Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2017, Vol. 14, No. 7, pp. 89-99
Application of discriminant analysis for recognition agricultural crops
1 Belgorod State National Research University, Belgorod, Russia
Accepted: 19.07.2017
DOI: 10.21046/2070-7401-2017-14-7-89-99
Automated recognition of agricultural crops is one of key problems in monitoring of arable lands. This paper presents the results of stepwise discriminant analysis employed to recognize crops typical of the Belgorod Oblast and Central Black Earth Region: winter wheat, barley, soybean, corn, sunflower, sugar beet, oat and perennial grasses. Experimental data were received from 1033 sowing areas. Spectral parameters of crops were calculated using MOD09Q1 and MOD13Q1 data. Efficiency of crops recognition was analyzed for the time series of reflectance in the red (620-670 nm) and near infrared (841-876 nm) bands and NDVI vegetation index. The use of discriminant analysis made it possible to assess the utility of the seasonal values of spectral parameters for identification of crops types. The values of all spectral reflection parameters of the middle of July or its second half contribute the most to the distinction of the crops. The highest total crops recognition accuracy (about 85%) was established for near infrared reflectance (841-876 nm). The highest accuracy of interpretation was established for winter cereals (96%). The recognition of perennial grasses and oats is the most problematic. The possibility of using discriminant analysis in geoinformation mapping of the crops was shown.
Keywords: vegetation cover, sown areas, stepwise discriminant analysis, vegetation indices, spectral reflectance, NDVI, remote sensing
Full textReferences:
- Bartalev S.A., Loupian E.A., Neishtadt I.A., Savin I.Yu., Klassifikatsiya nekotorykh tipov sel’skokhozyaistvennykh posevov v yuzhnykh regionakh Rossii po sputnikovym dannym MODIS (Gropland Area Classification in South Regions of Russia Using MODIS Satellite Data), Issledovanie Zemli iz kosmosa, 2006, No. 3, pp. 68–75.
- Bartalev S.A., Egorov V.A., Loupian E.A., Plotnikov D.E., Uvarov I.A., Raspoznavanie pakhotnykh zemel’ na osnove mnogoletnikh sputnikovykh dannykh spektroradiometra MODIS i lokal’no-adaptivnoi klassifikatsii (Recognition of arable lands using multi-annual satellite data from spectroradiometer MODIS and locally adaptive supervised classification), Komp’yuternaya optika, 2011, Vol. 35. No. 1, pp. 103–116.
- Kuz’menko Ya.V., Lisetskii F.N., Pichura V.I., Otsenka i prognozirovanie stoka malykh rek v usloviyakh antropogennykh vozdeistvii i izmenenii klimata (Evaluation and prediction of small rivers flow in condition of anthropogenic impacts and climate change), Sovremennye problemy nauki i obrazovaniya, 2012, No. 6, pp. 619–627.
- Loupian E.A., Bartalev S.A., Tolpin V.A., Zharko V.O., Krasheninnikova Yu.S., Oksyukevich A.Yu., Ispol’zovanie sputnikovogo servisa VEGA v regional’nykh sistemakh distantsionnogo monitoring (VEGA satellite service applications in regional remote monitoring systems), Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2014, Vol. 11, No. 3, pp. 215–232.
- Medvedeva M.A., Savin I.Yu., Bartalev S.A., Loupian E.A., Ispol’zovanie dannykh NOAA-AVHRR dlya vyyavleniya mnogoletnei dinamiki rastitel’nosti severnoi Evrazii (Usage of NOAA-AVHRR Data for Detection of Vegetation Dynamics in Northern Eurasia), Issledovanie Zemli iz kosmosa, 2011, No. 4, pp. 55–62.
- Plotnikov D.E., Bartalev S.A., Zharko V.O., Mikhailov V.V., Prosyannikova O.I., Eksperimental’naya otsenka raspoznavaemosti agrokul’tur po dannym sezonnykh sputnikovykh izmerenii spektral’noi yarkosti (An experimental assessment of crop types recognisability using time-series of intra-seasonal spectral reflectance measurements by satellite sensor), Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2011, Vol. 8, No. 1, pp. 199–208.
- Povkh V.I., Shlyakhova L.A., Boeva I.N., Otsenka struktury posevnykh ploshchadei sel’skokhozyaistvennykh kul’tur po sputnikovoi informatsii vysokogo razresheniya (Assessment of the structure of agricultural crop areas using high resolution satellite data), Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2013, Vol. 10, No. 4, pp. 224–228.
- Popov S.Yu. Opyt sozdaniya geobotanicheskoi karty metodom diskriminantnogo analiza polevykh i distantsionnykh dannykh (Experience of creating a geobotanical map using discriminant analysis of field vegetation description and remote sensing data), Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2016, Vol. 1, No. 1, pp. 25–35.
- Terekhin E.A., Analiz mnogoletnei dinamiki vegetatsionnogo indeksa dlya posevnykh ploshchadei (Analysis of vegetation index long-term dynamics for crop areas), Sovremennye problemy distantsionnogo zondirovaniya Zemli iz kosmosa, 2015, Vol. 12, No. 6, pp. 48–58.
- Khalafyan A.A. STATISTICA 6. Statisticheskii analiz dannykh (STATISTICA 6. Statistical analysis), Moscow: Binom-Press, 2007, 512 p.
- Atzberger C., Rembold F., Mapping the spatial distribution of winter crops at sub-pixel level using AVHRR NDVI time series and neural nets, Remote Sensing, 2013, Vol. 5, No. 3, pp. 1335–1354.
- Bartalev S.A., Plotnikov D.E., Loupian E.A., Mapping of arable land in Russia using multi-year time series of MODIS data and the LAGMA classification technique, Remote Sensing Letters, 2016, Vol. 7, No. 3, pp. 269–278.
- Li Z., Huffman T., McConkey B., Townley-Smith L., Monitoring and modeling spatial and temporal patterns of grassland dynamics using time-series MODIS NDVI with climate and stocking data, Remote Sensing of Environment, 2013, Vol. 138, pp. 232–244.
- Son N.T., Chen C.F., Chen C.R., Minh V.Q., Trung N.H., A comparative analysis of multitemporal MODIS EVI and NDVI data for large-scale rice yield estimation, Agricultural and Forest Meteorology, 2014, Vol. 197, pp. 52–64.
- Zhou J., Jia L., Menenti M., Reconstruction of global MODIS NDVI time series: performance of harmonic analysis of time series (hants), Remote Sensing of Environment, 2015, Vol. 163, pp. 217–228.