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

PLoS One. 2017 Nov 28;12(11):e0188808. doi: 10.1371/journal.pone.0188808. eCollection 2017.

Abstract

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.

MeSH terms

  • Forecasting
  • Machine Learning*
  • Poverty
  • Water Supply*

Grants and funding

This work was funded by the National Science Foundation’s Small Business Innovative Research program, under award number 1621444 (https://nsf.gov/awardsearch/) to SweetSense Inc. The NSF as funder provided support in the form of salaries through SweetSense Inc. for authors DW, JC, ET, but did not have any additional role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript. The authors are also affiliated with the universities listed. The authors were not compensated for this work by their universities. The specific roles of these authors are articulated in the author contributions section.