SRAI: Towards Standardization of Geospatial AI
This work addresses the problem of fragmented tooling for researchers and practitioners in geospatial AI, though it is incremental as it builds on existing methods.
The authors tackled the lack of standardization in geospatial AI by developing SRAI, a Python library that provides tools for downloading data, splitting areas, and training embedding models, enabling complete pipelines for geospatial tasks.
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.