Sharma et al. (2025) IoT-Enhanced Machine Learning for Remote Sensing and Image Processing in Agriculture

Identification

• Journal: Lecture notes in networks and systems
• Year: 2025
• Date: 2025-10-06
• Authors: Avinash Sharma, Dankan Gowda, Sevinthi Kali Sankar Nagarajan, Kevin Shah, P. Vishnu Prasanth, Rini Saxena
• DOI: 10.1007/978-981-96-7289-9_45

Research Groups

• School of Engineering and Technology, CT University, Ludhiana, Punjab, India
• Department of Electronics and Communication Engineering, BMS Institute of Technology and Management, Bangalore, Karnataka, India
• Independent Researcher, San Antonio, TX, USA
• Independent Researcher, Ashburn, VA, USA
• Department of Physics, Mohan Babu University, Tirupati, India
• Department of Computer Science and Engineering, Chandigarh Engineering College, Chandigarh Group of Colleges Jhanjeri, Mohali, Punjab, India

Short Summary

This paper presents an IoT-enhanced machine learning system for precision agriculture, integrating sensor data and remote sensing imagery to improve crop health monitoring, yield estimation, and resource utilization. The system achieved a 92% accuracy in crop health classification, demonstrating its potential for sustainable smart farming.

Objective

• To develop and demonstrate a comprehensive system that integrates IoT for sensor data capture and machine learning for remote sensing image analysis to enhance crop health monitoring, yield estimation, and resource utilization in agriculture.

Study Configuration

• Spatial Scale: Agricultural fields/farms (implied by crop health, yield estimation, and use of satellite and drone images).
• Temporal Scale: Real-time or near real-time monitoring for timely intervention.

Methodology and Data

• Models used: Convolutional Neural Networks (CNNs) for image-based assessments and crop health classification.
• Data sources:
  • IoT sensors: Soil moisture, soil temperature, environmental conditions.
  • Remote sensing images: Satellite images, drone images (used to produce vegetation indices and identify crop stress).

Main Results

• The proposed system achieved a high accuracy rate of 92% for crop health classification through image-based assessments.
• Experimental results indicate that the framework can increase yield rates in agricultural activities.
• The system helps minimize wastage of resources.
• It enables timely intervention in agricultural processes.

Contributions

• Presents a wide-ranging system integrating IoT and machine learning for comprehensive agricultural monitoring.
• Demonstrates the effectiveness of combining sensorial feedback and image analysis for enhanced precision farming.
• Provides a framework for efficient smart farming methods, contributing to sustainable agriculture and global food security.

Funding

• Not explicitly mentioned in the provided text.

Citation

@article{Sharma2025IoTEnhanced,
  author = {Sharma, Avinash and Gowda, Dankan and Nagarajan, Sevinthi Kali Sankar and Shah, Kevin and Prasanth, P. Vishnu and Saxena, Rini},
  title = {IoT-Enhanced Machine Learning for Remote Sensing and Image Processing in Agriculture},
  journal = {Lecture notes in networks and systems},
  year = {2025},
  doi = {10.1007/978-981-96-7289-9_45},
  url = {https://doi.org/10.1007/978-981-96-7289-9_45}
}