MUMBAI, India, Sept. 14 -- Intellectual Property India has published a patent application (202641094705 A) filed by Dhanalakshmi Srinivasan College Of Engineering And Technology on August 05, 2026, for A Multi-Stage Ai Framework For Prenatal Crop Monitoring,risk Prediction And Storage.

Inventors include K. Senbagam; Akash Kumar V; Amuthavan M; and Kishore E.

The application for the patent was published on September 11, 2026, under issue no. 37/2026.

Abstract: Multi-Stage Al Framework for Prenatal Crop Monitoring, Risk Prediction, and Storage Management The present invention relates to an Artificial Intelligence (AI)- based system and method for intelligent crop monitoring, risk prediction, and storage management using Internet of Things (IoT), Machine Learning (ML), and Deep Learning (DL) technologies. The system collects real-time environmental and soil data through ESP32-based loT sensors, including soil moisture, temperature, humidity, atmospheric pressure, and air quality sensors, while an ESP32-CAM module captures crop leaf images for visual analysis. The collected data are processed through a preprocessing module that performs data cleaning, normalization, missing value handling, and image enhancement to generate high-quality inputs suitable for intelligent analysis. A Random Forest model analyzes soil conditions and recommends suitable crops, a YOL0v8 deep learning model detects pests and diseases from crop leaf images, and a Long Short-Term Memory (LSTM) network forecasts future agricultural market prices based on historical data. The generated outputs are integrated through a Flask-based backend and displayed on a Streamlit web dashboard, providing real-time monitoring, crop recommendations, pest detection results, market price forecasts, storage management insights, and early risk alerts. The proposed framework offers an automated, scalable, and intelligent smart agriculture solution that supports farmers, agricultural organizations, and government agencies in improving crop productivity, minimizing losses, optimizing resource utilization, and enabling informed decision-making throughout the agricultural lifecycle.

Disclaimer: Curated by HT Syndication.