Large scale crop classification using Google earth engine platform

For many applied problems in agricultural monitoring and food security it is important to provide reliable crop classification maps in national or global scale. Large amount of satellite data for large scale crop mapping generate a “Big Data” problem. The main idea of this paper was comparison of pixel-based approaches to crop mapping in Ukraine and exploring efficiency of the Google Earth Engine (GEE) cloud platform for solving “Big Data” problem and providing high resolution crop classification map for large territory. The study is carried out for the Joint Experiment of Crop Assessment and Monitoring (JECAM) test site in Ukraine covering the Kyiv region (North of Ukraine) in 2013. We found that Google Earth Engine (GEE) provided very good performance in enabling access to remote sensing products through the cloud platform, but our own approach based on ensemble of neural networks outperformed SVM, decision tree and random forest classifiers that are available in GEE.

[1]  Zhengwei Yang,et al.  Deriving crop specific covariate data sets from multi-year NASS geospatial cropland data layers , 2013, 2013 IEEE International Geoscience and Remote Sensing Symposium - IGARSS.

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

[3]  Nataliia Kussul,et al.  The use of satellite data for agriculture drought risk quantification in Ukraine , 2016 .

[4]  Martha C. Anderson,et al.  Landsat-8: Science and Product Vision for Terrestrial Global Change Research , 2014 .

[5]  Rajiv Ranjan,et al.  Towards building a data-intensive index for big data computing - A case study of Remote Sensing data processing , 2015, Inf. Sci..

[6]  Nataliia Kussul,et al.  Winter wheat yield forecasting in Ukraine based on Earth observation, meteorological data and biophysical models , 2013, Int. J. Appl. Earth Obs. Geoinformation.

[7]  Nataliia Kussul,et al.  Regional scale crop mapping using multi-temporal satellite imagery , 2015 .

[8]  Nataliia Kussul,et al.  Comparison of biophysical and satellite predictors for wheat yield forecasting in Ukraine , 2015 .

[9]  Olga Kussul,et al.  Analysis of Applicability of Neural Networks for Classification of Satellite Data , 2007 .

[10]  Andrey Yu. Shelestov,et al.  Disaster Risk Assessment Based on Heterogeneous Geospatial Information , 2010 .

[11]  Albert Y. Zomaya,et al.  Remote sensing big data computing: Challenges and opportunities , 2015, Future Gener. Comput. Syst..

[12]  J. Gallego,et al.  Accuracy, Objectivity and Efficiency of Remote Sensing for Agricultural Statistics , 2010 .

[13]  Mykola Lavreniuk,et al.  Large-Scale Classification of Land Cover Using Retrospective Satellite Data , 2016 .

[14]  Javier Gallego,et al.  Efficiency Assessment of Different Approaches to Crop Classification Based on Satellite and Ground Observations , 2012 .

[15]  Guido Lemoine,et al.  Parcel-Based Crop Classification in Ukraine Using Landsat-8 Data and Sentinel-1A Data , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[16]  Nataliia Kussul,et al.  Efficiency Assessment of Multitemporal C-Band Radarsat-2 Intensity and Landsat-8 Surface Reflectance Satellite Imagery for Crop Classification in Ukraine , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[17]  Steffen Fritz,et al.  The Need for Improved Maps of Global Cropland , 2013 .

[18]  Francisco Javier Gallego,et al.  Efficiency assessment of using satellite data for crop area estimation in Ukraine , 2014, Int. J. Appl. Earth Obs. Geoinformation.

[19]  Nataliia Kussul,et al.  Geospatial Intelligence and Data Fusion Techniques for Sustainable Development Problems , 2015, ICTERI.