<> "The repository administrator has not yet configured an RDF license."^^ . <> . . . "Crop type identification and spatial mapping using Sentinel-2 satellite data with focus on field-level information"^^ . "Accurate monitoring of croplands helps in making decisions (for\r\ninsurance claims, crop management and contingency plans) at\r\nthe macro-level, especially in drylands where variability in cropping\r\nis very high owing to erratic weather conditions. Dryland\r\ncereals and grain legumes are key to ensuring the food and nutritional\r\nsecurity of a large number of vulnerable populations living\r\nin the drylands. Reliable information on area cultivated to such\r\ncrops forms part of the national accounting of food production\r\nand supply in many Asian countries, many of which are employing\r\nremote sensing tools to improve the accuracy of assessments\r\nof cultivated areas. This paper assesses the capabilities and limitations\r\nof mapping cultivated areas in the Rabi (winter) season and\r\ncorresponding cropping patterns in three districts characterized\r\nby small-plot agriculture. The study used Sentinel-2 Normalized\r\nDifference Vegetation Index (NDVI) 15-day time-series at 10m\r\nresolution by employing a Spectral Matching Technique (SMT)\r\napproach. The use of SMT is based on the well-studied relationship\r\nbetween temporal NDVI signatures and crop phenology. The\r\nrabi season in India, dominated by non-rainy days, is best suited\r\nfor the application of this method, as persistent cloud cover will\r\nhamper the availability of images necessary to generate clearly\r\ndifferentiating temporal signatures. Our study showed that the\r\ntemporal signatures of wheat, chickpea and mustard are easily\r\ndistinguishable, enabling an overall accuracy of 84%, with wheat\r\nand mustard achieving 86% and 94% accuracies, respectively. The\r\nmost significant misclassifications were in irrigated areas for mustard\r\nand wheat, in small-plot mustard fields covered by trees and\r\nin fragmented chickpea areas. A comparison of district-wise\r\nnational crop statistics and those obtained from this study\r\nrevealed a correlation of 96%."^^ . "2020-08" . . . . "Taylor and Francis"^^ . . . "Geocarto International (TSI)"^^ . . . "10106049" . . . . . . . . . . . . . . . . . . . . . . . . . "M K"^^ . "Gumma"^^ . "M K Gumma"^^ . . "R N"^^ . "Kolli"^^ . "R N Kolli"^^ . . "F"^^ . "Holecz"^^ . "F Holecz"^^ . . "F"^^ . "Collivignarelli"^^ . "F Collivignarelli"^^ . . "K"^^ . "Tummala"^^ . "K Tummala"^^ . . "A M"^^ . "Whitbread"^^ . "A M Whitbread"^^ . . "S"^^ . "Dixit"^^ . "S Dixit"^^ . . . . . . "Crop type identification and spatial mapping using Sentinel-2 satellite data with focus on field-level information (PDF)"^^ . . . . . "07_Crop type identification with focus on field level information.pdf"^^ . . . "Crop type identification and spatial mapping using Sentinel-2 satellite data with focus on field-level information (Other)"^^ . . . . . . "indexcodes.txt"^^ . . "HTML Summary of #11558 \n\nCrop type identification and spatial mapping using Sentinel-2 satellite data with focus on field-level information\n\n" . "text/html" . . . "GIS Techniques/Remote Sensing"@en . .