On 17th September, the mystery surrounding the Samrat handpump which has been installed in the car park of Oxford University’s School of Geography and the Environment was revealed. Learn more about the pump’s research purpose at www.oxwater.uk/oxford-smart-handpump.html or download the presentation below.
Delivering reliable drinking water to millions of rural people in Africa and Asia is an elusive and enduring global goal. A systematic information deficit on the performance of and demand for infrastructure investments limits policy design and development outcomes.
Since 2010, the ‘Smart Handpump’ project has been exploring new technologies, methods and models to understand and respond to this challenge. A mobile-enabled data transmitter provides foundational data on hourly water usage and failure events which has enabled the establishment of performance-based maintenance companies in Kenya that are improving handpump reliability by an order of magnitude.
The research is a collaboration between the School of Geography and the Environment and the Department of Engineering Science with a range of partners including government, international bodies such as UNICEF and the private sector. New research involves modelling the accelerometry data from the handpumps to predict aquifer depth.
We invite you to test the Smart Handpump in the car park and debate how the ‘accidental infrastructure’ of rural handpumps can spark bolder initiatives to deliver water security for millions of poor people in Africa and Asia.
17 October 2016 at 5-6pm
Hertbertson Room and the Car Park, School of Geography and the Environment, South Parks Road, Oxford, OX1 3QY
The ‘Smart Handpump’ was developed in 2011 by a team at Oxford University with a field-ready prototype starting operational trials in Kenya in 2012. These trials demonstrated proof-of-concept for remote monitoring of handpumps using simple microprocessor, accelerometer and global system for mobile communications (GSM) components. Smart Handpumps provide hourly data related to pump usage, providing information on functionality as well as insights into daily and seasonal water use patterns.
In 2014, a preliminary analysis of the high frequency accelerometer data to show that the “noise” generated by pumping also contains useful information. High-rate waveforms from the data can be processed using robust machine learning methods that are sensitive not only to the dynamics of the whole system but also the subtle interaction between the user and the pump. The small changes in pump dynamics and the subtle reactions of the user become a prominent signal in determining the deterioration of pump mechanics and imminent failure. This same signal can also be used to for shallow aquifer monitoring at the pump and user phenotyping.
The SoGE borehole is drilled to 7m and will have a Samrat handpump installed. This suction pump is commonly used at shallow wells in Bangladesh. The different dynamics of this pump, compared to current studies on deep well Afridev pumps in Kenya, will enable researchers to build a more robust predictive algorithm that is able to distinguish across multiple pump types, user characteristics, and aquifer variabilities.
These data will be used to produce a low-cost predictive maintenance system that is scalable across large rural regions. This work is being supported by UNICEF, funded through a competitive tender process, as part of their Product Innovation portfolio. Field testing will be conducted in partnership with UNICEF country programmes in Eastern and Southern Africa.
By retrofitting a simple and inexpensive device to a standard pump handle the smart handpumps are able to pro-actively monitor the condition of handpumps and ensure that millions of people can have access to a reliable water source.
Take a look at the video to see our work in Kwale County in Kenya in action.
Kenji Takeda, Solution Architect and Technical Manager, Microsoft Research
Jacob Katuva used to get up at dawn to cycle 12 miles from his village to collect water with his uncles and cousins when he was growing up in Kenya. Now he is part of a research team at Oxford University using cloud computing and mobile sensors to monitor water wells and help ensure that thousands of villages in rural Africa and Asia have a safe, secure supply of water.
Patrick Thomson, from the Oxford-led UPGro project “Gro For Good”, has won the prize for the best poster at World Water Week 2015 for the work that he and colleagues at the Institute of Biomedical Engineering at Oxford have been doing on shallow groundwater monitoring using Smart Handpumps in Kenya. This work will continue under the UPGro Consortium phase.
A briefing note based on the information presented in the poster can be downloaded: