Patel et al. (2026) AI-Driven Precision Farming: Leveraging Environmental and Soil Parameters for Accurate Crop Yield Prediction

Identification

• Journal: Lecture notes in networks and systems
• Year: 2026
• Date: 2026-01-01
• Authors: Juhi Patel, Tejaskumar Bhatt
• DOI: 10.1007/978-3-032-13419-6_9

Research Groups

• Faculty of Computer Application and Information Technology, GLS University, Ahmedabad, India
• Faculty of Engineering and Technology Technology, GLS University, Ahmedabad, India

Short Summary

This study develops an AI-driven model utilizing multi-modal data (soil attributes, weather, vegetation indices) to accurately predict crop yield, demonstrating its potential for sustainable precision agriculture with a Linear Regression model achieving an R² score of 0.9714.

Objective

• To develop and evaluate an AI-driven model for accurate crop yield prediction by leveraging multi-modal environmental and soil parameters, aiming to support sustainable precision agriculture.

Study Configuration

• Spatial Scale: General agricultural context, with implications for smallholder farming and potential applicability across various agricultural regions.
• Temporal Scale: Not explicitly defined in the provided text; the model is for predicting crop yield based on current/recent environmental and soil data.

Methodology and Data

• Models used: Linear Regression (as a foundational model), with future considerations for Neural Networks and Ensemble Learning models.
• Data sources: Multi-modal data including soil attributes, weather parameters, and vegetation indices (specifically Normalized Difference Vegetation Index - NDVI).

Main Results

• The developed AI-driven model, based on Linear Regression, achieved a satisfactory test prediction accuracy for crop yield with a Mean Squared Error (MSE) of 0.0835 and an R² score of 0.9714.
• Feature correlation analysis identified Normalized Difference Vegetation Index (NDVI) and soil moisture as the most significant predictors of crop yield.
• The study confirmed the utility of interpretable models for their scalability, reliability, and applicability, particularly in smallholder farming contexts.

Contributions

• Provides a widely replicable AI-driven artifact that bridges the gap between abstract AI structures and usable applications for improved decision-making in precision agriculture.
• Emphasizes the importance of scalability and ethical considerations in AI-powered agricultural systems, alongside prediction accuracy.
• Contributes to global efforts in achieving sustainable agriculture, enhancing food security, and mitigating the environmental impact of farming.

Funding

• The author(s) received no financial support for the research, authorship, and/or publication of this article.

Citation

@article{Patel2026AIDriven,
  author = {Patel, Juhi and Bhatt, Tejaskumar},
  title = {AI-Driven Precision Farming: Leveraging Environmental and Soil Parameters for Accurate Crop Yield Prediction},
  journal = {Lecture notes in networks and systems},
  year = {2026},
  doi = {10.1007/978-3-032-13419-6_9},
  url = {https://doi.org/10.1007/978-3-032-13419-6_9}
}