摘要： Remote sensing data provides scientists with synoptic coverage of the Earth's surface, allowing us to understand its system dynamics in a way that would be impossible with more direct observation. As more satellites have been deployed in recent years, imagery has become more readily available and diverse, encompassing a wider range of spatial, temporal, and spectral resolutions than ever before. While these data better inform our understanding of the Earth, anyone hoping to leverage this information is hampered by the large size and complexity of these datasets, a lack of easily accessible computing resources, and the broad expertise required to correctly interpret the imagery. To fully leverage the information in these disparate datasets, data fusion methods must be implemented that abstract access to them. Large scale fusion of geospatial data, using physically based and statistical methods, can be accomplished to create a living model of the earth. This presentation will discuss the Descartes Labs approach to data fusion and normalization as well as our effort to leverage these capabilities toward a synoptic earth model. Topics will include the current status of the physical normalization algorithms deployed into the Descartes Labs Platform as well as efforts to harmonize and abstract access to multi-vendor constellations.