Nitrogen Estimation in Maize Using RGB Leaf Image Analysis and Deep Learning

Rabia Zafar; Muhammad Shahid Farid; Muhammad Hassan Khan; Rashid Mahmood

doi:10.15832/ankutbd.1763304

Nitrogen Estimation in Maize Using RGB Leaf Image Analysis and Deep Learning

Abstract

The integration of digitization and automation into traditional farming has transformed agriculture, enhanced productivity and delivered significant economic benefits. Recent advances in deep learning (DL) provide new opportunities for automating crop monitoring and nutrient management. This paper proposes a framework for estimating nitrogen content in maize leaves using RGB images captured under field conditions. A UNet-based segmentation model isolates leaves from complex, uncontrolled backgrounds, and a convolutional neural network (CNN) extracts discriminative features. These features are evaluated using three regression models, Support Vector Regressor (SVR), Random Forest Regressor (RFR), and Gradient Boosting Regressor (GBR), to predict SPAD values, ranges from 24.9 to 59.5, an indirect measure of chlorophyll and nitrogen content. Experiments conducted on six maize varieties (three open-pollinated and three hybrid) across four growth stages yielded an overall lowest mean absolute error (MAE) of 3.56 and a correlation coefficient of 0.76. Aggregating results by dataset type, the best-performing method achieved an average MAE of 3.56 for OPV and 4.04 for Hybrid varieties. Further analysis by individual variety type revealed that RFR was most effective, attaining the lowest MAEs of 1.34 and 1.47 for OPV and Hybrid varieties, respectively. A second contribution is MaizeRGB, a comprehensive, publicly available dataset containing RGB images and ground-truth SPAD measurements for multiple maize varieties, nitrogen levels, and growth stages. The proposed approach demonstrates high accuracy, robustness to variable field conditions, and strong potential for low-cost, scalable nitrogen management in precision agriculture.

Keywords

References

Adhikari R, Li C, Kalbaugh K & Nemali K (2020). A low-cost smartphone controlled sensor based on image analysis for estimating whole plant tissue nitrogen (N) content in floriculture crops. Computers and Electronics in Agriculture 169: 105173. https://doi.org/10.1016/j.compag.2019.105173
Agarap A F (2018). Deep learning using rectified linear units (relu). ArXiv Preprint ArXiv:1803.08375. https://doi.org/10.48550/arXiv.1803.08375
Alpsalaz F, Özüpak Y, Aslan E & Uzel H (2025). Classification of maize leaf diseases with deep learning: Performance evaluation of the proposed model and use of explicable artificial intelligence. Chemometrics and Intelligent Laboratory Systems 105412. https://doi.org/10.1016/j.chemolab.2025.105412
Altuntaş Y, Elkoca E, & Kodaz S (2024). Impact of Mesorhizobium ciceri Inoculation on Symbiotic Nitrogen Fixation of Various Chickpea (Cicer arietinum L.) Cultivars. Journal of Agricultural Production 5(4): 255–264. https://doi.org/10.56430/japro.1565531
Awad M, Khanna R, Awad M & Khanna R (2015). Support vector regression. Efficient Learning Machines: Theories, Concepts, and Applications for Engineers and System Designers pp. 67–80
Bjorck N, Gomes C P, Selman B & Weinberger K Q (2018). Understanding batch normalization. Advances in Neural Information Processing Systems 31
Candiani G, Tagliabue G, Panigada C, Verrelst J, Picchi V, Rivera Caicedo J P & Boschetti M (2022). Evaluation of hybrid models to estimate chlorophyll and nitrogen content of maize crops in the framework of the future CHIME mission. Remote Sensing 14(8): 1792. https://doi.org/10.3390/rs14081792
Colorado J D, Cera-Bornacelli N, Caldas J S, Petro E, Rebolledo M C, Cuellar D & others (2020). Estimation of nitrogen in rice crops from UAV-captured images. Remote Sens 12: 3396. https://doi.org/10.3390/rs12203396

Erman M, Çğ F& Ceritoğlu M (2025). Optimizing Fenugreek (Trigonella foenum-graecum L.) Cultivation: Role of Rhizobium Inoculation and Phosphorus Fertilization on Growth, Nodulation, and Yield Attributes. Turkish Journal of Applied Sciences and Technology 6(1): 43 53. https://doi.org/10.70562/tubid.1662619
Gallegos Á, Gavito M E & Ferreira Medina H (2024). Foliar Nitrogen Estimation with Artificial Intelligence and Technological Tools: State of the Art and Future Challenges. International Journal of Advanced Computer Science & Applications 15(6) Ghazal S, Kommineni N & Munir A (2024). Comparative analysis of machine learning techniques using RGB imaging for nitrogen stress detection in maize. AI 5(3): 1286. https://doi.org/10.3390/ai5030062
Ghazal S, Munir A & Qureshi W S (2024). Computer vision in smart agriculture and precision farming: Techniques and applications. Artificial Intelligence in Agriculture. https://doi.org/10.1016/j.aiia.2024.06.004 Gürbüz M A & Kardeş T A (2024). Sunflower-nitrogen calibration based on the amount of mineral nitrogen in soil under rainfed conditions in thrace region. Soil Studies 13(1): 43–54. https://doi.org/10.21657/soilst.1520597
Haider T, Farid M S, Mahmood R, Ilyas A, Khan M H, Haider S T A, Chaudhry M H & Gul, M. (2021). A Computer-Vision-Based Approach for Nitrogen Content Estimation in Plant Leaves. Agriculture 11(8). https://doi.org/10.3390/agriculture11080766
Haliloğlu H & Aydogdu A (2024). The effect of different nitrogen doses on growth attributes of some sunflower (Helianthus annuus L.) cultivars grown as second crop. Akademik Ziraat Dergisi 13(1): 129–136. https://doi.org/10.29278/azd.1393338
Hao W, Yizhou W, Yaqin L & Zhili S (2020). The role of activation function in CNN. 2020 2nd International Conference on Information Technology and Computer Application (ITCA) 429–432. 10.1109/ITCA52113.2020.00096
Li J, Ge Y, Puntel L A, Heeren D M, Bai G, Balboa G R, Gamon J A, Arkebauer T J & Shi Y (2024). Integrating UAV hyperspectral data and radiative transfer model simulation to quantitatively estimate maize leaf and canopy nitrogen content. International Journal of Applied Earth Observation and Geoinformation 129: 103817. https://doi.org/10.1016/j.jag.2024.103817
Li Z W, Wang G Y, Khan K, Yang L, Chi Y X, Wang Y & Zhou X B (2024). Irrigation combines with nitrogen application to optimize soil carbon and nitrogen, increase maize yield, and nitrogen use efficiency. Plant and Soil 499(1): 605–620. https://doi.org/10.1007/s11104 024-06480-6
Lu B, Dao P D, Liu J, He Y & Shang J (2020). Recent advances of hyperspectral imaging technology and applications in agriculture. Remote Sensing 12(16): 2659. https://doi.org/10.3390/rs12162659
Özüpak Y, Alpsalaz F, Aslan E & Uzel H (2025). Hybrid deep learning model for maize leaf disease classification with explainable AI. New Zealand Journal of Crop and Horticultural Science 1–23. https://doi.org/10.1080/01140671.2025.2519570
Pagola M, Ortiz R, Irigoyen I, Bustince H, Barrenechea E, Aparicio-Tejo P, Lamsfus C & Lasa B (2009). New method to assess barley nitrogen nutrition status based on image colour analysis: Comparison with SPAD-502. Computers and Electronics in Agriculture 65(2): 213–218. https://doi.org/10.1016/j.compag.2008.10.003
Prettenhofer P & Louppe G (2014). Gradient boosted regression trees in scikit-learn. PyData 2014 Richmond H D (1908). The estimation of nitrogen. Analyst 33(386): 179–184
Ronneberger O, Fischer P & Brox T (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. International conference on Medical Image Computing and Computer-Assisted Intervention – MICCAI 234–241. https://doi.org/10.1007/978-3-319-24574-4_28
Sáez-Plaza P, Michałowski T, Navas M J, Asuero A G, & Wybraniec S (2013). An overview of the Kjeldahl method of nitrogen determination. Part I. Early history, chemistry of the procedure, and titrimetric finish. Critical Reviews in Analytical Chemistry 43(4): 178–223. https://doi.org/10.1080/10408347.2012.751786
Segal M R (2004). Machine learning benchmarks and random forest regression. UCSF: Center for Bioinformatics and Molecular Biostatistics Siqueira R, Mandal D, Longchamps L & Khosla R (2022). Assessing nitrogen variability at early stages of maize using mobile fluorescence sensing. Remote Sensing 14(20): 5077. https://doi.org/10.3390/rs14205077
Sun L, Yang C, Wang J, Cui X, Suo X, Fan X, Ji P, Gao L & Zhang Y (2024). Automatic Modeling Prediction Method of Nitrogen Content in Maize Leaves Based on Machine Vision and CNN. Agronomy 14(1). https://doi.org/10.3390/agronomy14010124
Sun X, Zhang P & Wang Z (2024). Potential of multi-seasonal vegetation indices to predict rice yield from UAV multispectral observations. Precision Agriculture 1–27. https://doi.org/10.1007/s11119-023-10109-6
Vesali F, Omid M, Kaleita A & Mobli H (2015). Development of an android app to estimate chlorophyll content of corn leaves based on contact imaging. Computers and Electronics in Agriculture 116: 211–220. https://doi.org/10.1016/j.compag.2015.06.012
Wang D, Struik P C, Liang L & Yin X (2025). Estimating leaf and canopy nitrogen contents in major field crops across the growing season from hyperspectral images using nonparametric regression. Computers and Electronics in Agriculture 233: 110147. https://doi.org/10.1016/j.compag.2025.110147
Xin Q I, Yang W, YouLiang Y E, YuLong G U O, YaNan Z & others (2024). Nitrogen Nutrition Diagnosis Method Based on Mobile Phone Image of Summer Maize Canopy. Scientia Agricultura Sinica 57(20): 4094–4106. https://doi.org/10.3864/j.issn.0578-1752.2024.20.014

Details

Primary Language

English

Subjects

Agricultural Biotechnology Diagnostics, Agronomy, Soil Sciences and Plant Nutrition (Other)

Journal Section

Research Article

Authors

Rabia Zafar ^*
0000-0002-4231-410X
Pakistan

Muhammad Shahid Farid This is me
0000-0002-8384-2830
Pakistan

Muhammad Hassan Khan This is me
0000-0002-6145-5848
Pakistan

Rashid Mahmood This is me
0000-0002-5972-6223
Pakistan

Publication Date

July 28, 2026

Submission Date

August 12, 2025

Acceptance Date

February 24, 2026

Published in Issue

Year 2026 Volume: 32 Number: 3

DOI

https://doi.org/10.15832/ankutbd.1763304

IZ

https://izlik.org/JA54AC25LX

Cite

RIS / Bibtex

APA

Zafar, R., Farid, M. S., Khan, M. H., & Mahmood, R. (2026). Nitrogen Estimation in Maize Using RGB Leaf Image Analysis and Deep Learning. Journal of Agricultural Sciences, 32(3), 669-681. https://doi.org/10.15832/ankutbd.1763304

AMA

1.Zafar R, Farid MS, Khan MH, Mahmood R. Nitrogen Estimation in Maize Using RGB Leaf Image Analysis and Deep Learning. J Agr Sci-Tarim Bili. 2026;32(3):669-681. doi:10.15832/ankutbd.1763304

Chicago

Zafar, Rabia, Muhammad Shahid Farid, Muhammad Hassan Khan, and Rashid Mahmood. 2026. “Nitrogen Estimation in Maize Using RGB Leaf Image Analysis and Deep Learning”. Journal of Agricultural Sciences 32 (3): 669-81. https://doi.org/10.15832/ankutbd.1763304.

EndNote

Zafar R, Farid MS, Khan MH, Mahmood R (July 1, 2026) Nitrogen Estimation in Maize Using RGB Leaf Image Analysis and Deep Learning. Journal of Agricultural Sciences 32 3 669–681.

IEEE

[1]R. Zafar, M. S. Farid, M. H. Khan, and R. Mahmood, “Nitrogen Estimation in Maize Using RGB Leaf Image Analysis and Deep Learning”, J Agr Sci-Tarim Bili, vol. 32, no. 3, pp. 669–681, July 2026, doi: 10.15832/ankutbd.1763304.

ISNAD

Zafar, Rabia - Farid, Muhammad Shahid - Khan, Muhammad Hassan - Mahmood, Rashid. “Nitrogen Estimation in Maize Using RGB Leaf Image Analysis and Deep Learning”. Journal of Agricultural Sciences 32/3 (July 1, 2026): 669-681. https://doi.org/10.15832/ankutbd.1763304.

JAMA

1.Zafar R, Farid MS, Khan MH, Mahmood R. Nitrogen Estimation in Maize Using RGB Leaf Image Analysis and Deep Learning. J Agr Sci-Tarim Bili. 2026;32:669–681.

MLA

Zafar, Rabia, et al. “Nitrogen Estimation in Maize Using RGB Leaf Image Analysis and Deep Learning”. Journal of Agricultural Sciences, vol. 32, no. 3, July 2026, pp. 669-81, doi:10.15832/ankutbd.1763304.

Vancouver

1.Rabia Zafar, Muhammad Shahid Farid, Muhammad Hassan Khan, Rashid Mahmood. Nitrogen Estimation in Maize Using RGB Leaf Image Analysis and Deep Learning. J Agr Sci-Tarim Bili. 2026 Jul. 1;32(3):669-81. doi:10.15832/ankutbd.1763304