georeader-spaceml 1.0.24

Lightweight reader for raster files

georeader

georeader is a package to process raster data from different satellite missions. georeader makes easy to read specific areas of your image, to reproject images from different satellites to a common grid and to go from vector to raster formats (vectorize and rasterize). georeader is mainly used to process satellite data for scientific usage, to create ML-ready datasets and to implement end-to-end operational inference pipelines.

Install

The core package has very few dependencies; it is build on top of the geospatial libraries rasterio, shapely and geopandas.

# From pip
pip install georeader-spaceml

# From GitHub
pip install git+https://github.com/spaceml-org/georeader#egg=georeader

# Install with Google dependencies (to read objects from Google Cloud Storage or Google Earth Engine)
pip install git+https://github.com/spaceml-org/georeader#egg=georeader[google]

# Install with Planetary Computer requirements
pip install git+https://github.com/spaceml-org/georeader#egg=georeader[microsoftplanetary]

Getting started

Read from a Sentinel-2 image a fixed size subimage on an specific lon,lat location (directly from the S2 public Google Cloud bucket):

# This snippet requires:
# pip install fsspec gcsfs google-cloud-storage
import os
os.environ["GS_NO_SIGN_REQUEST"] = "YES"

from georeader.readers import S2_SAFE_reader
from georeader import read

cords_read = (-104.394, 32.026) # long, lat
crs_cords = "EPSG:4326"
s2_safe_path = S2_SAFE_reader.s2_public_bucket_path("S2B_MSIL1C_20191008T173219_N0208_R055_T13SER_20191008T204555.SAFE")
s2obj = S2_SAFE_reader.s2loader(s2_safe_path, 
                                out_res=10, bands=["B04","B03","B02"])

# copy to local avoids http errors specially when not using a Google Cloud project.
# This will only copy the bands set up above B04, B03 and B02
s2obj = s2obj.cache_product_to_local_dir(".")

# See also read.read_from_bounds, read.read_from_polygon for different ways of croping an image
data = read.read_from_center_coords(s2obj,cords_read, shape=(2040, 4040),
                                    crs_center_coords=crs_cords)

data_memory = data.load() # this loads the data to memory

data_memory # GeoTensor object

>>  Transform: | 10.00, 0.00, 537020.00|
| 0.00,-10.00, 3553680.00|
| 0.00, 0.00, 1.00|
         Shape: (3, 2040, 4040)
         Resolution: (10.0, 10.0)
         Bounds: (537020.0, 3533280.0, 577420.0, 3553680.0)
         CRS: EPSG:32613
         fill_value_default: 0

In the .values attribute we have the plain numpy array that we can plot with show:

from rasterio.plot import show
show(data_memory.values/3500, transform=data_memory.transform)

Saving the GeoTensor as a COG GeoTIFF:

from georeader.save import save_cog

# Supports writing in bucket location (e.g. gs://bucket-name/s2_crop.tif)
save_cog(data_memory, "s2_crop.tif", descriptions=s2obj.bands)

Tutorials

Sentinel-2:

• Reading Sentinel-2 images from the public Google bucket
• Explore metadata of Sentinel-2 object
• Query Sentinel-2 images over a location and time span, mosaic and plot them

Other:

• Tutorial to read overlapping tiles from a GeoTIFF and a Sentinel-2 image
• Example of reading a Proba-V image overlapping with Sentinel-2 forcing same resolution
• Work with EMIT images
• Read overlapping images of PRISMA and EMIT
• Read high resolution tile layers

Used in other projects:

• georeader with ml4floods to automatically download and produce flood extent maps: the Kherson Dam Break example
• georeader with STARCOP to simulate Sentinel-2 from AVIRIS images
• georeader with STARCOP to run plume detection in EMIT images

Citation

If you find this code useful please cite:

@article{portales-julia_global_2023,
	title = {Global flood extent segmentation in optical satellite images},
	volume = {13},
	issn = {2045-2322},
	doi = {10.1038/s41598-023-47595-7},
	number = {1},
	urldate = {2023-11-30},
	journal = {Scientific Reports},
	author = {Portalés-Julià, Enrique and Mateo-García, Gonzalo and Purcell, Cormac and Gómez-Chova, Luis},
	month = nov,
	year = {2023},
	pages = {20316},
}
@article{ruzicka_starcop_2023,
	title = {Semantic segmentation of methane plumes with hyperspectral machine learning models},
	volume = {13},
	issn = {2045-2322},
	url = {https://www.nature.com/articles/s41598-023-44918-6},
	doi = {10.1038/s41598-023-44918-6},
	number = {1},
	journal = {Scientific Reports},
	author = {Růžička, Vít and Mateo-Garcia, Gonzalo and Gómez-Chova, Luis and Vaughan, Anna, and Guanter, Luis and Markham, Andrew},
	month = nov,
	year = {2023},
	pages = {19999},
}