Hemasundari et al. (2025) Optimizing Agricultural Resource Management Through IoT-Enabled Sentinel-Based Vegetation Monitoring

Identification

• Journal: Journal of Wireless Mobile Networks Ubiquitous Computing and Dependable Applications
• Year: 2025
• Date: 2025-12-05
• Authors: Dr.M. Hemasundari, D. Harini, Dr.R. Velanganni, Arasuraja Ganesan
• DOI: 10.58346/jowua.2025.i4.012

Research Groups

• Department of Management Studies, SRM Valliammai Engineering College, Kattankulathur, India.
• School of Management, PG and Doctoral Research, Dwaraka Doss Goverdhan Doss Vaishnav College, Chennai, Tamil Nadu, India.
• Crescent School of Law, (Management Studies), BS Abdur Rahman Crescent Institute of Science and Technology, Chennai, Tamil Nadu, India.
• Department of Management Studies, St. Joseph’s Institute of Technology, OMR, Chennai, Tamil Nadu, India.

Short Summary

This research introduces the Sentinel-IoT Adaptive Multi-Objective Resource Optimizer (SIAM-RO) model, which integrates IoT sensor data with Sentinel satellite-derived vegetation indices and uses NSGA-II for multi-objective optimization to enhance agricultural resource management. The SIAM-RO system significantly improves crop yield, water use efficiency, and nutrient use efficiency compared to traditional methods, promoting sustainable and cost-effective farming.

Objective

• To integrate satellite-based vegetation analysis with IoT environmental and soil attributes, implementing evolutionary optimization techniques for optimal resource management in agriculture.
• To merge IoT sensor data with Sentinel-based vegetation indices for monitoring soil and crops in real-time.
• To create SIAM-RO (Sentinel-IoT Adaptive Multi-Objective Resource Optimizer), which uses the NSGA-II-based trainer for the optimization of water, fertilizers, and energy in precision agriculture.
• To refine the optimization problem in agricultural resources to control the minimization of investment required and the maximization of available yield within climate and resource limitations for better sustainability.
• To demonstrate that advanced precision agriculture IoT sensing, remote satellite monitoring, and evolutionary optimization algorithms can be integrated to enhance the sustainability, cost-effectiveness, and resiliency of precision agriculture.

Study Configuration

• Spatial Scale: Microclimates, entire fields, broad-area and wide swath (above 20 meters), continental levels, regional scale, and a mid-sized agricultural testing domain.
• Temporal Scale: Real-time monitoring, continuous data collection, and analysis over control sensing intervals.

Methodology and Data

• Models used: Sentinel-IoT Adaptive Multi-Objective Resource Optimizer (SIAM-RO) model, Non-dominated Sorting Genetic Algorithm II (NSGA-II).
• Data sources:
  • IoT sensors: Soil moisture, nutrient content, microclimate data (temperature, humidity).
  • Sentinel-2 satellite imagery: Derived vegetation indices (Normalized Difference Vegetation Index - NDVI, Enhanced Vegetation Index - EVI).
  • Archived climatic data.

Main Results

• The SIAM-RO framework consistently boosted crop yield.
• Water Use Efficiency (WUE) improved by 18-22% compared to Genetic Algorithm (GA) and 12-15% compared to Particle Swarm Optimization (PSO) using SIAM-RO.
• Nutrient Use Efficiency (NUE) was enhanced by 15-20% compared to baseline methods with SIAM-RO.
• Vegetation Health Index (VHI) scores were higher across all assessments, indicating better optimized scheduling for vegetation growth.
• The NSGA-II-based multi-objective framework increased crop yield by 10-15% and reduced water and fertilizer usage compared to traditional heuristic methods and single-objective optimization approaches.
• Trade-off analysis using Pareto fronts effectively illustrated the balance between maximizing yield and minimizing water and fertilizer consumption.
• The system demonstrated scalability for managing multiple crop scenarios and large datasets, and adaptability across diverse climatic and soil conditions.

Contributions

• Development of SIAM-RO, an innovative integrative architecture that synchronizes terrestrial IoT sensing with orbital Sentinel monitoring for comprehensive, multi-objective optimization in agricultural resource management.
• Achieved seamless fusion of fine-grained IoT sensor data (microclimate, soil moisture, nutrients) with spatially extensive Sentinel satellite data (vegetation indices like NDVI, EVI).
• Applied the Non-dominated Sorting Genetic Algorithm II (NSGA-II) for multi-objective optimization, simultaneously maximizing agronomic yield, minimizing hydro-productive expenditures, and calibrating nitrogen and phosphorus dosing.
• Demonstrated superior performance in Water Use Efficiency, Nutrient Use Efficiency, and Vegetation Health Index compared to existing methods (GA, PSO, heuristic scheduling).
• Provided a scalable and adaptable framework for smart agriculture, offering data-driven insights for precise irrigation and fertilization scheduling, leading to increased sustainability and cost-effectiveness.

Funding

[No explicit funding information was provided in the paper text.]

Citation

@article{Hemasundari2025Optimizing,
  author = {Hemasundari, Dr.M. and Harini, D. and Velanganni, Dr.R. and Ganesan, Arasuraja},
  title = {Optimizing Agricultural Resource Management Through IoT-Enabled Sentinel-Based Vegetation Monitoring},
  journal = {Journal of Wireless Mobile Networks Ubiquitous Computing and Dependable Applications},
  year = {2025},
  doi = {10.58346/jowua.2025.i4.012},
  url = {https://doi.org/10.58346/jowua.2025.i4.012}
}

Generated by BiblioAssistant using gemini-2.5-flash (Google API)