MUMBAI, India, Oct. 5 -- Intellectual Property India has published a patent application (202621099900 A) filed by Dr. Sanjeev Kumar Sharma; Kiruthika S; Shaikh Rasheed; Aashitha Joy; Roopa R; Sujata Dharamsingh Palheriya; Shaikh Waseem Abdul Lateef; M. Gughan Raja; Vishal Singh; Mohd Ashfaque Shaikh; Dharani Ramasamy; and Vijayakumar S. D on August 19, 2026, for An Intelligent Ai-Based Iot System For Early Plant Disease Prediction And Sustainable Crop Management.
Inventors include Dr. Sanjeev Kumar Sharma; Kiruthika S; Shaikh Rasheed; Aashitha Joy; Roopa R; Sujata Dharamsingh Palheriya; Shaikh Waseem Abdul Lateef; M. Gughan Raja; Vishal Singh; Mohd Ashfaque Shaikh; Dharani Ramasamy; and Vijayakumar S. D.
The application for the patent was published on October 02, 2026, under issue no. 40/2026.
Abstract: The present invention relates to an intelligent AI-based IoT system for early plant disease prediction and sustainable crop management. Existing approaches to crop health monitoring have increasingly used field sensors, plant images, and machine learning to identify disease conditions. However, many such approaches depend mainly on visual symptoms or individual sensor readings and may not provide a complete view of changing crop and environmental conditions. They may also provide limited support for deciding what action should be taken after a possible disease condition is identified. The proposed invention addresses these limitations by combining IoT-based crop monitoring, plant image collection, crop-health feature generation, machine learning-based disease prediction, and sustainable management recommendations in a single system. The system collects information including soil moisture, temperature, humidity, rainfall, light intensity, soil condition, plant images, crop growth stage, and field location. From this information, the system generates indicators including a Crop Stress Index, Disease Risk Score, Soil Moisture Suitability Index, Environmental Disease Favourability Index, and Crop Health Score. A machine learning prediction module uses these indicators together with image and historical crop information to estimate disease risk and identify areas requiring attention. Depending on the predicted state, it then offers recommendations for conserving water through irrigation adjustment, more inspections or treatment of affected plants, and isolation of infected plants, with others monitored closely. Later predictions can be improved with input from, or the results of management. This should help detect potential plant disease earlier, implement more targeted interventions, reduce needless drawing from water reserves and unnecessary application of agricultural inputs, improve crop surveillance and support better farming decision making. FIG.1
Disclaimer: Curated by HT Syndication.
