure and parameter set, allowing the network to be tailored specifically for different CSO locations and forecast horizons without significant human input. The CEANN model was tested and evaluated on real level data from 4 CSOs located in Northern England and the results compared to three other ANN models. The results demonstrate that the CEANN model is superior in terms of accuracy for almost all forecast horizons considered. It is able to accurately forecast the dry weather and wet weather level, predicting the timing and magnitude of upcoming spill events, thus providing information that is of clear use to a wastewater utility.@en

Blockages are a major issue for wastewater utilities around the world, causing loss of service, environmental pollution, and significant cleanup costs. Increasing telemetry in combined sewer overflows (CSOs) provides the opportunity for near real-time data-driven modelling of wastewater networks. This paper presents a novel methodology, designed to detect blockages and other unusual events in the proximity of CSO chambers in near real-time. The methodology utilises an evolutionary artificial neural network (EANN) model for short-term CSO level predictions and statistical process control (SPC) techniques to analyse unusual level behaviour. The methodology was evaluated on historic blockage events from several CSOs in the UK and was demonstrated to detect blockage events quickly and reliably, with a low number of false alarms.@en