CCWI2017: F54 'Data-driven Approach to Short-Term Forecasting of Turbidity in a Trunk Main Network'
journal contributionposted on 01.09.2017 by Gregory Meyers, Zoran Kapelan, Edward Keedwell
Any type of content formally published in an academic journal, usually following a peer-review process.
Water discolouration is an increasingly important and expensive issue due stricter regulatory demands and ageing Water Distribution Systems (WDSs) in the UK and abroad. This paper presents a turbidity forecasting methodology capable of aiding operational staff and enabling proactive management strategies. The methodology presented here does not require a hydraulic or water quality network model that can be expensive to build and maintain. The methodology is tested and verified on a real UK trunk main network with observed turbidity measurement data. Results obtained show that the classification based forecasts of turbidity can reliably detect if discolouration material is mobilised up to 5 hours ahead. The methodology could be used as an early warning system to enable a range of proactive management strategies as an alternative to regular trunk mains cleaning.