NDRE index application for nitrogen fertilizers management automatization in sugar beet crops seeding using UAVS
DOI:
https://doi.org/10.7868/S3034519726010119Keywords:
sugar beet, precision farming, NDRE, UAVs, multispectral imaging, nitrogen fertilizers, machine learning, task map, differentiated application, yieldAbstract
Balanced nitrogen nutrition of sugar beets is a key factor in achieving high yields and root crop quality. However, traditional nitrogen diagnostic methods fail to account for spatial field heterogeneity. The objective of the study was to develop a technology for automated management of nitrogen application using the NDRE index (Nitrogen Dependency Index) derived from multispectral UAV imagery. The experiment was conducted in 2024 on sugar beet crops in the Republic of Bashkortostan. A DJI Phantom 4 quadcopter with a Parrot Sequoia multispectral camera was used for monitoring. Using orthophotos, the NDVI, GNDVI, and NDRE indices were calculated, radiometric calibration was performed, and artifact masking was performed. Machine learning algorithms (regression, random forest, SVM), as well as threshold zoning, were used to convert NDRE values into nitrogen doses. Based on the NDRE, a task map with three nutrient zones was automatically generated. The average additional dose was 29.8 kg/ha, which reduced the total nitrogen application to 90 kg/ha versus 110 kg/ha in the control. Root crop yields were comparable (49.1–49.8 t/ha), while sugar content increased by 0.5%. Fertilizer savings were approximately 20% without yield loss, resulting in cost savings and a reduced risk of nitrate accumulation. The use of NDRE and UAVs confirmed the high efficiency of the differentiated fertilizer application technology. This method ensures rational nitrogen use, helps increase sugar content, and is environmentally sustainable. The technology can potentially be scaled up to other crops and integrated into precision farming systems.
References
1. Демидов П.В. Характеристика и функциональные возможности цифровых сервисов агроскаутинга в экономике АПК // Теория и практика инновационных технологий в АПК. 2023. С. 178–183.
2. Мударисов С.Г., Мифтахов И.Р. Автоматическое определение и идентификация заболеваний пшеницы методами глубокого обучения с применением БПЛА в режиме реального времени // Вестник Казанского государственного аграрного университета. 2024. Т. 19. № 2. С. 90–104.
3. Мыслыва Т.Н. и др. Использование данных дистанционного зондирования, полученных с БЛА, для оценки продуктивности биомассы Silphium perfoliatum // Известия Национальной академии наук Беларуси. Серия аграрных наук. 2021. Т. 59. № 2. С. 186–197.
4. Barreto A. et al. Disease incidence and severity of cercospora leaf spot in sugar beet assessed by multispectral unmanned aerial images and machine learning // Plant Disease. 2023. Vol. 107. No. 1. P. 188–200.
5. Drimzakas-Papadopoulos V. et al. Use of UAVs’ multispectral images for sugar beet cultivars discrimination and yield estimation // Journal of Central European Agriculture. 2024. Vol. 25. No. 4. P. 1135–1147.
6. EOSDA. NDRE maps in precision agriculture: applications for nitrogen management. 2024. URL: https://eos.com/blog/ndre-index (дата обращения: 22.09.2025).
7. Elsayed S. et al. Estimating chlorophyll content, production, and quality of sugar beet under various nitrogen levels using machine learning models and novel spectral indices // Agronomy. 2023. Vol. 13. No. 11. P. 2743.
8. Hunt E., Doraiswamy P. C., McMurtrey J. E. et al. A visible band index for remote sensing leaf chlorophyll content at the canopy scale // International Journal of Applied Earth Observation and Geoinformation. 2013. Vol. 21. P. 103–112.
9. Li F., Mistele B., Hu Y. et al. Reflectance estimation of canopy nitrogen content in winter wheat using optimised hyperspectral spectral indices and partial least squares regression // European Journal of Agronomy. 2014. Vol. 52. P. 198–209.
10. Li X. et al. A Comprehensive Review of Crop Chlorophyll Mapping Using Remote Sensing Approaches: Achievements, Limitations, and Future Perspectives // Sensors. 2025. Vol. 25. No. 8. P. 2345.
11. Lu N. et al. An assessment of multi-view spectral information from UAV-based color-infrared images for improved estimation of nitrogen nutrition status in winter wheat // Precision Agriculture. 2022. Vol. 23. No. 5. P. 1653–1674.
12. Mahajan G.R., Pandey R.N., Datta S.C. et al. Monitoring nitrogen, phosphorus and sulphur in hybrid rice (Oryza sativa L.) using hyperspectral remote sensing // Precision Agriculture. 2017. Vol. 18. No. 5. P. 736–761. https://doi.org/ 10.1007/s11119-016-9485-2.
13. Radocaj D., Jurisic M., Gasparovic M. The role of remote sensing data and methods in a modern approach to fertilization in precision agriculture // Remote Sensing. 2022. Vol. 14. No. 3. P. 778.
14. Sun Y., Wang B., Zhang Z. Improving leaf area index estimation with chlorophyll insensitive multispectral red-edge vegetation indices // IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2023. Vol. 16. P. 3568–3582.
15. Wang J. et al. Nitrogen Monitoring and Sugar Yield Estimation Analysis of Sugar Beet Based on Multisource and Multi-temporal Remote Sensing Data // Sugar Tech. 2025. Vol. 27. No. 4. P. 1089–1101.
16. Xing X., Dong S., Guo M. et al. Optimizing Nitrogen Application Enhances Sugar Beet (Beta vulgaris L.) Productivity by Modulating Carbon and Nitrogen Metabolism // Agronomy. 2025. Vol. 15. No. 1142.
Исследование выполнено за счет гранта Российского научного фонда № 25-16-20094, https://rscf.ru/project/25-16-20094/. Материалы, представленные в статье, получены в рамках реализации программы развития ФГБОУ ВО Башкирский ГАУ программы стратегического академического лидерства «Приоритет-2030»
