03460naa a2200253 a 450000100080000000500110000800800410001902400390006010000150009924501090011426000090022350006250023252020480085765000120290565300210291765300310293865300120296965300190298165300220300065300100302265300230303270000160305577301350307110642542023-07-14       2016    bl uuuu     u00u1 u    #d7 a10.1080/2150704X.2016.12524712DOI1 aLESSEL, J.  aCreating a basic customizable framework for crop detection using Landsat imagery.h[electronic resource]  c2016  aArticle history: Received 06 May 2016, Accepted 15 Oct 2016, Published online: 14 Nov 2016. -- Correspondence author:   Lessel, J.; The International Research Institute for Climate and Society, The Earth Institute, Columbia University, Lamont Campus, 61 Route 9W, Monell Building, Palisades, NY, United States; email:jlessel@iri.columbia.edu  -- Acknowledgements: The authors thanks Walter Baethgen and Guadalupe Tiscornia for all their guidance and valuable conversations. We would also wish to give a special thanks to INIA for providing the 2013-2014 proposed crop plan and the verified partial crop location maps. --  aRemotely sensed crop identification is essential for countries whose economic vitality is closely tied to agriculture, such as Uruguay. It has been shown that using Normalized Difference Vegetation Index (NDVI) can sometimes produce spurious results when classifying land cover in certain environments. Furthermore, many current crop identification tools use NDVI in order to study and identify crop land-cover for classification techniques. In this study, we present the basic framework for a semi-automated crop identification methodology, which uses a time series analysis to identify soil and vegetation patterns for various crop-cycle scenarios by using the pixel Hue values for land cover identification, at high (30 m) spatial resolution. This is accomplished by converting the Red-Green-Blue (RGB) colour space of a shortwave infrared (SWIR), near-infrared, and red channel composite images, into a Hue-Saturation-Value colour space, then extracting the Hue pixel values that correspond to soil and vegetation over a series of images. We then combine the soil and vegetation pixels in order to create a ?time series? to identify which pixels match different crop-cycle scenarios and isolate them. The shapes are then further isolated to only include those that fit a specific shape area (>20 ha), in order to eliminate spurious results. Our results show an 80% accuracy score between the crop identification methodology and a proposed crop plan over the years 2013-2014 and probabilities of detection of 0.76, 0.89, and 0.88 for the seasons of 2009-2010, 2010-2011, and 2011-2012 respectively, when compared to verified partial crop location maps. The proposed crop plan and the partial crop location maps were provided to us by the Instituto Nacional de Investigación Agropecuaria (INIA) in Uruguay. We also quantitatively investigated the shortcomings of the crop identification methodology, which mostly came from cloud cover and low temporal resolution of the images. © 2016 Informa UK Limited, trading as Taylor & Francis Group.  aURUGUAY  aImage processing  aLand cover identifications  aLandsat  aRemote sensing  aSatellite imagery  aSOILS  aSpatial resolution1 aCECCATO, P.  tInternational Journal of Remote Sensing. 2016, Volume 37, Issue 24, Pages 6097-6107. https://doi.org/10.1080/2150704X.2016.1252471