The ML Platform Behind Uber's AI
Michelangelo AI: 우버의 엔드‑투‑엔드 머신러닝 플랫폼
메이커가 쓴 소개는 위의 한 줄이 전부입니다. 더 자세한 내용은 저장소 README에서 읽을 수 있습니다. 저장소 README ↗
README 전체를 불러오는 중입니다.
README 전문 보기 ↗Sentinel-1 download, processing and compositing in Python.
s1bursts makes Sentinel-1 synthetic aperture radar (SAR) data easy to use from Python. It searches and downloads the data from the Copernicus Data Space Ecosystem (CDSE), processes it with ESA SNAP into backscatter and coherence, and composites them on the MGRS grid with local resolution weighting.
pip install s1bursts
Processing needs ESA SNAP 13 or 14, and downloading a free CDSE account. The installation guide covers both.
With your CDSE credentials in the environment, download and process two acquisitions of one burst over the Aletsch glacier, 12 days apart:
from s1bursts import BurstCatalog, BurstProcessor, FileManager, SearchQuery, TimeRange
fm = FileManager("data/quickstart")
catalog = BurstCatalog(fm)
bursts = catalog.search(
SearchQuery(
time_range=TimeRange("2022-08-01", "2022-08-13"),
burst_id=30346,
sub_swath="IW1",
polarization="VV",
)
)
catalog.download(bursts).raise_on_failure()
# "auto" geocodes each burst in its own UTM zone, here EPSG:32632.
processor = BurstProcessor(fm)
rtc = processor.create_backscatter(bursts, crs="auto").raise_on_failure()
pairs = bursts.find_pairs(baseline=12)
coherence = processor.create_coherences(pairs, crs="auto").raise_on_failure()
The documentation has a user guide, tutorials on real data, and the API reference.
The contributing guide covers setting up the environment with uv, the tests and other checks, and building the documentation, locally and in CI.
If you use s1bursts in your research, please cite it with its DOI,
10.5281/zenodo.23918246, which always
points to the latest release. Zenodo lists a DOI for each version, and
CITATION.cff
holds the citation metadata.