IWRA Proceedings

< Return to abstract list

Oral O-6-8-51: Application of edge computing and deep learning to analyse domestic water use data and to sustain water-conscious behaviour - A case study of Hong Kong

XVIII IWRA World Water Congress Beijing China 2023
Sub-theme 6: Innovation for Water Governance and Management
Author(s): Dr. Angela Lee, Centre for Water Technology and Policy, The University of Hong Kong
Presenter: Dr. Angela Lee, Centre for Water Technology and Policy, The University of Hong Kong

Keyword(s): Internet of Things, nudge, data analytics, Water conservation, Domestic water use
Oral: PDF

Abstract

Sub-theme

6. Innovation for Water Governance and Management

Topic

6-8. Creative technology and tools for water resources management

Body

In the past two decades, while many world cities have made strides in reducing per capita domestic water usage, Hong Kong has trodden in the opposite direction. In order to discern the causes of this peculiar phenomenon, an inter-disciplinary research team at the University of Hong Kong launched a novel project, in 2019, to collect, and analyse, fine-grained data on household-level water use. For the first time in Hong Kong, such high-resolution data allow the researchers to map the composition of domestic water-use in each participating household and understand how Hong Kong people, in general, use water at home. The analysis will, subsequently, point to solutions to tackling the problem of over-use. To assist with data collection, the research team built a non-invasive device called a Smart Meter Analyser (SMAN, in short). By fastening a SMAN onto a government-issued billing meter, the latter is instantly transformed into a smart water meter with automatic metering capabilities. High resolution household-level water data are captured by SMAN and transmitted to cloud for data analytics. A deep learning algorithm is next employed to disaggregate household-level water use data into specific tap-based, end-use categories—such as showering, basin-tap, kitchen-tap and washing machine. Project participants can log on to the Project’s mobile website to track their own water usage level and the composition of that usage at anytime, anywhere. This research study harnesses the power of IoT technologies, data analytics and advanced household profiling techniques to generate insights to assist policymakers to formulate more effective water conservation measures. Preliminary findings show that end-use distribution information and timely feedback can help users conjure targeted conservation solutions and evaluate the efficacy of these solutions. In particular, empirical data show that, on average, water is mostly used for showering in a household setting. Personalised messaging that focuses on showering use has been proven to be an effective tool to nudge people to reduce their domestic water consumption and, simultaneously, lower their carbon footprint.

IWRA Proceedings office@iwra.org - https://www.iwra.org/member/index.php