logo mobile

e-Agriculture mobile logo

Languages

New app to diagnose crop diseases, alert smallholders

e-Agriculture's picture
[News]

The CGIAR Research Program on Roots, Tubers and Bananas team won US$100,000 grant to refine a mobile application that uses artificial intelligence to diagnose crop diseases.

This new app will attempt to solve the problem of pests and diseases that be face farmers with small holder farmers hardly hit. Its estimated that every year pests and diseases costs billions of dollars to potential agricultural economy as they damage agricultural outputs such as crops, livestock and fish harvests.

Technology plays a big role in warning the communities of possible outbreaks and also as a monitoring tool for pests and diseases.So the new app will be used against the cassava brown streak disease.

The app uses TensorFlow, a Google programme that allows machines to train and learn. According to the project lead, David Hughes as cited by sciedev.net said

We trained it to recognize plant diseases. What the app does in real-time is to assign a score to a video being captured…that score is the probability that the plant in the video shows symptoms of one of five diseases or pests”.

The project will be expanded to identify more diseases in more crops – such as banana, sweet potato and yam. One can view the video below

Video credits:CGIAR

About the CGIAR Big Data in Agriculture Inspire Challenge 2017

The CGIAR Platform for Big Data in Agriculture serves to provide leadership in organizing open data, convening partners, and demonstrating the power of big data analytics through inspiring projects. In essence CGIAR is challenging its partners and anyone using their data to create “incentivized pilot opportunities that scale”. In this challenge they were searching novel approaches that democratize the data-driven insights to inform policies on agriculture and food security in real time.

The winning team were set to receive $100 000 as seed money to help them in 12 months to implement small-scale proof of concepts pilots to demonstrate viability. More information here 

In this year’s edition, 120 proposals across four Inspire Challenge Categories –

  1. Revealing Food Systems
  2. Monitoring Pests and Diseases
  3. Disrupting Impact Assessment Empowering
  4. Data-Driven Farming

The above reported app won in the Monitoring Pests and Diseases category.

Sources used for this news Sciedev; CGIAR Inspire and 

 

Tags: