Bin Li, Xuhui Fan, Jianjia Zhang, Yuhuai Wang, Feixiong Chen, Sarath Kodagoda, Terence Wells, Louisa Vorreiter, Dammika Vitanage, Gino Iori, Dave Cunningham, Tao Chen
This paper presents a predictive analytics toolkit, which is based on the emerging spatiotemporal data analysis techniques, for the estimation of hydrogen sulphide (H2S) gas distribution and prediction of sewer concrete corrosion level. The toolkit is an easy-to-use desktop application with a user-friendly interface for querying and producing output results on GIS. The inputs to the toolkit are the sewer network geometry, monitored factors, and hydraulic information; the outputs of the toolkit are spatiotemporal estimates of H2S gas concentration and concrete corrosion levels on the entire sewer network with uncertainties of the predictions. The toolkit is also able to integrate experts’ domain knowledge or existing physical model’s results as prior knowledge into the analytics model. The final outcomes of the toolkit can be used to prioritise high risk areas, recommend chemical dosing locations, and suggest deployment of sensors. A simulation of H2S and corrosion level prediction on a subsystem of the sewer network in the greater Sydney area is reported to demonstrate the capability of the toolkit.