Sangpradit et al. (2026) Field-validated explainable AI-based UAV remote sensing for variable-rate fertilization in precision sugarcane nutrient management

Identification

• Journal: Smart Agricultural Technology
• Year: 2026
• Date: 2026-09-21
• Authors: Kiattisak Sangpradit, Grianggai Samseemoung
• DOI: 10.1016/j.atech.2026.102585

Research Groups

• Department of Agricultural Engineering, Faculty of Engineering, Rajamangala University of Technology Thanyaburi, Pathum Thani, 12110, Thailand

Short Summary

This study develops an explainable artificial intelligence (AI)-driven UAV remote sensing-based variable-rate fertilization framework for precision sugarcane nutrient management. The framework integrates UAV multispectral sensing, XGBoost-based fertilizer recommendation, SHapley Additive exPlanations (SHAP), GIS-based prescription mapping, and embedded edge control to improve fertilizer-use efficiency while maintaining explainable decision-making.

Objective

• Develop an end-to-end architecture linking spatial sensing, explainable nutrient prediction, georeferenced prescription generation, edge control, and physical fertilizer actuation for precision sugarcane nutrient management.

Study Configuration

• Spatial Scale: Field-scale (5 × 5 m management zones)
• Temporal Scale: Real-time field execution during fertilizer application

Methodology and Data

• Models used: Extreme Gradient Boosting (XGBoost) model
• Data sources: UAV multispectral sensing, ground-truth fertilizer recommendation dataset, and in-field TDR measurements for soil moisture

Main Results

• The XGBoost model achieved R² > 0.91 with low prediction error.
• SHAP analysis identified NDVI, canopy temperature, and chlorophyll-related indices as the dominant predictive factors.
• Compared with conventional practice, the proposed approach reduced nitrogen fertilizer use by 21.8%, increased nitrogen-use efficiency by 27.4%, and increased sugarcane yield by 11.6% (p < 0.05).

Contributions

• The study provides an interpretable and practical pathway toward data-driven, resource-efficient, and sustainable sugarcane fertilization.
• The integrated architecture offers a scalable foundation for intelligent, data-driven, and sustainable agricultural automation.

Funding

• This research was funded by [insert funding agency/project name] with reference code [insert reference code].

Citation

@article{Sangpradit2026Fieldvalidated,
  author = {Sangpradit, Kiattisak and Samseemoung, Grianggai},
  title = {Field-validated explainable AI-based UAV remote sensing for variable-rate fertilization in precision sugarcane nutrient management},
  journal = {Smart Agricultural Technology},
  year = {2026},
  doi = {10.1016/j.atech.2026.102585},
  url = {https://doi.org/10.1016/j.atech.2026.102585}
}