Himanshu et al. (2025) AI Crop Analysis and Recommendation System

Identification

• Journal: Lecture notes in networks and systems
• Year: 2025
• Date: 2025-10-19
• Authors: Himanshu, Avneesh Vashistha, Pushpendra Singh
• DOI: 10.1007/978-3-032-04222-4_16

Research Groups

Department of Computer Science and Engineering, SRM Institute of Science and Technology, Delhi-NCR Campus, Ghaziabad, Uttar Pradesh, India.

Short Summary

This study develops an AI-powered Crop Analysis and Recommendation System that integrates machine learning with extensive environmental and historical data to provide data-driven decision support for farming, achieving over 99% prediction accuracy for crop recommendations and yield predictions.

Objective

• To develop and evaluate an AI-powered Crop Analysis and Recommendation System that optimizes crop selection and predicts yields for specific conditions, aiming to enhance resource efficiency and promote sustainable farming, particularly for smallholder farmers.

Study Configuration

• Spatial Scale: Field implementation across several agricultural zones.
• Temporal Scale: Utilizes historical yield records for analysis and prediction.

Methodology and Data

• Models used: Naive Bayes, Random Forest, XGBoost (classification methods).
• Data sources: Soil nutrient profiles (nitrogen, phosphorus, potassium values, pH), meteorological data (temperature, humidity, rainfall), historical yield records.

Main Results

• The developed system demonstrated a predicted accuracy of over 99% in comprehensive experiments for crop analysis and recommendation.
• It provides four primary functionalities: yield prediction, crop recommendation, soil analysis, and resource optimization.
• Field implementation showed notable gains in yield consistency and resource utilization across various agricultural zones.
• The system is designed to reduce uncertainty, improve resource efficiency, and encourage sustainable farming practices, especially for smallholder farmers.

Contributions

• Presents a comprehensive AI-powered system that integrates crop analysis, recommendation, yield prediction, soil analysis, and resource optimization into a single platform.
• Achieves high prediction accuracy (over 99%) using a combination of established machine learning techniques.
• Focuses on practical applicability and accessibility for smallholder farmers, aiming to improve food security and economic resilience.
• Represents a significant step towards precision agriculture by balancing environmental sustainability with economic viability through advanced computational tools.

Funding

Not specified in the provided text.

Citation

@article{Himanshu2025AI,
  author = {Himanshu and Vashistha, Avneesh and Singh, Pushpendra},
  title = {AI Crop Analysis and Recommendation System},
  journal = {Lecture notes in networks and systems},
  year = {2025},
  doi = {10.1007/978-3-032-04222-4_16},
  url = {https://doi.org/10.1007/978-3-032-04222-4_16}
}