THE METHOD OF FORECASTING YIELDS ON THE BASIS OF REMOTE SENSING DATA OF HIGH RESOLUTION ON THE EXAMPLE OF WHEAT HAS BEEN SUGGESTED
DOI:
https://doi.org/10.33730/2310-4678.2.2020.208824Keywords:
SlantRange, Stress index, UAVAbstract
Developed a method of interpreting the results of remote monitoring in the form of values of vegetation (stress) indices in the expected yields has been developed. The studies were carried out in 2019 in the Kiev region at the production site of winter wheat crops in the separate division of the National Research and Training Institute of Ukraine “Agronomic Experimental Station”. Remote monitoring was performed on 06/25/2019 using the SlantRange 3p multispectral sensor complex mounted on a UAV. The flight altitude was 100 m. Both standard indices such as the NDVI and Chlorophyll index variations as well as the stresses of own production proposed by Slantrange were calculated: Stress, Vegetation fraction, Yield potential. Separately, we examined the output directly from the spectral channels, which were obtained from a wreath of images of SlantView’s proprietary software. The calculations were performed in MathCad software, where the image was considered in the form of a matrix. Harvest accounting was carried out using John Deere combines, which monitored every second with the establishment of positioning by satellite navigation system. False results were removed from the results of ground monitoring due to errors in the sensor equipment, incomplete use of the header width. It was found that a comparison of the yield of winter wheat and the conditions of these plants 2 months before the indicated procedure according to the results of spectral analysis using UAVs made it possible to establish a relationship between the quantitative characteristics of yield and divisions of stress indices. Of the indices studied, the best result of a linear approximation of the experimental dependence with a determination coefficient of 0.845 between yield and the numerical value of the spectral characteristic was shown by the Stress index developed by SlantRange. The best sensitivity was obtained using the Vegetation index. Fraction, also proposed by SlantRange, making it also promising for crop forecasting.
References
Pallottino, F. (2019). Optoelectronic proximal sensing vehicle-mounted technologies in precision agriculture: A review Pallottino, F., Antonucci, F., Costa, C. et. al. Computers and Electronics in Agriculture. Vol. 162. Pр. 859–873 [In English].
Lai, Y.R. (2018). An empirical model for prediction of wheat yield, using time-integrated Landsat NDVI. Pringle, M.J., Kopittke, P.M. International Journal of Applied Earth Observation and Geoinformation. Vol. 72. Pр. 99–108 [In English].
Bai, G. (2016). A multi-sensor system for high throughput field phenotyping in soybean and wheat breeding. Ge, Y., Hussain, W. et. al. Computers and Electronics in Agriculture. Vol. 128. Pр. 181–192 [In English].
Zatserkovnyi, V.I. (2019). Monitoring surface water status using an integrated indicator. Plichko, L.V., Malik, T.M. et. al. 13th International Conference on Monitoring of Geological Processes and Ecological Condition of the Environment. Taras Schevchenko National University of Kyiv (12 November 2019). DOI: 10.3997/2214-4609.201903239. [In Ukrainian].
Saberioona, M.M. (2014). Assessment of rice leaf chlorophyll content using visible bands atdifferent growth stages at both the leaf and canopy scale // Amina, M.S.M., Anuarb, A.R. et. al. International Journal of Applied Earth Observation and Geoinformation. Vol.32. Pр. 35–45 [In English].
Lysenko, V. (2017). Usage of Flying Robots for Monitoring Nitrogen in Wheat Crops. Opryshko, O., Komarchuk, D. et. al. The 9th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications. Vol.1. Pp. 30–34 [In Ukrainian].
Korobiichuk, I. (2018). Crop monitoring for nitrogen nutrition level by digital camera. Lysenko, V., Opryshko, O., et. al. Automation 2018. Advances in Intelligent Systems and Computing. Vol. 743. Springer, Cham. Pp. 595–603 [In Ukrainian].
Talavera, J.M. (2017). Review of IoT applications in agro-industrial and environmental fields. Tobón, L. E., Gómez, J.A. et. al. Computers and Electronics in Agriculture. Vol.142 (A). Pр. 283–297 [In English].
Shvorov, S.A. (2018). UAV Navigation and Management System Based on the Spectral Portrait of Terrain. Komarchuk, D.S., Pasichnyk, N.A. et. al. 2018 IEEE 5th International Conference on Methods and Systems of Navigation and Motion Control. MSNMC 2018 — Proceedings. Pp. 68–71 [In Ukrainian].
Pasichnyk, N.A. (2019). Experience in using mathcad to analyze data from UAVS for remote sensing of crops. Opryshko, O.O., Komarchuk, D.S. et. al. Scientific Bulletin of NULES of Ukraine. Series: Agronomy. Pр. 244–250 [In Ukrainian].
Downloads
Published
Issue
Section
License
- The authors reserve the right to authorship their work and pass the journal the right to publish this work under a Creative Commons Attribution License license, which allows other persons to freely distribute the published work with the obligatory The authors of the original work and the first publication of this magazine.
- The authors have the right to make independent additional agreements on the nonexclusive dissemination of the work in the form in which it was published by this magazine (for example, to post work in the company's electronic storage or to publish as a monograph) , subject to the first publication of the link to this journal.
- Journal policy allows and encourages the placement of authors on the Internet (for example, in the repositories of institutions or on personal websites) manuscript work as to the presentation of this manuscript to the editorial board and during its editorial processing, as it contributes to The productive scientific discussion and positively affects the efficiency and dynamics of citation published work (see The Effect of Open Access).
