odc-stac is a Python library that converts STAC (SpatioTemporal Asset Catalog) metadata into the Open Data Cube (ODC) data model, enabling efficient loading of satellite imagery (Sentinel-2, Landsat) into xarray Datasets with Dask support. It defines a pluggable metadata parser (`StacMDParser`) and auxiliary reader (`StacAuxReader`) that integrate with the odc-loader framework, handles STAC extensions for projection, raster, and EO, and provides flexible spatial-temporal binning and grouping. The library also includes a CLI benchmark tool, test utilities for generating synthetic STAC items, and a comprehensive test suite with realistic STAC item fixtures from multiple providers (Planetary Computer, USGS, Geoscience Australia). While primarily an application library, it is used extensively in geospatial data research pipelines. The codebase is well-structured and modular, though it depends on evolving STAC specifications and extensions, introducing moderate technical drift risk.
GeoWombat is an open-source Python library for geospatial raster data processing and remote sensing analysis at scale. It provides a high-level API built on xarray, rasterio, Dask, and geopandas, enabling lazy, parallel processing of multi-spectral satellite imagery (Landsat, Sentinel-2, NAIP, etc.). The library's architecture centers on a custom xarray accessor (`.gw`) that exposes geospatial properties and methods, and a configuration context manager for setting sensor profiles, reprojection parameters, and other global settings. Key capabilities include raster I/O with on-the-fly warping/mosaicking, vegetation indices, radiometric corrections (BRDF, 6S, topographic), QA masking, time-series analysis, moving-window statistics (Cython-accelerated), and machine/deep learning classification and object detection (YOLO, TorchGeo, SAM). It supports STAC cloud access and distributed computation via Dask. The codebase demonstrates solid engineering with modular backends, extensible patterns, and comprehensive test coverage, though it carries some technical debt from pinned dependencies and large monolithic modules. It is actively maintained, with a broad user community and integrations with wider geospatial ecosystems.
This repository provides PyTorch implementations of Google Research's MetNet family of models for short-term weather forecasting, including MetNet, MetNet-2, MetNet-3, MetNetPV (photovoltaic), and MetNetSingleShot. The codebase is structured as a Python package with modular layers (ConvGRU, ConvLSTM, CoordConv, FiLM conditioning, MaxViT, partition attention, etc.) and data preprocessing utilities (Gaussian satellite merging, point-to-grid translation, MRMS normalization). The models are designed to ingest satellite imagery and radar data and output precipitation or other weather variables. The repository also includes pretrained weights hosted on HuggingFace Hub and a test suite covering layers, data utilities, and model forward/backward passes. While primarily an application library, it contains reusable data engineering components for geospatial data fusion.
This repository curates and distributes Maxar Open Data satellite imagery for disaster response events. It provides a structured catalog of pre- and post-event high-resolution imagery (WorldView, GeoEye) in multiple formats: GeoJSON footprints, union geometries, MosaicJSON tile indices, and TSV metadata tables. The core pipeline (`maxar_data_catalog.py`) fetches the official Maxar STAC catalog, iterates over event collections, and generates these derived files, which are then committed to the repository. A Streamlit web app (`streamlit_app.py`) offers interactive browsing of footprints and mosaics. The repository is primarily a data asset with a supporting ETL pipeline and a thin frontend, making it a hybrid of data curation and a lightweight application. The data is organized by disaster event (e.g., hurricanes, earthquakes, floods) and includes rich acquisition metadata (platform, GSD, cloud cover, viewing angles) suitable for geospatial analysis and machine learning.