MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202511115793 A) filed by Ajay Kumar Garg Engineering College, Ghaziabad, Uttar Pradesh, on Nov. 23, 2025, for 'spatiotemporal cnn-lstm system for forecasting crop disease progression and working method thereof.'
Inventor(s) include Shashank Sahu; Sunny Teotia; Ritwik Goswami; Yash Jain; and Dr. Santosh Kumar Upadhyay.
The application for the patent was published on Jan. 9, under issue no. 02/2026.
According to the abstract released by the Intellectual Property India: "The present invention discloses a spatiotemporal CNN-LSTM system for forecasting crop disease progression by integrating spatial feature extraction with temporal sequence modelling. The system employs a pre-trained Inception V3 network to generate 2048-dimensional feature vectors from each image frame, and two stacked LSTM layers to learn temporal evolution of disease symptoms. To address the scarcity of longitudinal datasets, the invention utilises weighted alpha blending interpolation to generate synthetic temporal sequences between healthy and diseased leaf images. The combined architecture enables robust, context-aware disease classification demonstrated on rice leaf diseases including Blast, Brown Spot, Blight, Sheath Blight, and Tungro. The method operates by acquiring sequential images, preprocessing them, extracting spatial features, modelling their temporal trajectory, and producing a final classification through a softmax layer. The system provides improved accuracy, early detection capability, and enhanced field robustness for predictive plant disease monitoring."
Disclaimer: Curated by HT Syndication.
