Big data analysis using Google Earth Engine (GEE), by Vegar Bakkestuen
The Google Earth Engine (GEE) platform contains petabyte-scale data for scientific analysis. After the Landsat image series were made freely available in 2008, GEE merged this very large and useful data set and linked it to its cloud computing resources to make available to the scientific community. GEE now includes satellite datasets, digital terrain models, climate data and so on, from a number of other platforms, as well as many vector-based datasets.
The easily accessible and user-friendly front-end provides a convenient environment for interactive data and algorithm development. Users are also able to add and curate their own data and collections, while using Google’s cloud resources to undertake all the processing. The end result is that this now allows scientists, to mine this massive warehouse of data for change detection, map trends and quantify resources on the Earth's surface like never before. One does not need large processing powers of the latest computers or the latest software, meaning that all calculations can be performed on a net of supercomputers.
Applications of GEE include, but are not limited to: mapping forest cover, detecting deforestation, climate change analysis and scnarios, classifying land cover, estimating forest biomass and carbon, mapping urban area expansion, population mapping, changes in agricultural production and forecasting, and rangeland dynamics. These are all ecological base maps that can be used in traditional GIS analyses, for input in species distribution models, time series analysis and so on.
The use of GEE is covering all the world and many disciplines. The availability of GEE data and processing has enabled new research that was difficult or impossible before. There is a growing amount of biolocical papers on global and regional issues using GEE in high rated journals. Combined with other biological data available, such as GBIF and biotime time series for the Anthropocene, give now the possibility to explore and analysis data never on a scale never done before.