Sunflower yield structure at differentiated sowing

The article examines and proposes an automated method for determining the structure and yield of sunflower, which allows predicting yields and offering recommendations for optimizing the placement of crops depending on the potential of fields. The main objectives of the study included the development and implementation of innovative steppe agriculture aimed at ensuring the productivity of agricultural lands in accordance with their biopotential. The technology of differentiated seed sowing and mineral fertilizer application was tested for 3 years (from 2022 to 2024) on experimental fields in two farms of the Altai Territory using different tillage systems (classical flat-cutting and No-till system). The farms are located in the Prialeiskaya soil-climatic zone. It has been established that one of the main indicators determining the level of soil fertility diversity is the spatial differentiation of the humus content and basic nutrition elements. Algorithms for the allocation of soil fertility zones subject to differentiation of seed and mineral fertilizer rates have been developed with regional specificity. In the farm working under the No-till system, there is a higher organic matter content of the experimental field (4.0%). At classical flat-cuting tillage the humus content is noted at the level of 3.5%. It has been found that the higher the humus content, the higher the level of soil fertility. Automated methods of recognizing and counting the number of sunflower sprouts, as well as building the maps of weed vegetation using RGB images of ultra-high spatial resolution obtained by an unmanned aerial vehicle have been proposed and investigated. It has been identified that when choosing rational ratios of the seeding rate and fertilizer application doses by zones of soil fertility of the field, their joint influence on the field germination of plants and the number of sprouts obtained should be taken into account.

1. Shpanev A.M., Smuk V.V. Effectiveness of differentiated application of herbicides in winter wheat crops. Rossiyskaya sel’skokhozyaistvennaya nauka = Russian Agricultural Sciences, 2020, no. 4, pp. 25–27. (In Russian).

2. Byshov N.V., Oleinik D.O., Bogdanchikov I.Yu., Bachurin A.N., Lipatov N.V. Application of geoinformation systems and differentiated distribution of seeds and fertilizers in sowing winter wheat. Vestnik Ryazanskogo gosudarstvennogo agrotekhnologicheskogo universiteta imeni P.A. Kostycheva = Herald of Ryazan State Agrotechnological University named after P.A. Kostychev, 2020, no. 4 (48), pp. 92–97. (In Russian).

3. Shpanev A.M., Smuk V.V., Fesenko M.A. Differentiated application of herbicides in the conditions of the North-West of Russia. Zashchita i karantin rasteniy = Plant Protection and Quarantine, 2021, no. 6, pp. 17–20. (In Russian).

4. Strygin S.P., Khairullina S.G., Tulegenov K.K. Application of a precision farming system in soya cultivation. Science and Education, 2023, no. 4-2 (73), pp. 186–194.

5. Shapovalov D.A., Koroleva P.V., Kalinina N.V., Vilchevskaya E.V., Kulyanitsa A.L., Rukhovich D.I. ASF-INDEX – a map of stable intra-field heterogeneity of soil cover fertility based on large satellite data. Zemel’nye otnosheniya i zemleustroystvo = Land relations and Land Management, 2020, no. 1, pp. 9–15. (In Russian).

6. Ovcharova N.V., Silantieva M.M., Bеlyaev V.I., Gulyanov Yu.A., Sokolova L.V., Plutalova T.G., Botvich I.Yu., Emelyanov D.V., Belov N.P. Identification of fertility zones and assessment of potential crop yield based on biological farming approaches. Acta Biologica Sibirica, 2023, vol. 9, pp. 1083–1107. DOI: 10.5281/zenodo.10255212.

7. Xu B., Fan J., Chao J., Arsenijevic N., Werle R., Zhang Z. Instance segmentation method for weed detection using UAV imagery in soybean fields. Computers and Electronics in Agriculture, 2023, no. 211 (3), p. 107994. DOI: 10.1016/j.compag.2023.107994.

8. Fawakherji M., Potena C., Pretto A., Bloisi D., Nardi D. Multi-Spectral Image Synthesis for Crop/Weed Segmentation in Precision Farming. Robotics and Autonomous Systems, 2021, no. 146 (1), p. 103861.

9. Sahin H.M., Miftahushudur T., Grieve B., Yin H. Segmentation of weeds and crops using multispectral imaging and CRF-enhanced U-Net. Computers and Electronics in Agriculture, 2023, p. 211.

10. Gao M., Yang F., Wei H., Liu X. Automatic Monitoring of Maize Seedling Growth Using Unmanned Aerial Vehicle-Based RGB Imagery. Remote Sens, 2023, vol. 15, p. 3671.

11. Wang B., Zhou J., Costa M., Kaeppler S.M., Zhang Z. Plot-Level Maize Early Stage Stand Counting and Spacing Detection Using Advanced Deep Learning Algorithms Based on UAV Imagery. Agronomy, 2023, vol. 13, p. 1728.

12. Yang T., Zhu S., Zhang W., Zhao Y., Song X., Yang G., Yao Z., Wu W., Liu T., Sun C. Unmanned Aerial Vehicle-Scale Weed Segmentation Method Based on Image Analysis Technology for Enhanced Accuracy of Maize Seedling Counting. Agriculture, 2024, vol. 14, p. 175.

13. Danilevicz M.F., Bayer P.E., Boussaid F., Bennamoun M., Edwards D. Maize Yield Prediction at an Early Developmental Stage Using Multispectral Images and Genotype Data for Preliminary Hybrid Selection. Remote Sens, 2021, vol. 13, p. 3976.

14. Stepanov A.S., Dubrovin K.N., Verkhoturov A.L., Selezneva N.A., Sunyakin A.A. Prospects of using optical and radar images to monitor crop rotations in the Khabarovsk Territory. Dostizheniya nauki i tekhniki APK = Achievements of Science and Technology of AIC, 2021, vol. 35, no. 12, pp. 23–28. (In Russian).

15. Kurbanov R.K., Zakharova N.I., Zakharova O.M., Gorshkov D.M. Assessment of seedlings breeding winter wheat after overwintering using UAVS. Innovatsii v sel’skom khozyaistve = Innovations in Agriculture, 2019, no. 3 (32), pp. 133–139. (In Russian).

16. Pisman T.I., Shevyrnogov A.P., Larkov A.A., Botvich I.Yu., Yemelyanov D.V., Shpedt A.A., Trubnikov Yu.N. The information content of spectral vegetation indices for interpretation of the satellite images of agricultural fields. Biofizika = Biophysics, 2019, no. 4, pp. 740–746. (In Russian).

17. Alt V.V., Pestunov I.A., Melnikov P.V., Elkin O.V. Automated detection of weeds and evaluation of crop sprouts quality based on RGB images. Sibirskii vestnik sel’skokhozyaistvennoi nauki = Siberian Herald of Agricultural Science, 2018, vol. 48, no. 5, pp. 52–60. (In Russian).