Researchers at the Indian Institute of Technology in Mandi (IIT-Mandi) and the Central Potato Research Institute (CPRI) in Shimla have developed an artificial intelligence (AI) solution that can detect diseased parts of potato crop using photographs of its leaves. According to news reports, the team that developed this computational model for automated disease detection was led by an associate professor at the School of Computing and Electrical Engineering, and CPRI colleagues under a project funded by the Department of Biotechnology. The results of this research have recently been published in the journal Plant Phenomics.
The report noted that blight is a common disease of the potato plant. It starts as uneven light green lesions near the tip and the margins of the leaf and then spreads into large brown to purplish-black necrotic patches. It eventually leads to the rotting of the plant. If left undetected and unchecked, blight could destroy the entire crop within a week under conducive conditions.
IIT-Mandi’s computational tool can detect blight in potato leaf images. The model is built using an AI tool called mask region-based convolutional neural network architecture and can accurately highlight the diseased portions of the leaf amid a complex background of plant and soil matter.
In India, as with most developing countries, the detection and identification of blight are performed manually by trained personnel who scout the field and visually inspect potato foliage. This process, as expected, is tedious and often impractical, especially for remote areas, because it requires the expertise of a horticultural specialist who may not be physically accessible.
Automated disease detection can help in this regard and given the extensive proliferation of mobile phones across the country, the smartphone could be a useful tool, according to a researcher on the team. The advanced HD cameras, better computing power, and communication avenues offered by smartphones offer a promising platform for automated disease detection in crops.
To develop a robust model, healthy and diseased leaf data were collected from fields across Punjab, Uttar Pradesh, and Himachal Pradesh, the scientists said. Analysis of the detection performance indicates an overall precision of 98% on leaf images in field environments, the report added.
Following this success, the team is sizing down the model to a few tens of megabytes so that it can be hosted on a smartphone as an application. With this, when the farmer will photograph the leaf which appears unhealthy, the application will confirm in real-time if the leaf is infected or not. With this timely knowledge, the farmer would know exactly when to spray the field, saving their produce and minimising costs associated with unnecessary use of fungicides. “model is being refined as more states are covered. The technology would be deployed as part of the FarmerZone app that will be available to potato farmers for free.
Last month, IIT-Mandi collaborated with an online learning solution provider to launch post-graduate certification programmes in applied artificial intelligence/machine learning (AI/ML) and full-stack development. The programmes focus on contextual learning to complement conceptual learning with skilling exercises. It offers projects based on real-life business problems, and the curriculum has been designed to bridge the skill gap and prepare a workforce for the future, OpenGov Asia had reported.