Authors:
Sayyed Khawar Abbas, M. Deepak, S. Monish Kumar, S. Govarthanan, Premanand Jothilingam, Sai Vishaal Saibaskar

Addresses:
Department of Information Systems, Corvinus University of Budapest, Budapest, Hungary. Department of Computer Science and Engineering, SRM Institute of Science and Technology, Ramapuram, Chennai, Tamil Nadu, India. Department of Life Cycle Service, Yokogawa Corporation of America, West Valley City, Utah, United States of America. Department of Data Science, University of Wisconsin, Madison, Wisconsin, United States of America.

Abstract:

Although agriculture fuels growing world economies, crop output forecasting remains one of the most challenging and critical tasks in modern agricultural management. Uncertain weather, soil composition, fertiliser use, and crop-specific growth requirements make conventional production forecasting difficult. AgroMind, an AI-based Crop Disease Prediction and Crop Preference System, helps farmers, agronomists, and policymakers make data-driven cultivation decisions. A robust Scikit-learn Pipeline with a Random Forest Regressor automatically preprocesses features, including One-Hot Encoding for categorical variables (crop kind and soil type) and Standard Scaling for numerical variables. The training dataset includes 2,000 synthetic records for 15 crop types across 16 soil categories, including domain-specific agronomic variables such as crop temperature sensitivity, water needs, soil-crop synergy, and fertiliser impact. The model's 97% R-squared (R2) indicates strong predictive performance across numerous agricultural settings. The 6-stage interactive wizard front-end interface employs HTML5, CSS3, JavaScript, and Chart.js to give a smooth user experience with real-time Indian Rupee financial profit estimation. Python web server Flask provides the system. Inputs include crop name, soil type, temperature (°C), rainfall (mm), relative humidity (%), and fertiliser (kg/hectare). With smart agronomic advice, yield is tonnes per acre. Crop selection (15 types), soil type (16 categories), temperature (10–45°C), rainfall (100–3500 mm), humidity (20–95%), and fertiliser (20–500 kg/ha) are crucial. This approach links modern AI to farming decisions.

Keywords: Crop Output Forecasting; Random Forest Regressor; Scikit-Learn Pipeline; Soil-Crop Synergy; Fertiliser Impact; Agronomic Advice; Soil Type; Agricultural Management.

Received on: 17/07/2025, Revised on: 24/09/2025, Accepted on: 25/11/2025, Published on: 18/08/2026

DOI: 10.69888/FTSHSL.2026.000732

FMDB Transactions on Sustainable Health Science Letters, 2026 Vol. 4 No. 3, Pages: 212-223

• Views : 29
• Downloads : 10

Download PDF