Global and Dense Embeddings of Earth: Major TOM Floating in the Latent Space

TL;DR

This paper introduces a new set of dense, global geospatial embeddings derived from deep neural networks, enhancing semantic representation of Earth observation data and providing a comprehensive open dataset for the community.

Contribution

It extends the Major TOM project by releasing four dense global geospatial embedding datasets, creating the most extensive open dataset of Earth surface embeddings.

Findings

Released four new dense geospatial embedding datasets

Achieved comprehensive global coverage of Earth's surface

Enhanced semantic abstraction of Earth observation imagery

Abstract

With the ever-increasing volumes of the Earth observation data present in the archives of large programmes such as Copernicus, there is a growing need for efficient vector representations of the underlying raw data. The approach of extracting feature representations from pretrained deep neural networks is a powerful approach that can provide semantic abstractions of the input data. However, the way this is done for imagery archives containing geospatial data has not yet been defined. In this work, an extension is proposed to an existing community project, Major TOM, focused on the provision and standardization of open and free AI-ready datasets for Earth observation. Furthermore, four global and dense embedding datasets are released openly and for free along with the publication of this manuscript, resulting in the most comprehensive global open dataset of geospatial visual embeddings in terms of covered Earth's surface.