Next Article in Journal
The Contribution of Sustainable Development Goals and Forest-Related Indicators to National Bioeconomy Progress Monitoring
Next Article in Special Issue
A Review of Practice and Implementation of the Internet of Things (IoT) for Smallholder Agriculture
Previous Article in Journal
Determining Factors in MOOCs Completion Rates: Application Test in Energy Sustainability Courses
Previous Article in Special Issue
Combining Multi-Modal Statistics for Welfare Prediction Using Deep Learning
Open AccessArticle

Anomaly Detection System for Water Networks in Northern Ethiopia Using Bayesian Inference

1
Accenture Labs, San Francisco, CA 94105, USA
2
Charity Water, New York City, NY 10013, USA
*
Authors to whom correspondence should be addressed.
Sustainability 2020, 12(7), 2897; https://doi.org/10.3390/su12072897
Received: 28 February 2020 / Revised: 2 April 2020 / Accepted: 2 April 2020 / Published: 5 April 2020
For billions of people living in remote and rural communities in the developing countries, small water systems are the only source of clean drinking water. Due to the rural nature of such water systems, site visits may occur infrequently. This means broken water systems can remain in a malfunctioning state for months, forcing communities to return to drinking unsafe water. In this work, we present a novel two-level anomaly detection system aimed to detect malfunctioning remote sensored water hand-pumps, allowing for a proactive approach to pump maintenance. To detect anomalies, we need a model of normal water usage behavior first. We train a multilevel probabilistic model of normal usage using approximate variational Bayesian inference to obtain a conditional probability distribution over the hourly water usage data. We then use this conditional distribution to construct a level-1 scoring function for each hourly water observation and a level-2 scoring function for each pump. Probabilistic models and Bayesian inference collectively were chosen for their ability to capture the high temporal variability in the water usage data at the individual pump level as well as their ability to estimate interpretable model parameters. Experimental results in this work have demonstrated that the pump scoring function is able to detect malfunctioning sensors as well as a change in water usage behavior allowing for a more responsive and proactive pump system maintenance. View Full-Text
Keywords: anomaly detection; Bayesian inference; machine learning; water network; pump; well; remote monitoring; sensors; Ethiopia; rural water supply anomaly detection; Bayesian inference; machine learning; water network; pump; well; remote monitoring; sensors; Ethiopia; rural water supply
Show Figures

Figure 1

MDPI and ACS Style

Tashman, Z.; Gorder, C.; Parthasarathy, S.; Nasr-Azadani, M.M.; Webre, R. Anomaly Detection System for Water Networks in Northern Ethiopia Using Bayesian Inference. Sustainability 2020, 12, 2897. https://doi.org/10.3390/su12072897

AMA Style

Tashman Z, Gorder C, Parthasarathy S, Nasr-Azadani MM, Webre R. Anomaly Detection System for Water Networks in Northern Ethiopia Using Bayesian Inference. Sustainability. 2020; 12(7):2897. https://doi.org/10.3390/su12072897

Chicago/Turabian Style

Tashman, Zaid; Gorder, Christoph; Parthasarathy, Sonali; Nasr-Azadani, Mohamad M.; Webre, Rachel. 2020. "Anomaly Detection System for Water Networks in Northern Ethiopia Using Bayesian Inference" Sustainability 12, no. 7: 2897. https://doi.org/10.3390/su12072897

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop