Ensemble machine learning and forecasting can achieve 99% uptime for rural handpumps

Broken water pumps continue to impede efforts to deliver clean and economically-viable water to the global poor. The literature has demonstrated that customers' health benefits and willingness to pay for clean water are best realized when clean water infrastructure performs extremely well (>...

Full description

Saved in:
Bibliographic Details
Published in:PloS one 2017-11, Vol.12 (11), p.e0188808-e0188808
Main Authors: Wilson, Daniel L, Coyle, Jeremy R, Thomas, Evan A
Format: Article
Language:English
Subjects:
Accountability
Artificial intelligence
Biology and Life Sciences
Community
Computer and Information Sciences
Consumption
Customers
Delivery scheduling
Developing countries
Drinking water
Ecology and Environmental Sciences
Engineering
Engineering and Technology
Ensemble forecasting
Environmental science
Failure
Forecasting
Infrastructure
LDCs
Learning algorithms
Machine learning
Maintenance management
Neural networks
People and Places
Physical Sciences
Preventive maintenance
Research and Analysis Methods
Sensors
Social Sciences
Sustainability
Useful life
Water pumps
Water shortages
Water supply
Water supply systems
Water utilities
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Broken water pumps continue to impede efforts to deliver clean and economically-viable water to the global poor. The literature has demonstrated that customers' health benefits and willingness to pay for clean water are best realized when clean water infrastructure performs extremely well (>99% uptime). In this paper, we used sensor data from 42 Afridev-brand handpumps observed for 14 months in western Kenya to demonstrate how sensors and supervised ensemble machine learning could be used to increase total fleet uptime from a best-practices baseline of about 70% to >99%. We accomplish this increase in uptime by forecasting pump failures and identifying existing failures very quickly. Comparing the costs of operating the pump per functional year over a lifetime of 10 years, we estimate that implementing this algorithm would save 7% on the levelized cost of water relative to a sensor-less scheduled maintenance program. Combined with a rigorous system for dispatching maintenance personnel, implementing this algorithm in a real-world program could significantly improve health outcomes and customers' willingness to pay for water services.
ISSN:1932-6203
1932-6203
DOI:10.1371/journal.pone.0188808