SRAI: Towards Standardization of Geospatial AI

Piotr Gramacki, Kacper Leśniara, Kamil Raczycki, Szymon Woźniak, Marcin Przymus +1 more
10/19/2023
cs.LG

Official code: kraina-ai/srai (381 stars, Apache-2.0, last commit 2026-04-06).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

kraina-ai/sraiOfficial
Apache-2.0

Spatial Representations for Artificial Intelligence - a Python library toolkit for geospatial machine learning focused on creating embeddings for downstream tasks

38132Python, MakefileOct 8, 20226 months agoApache-2.0
artificial-intelligencedata-sciencegeogeospatialmachine-learning+4 more

Cite this paper

@article{gramacki2023srai,
  title  = {SRAI: Towards Standardization of Geospatial AI},
  author = {Piotr Gramacki and Kacper Leśniara and Kamil Raczycki and Szymon Woźniak and Marcin Przymus and Piotr Szymański},
  year   = {2023},
  eprint = {2310.13098},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2310.13098v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2310.13098.svg)](https://codeofpaper.com/paper/2310.13098)

Discussion