Document Type
Presentation
Publication Date
8-1-2014
Abstract
Access to safe drinking water is universally considered as a fundamental human right and customers regard a reliable supply of safe, clean water as the most important aspect of the water supply service. However, water quality failures do occur, with some of the hardest to understand and manage occurring within distribution systems. In the UK, a regulatory process is applied in which water companies must report on significant water quality incidents, their causes, actions, responses, and outcomes. The Drinking Water Inspectorate (DWI) assesses these reports on an annual basis and their findings are made publically available. It is hypothesised here that these reports form a valuable resource that can be ‘data mined’ for improved understanding and to help with future incident management. Developed in the late 1970s, case-based reasoning (CBR) is a knowledge-based problem-solving technique that relies on the reuse of past experience. It is based on the assumption that similar problems have similar solutions and hence new problems can be solved by reusing (and adapting) solutions. The WaterQualityCBR software system, reported on here, was developed as a decision support tool for water companies to deal more effectively with water quality incidents (e.g. water discolouration, contamination and loss of supply) by using information from previous incidents. The tool manipulates a database (compiled in XML) of past significant events from several years DWI reporting. The system can provide information at a strategic level, for example to help inform policy or water company guidance documents. In addition, a complete closed CBR cycle is possible for operational event management providing information from similar cases from the past and, importantly, ranking past actions in response to similar incidents. Examples are provided to illustrate both aspects of the software, demonstrating how the CBR methodology can support decision-making for water utilities in managing drinking water incidents.
Comments
Session R77, From Data to Information: Water Resources Applications