Intellectual Property India Publishes Patent Application for 'Smart Crop Prediction Using Soil Moisture By Machine Learning' Filed by Seshadri Rao Gudlavalleru Engineering College; K. Subrhamanyam; Attili Nithish; Chandika Vishnu Vardhan; Chilakala Prasanna Lakshmi; and Anaparthy Anurag

MUMBAI, India, May 1 -- Intellectual Property India has published a patent application (202641047804 A) filed by Seshadri Rao Gudlavalleru Engineering College; K. Subrhamanyam; Attili Nithish; Chandika Vishnu Vardhan; Chilakala Prasanna Lakshmi; and Anaparthy Anurag, Gudlavalleru, Andhra Pradesh, on April 15, for 'smart crop prediction using soil moisture by machine learning.'

Inventor(s) include Seshadri Rao Gudlavalleru Engineering College; K. Subrhamanyam; Attili Nithish; Chandika Vishnu Vardhan; Chilakala Prasanna Lakshmi; and Anaparthy Anurag.

The application for the patent was published on May 1, under issue no. 18/2026.

According to the abstract released by the Intellectual Property India: "Accurate crop selection is essential for enhancing agricultural productivity and sustainability. Traditional methods rely on experience rather than systematic analysis of soil and climatic conditions, often leading to suboptimal outcomes. This study models crop selection as a classification problem using soil nutrients (N, P, K, pH) and environmental features such as temperature, humidity, and rainfall as inputs. Multiple machine learning algorithms were evaluated, with XGBoost achieving the highest accuracy of approximately 99%. Cross-validation techniques were applied to ensure robustness and generalization across different conditions. SHAP (SHapley Additive exPlanations) was used to interpret feature importance, revealing that humidity and rainfall significantly influence crop prediction. The system effectively captures nonlinear relationships between soil and climate variables, improving prediction reliability. The proposed framework provides a scalable and interpretable decision-support tool for data-driven crop planning, enabling efficient resource utilization and supporting sustainable agricultural practices. Keywords: Crop Prediction, Machine Learning, XGBoost, Soil Nutrients, Climate Data, SHAP Analysis, Decision Support System, Precision Agriculture, Supervised Learning, Feature Importance, Data Preprocessing, Agricultural Analytics."

Disclaimer: Curated by HT Syndication.