Rice Canopy Nitrogen Content Estimation Using UAV and XGBoost

Francis Kioni; Emily Gichuhi; Solomon Kariuki; Eunice Nduati

doi:10.48084/etasr.15820

Authors

Francis Kioni Department of Geomatics Engineering and Geospatial Information Systems (GEGIS), Jomo Kenyatta University of Agriculture and Technology (JKUAT), Juja, Kenya
Emily Gichuhi Kenya Agriculture and Livestock Research Organization (KALRO), Mwea, Kenya
Solomon Kariuki Geoid Technologies, Nairobi, Kenya
Eunice Nduati Department of Geomatics Engineering and Geospatial Information Systems (GEGIS), Jomo Kenyatta University of Agriculture and Technology (JKUAT), Juja, Kenya

Volume: 16 | Issue: 3 | Pages: 37111-37118 | June 2026 | https://doi.org/10.48084/etasr.15820

Received: 27 October 2025 | Revised: 25 February 2026 and 24 March 2026 | Accepted: 3 April 2026 | Online: 1 June 2026

Corresponding author: Francis Kioni

Abstract

An operational framework for the estimation of rice Canopy Nitrogen Content (CNC) at KALRO Kirogo farm in Kenya's Mwea Irrigation Scheme is proposed in this paper. The proposed framework integrated UAV multispectral imagery with XGBoost. A DJI Phantom 2 Multispectral drone captured imagery at 50 m altitude, achieving 5 cm spatial resolution. Five Vegetation Indices (Vis) (NDRE, ReCI, GCI, NRI, GLI) were extracted from radiometrically corrected orthomosaics and paired with Soil and Plant Analysis Development (SPAD) measurements from stratified random sampling across three growth stages (Vegetative Stage (VS), Early Maturity (EM), and Late Maturity (LM)). XGBoost hyperparameters were optimized via grid search (144 combinations, 5-fold CV), achieving superior performance. SHAP analysis identified NDRE as the primary predictor with agronomically sensible contribution. High-resolution nitrogen maps enabled the detection of within-field variability at management-relevant scales for smallholder plots. The results demonstrated that UAV-XGBoost integration provides accurate, non-destructive nitrogen estimation for sub-Saharan African smallholder rice systems, offering a scalable framework for precision nitrogen management.

Keywords:

rice, nitrogen, UAV, XGBoost

References

[1] E. A. Atera, F. N. Onyancha, and E. B. O. Majiwa, "Production and marketing of rice in Kenya: Challenges and opportunities," Journal of Development and Agricultural Economics, vol. 10, no. 3, pp. 64–70, Mar. 2018.

[2] NERICA: The new rice for Africa–a compendium. E. A. Somado, R. G. Guei, and S. O. Keya (eds.). Cotonou, Benin: Africa Rice Center (WARDA), 2008.

[3] "FAO Rice Market Monitor (RMM)," Food and Agriculture Organization of the United Nations, Rome, Italy, Apr. 2018.

[4] H. Samejima et al., "Analysis of rice yield response to various cropping seasons to develop optimal cropping calendars in Mwea, Kenya," Plant Production Science, vol. 23, no. 3, pp. 297–305, July 2020.

[5] J. P. Gweyi-Onyango et al., "Differences in seasons and rice varieties provide opportunities for improving nitrogen use efficiency and management in irrigated rice in Kenya," Environmental Research Letters, vol. 16, no. 7, June 2021, Art. no. 075003.

[6] A. O. Onyango, "Exploring options for improving rice production to reduce hunger and poverty in Kenya," World Environment, vol. 4, no. 4, pp. 172–179, 2014.

[7] National Rice Development Strategy-2 (2019-2030), Republic of Kenya: Ministry of Agriculture, Fisheries and Cooperatives, 2020.

[8] M. Iatrou et al., "Topdressing Nitrogen Demand Prediction in Rice Crop Using Machine Learning Systems," Agriculture, vol. 11, no. 4, Apr. 2021, Art. no. 312.

[9] H. T. Nguyen and B.-W. Lee, "Assessment of rice leaf growth and nitrogen status by hyperspectral canopy reflectance and partial least square regression," European Journal of Agronomy, vol. 24, no. 4, pp. 349–356, May 2006.

[10] P. Shi et al., "Rice nitrogen nutrition estimation with RGB images and machine learning methods," Computers and Electronics in Agriculture, vol. 180, Jan. 2021, Art. no. 105860.

[11] T. R. Sinclair, J. R. Farias, N. Neumaier, and A. L. Nepomuceno, "Modeling nitrogen accumulation and use by soybean," Field Crops Research, vol. 81, no. 2, pp. 149–158, Feb. 2003.

[12] Y. Çimtay, "Estimating Plant Nitrogen by Developing an Accurate Correlation between VNIR-Only Vegetation Indexes and the Normalized Difference Nitrogen Index," Remote Sensing, vol. 15, no. 15, Aug. 2023, Art. no. 3898.

[13] J. D. Colorado et al., "Estimation of Nitrogen in Rice Crops from UAV-Captured Images," Remote Sensing, vol. 12, no. 20, Oct. 2020, Art. no. 3396.

[14] H. Yang, J. Yang, Y. Lv, and J. He, "SPAD Values and Nitrogen Nutrition Index for the Evaluation of Rice Nitrogen Status," Plant Production Science, vol. 17, no. 1, pp. 81–92, 2014.

[15] P. Feng et al., "Dynamic wheat yield forecasts are improved by a hybrid approach using a biophysical model and machine learning technique," Agricultural and Forest Meteorology, vol. 285–286, May 2020, Art. no. 107922.

[16] Y. Chen et al., "Nationwide crop yield estimation based on photosynthesis and meteorological stress indices," Agricultural and Forest Meteorology, vol. 284, Apr. 2020, Art. no. 107872.

[17] Y. Fu et al., "An overview of crop nitrogen status assessment using hyperspectral remote sensing: Current status and perspectives," European Journal of Agronomy, vol. 124, Mar. 2021, Art. no. 126241.

[18] J. Huang, R. Wang, X. Wang, L. S. Liu, and J. Zhang, "Study on multiple yield estimation models of winter wheat using remote sensing data.," Journal of Zhejiang Agricultural University, vol. 25, no. 5, pp. 519–523, Feb. 2000.

[19] J. Wang et al., "Estimating leaf area index and aboveground biomass of grazing pastures using Sentinel-1, Sentinel-2 and Landsat images," ISPRS Journal of Photogrammetry and Remote Sensing, vol. 154, pp. 189–201, Aug. 2019.

[20] M. Colovic et al., "Hyperspectral Vegetation Indices to Assess Water and Nitrogen Status of Sweet Maize Crop," Agronomy, vol. 12, no. 9, Sept. 2022, Art. no 2181.

[21] L. Wang et al., "Estimation of Paddy Rice Nitrogen Content and Accumulation Both at Leaf and Plant Levels from UAV Hyperspectral Imagery," Remote Sensing, vol. 13, no. 15, July 2021, Art. no. 2956.

[22] U. V. Nikhil, A. M. Pandiyan, S. P. Raja, and Z. Stamenkovic, "Machine Learning-Based Crop Yield Prediction in South India: Performance Analysis of Various Models," Computers, vol. 13, no. 6, May 2024, Art. no. 137.

[23] H. Zha et al., "Improving Unmanned Aerial Vehicle Remote Sensing-Based Rice Nitrogen Nutrition Index Prediction with Machine Learning," Remote Sensing, vol. 12, no. 2, Jan. 2020, Art. no. 215.

[24] S. Xu et al., "Monitoring leaf nitrogen content in rice based on information fusion of multi-sensor imagery from UAV," Precision Agriculture, vol. 24, no. 6, pp. 2327–2349, July 2023.