Rasteret 0.3 : EO image datasets should be tables, not folders
Index COG metadata once into Parquet, skip cold starts forever. Filter with DuckDB, train with TorchGeo, fetch pixels on demand. 20x faster runs
Index COG metadata once into Parquet, skip cold starts forever. Filter with DuckDB, train with TorchGeo, fetch pixels on demand. 20x faster runs
Rasteret sped up geo image reads by 10x. But users still spend 80% time doing ETL before even feeding GPUs. Its like having a fast car on roads full of potholes. We investigate why, and share our solution
Happy New Year, Everyone! It’s been just over a month since we published our last blog describing a method that improves reading of Cloud-Optimized GeoTIFFs (COGs). Over the New Year break, we worked on open-sourcing not just the core logic but also creating a library with simple high-level APIs
A journey of optimization of cloud-based geospatial data processing.