Saxena et al. (2026) AI-Powered Precision Agriculture: Integrating Computer Vision and IoT for Sustainable Crop Management

Identification

• Journal: Lecture notes in networks and systems
• Year: 2026
• Date: 2026-01-01
• Authors: Navom Saxena, Anushka Raj Yadav, Shubneet, Navjot Singh Talwandi
• DOI: 10.1007/978-3-032-08859-8_8

Research Groups

• Senior Machine Learning Engineer, Meta, New York, NY, USA
• Department of Computer Science, Chandigarh University, Gharuan, Mohali, Punjab, India

Short Summary

This study presents an AI-driven framework integrating computer vision and IoT for sustainable crop management, demonstrating significant improvements in resource efficiency, water, and pesticide reduction, alongside high yield prediction accuracy through sub-field-level decision-making.

Objective

• To develop and evaluate an AI-driven framework that integrates computer vision and IoT technologies to optimize crop management for sustainable agricultural production.

Study Configuration

• Spatial Scale: Sub-field-level management decisions across three major crops.
• Temporal Scale: Real-time data capture and adaptive irrigation control.

Methodology and Data

• Models used: Novel deep learning architecture, spatial-temporal graph convolutional networks.
• Data sources: Multimodal sensor networks (real-time soil moisture, nutrient levels, crop health data), drone-based hyperspectral imaging.

Main Results

• Achieved 94.3% accuracy in yield prediction across three major crops.
• Demonstrated a pest detection F1-score of 0.92.
• Reduced water usage by 37% through adaptive irrigation control.
• Decreased pesticide application by 42% via targeted treatment zones.
• Showed 28% higher resource efficiency compared to conventional precision agriculture methods.
• Enabled sub-field-level management decisions through edge computing devices with 89% lower latency than cloud-based alternatives.
• Soil moisture sensors achieved an accuracy of ± 1.8%.

Contributions

• Introduction of an integrated AI-driven framework combining computer vision and IoT for comprehensive crop management.
• Implementation of sub-field-level management decisions using edge computing, significantly reducing latency compared to cloud-based systems.
• Demonstrated substantial quantitative improvements in resource efficiency, water conservation, and reduced pesticide use.
• Developed a novel deep learning architecture utilizing spatial-temporal graph convolutional networks for high-accuracy yield prediction.
• Proposed a scalable and interoperable solution for sustainable intensification of agricultural production.

Funding

Not specified in the provided text.

Citation

@article{Saxena2026AIPowered,
  author = {Saxena, Navom and Yadav, Anushka Raj and Shubneet and Talwandi, Navjot Singh},
  title = {AI-Powered Precision Agriculture: Integrating Computer Vision and IoT for Sustainable Crop Management},
  journal = {Lecture notes in networks and systems},
  year = {2026},
  doi = {10.1007/978-3-032-08859-8_8},
  url = {https://doi.org/10.1007/978-3-032-08859-8_8}
}