SRAI: Towards Standardization of Geospatial AI
Gramacki, Piotr, Leśniara, Kacper, Raczycki, Kamil, Woźniak, Szymon, Przymus, Marcin, Szymański, Piotr
–arXiv.org Artificial Intelligence
Spatial Representations for Artificial Intelligence (srai) is a Python library for working with geospatial data. The library can download geospatial data, split a given area into micro-regions using multiple algorithms and train an embedding model using various architectures. It includes baseline models as well as more complex methods from published works. Those capabilities make it possible to use srai in a complete pipeline for geospatial task solving. The proposed library is the first step to standardize the geospatial AI domain toolset. It is fully open-source and published under Apache 2.0 licence.
arXiv.org Artificial Intelligence
Oct-23-2023
- Country:
- Asia > China
- Europe
- Germany
- Baden-Württemberg > Karlsruhe Region
- Heidelberg (0.04)
- Hamburg (0.05)
- Baden-Württemberg > Karlsruhe Region
- Poland > Lower Silesia Province
- Wroclaw (0.05)
- Germany
- North America > United States
- California (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- New Mexico > Los Alamos County
- Los Alamos (0.04)
- New York > New York County
- New York City (0.05)
- Washington > King County
- Seattle (0.05)
- Genre:
- Overview (0.46)
- Research Report (0.64)
- Industry:
- Information Technology (0.94)
- Transportation
- Ground > Road (0.46)
- Infrastructure & Services (0.47)
- Technology: