Streamlining Geospatial Machine Learning with SRAI (+ tutorial video & code)
representation learning
software
library
recording
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. We hope our library will take the first steps to standardize the geospatial AI domain. The library is fully open-source and published under Apache 2.0 license.
Authors
Szymon Woźniak
Kamil Raczycki
Kacper Leśniara
Piotr Gramacki
Piotr Szymański
Published
August 14, 2023
We’ve made the recording and tutorial code freely available. Enjoy!