In this article, we focus on the technical aspects of the machine learning solution we implemented for the xView2 competition. We used PyTorch to build our models for satellite image analysis and fast.ai to develop their critical parts.

As part of our AI4G Initiative and with the support of a Google grant, Appsilon Data Science will be contributing to to the work of biodiversity conservationists at the National Parks Agency in Gabon in collaboration with the University of Stirling.

Satellite image datasets are now readily accessible for use in Data Science and Machine Learning projects. This article will explain how to acquire these datasets and what you can do with them.