Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2019, Vol. 16, No. 6, pp. 194-198
Assessment of soybean yield in the Far East using regression models based on remote sensing data
A.S. Stepanov
1 , S.V. Makogonov
1, 2 , V.A. Tolpin
3 1 Far Eastern Research Institute of Agriculture, Vostochny-1, Khabarovsk Territory, Russia
2 Computer Centre FEB RAS, Khabarovsk, Russia
3 Space Research Institute RAS, Moscow, Russia
Accepted: 06.09.2019
DOI: 10.21046/2070-7401-2019-16-6-194-198
Soybean is the main cultivated crop in the structure of agriculture in the Far Eastern regions of Russia. From a practical point of view, within the framework of the implementation of the state strategy for the development of the agro-industrial complex, the issue of forecasting crop yields, including soybeans, which is widely spread in the regions of the Far Eastern Federal District (FEFD), is of particular importance. As part of the work performed, regression models for estimating the yield of soybean were constructed, their accuracy was assessed and forecast deviations calculated. The study used data on acreage and gross soybean harvest at the regional level in the period from 2007 to 2018. The indicators included in the regression model reflected both satellite and meteorological information for these regions. The major soybean cultivation areas were selected for modeling in each subject of the Russian Federation. As independent variables, it was proposed to use the maximum NDVI value among the 7-day composites of the NDVI index for the calendar year, calculated using a mask of arable land, as well as integrated indicators calculated using meteorological data: hydrothermal coefficient and climate biological efficiency index. The analysis performed to assess the accuracy of the models showed that the regression model was the most accurate for the time series that was previously cleared of the influence of the long-term trend: the average model deviation for the Amur Region was 8.1±2.4 %, Primorsky Krai ― 9.5±3.9 %, Khabarovsk Krai ― 8.3±2.6 %, Jewish Autonomous Oblast ― 10.2±3.1 %. In practice, to solve the problem of forecasting the yield of the current year, it is more convenient to apply the regression model, where the maximum value of the NDVI index is used as one of the dependent variables. The soybean yield forecast for 2018 according to 2007–2017 data showed a deviation from the actual yield in the range of 2.1–7.3 % for different subjects of FEFD. In general, the proposed models with the stated level of accuracy can be used to predict the yield of soybeans, as well as to make management decisions both at the level of regional ministries and individual agro-industrial enterprises.
Keywords: soybean, yield, Far East, agriculture, regression model, remote sensing, NDVI
Full textReferences:
- Aseeva T. A., Terekhova M. V., Ratsional’nye priemy ispol’zovaniya sel’skokhozyaistvennykh zemel’ v Khabarovskom krae pri vozdelyvanii soi (Rational use of agricultural land in the Khabarovsk region in the cultivation of soybeans), Dal’nii Vostok: problemy razvitiya arkhitekturno-stroitel’nogo kompleksa, 2016, No. 1, pp. 168–171.
- Zaitsev N. I., Bochkarev N. I., Zelentsov S. V., Perspektivy i napravleniya selektsii soi v Rossii v usloviyakh realizatsii natsional’noi strategii importozameshcheniya (Prospects and directions of soybean breeding in Russia in the context of the implementation of the national strategy of import substitution), Maslichnye kul’tury. Nauchno-tekhnicheskii byulleten’ VNIIMK (Scientific and Technical Bulletin VNIIMK), 2016, No. 2(166), pp. 3–11.
- Kussul N. N., Kravchenko A. N., Skakun S. V., Adamenko T. I., Shelestov A. Yu., Kolotii A. V., Gripich Yu. A., Regressionnye modeli otsenki urozhainosti sel’skokhozyaistvennykh kul’tur po dannym MODIS (Crop Yield Forecasting Regression Models based on MODIS Data), Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa , 2012, Vol. 9, No. 1, pp. 95–107.
- Loupian E. A., Proshin A. A., Burtsev M. A., Balashov I. V., Bartalev S. A., Efremov V. Yu., Kashnitskii A. V., Mazurov A. A., Matveev A. M., Sudneva O. A., Sychugov I. G., Tolpin V. A., Uvarov I. A., Tsentr kollektivnogo pol’zovaniya sistemami arkhivatsii, obrabotki i analiza sputnikovykh dannykh IKI RAN dlya resheniya zadach izucheniya i monitoringa okruzhayushchei sredy (The center for collective use of systems for archiving, processing and analyzing satellite data of the IKI RAS for solving problems of studying and monitoring the environment), Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2015, Vol. 12, No. 5, pp. 247–267.
- Perevedentsev Yu. P., Sharipova R. B., Vazhnova N. A., Agroklimaticheskie resursy Ul’yanovskoi oblasti i ikh vliyanie na urozhainost’ zernovykh kul’tur (Agroclimatic resources of the Ulyanovsk region and their impact on the yield of grain crops), Vestnik Udmurtskogo universiteta. Ser.: Biologiya. Nauki o zemle, 2012, No. 2, pp. 120–126.
- Regiony Rossii. Sotsial’no-ekonomicheskie pokazateli. 2018 (Regions of Russia. Socio-economic indicators. 2018), Moscow: Rosstat, 2018, 1162 p.
- Strashnaya A. I., Tarasova L. L., Bogomolova N. A., Maksimenkova T. A., Bereza O. V., Prognozirovanie urozhainosti zernovykh i zernobobovykh kul’tur v tsentral’nykh chernozemnykh oblastyakh na osnove kompleksirovaniya nazemnykh i sputnikovykh dannykh (Predicting the yield of grain and leguminous crops in the central black earth regions based on the integration of ground-based and satellite data), Trudy Gidrometeorologicheskogo nauchno-issledovatel’skogo tsentra Rossiiskoi Federatsii , 2015, No. 353, pp. 128–153.
- Tolpin V. A., Loupian E. A., Bartalev S. A., Plotnikov D. E., Matveev A. M., Vozmozhnosti analiza sostoyaniya sel’skokhozyaistvennoi rastitel’nosti s ispol’zovaniem sputnikovogo servisa “VEGA” (Opportunities for analyzing the state of agricultural vegetation using the VEGA satellite service), Optika atmosfery i okeana , 2014, Vol. 27, No. 7(306), pp. 581–586.
- Sorokin A. A., Makogonov S. I., Korolev S. P., The Information Infrastructure for Collective Scientific Work in the Far East of Russia, Scientific and Technical Information Processing, 2017, Vol. 44, No. 4, pp. 302–304.