Aflatoxin is carcinogenic mycotoxin that cripples the immune system. It is widely present in our food and is one of the major natural toxins that humans consume. Yet, there is no easy way to monitor & limit its occurrence in our supply chain.

Current detection methods are elaborate, expensive and destructive. As a result, there is essentially no controls for aflatoxin in the supply chain and farmers/ traders do not get additional value for better quality/aflatoxin-free material. This brings focus on quantity rather than quality and deters efforts towards quality upkeep resulting in more aflatoxin. Industries find it hard to source aflatoxin-free material.

This project seeks to improve an existing low-cost device (<USD50) for rapid aflatoxin detection in peanuts and maize using image processing under UV light.

The device, a handy and portable little box (about 5*5*5inches), uses blacklight fluorescence of aflatoxin to predict aflatoxin quantity within an error margin of 1ppb (as achieved till date). This fluorescence is captured by simple cameras with filters and the resulting images are processed to analyze the amount and pattern of fluorescence by a machine learning model to predict the amount of aflatoxin.

The aflatoxin reading happens by placing a handful of peanuts into the box/device, which connects to an android application (to be built). A web platform will also be built to enable industries and buyers to view aflatoxin contents and other allied data and inform their choice to bid on identified peanut lots.

Better value for aflatoxin-free material will promote efforts towards post harvest handling and quality upkeep. This would help lower the amount of aflatoxin that enters our food chain and have multitudes of impact on population health.

The Inspire Challenge is an initiative to challenge partners, universities, and others to use CGIAR data to create innovative pilot projects that will scale. We look for novel approaches that democratize data-driven insights to inform local, national, regional, and global policies and applications in agriculture and food security in real time; helping people–especially smallholder farmers and producers–to lead happier and healthier lives.

This entry is among the 2020 finalists of the CGIAR Platform for Big Data in Agriculture Inspire Challenge.

Facebook IconYouTube IconTwitter Icon