The Future Of Farming: Phone-Powered AI Detects Diseases In Cassava Plant With Incredible Accuracy

will's picture

By Fattima Mahdi Truth Theory

With Artificial Intelligence (AI) on the rise, many industries are now looking to this advanced technology to help businesses grow more efficient. One such industry is modern agriculture. AI-based digital farming solutions can significantly accelerate learning. Farmers are now making informed decisions about how they use resources like soil, water and energy by using AI technology.

The cassava plant is the most widely grown root crop on Earth. Researchers just developed a program that detect diseases in the plant with almost 100 percent accuracy. The technology does not require cloud computing or hulking processors for that matter. Instead, the network that powers it runs entirely on a smartphone-based program.

“Some neural networks require hundreds of millions of parameters and just the file size you would need to store those is beyond what you could include in an app,” says Google’s Pete Warden. “Happily, it turns out that networks trained to recognise certain kinds of objects can actually be taught to recognise other things with a lot less data, and that’s really the idea behind transfer learning,” says Warden.

The researchers only had to feed the network 2,756 images of cassava leaves. They then trained the program to recognise defects such as cassava brown streak disease and cassava mosaic disease. Remarkably, the system was able to identify red mites with 96 percent accuracy and brown leaf spot with 98 percent accuracy. These results are impressive and the researchers are confident that they can adapt the system to work with other crops. Co-author and biologist, David Hughes, shared his excitement: “In the same way we have personalised medicine, I think we can have personalised agriculture on scale for hundreds of millions of people in real time.”

“It really comes down to the data, because garbage in, garbage out. So you want to have really clean, high-quality data sets” says Penn State agricultural engineer Amanda Ramcharan, lead author on the study. “She also went on to say that: “With globalization, the spread of pests and pathogens is increasing rapidly. So having tools that you can deploy quickly can be really beneficial and really help with food security.”

IMAGE CREDIT: maytee2518 / 123RF Stock Photo

THIS ARTICLE IS OFFERED UNDER CREATIVE COMMONS LICENSE. IT’S OKAY TO REPUBLISH IT ANYWHERE AS LONG AS ATTRIBUTION BIO IS INCLUDED AND ALL LINKS REMAIN INTACT.Creative Commons License


https://truththeory.com/2017/10/04/future-farming-phone-powered-ai-detects-diseases-cassava-plant-incredible-accuracy/

Category: