Mapping croplands of Europe, Middle East, Russia, and Central Asia using Landsat, Random Forest, and Google Earth Engine

Abstract Accurate and timely information on croplands is important for environmental, food security, and policy studies. Spatially explicit cropland datasets are also required to derive information on crop type, crop yield, cropping intensity, as well as irrigated areas. Large area – defined as continental to global – cropland mapping is challenging due to differential manifestation of croplands, wide range of cultivation practices and limited reference data availability. This study presents the results of a cropland extent mapping of 64 countries covering large parts of Europe, Middle East, Russia and Central Asia. To cover such a vast area, roughly 160,000 Landsat scenes from 3351 footprints between 2014 and 2016 were processed within the Google Earth Engine (GEE) platform. We used a pixel-based Random Forest (RF) machine learning algorithm with a set of satellite data inputs capturing diverse spectral, temporal and topographical characteristics across twelve agroecological zones (AEZs). The reference data to train the classification model were collected from very high spatial resolution imagery (VHRI) and ancillary datasets. The result is a binary map showing cultivated/non-cultivated areas ca. 2015. The map produced an overall accuracy of 93.8% with roughly 14% omission and commission errors for the cropland class based on a large set of independent validation samples. The map suggests the entire study area has a total 546 million hectares (Mha) of net croplands (nearly 30% of global net cropland areas) occupying 18% of the study land area. Comparison between national cropland area estimates from United Nations Food and Agricultural Organizations (FAO) and those derived from this work also showed an R-square value of 0.95. This Landsat-derived 30-m cropland product (GFSAD30) provided 10–30% greater cropland areas compared to UN FAO in the 64 Countries. Finally, the map-to-map comparison between GFSAD30 with several other cropland products revealed that the best similarity matrix was with the 30 m global land cover (GLC30) product providing an overall similarity of 88.8% (Kappa 0.7) with producer’s cropland similarity of 89.2% (errors of omissions = 10.8%) and user’s cropland similarity of 81.8% (errors of commissions = 8.1%). GFSAD30 captured the missing croplands in GLC30 product around significantly irrigated agricultural areas in Germany and Belgium and rainfed agriculture in Italy. This study also established that the real strengths of GFSAD30 product, compared to other products, were: 1. identifying precise location of croplands, and 2. capturing fragmented croplands. The cropland extent map dataset is available through NASA’s Land Processes Distributed Active Archive Center (LP DAAC) at https://doi.org/10.5067/MEaSUREs/GFSAD/GFSAD30EUCEARUMECE.001 , while the training and reference data as well as visualization are available at the Global Croplands https://croplands.org > website, GEE code is accessible at: https://code.earthengine.google.com/1666e8bed34e0ce2b2aaf1235ad8c6bd .

[1]  J. Mueller,et al.  War, presidents, and public opinion , 1973 .

[2]  Ronald J. Hall,et al.  Operational mapping of the land cover of the forested area of Canada with Landsat data: EOSD land cover program , 2003 .

[3]  William B. Meyer,et al.  HUMAN POPULATION GROWTH AND GLOBAL LAND-USE/COVER CHANGE , 1992 .

[4]  Russell G. Congalton,et al.  Assessing the accuracy of remotely sensed data : principles and practices , 1998 .

[5]  V. Radeloff,et al.  Effects of institutional changes on land use: agricultural land abandonment during the transition from state-command to market-driven economies in post-Soviet Eastern Europe , 2012 .

[6]  C. Woodcock,et al.  Resolution dependent errors in remote sensing of cultivated areas , 2006 .

[7]  A. Huete,et al.  A 30-m landsat-derived cropland extent product of Australia and China using random forest machine learning algorithm on Google Earth Engine cloud computing platform , 2018, ISPRS Journal of Photogrammetry and Remote Sensing.

[8]  Onisimo Mutanga,et al.  Land-use/cover classification in a heterogeneous coastal landscape using RapidEye imagery: evaluating the performance of random forest and support vector machines classifiers , 2014 .

[9]  Steffen Fritz,et al.  Improved global cropland data as an essential ingredient for food security , 2015 .

[10]  J. G. Lyon,et al.  Hyperspectral Remote Sensing of Vegetation , 2011 .

[11]  Russell G. Congalton,et al.  Nominal 30-m Cropland Extent Map of Continental Africa by Integrating Pixel-Based and Object-Based Algorithms Using Sentinel-2 and Landsat-8 Data on Google Earth Engine , 2017, Remote. Sens..

[12]  Alan H. Strahler,et al.  Global land cover mapping from MODIS: algorithms and early results , 2002 .

[13]  Russell G. Congalton,et al.  Accuracy Assessment of Global Food Security-Support Analysis Data (GFSAD) Cropland Extent Maps Produced at Three Different Spatial Resolutions , 2018, Remote. Sens..

[14]  R. R. Palmer.  The world of the French Revolution , 1971 .

[15]  T. Benton,et al.  Relationships among multiple aspects of agriculture's environmental impact and productivity: a meta‐analysis to guide sustainable agriculture , 2017, Biological reviews of the Cambridge Philosophical Society.

[16]  Changsheng Li,et al.  Combining remote sensing and ground census data to develop new maps of the distribution of rice agriculture in China , 2002 .

[17]  Laure Latruffe,et al.  Farm Expansion in Lithuania after Accession to the EU: The Role of CAP Payments in Alleviating Potential Credit Constraints , 2010 .

[18]  Mutlu Ozdogan,et al.  A new methodology to map irrigated areas using multi-temporal MODIS and ancillary data: An application example in the continental US , 2008 .

[19]  P. Verburg,et al.  Trajectories of land use change in Europe: a model-based exploration of rural futures , 2010, Landscape Ecology.

[20]  J. Nasr,et al.  Urban Agriculture Food, Jobs and Sustainable Cities , 2001 .

[21]  E. Lambin,et al.  Predicting land-use change , 2001 .

[22]  N. Ramankutty,et al.  Characterizing patterns of global land use: An analysis of global croplands data , 1998 .

[23]  M. S. Moran,et al.  Opportunities and limitations for image-based remote sensing in precision crop management , 1997 .

[24]  G. Fischer,et al.  Socio-economic and climate change impacts on agriculture: an integrated assessment, 1990–2080 , 2005, Philosophical Transactions of the Royal Society B: Biological Sciences.

[25]  P. Rietveld,et al.  Manifestations and underlying drivers of agricultural land use change in Europe , 2015 .

[26]  Prasad S. Thenkabail,et al.  A Global Irrigated Area Map (GIAM) using remote sensing at the end of the last millennium , 2008 .

[27]  P. Hostert,et al.  Post-socialist forest disturbance in the Carpathian border region of Poland, Slovakia, and Ukraine. , 2007, Ecological applications : a publication of the Ecological Society of America.

[28]  V. Radeloff,et al.  Underlying Drivers and Spatial Determinants of post-Soviet Agricultural Land Abandonment in Temperate Eastern Europe , 2017 .

[29]  S. Robinson,et al.  Food Security: The Challenge of Feeding 9 Billion People , 2010, Science.

[30]  Hankui K. Zhang,et al.  Finer resolution observation and monitoring of global land cover: first mapping results with Landsat TM and ETM+ data , 2013 .

[31]  Michael Dixon,et al.  Google Earth Engine: Planetary-scale geospatial analysis for everyone , 2017 .

[32]  Petra Döll,et al.  Global Patterns of Cropland Use Intensity , 2010, Remote Sensing.

[33]  Hui Zhang,et al.  Effect of fusing features from multiple DCNN architectures in image classification , 2018, IET Image Process..

[34]  H. Alphan.  Land‐use change and urbanization of Adana, Turkey , 2003 .

[35]  Volker C. Radeloff,et al.  The effect of Landsat ETM/ETM + image acquisition dates on the detection of agricultural land abandonment in Eastern Europe , 2012 .

[36]  R. Congalton,et al.  Integrating cloud-based workflows in continental-scale cropland extent classification , 2018, Remote Sensing of Environment.

[37]  S. Nilsson,et al.  A spatial comparison of four satellite derived 1 km global land cover datasets , 2006 .

[38]  Mark Rounsevell,et al.  Drivers for global agricultural land use change: The nexus of diet, population, yield and bioenergy , 2015 .

[39]  Patrick Hostert,et al.  Intra-annual reflectance composites from Sentinel-2 and Landsat for national-scale crop and land cover mapping , 2019, Remote Sensing of Environment.

[40]  Prasad S. Thenkabail,et al.  An Automated Cropland Classification Algorithm (ACCA) for Tajikistan by Combining Landsat, MODIS, and Secondary Data , 2012, Remote. Sens..

[41]  C. Csáki.  Agricultural Changes in Eastern Europe at the Beginning of the 1990s , 1990 .

[42]  Stéphane Dupuy,et al.  Towards a set of agrosystem-specific cropland mapping methods to address the global cropland diversity , 2016 .

[43]  François Waldner,et al.  Automated annual cropland mapping using knowledge-based temporal features , 2015 .

[44]  Gérard Dedieu,et al.  Assessing the robustness of Random Forests to map land cover with high resolution satellite image time series over large areas , 2016 .

[45]  Martin Herold,et al.  Some challenges in global land cover mapping : An assessment of agreement and accuracy in existing 1 km datasets , 2008 .

[46]  Christopher O. Justice,et al.  Estimating Global Cropland Extent with Multi-year MODIS Data , 2010, Remote. Sens..

[47]  V. Radeloff,et al.  Using the Landsat record to detect forest-cover changes during and after the collapse of the Soviet Union in the temperate zone of European Russia , 2012 .

[48]  Pandi Zdruli,et al.  LAND RESOURCES OF THE MEDITERRANEAN: STATUS, PRESSURES, TRENDS AND IMPACTS ON FUTURE REGIONAL DEVELOPMENT , 2014 .

[49]  J. von Braun,et al.  Climate Change Impacts on Global Food Security , 2013, Science.

[50]  Jin Chen,et al.  Global land cover mapping at 30 m resolution: A POK-based operational approach , 2015 .

[51]  L. Rieseberg,et al.  Trends in Global Agricultural Land Use: Implications for Environmental Health and Food Security. , 2018, Annual review of plant biology.

[52]  Patrick Hostert,et al.  Patterns and drivers of post-socialist farmland abandonment in Western Ukraine , 2011 .

[53]  Russell G. Congalton,et al.  Global Land Cover Mapping: A Review and Uncertainty Analysis , 2014, Remote. Sens..

[54]  Patrick Hostert,et al.  Agricultural land change in the Carpathian ecoregion after the breakdown of socialism and expansion of the European Union , 2013 .

[55]  Giles M. Foody,et al.  Good practices for estimating area and assessing accuracy of land change , 2014 .

[56]  R. Dorfman.  A Formula for the Gini Coefficient , 1979 .

[57]  Mark A. Friedl,et al.  Global rain-fed, irrigated, and paddy croplands: A new high resolution map derived from remote sensing, crop inventories and climate data , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[58]  Jie Wang,et al.  Comparison of Classification Algorithms and Training Sample Sizes in Urban Land Classification with Landsat Thematic Mapper Imagery , 2014, Remote. Sens..

[59]  Prasad S. Thenkabail,et al.  Agricultural cropland extent and areas of South Asia derived using Landsat satellite 30-m time-series big-data using random forest machine learning algorithms on the Google Earth Engine cloud , 2019, GIScience & Remote Sensing.

[60]  Dirk Pflugmacher,et al.  Mapping the timing of cropland abandonment and recultivation in northern Kazakhstan using annual Landsat time series , 2018 .

[61]  Mitchell C. Hunter,et al.  Agriculture in 2050: Recalibrating Targets for Sustainable Intensification , 2017 .

[62]  Yuanjie Li,et al.  A global map of rainfed cropland areas (GMRCA) at the end of last millennium using remote sensing , 2009, Int. J. Appl. Earth Obs. Geoinformation.

[63]  P. Meyfroidt.  Trade-Offs Between Environment and Livelihoods: Bridging the Global Land Use and Food Security Discussions , 2017 .

[64]  Alexey Terekhov,et al.  Long-term agricultural land-cover change and potential for cropland expansion in the former Virgin Lands area of Kazakhstan , 2015 .

[65]  Annemarie Schneider,et al.  Monitoring land cover change in urban and peri-urban areas using dense time stacks of Landsat satellite data and a data mining approach , 2012 .

[66]  U. Gessner,et al.  Regional land cover mapping and change detection in Central Asia using MODIS time-series , 2012 .

[67]  Eric F. Lambin,et al.  Globalization of land use: distant drivers of land change and geographic displacement of land use , 2013 .

[68]  P. Döll,et al.  MIRCA2000—Global monthly irrigated and rainfed crop areas around the year 2000: A new high‐resolution data set for agricultural and hydrological modeling , 2010 .

[69]  Mutlu Ozdogan,et al.  Large area cropland extent mapping with Landsat data and a generalized classifier , 2018, Remote Sensing of Environment.

[70]  S. Maxwell.  Food Security: A Post-modern Perspective , 1996 .

[71]  A. Bilgili,et al.  Post-irrigation degradation of land and environmental resources in the Harran plain, southeastern Turkey , 2018, Environmental Monitoring and Assessment.

[72]  R. Congalton,et al.  Accuracy assessment: a user's perspective , 1986 .

[73]  Russell G. Congalton,et al.  Mapping cropland extent of Southeast and Northeast Asia using multi-year time-series Landsat 30-m data using a random forest classifier on the Google Earth Engine Cloud , 2019, Int. J. Appl. Earth Obs. Geoinformation.

[74]  Erez Hatna,et al.  Abandonment and Expansion of Arable Land in Europe , 2011, Ecosystems.

[75]  Arnaud Banos,et al.  Farming under urban pressure: Farmers' land use and land cover change intentions , 2019, Applied Geography.

[76]  E. Lambin,et al.  INAUGURAL ARTICLE by a Recently Elected Academy Member:Global land use change, economic globalization, and the looming land scarcity , 2011 .

[77]  Qihao Weng,et al.  A time series analysis of urbanization induced land use and land cover change and its impact on land surface temperature with Landsat imagery , 2016 .

[78]  E. Lambin,et al.  Dynamics of Land-Use and Land-Cover Change in Tropical Regions , 2003 .