地球的全球和密集嵌入：潛在空間中漂浮的 Major TOM

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

December 7, 2024

作者: Mikolaj Czerkawski, Marcin Kluczek, Jędrzej S. Bojanowski

cs.AI

摘要

隨著像 Copernicus 這樣的大型計畫檔案中地球觀測數據量不斷增加，對於有效率的底層原始數據向量表示的需求日益增長。從預先訓練的深度神經網絡中提取特徵表示的方法是一種強大的方法，可以提供輸入數據的語義抽象。然而，對於包含地理空間數據的影像檔案，這種方法尚未被確定。本研究提出了對現有社區項目 Major TOM 的擴展，該項目專注於為地球觀測提供和標準化開放且免費的 AI-ready 數據集。此外，隨著本手稿的發表，釋出了四個全球和密集的嵌入數據集，這是地球表面範圍最廣泛的全球開放地理空間視覺嵌入數據集，並且是免費提供的。

English

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.