Title: A global reference database of crowdsourced cropland data collected using the Geo-Wiki platform
Authors: LASO-BAYAS JUAN CARLOSLESIV MYROSLAVAWALDNER FRANÇOISSCHUCKNECHT ANNEDUERAUER MARTINASEE LINDAFRITZ STEFFENFRAISL DILEKMOORTHY INIANMCCALLUM IANPERGER CHRISTOPHDANYLO OLHADEFOURNY PIERREGALLEGO PINILLA FRANCISCOGILLIAMS SVENAKHTAR IBRAR UL HASSANBAISHYA SWARUP JYOTIBARUAH MRINALBUNGNAMEI KHANSEMBOUCAMPOS ALFREDO N.CHANGKAKATI TRISHNACIPRIANI ANNADAS KRISHNADAS KEEMEEDAS INAMANIDAVIS KYLE FRANKELHAZARIKA PURABIJOHNSON BRIAN ALANMALEK ZIGAMOLINARI MONIA ELISAPANGING KRIPALPAWE CHANDRA KANTPEREZ HOYOS ANASAHARIAH PARAG KUMARSAHARIAH DHRUBAJYOTISAIKIA ANUPSAIKIA MEGHNASCHLESINGER PETERSEIDACARU ELENASINGHA KULESWARWILSON JOHN
Citation: SCIENTIFIC DATA vol. 4 p. 170136
Publisher: NATURE PUBLISHING GROUP
Publication Year: 2017
JRC N°: JRC108154
ISSN: 2052-4463
URI: https://www.nature.com/articles/sdata2017136
http://publications.jrc.ec.europa.eu/repository/handle/JRC108154
DOI: 10.1038/sdata.2017.136
Type: Articles in periodicals and books
Abstract: A global reference dataset on cropland was collected through a crowdsourcing campaign using the Geo-Wiki crowdsourcing tool. The campaign lasted three weeks, with over 80 participants from around the world reviewing almost 36,000 sample units, focussing on cropland identification. For quality assessment purposes, two additional data sets are provided. The first is a control set of 1793 sample locations validated by students trained in satellite image interpretation. This dataset was used to assess the quality of the crowd as the campaign progressed. The second dataset contains 60 expert validations for additional evaluation of contributions quality. All data sets are split into two parts: the first part shows all areas classified as cropland and the second part shows cropland average per location and user. The results of the cropland validation campaign can be used to validate and compare medium and high resolution cropland maps that have been generated using remote sensing. These can also be used to train classification algorithms for developing new maps of land cover and cropland extent.
JRC Directorate:Sustainable Resources

Files in This Item:
There are no files associated with this item.


Items in repository are protected by copyright, with all rights reserved, unless otherwise indicated.