MUMBAI, India, July 11 -- Intellectual Property India has published a patent application (202511061134 A) filed by Sarabjit Kaur; Dr. Nagamani Molakatala; Dr. Sudhanshu Saurabh; Dr. K. Himabindu; and Dr. Sanjay Sharma, Jalandhar, Punjab, on June 26, for 'ml based crop disease identification for sustainable agriculture.'

Inventor(s) include Sarabjit Kaur; Dr. Nagamani Molakatala; Dr. Sudhanshu Saurabh; Dr. K. Himabindu; and Dr. Sanjay Sharma.

The application for the patent was published on July 11, under issue no. 28/2025.

According to the abstract released by the Intellectual Property India: "The Machine Learning (ML)-based Crop Disease Identification System aimed at promoting sustainable agriculture through early detection and precise classification of crop diseases. Leveraging advanced image processing and ML algorithms, the system utilizes field-acquired images of leaves, stems, and fruits captured via smartphones, drones, or low-cost sensors to identify a wide spectrum of crop diseases at an early stage. The system integrates convolutional neural networks (CNNs) and ensemble learning models that are trained on extensive, annotated datasets representing diverse agro-climatic zones and crop varieties, ensuring high accuracy even in complex field conditions. By enabling real-time disease diagnosis, the invention minimizes reliance on manual inspection, thereby reducing diagnostic errors and associated crop losses. The system further incorporates explainable AI features, offering farmers actionable insights on disease severity, potential spread patterns, and eco-friendly intervention measures, including bio-pesticide recommendations and integrated pest management practices. Designed to function offline after initial model deployment, it ensures usability in rural regions with limited internet connectivity. The invention not only enhances crop productivity and food security but also reduces indiscriminate use of chemical pesticides, thus safeguarding soil health and biodiversity. Furthermore, the platform supports continuous learning through farmer feedback and image updates, facilitating dynamic model refinement over time."

Disclaimer: Curated by HT Syndication.