摘要：This paper explores for the first time the contents, structure and relationships across institutions and disciplines of a global Big Earth Data cyber-infrastructure: the Global Earth Observation System of System (GEOSS). The analysis builds on 1.8 million metadata records harvested in GEOSS. Because this set includes almost all the major large data collections in GEOSS, the analysis represents more than 80% of all the data made available through this global system. We explore two major aspects: the collaborative networks and the thematic coverage in GEOSS. The first connects the contributing organisations through the more than 200,000 keywords used in the systems, and then explores who is citing whom, a proxy for of institutional thickness. The thematic coverage is analysed through neural network algorithms, first on the keywords, and then on the corpus of 653 million lemmatised lower case words built from the titles and abstracts of all 1.8 million metadata records. The findings not only give a good overview of the GEOSS data universe, but offer immediate priorities on how to increase the usability of GEOSS through improved data management, and the opportunity to augment the metadata with high level concept that synthetise well the contents of the data-set.
关键词：Machine learning ; GEOSS ; data management ; neural networks ; word embedding
