Introduction

Welcome to Google Earth Engine: the most advanced cloud-based geospatial processing platform in the world! Earth Engine combines Google-scale storage and processing power in order to make substantive progress on global challenges that involve large geospatial datasets. Earth Engine is a tool to:

  • Perform highly-interactive algorithm development at global scale
  • Push the edge of the envelope for big data in remote sensing
  • Enable high-impact, data-driven science

Explore the pages in this documentation to learn and explore the vast capabilities of Google Earth Engine. Get started right away! For a three-minute introduction to Earth Engine from developer advocate Dave Thau, check out the following video:

About Google Earth Engine

Google Earth Engine is a cloud-based platform for planetary-scale environmental data analysis. It combines a petabyte-scale archive of publicly available remotely sensed imagery and other data, Google’s computational infrastructure optimized for parallel processing of geospatial data, APIs for JavaScript and Python, and a web-based IDE for rapid prototyping and visualization of complex spatial analyses. The first three components are described in more detail below. The IDE is described in detail in the Code Editor section.

Applications of Earth Engine have included production of Google's cloud-free, fifteen-meter base map of Earth, global-scale multi-decadal time-lapse animations, numerous large and small analyses by scientists from a range of academic, government, and non-governmental institutions, and focused studies for detecting deforestation, classifying land cover and land cover change, estimating biomass, urban mapping, and species habitat modeling.

Combining science with massive data and technology resources in this way offers these advantages:

  • Unprecedented speed: On a top-of-the-line desktop computer, it can take days or weeks to compute an analysis over any large portion of the earth. Using our cloud-based computing power, we can reduce that by orders of magnitude.
  • Ease of use and lower costs: An online platform that offers easy access to data, scientific algorithms, and computation power from any web browser can dramatically lower the cost and complexity for analysis of geospatial data.

Data catalog

The massive data archive brings together over 40 years of historical and current Earth observation imagery. It consists of petabytes of data, constantly growing as new imagery is acquired. The data catalog includes a complete archive of scenes from Landsat 4, 5, 7, and 8 that have been processed by the United States Geological Survey (USGS), a wide variety of Moderate Resolution Imaging Spectro-Radiometer (MODIS) data products as global composites, and many other remotely-sensed and ancillary image data products. All data are pre-processed, georeferenced, and ready for use. Users may also upload their own raster and vector data, which can be kept private or made publicly available.

Computation engine

Earth Engine’s method of computation is remarkably efficient. It automatically parallelizes analyses so they run simultaneously on many CPUs across many computers in Google's data centers. It performs computations lazily, requesting only the input data required to fill your screen or compute your requested values. This just-in-time distributed computation model enables real-time exploration of results and experimental data analysis. After computation, results are cached so that multiple requests for the same image or values do not result in re-computation. Earth Engine’s computational framework facilitates a highly interactive approach to algorithm development and a rapid test and improvement cycle that scales to large-scale production data processing.

API

The functionality of Earth Engine is exposed through an API available in both JavaScript and Python. The API supports complex geospatial analyses including overlay, map algebra, array operations, image processing, classification, change detection, time series analysis, joins, raster-vector conversions, vector-based extraction of image statistics and much more. Algorithms are constantly being added, enhanced and updated. Through the API, users are free to script more complex analyses and creatively recombine existing algorithms. Reporting of results is supported through charting, mapping and table or image export.

About this documentation

This site describes the Earth Engine API, which you can use to programmatically access and analyze geospatial data in the catalog or uploaded by the user. The Earth Engine API and advanced Earth Engine functionality are experimental, subject to change and are restricted to Earth Engine Evaluators. If you're comfortable with that and are eager to use Earth Engine, please fill out this form to apply for an Evaluator account.

This documentation introduces the concepts needed to perform complex analyses in Earth Engine. The Earth Engine API currently supports two languages, JavaScript and Python. In the Get Started section, the main ideas and vocabulary used throughout the documentation are introduced. Specific details regarding use and application of API functionality are provided in later sections. Code samples in JavaScript are provided to demonstrate how the operations are performed. For those who prefer to program in Python, see the Python section. Links to relevant sections of the API reference (as shown in the Code Editor) are provided with the examples.

Envoyer des commentaires concernant…

Google Earth Engine API