What is it about?
We introduce an efficient big data framework based on the modern HDF5 technology, called AtlasHDF, in which we designed lossless data mappings (immediate mapping and analysis-ready mapping) from OpenStreetMap (OSM) vector data into a single HDF5 data container to facilitate fast and flexible GeoAI applications learnt from OSM data.
Featured Image
Photo by Dimitry Anikin on Unsplash
Why is it important?
AtlasHDF provides scalable, fast, and immediate access to raw data (e.g., geometries). The mapping of attributes to JSON strings provides solutions to language barriers (UTF-8) combined with easy parsing and tool support, but still medium storage size on disk (some wanted redundancy) Since the HDF5 is included as a default dependency in most GeoAI and high performance computing (HPC) environments, the proposed AtlasHDF provides a cross-platformm and single-techonology solution of handling heterogeneous big geodata for GeoAI.
Perspectives
In our future research, we plan to extend the AtlasHDF framework by including more types of heterogeneous big geodata (both vector and raster) so that different GeoAI models can be trained without any geospatial software dependency until the training stage of the GeoAI.
Dr. Hao Li
Technische Universitat Munchen
Read the Original
This page is a summary of: AtlasHDF, November 2022, ACM (Association for Computing Machinery),
DOI: 10.1145/3557917.3567615.
You can read the full text:
Resources
Contributors
The following have contributed to this page
