Source code for torchgeo.datasets.sentinel
# Copyright (c) Microsoft Corporation. All rights reserved.
# Licensed under the MIT License.
"""Sentinel datasets."""
from typing import Any, Callable, Dict, Optional, Sequence
from rasterio.crs import CRS
from .geo import RasterDataset
class Sentinel(RasterDataset):
"""Abstract base class for all Sentinel datasets.
`Sentinel <https://sentinel.esa.int/web/sentinel/home>`_ is a family of
satellites launched by the `European Space Agency (ESA) <https://www.esa.int/>`_
under the `Copernicus Programme <https://www.copernicus.eu/en>`_.
If you use this dataset in your research, please cite it using the following format:
* https://asf.alaska.edu/data-sets/sar-data-sets/sentinel-1/sentinel-1-how-to-cite/
"""
class Sentinel2(Sentinel):
"""Sentinel-2 dataset.
The `Copernicus Sentinel-2 mission
<https://sentinel.esa.int/web/sentinel/missions/sentinel-2>`_ comprises a
constellation of two polar-orbiting satellites placed in the same sun-synchronous
orbit, phased at 180° to each other. It aims at monitoring variability in land
surface conditions, and its wide swath width (290 km) and high revisit time (10 days
at the equator with one satellite, and 5 days with 2 satellites under cloud-free
conditions which results in 2-3 days at mid-latitudes) will support monitoring of
Earth's surface changes.
"""
# TODO: files downloaded from USGS Earth Explorer seem to have a different
# filename format than the official documentation
# https://sentinels.copernicus.eu/web/sentinel/user-guides/sentinel-2-msi/naming-convention
# https://sentinel.esa.int/documents/247904/685211/Sentinel-2-MSI-L2A-Product-Format-Specifications.pdf
filename_glob = "T*_*_B02_*m.*"
filename_regex = r"""
^T(?P<tile>\d{2}[A-Z]{3})
_(?P<date>\d{8}T\d{6})
_(?P<band>B\d{2})
_(?P<resolution>\d{2}m)
\..*$
"""
date_format = "%Y%m%dT%H%M%S"
# https://gisgeography.com/sentinel-2-bands-combinations/
all_bands = [
"B01",
"B02",
"B03",
"B04",
"B05",
"B06",
"B07",
"B08",
"B8A",
"B09",
"B10",
"B11",
"B12",
]
rgb_bands = ["B04", "B03", "B02"]
separate_files = True
[docs] def __init__(
self,
root: str = "data",
crs: Optional[CRS] = None,
res: Optional[float] = None,
bands: Sequence[str] = [],
transforms: Optional[Callable[[Dict[str, Any]], Dict[str, Any]]] = None,
cache: bool = True,
) -> None:
"""Initialize a new Dataset instance.
Args:
root: root directory where dataset can be found
crs: :term:`coordinate reference system (CRS)` to warp to
(defaults to the CRS of the first file found)
res: resolution of the dataset in units of CRS
(defaults to the resolution of the first file found)
bands: bands to return (defaults to all bands)
transforms: a function/transform that takes an input sample
and returns a transformed version
cache: if True, cache file handle to speed up repeated sampling
Raises:
FileNotFoundError: if no files are found in ``root``
"""
self.bands = bands if bands else self.all_bands
super().__init__(root, crs, res, transforms, cache)