The research is aimed at monitoring the state of crops and their possible loss using remote sensing and artificial intelligence tools. Using these tools in the research process, the following results were achieved: the boundaries of agricultural land arrays were determined; identified boundaries of crops and their areas under individual agricultural crops by vegetation phase; analysed volumes of cultivated areas, their structure in a territorial section. It is proved, that using both Sentinel-1 and Sentinel-2 satelite images data give more accurate results. Crop porofiles are proven to be the key to improving the quality of crop classification results, as they allow algorithms to better distinguish between crops.
Yang C., Everitt J.H., Murden D. [2011] Evaluating high resolution SPOT 5 satellite imagery for crop identification. Computers and Electronics in Agriculture. Volume 75. Issue 2. 347-354 pp. doi: https://doi.org/10.1016/j.compag.2010.12.012.
Peña J.M., Gutiérrez P.A., Hervás-Martínez C., Six J., Plant R.E., López-Granados F. [2014] Object-Based Image Classification of Summer Crops with Machine Learning Methods. Remote Sensing. 6. 5019-5041 pp. doi: https://doi.org/10.3390/rs6065019.
Kussul N., Lavreniuk M., Skakun S. and Shelestov A. [2017] Deep Learning Classification of Land Cover and Crop Types Using Remote Sensing Data. IEEE Geoscience and Remote Sensing Letters. Vol. 14. no. 5. 778-782 pp. doi: 10.1109/LGRS.2017.2681128.
Kussul N., Lavreniuk M., Shelestov A. and Skakun S. [2018] Crop inventory at regional scale in Ukraine: developing in season and end of season crop maps with multi-temporal optical and SAR satellite imagery. European Journal of Remote Sensing. 51:1. 627-636 pp. doi: 10.1080/22797254.2018.1454265.