An IBM research team in Brazil has built a prototype for rapid, on-location, chemical analysis of water and soil using AI, using a small paper testing strip dubbed the “AgroPad” that taps a smartphone’s visual recognition capabilities and machine learning algorithms to determine the exact amount of certain chemicals in the sample.
The prototype can currently assess pH, nitrogen dioxide, aluminum, magnesium and chlorine levels, IBM said today, with the research team working on extending the library of chemical indicators available for deployment. The company added that it is looking for development partners in the agriculture sector to field-test it.
The company hopes the AgroPad could help small farms better manage their water use while maximising crop production; regularly testing at low cost in order to inform decisions on when and how to fertilise for maximum crop yield.
A drop of water or soil sample is placed on the AgroPad, which is a paper device about the size of a business card. The microfluidics chip inside the card performs on-the-spot a chemical analysis of the sample, providing results in a sub-10 second range.
A set of circles on the back of the card provide colorimetric test results; the color of each circle represents the amount of a particular chemical in the sample. Using a smartphone, the farmer can then take a single snapshot of the AgroPad by using a dedicated mobile application and immediately get a chemical test result back.
IBM said in a release shared Thursday: “This ‘AI on the edge’ computing approach uses machine learning and machine vision algorithms to translate the measured color composition and intensity into concentrations of chemicals in the sample, making it more reliable than tests based on human vision alone.”
The company added: “The test data can be simultaneously streamed onto a cloud computing platform and labeled with a digital tag that uniquely identifies the time, location and results of the chemical analysis. The cloud platform allows management and integration of millions of individual tests performed at various times and locations. This is an important feature for monitoring, for example, the change in fertilizer concentration in a particular region throughout the year.”
“Longitudinal Data Collection Becomes a Real Possibility”
Mathias Steiner, Manager, Industrial Technology & Science, IBM Research – Brazil, told Computer Business Review in an emailed statement: “In order to increase likelihood of commercial roll-out of the AgroPAD, we are currently seeking opportunities with development partners in agriculture to test the technology in the field. This next step will allow us to validate and scale the technology and increase the maturity of the research prototype.”
He added: “Given that the AgroPad is a paper-based device enabled by cloud technology, we expect the cost for the user to be much lower than standard testing solutions used today…these rely on expensive and time-consuming laboratory tests and chemical analysis is quickly outdated and infrequent. Since the paper-based tests can be manufactured cheaply, and the tests performed by farmers in the field real-time, longitudinal data collection becomes a real possibility.”
The prototype’s release comes as the World Economic Forum’s 2018 Global Risks Report emphasised the potential systemic risk resulting from water shortages, soil pollution and agricultural monocultures.
This article is from the CBROnline archive: some formatting and images may not be present.
Join Our Newsletter
Want more on technology leadership?
Sign up for Tech Monitor's weekly newsletter, Changelog, for the latest insight and analysis delivered straight to your inbox.