buteo
Geospatial Analysis Meets AI
Buteo is a toolbox designed to simplify the process of working with geospatial data in machine learning. It includes tools for reading, writing, and processing geospatial data, as well as tools for creating labels from vector data and generating patches from geospatial data. Buteo makes it easy to ingest data, create training data, and perform inference on geospatial data.
Please note that Buteo is under active development, and its API may not be entirely stable. When using, please pin the version of Buteo you are using to avoid breaking changes. Feel free to report any bugs or suggest improvements.
Author: Casper Fibaek (github.com/casperfibaek)
Dependencies
numba (https://numba.pydata.org/)
gdal (https://gdal.org/)
Installation Using pip:
pip install gdal
pip install buteo
Using conda:
conda install gdal
pip install buteo
Quickstart
Reproject (and other functions) to references. (Vector and raster)
import buteo as beo
OUTDIR = "path/to/output/dir"
vector_file_correct_projection = "path/to/vector/file.gpkg"
raster_files_wrong_projection = "path/to/raster/files/*.tif:glob"
paths_to_reprojected_rasters = beo.reproject_raster(
raster_files_with_wrong_projection,
vector_file_with_correct_projection,
out_path=outdir
)
paths_to_reprojected_rasters
>>> [path/to/output/dir/file1.tif, path/to/output/dir/file2.tif, ...]
Align, stack, and make patches from rasters
import buteo as beo
SRCDIR = "path/to/src/dir/"
paths_to_aligned_rasters_in_memory = beo.align_rasters(
SRCDIR + "*.tif:glob",
)
stacked_numpy_arrays = beo.raster_to_array(
paths_to_aligned_rasters_in_memory,
)
patches = beo.array_to_patches(
stacked_numpy_arrays,
256,
n_offsets=1, # 1 overlap at 1/2 patch size (128)
)
# patches_nr, height, width, channels
patches
>>> np.ndarray([10000, 256, 256, 9])
Predict a raster using a model
import buteo as beo
RASTER_PATH = "path/to/raster/raster.tif"
RASTER_OUT_PATH = "path/to/raster/raster_pred.tif"
array = beo.raster_to_array(RASTER_PATH)
callback = model.predict # from pytorch, keras, etc..
# Predict the raster using overlaps, and borders.
# Merge using different methods. (median, mad, mean, mode, ...)
predicted = predict_array(
array,
callback,
tile_size=256,
)
# Write the predicted raster to disk
beo.array_to_raster(
predicted,
reference=RASTER_PATH,
out_path=RASTER_OUT_PATH,
)
# Path to the predicted raster
>>> "path/to/raster/raster_pred.tif"
| Example Colabs | |
|---|---|
| Create labels from OpenStreetMap data |  |
| Scheduled cleaning of geospatial data | |
| Clip and remove noise from rasters | |
| Sharpen nightlights data | |
| Filters and morphological operations | |
The toolbox is being developed by ESA-Philab, NIRAS, and Aalborg University.
Dependencies
gdal numba
optional: orfeo-toolbox esa-snap
1"""# Geospatial Analysis Meets AI 2 3Buteo is a toolbox designed to simplify the process of working with geospatial data in machine learning. It includes tools for reading, writing, and processing geospatial data, as well as tools for creating labels from vector data and generating patches from geospatial data. Buteo makes it easy to ingest data, create training data, and perform inference on geospatial data. 4 5Please note that Buteo is under active development, and its API may not be entirely stable. 6When using, please pin the version of Buteo you are using to avoid breaking changes. 7Feel free to report any bugs or suggest improvements. 8 9Author: *Casper Fibaek* (github.com/casperfibaek) </br> 10 11**Dependencies** </br> 12`numba` (https://numba.pydata.org/) </br> 13`gdal` (https://gdal.org/) </br> 14 15**Installation** </br> 16Using pip: 17``` 18pip install gdal 19pip install buteo 20``` 21Using conda: 22``` 23conda install gdal 24pip install buteo 25``` 26 27**Quickstart** 28 29### Reproject (and other functions) to references. (Vector and raster) 30```python 31import buteo as beo 32 33OUTDIR = "path/to/output/dir" 34 35vector_file_correct_projection = "path/to/vector/file.gpkg" 36raster_files_wrong_projection = "path/to/raster/files/*.tif:glob" 37 38paths_to_reprojected_rasters = beo.reproject_raster( 39 raster_files_with_wrong_projection, 40 vector_file_with_correct_projection, 41 out_path=outdir 42) 43 44paths_to_reprojected_rasters 45>>> [path/to/output/dir/file1.tif, path/to/output/dir/file2.tif, ...] 46``` 47 48### Align, stack, and make patches from rasters 49```python 50import buteo as beo 51 52SRCDIR = "path/to/src/dir/" 53 54paths_to_aligned_rasters_in_memory = beo.align_rasters( 55 SRCDIR + "*.tif:glob", 56) 57 58stacked_numpy_arrays = beo.raster_to_array( 59 paths_to_aligned_rasters_in_memory, 60) 61 62patches = beo.array_to_patches( 63 stacked_numpy_arrays, 64 256, 65 n_offsets=1, # 1 overlap at 1/2 patch size (128) 66) 67 68# patches_nr, height, width, channels 69patches 70>>> np.ndarray([10000, 256, 256, 9]) 71``` 72 73### Predict a raster using a model 74```python 75import buteo as beo 76 77RASTER_PATH = "path/to/raster/raster.tif" 78RASTER_OUT_PATH = "path/to/raster/raster_pred.tif" 79 80array = beo.raster_to_array(RASTER_PATH) 81 82callback = model.predict # from pytorch, keras, etc.. 83 84# Predict the raster using overlaps, and borders. 85# Merge using different methods. (median, mad, mean, mode, ...) 86predicted = predict_array( 87 array, 88 callback, 89 tile_size=256, 90) 91 92# Write the predicted raster to disk 93beo.array_to_raster( 94 predicted, 95 reference=RASTER_PATH, 96 out_path=RASTER_OUT_PATH, 97) 98# Path to the predicted raster 99>>> "path/to/raster/raster_pred.tif" 100``` 101 102</br> 103 104| Example Colabs | | 105|---------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| 106| Create labels from OpenStreetMap data | [](https://colab.research.google.com/github/casperfibaek/buteo/blob/master/examples/create_labels_from_osm_data.ipynb) | 107| Scheduled cleaning of geospatial data | [](https://colab.research.google.com/github/casperfibaek/buteo/blob/master/examples/rocket_example.ipynb) | 108| Clip and remove noise from rasters | [](https://colab.research.google.com/github/casperfibaek/buteo/blob/master/examples/clip_and_remove_noise_raster.ipynb) | 109| Sharpen nightlights data | [](https://colab.research.google.com/github/casperfibaek/buteo/blob/master/examples/process_nightlights.ipynb) | 110| Filters and morphological operations | [](https://colab.research.google.com/github/casperfibaek/buteo/blob/master/examples/filters_and_morphology.ipynb) | 111 112</br> 113 114The toolbox is being developed by ESA-Philab, NIRAS, and Aalborg University. 115 116# Dependencies 117gdal 118numba 119 120optional: 121orfeo-toolbox 122esa-snap 123""" 124from .utils import * 125from .raster import * 126from .vector import * 127from .array import * 128from .eo import * 129from .ai import * 130from .bindings import * 131 132# import os; os.environ["GDAL_PAM_ENABLED"] = "FALSE" 133 134try: 135 from osgeo import gdal 136 gdal.UseExceptions() 137except ModuleNotFoundError: 138 print("GDAL not installed. Some functions may not work.") 139 140__version__ = "0.9.64"