Overview
=====================

What is the SpaceSense python library?
-------------------------------------

`SpaceSense <https://pypi.org/project/spacesense/>`_ is a library which facilitates downloading, processing, and fusing of analysis ready
satellite and other geospatial data.

This short video will give you a quick overview!

.. raw:: html

    <iframe width="560" height="315" src="https://www.youtube.com/embed/bKL8cSDgNsk" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowfullscreen></iframe>

Why we built the SpaceSense library?
-------------------------------------

At `SpaceSense <http://www.spacesense.ai>`_, we saw that the use of satellite imagery within machine learning and deep learning processes was very complex, especially for non-experts.
We developed this library to make the process of satellite data acquisition, pre-processing and fusion with other data sources as simple as possible.
Our goal is to enable data scientists and developers to build advanced satellite imagery solutions, without the need for any specific expertise or infrastructure.

To start with, our solution is mainly directed towards teams working in Agriculture or Environment industries, but we'll be adding features regularly to expand the scope.
We hope you'll like it!


How does the SpaceSense library work?
-------------------------------------

It is a python library that you can install in your existing working environment in a matter of minutes. You can prepare all the settings of the processing you want to execute locally,
and then just execute it. The computationally heavy execution will be done on the SpaceSense servers. Based on your settings, the resulting data will either be stored on the SpaceSense
cloud, or downloaded locally.

We currently offer access to the following data catalogs:

.. csv-table::
    :header: "Catalog Data", "Type", "Description", "Link"

    "Sentinel-1", "Satellite (SAR)", "Sentinel-1 Interferometric Wide swath (IW) mode of level 1 Ground Range Detected (GRD) data", `Sentinel-1 <https://sentinels.copernicus.eu/web/sentinel/missions/sentinel-1>`_
    "Sentinel-2", "Satellite (Optical and NIR)", "Level 2A atmospherically corrected data", `Sentinel-2 <https://sentinel.esa.int/web/sentinel/missions/sentinel-2>`_
    "ERA5 Atmospheric Reanalysis", "Land and atmospheric reanalysis", "High quality global reanalysis dataset for land and atmospheric varaibles", `ERA5 <https://www.ecmwf.int/en/forecasts/datasets/reanalysis-datasets/era5>`_

Each of these data sources can be searched, filtered, pre-processed, downloaded, and cleaned at scale through SpaceSense.

In addition to that, they can also be fused, either between them, or you can also attach your own proprietary data sources. The following data sources are currently supported:

.. csv-table::
    :header: "Data Type", "Supported File Extensions", "Link"

    "Vector", "| .shp
    | .gpkg
    | .json
    | .geojson
    | GeoDataFrame (python object)", `Vector <https://docs.qgis.org/2.14/en/docs/gentle_gis_introduction/vector_data.html>`_
    "Raster", "| .tif
    | .tiff
    | .gpkg", `Raster <https://docs.qgis.org/2.14/en/docs/gentle_gis_introduction/raster_data.html>`_

The fusion features allows you to get cleaned datacubes containing harmonised data sources over numerous areas of interest and dates,
ready to be ingested into an algorithm or machine learning pipeline.