1
|
Abstract
Big optical Earth observation (EO) data analytics usually start from numerical, sub-symbolic reflectance values that lack inherent semantic information (meaning) and require interpretation. However, interpretation is an ill-posed problem that is difficult for many users to solve. Our semantic EO data cube architecture aims to implement computer vision in EO data cubes as an explainable artificial intelligence approach. Automatic semantic enrichment provides semi-symbolic spectral categories for all observations as an initial interpretation of color information. Users graphically create knowledge-based semantic models in a convergence-of-evidence approach, where color information is modelled a-priori as one property of semantic concepts, such as land cover entities. This differs from other approaches that do not use a-priori knowledge and assume a direct 1:1 relationship between reflectance values and land cover. The semantic models are explainable, transferable, reusable, and users can share them in a knowledgebase. We provide insights into our web-based architecture, called Sen2Cube.at, including semantic enrichment, data models, knowledge engineering, semantic querying, and the graphical user interface. Our implemented prototype uses all Sentinel-2 MSI images covering Austria; however, the approach is transferable to other geographical regions and sensors. We demonstrate that explainable, knowledge-based big EO data analysis is possible via graphical semantic querying in EO data cubes.
Collapse
|
2
|
A Sentinel-1 Backscatter Datacube for Global Land Monitoring Applications. REMOTE SENSING 2021. [DOI: 10.3390/rs13224622] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
The Sentinel-1 Synthetic Aperture Radar (SAR) satellites allow global monitoring of the Earth’s land surface with unprecedented spatio-temporal coverage. Yet, implementing large-scale monitoring capabilities is a challenging task given the large volume of data from Sentinel-1 and the complex algorithms needed to convert the SAR intensity data into higher-level geophysical data products. While on-demand processing solutions have been proposed to cope with the petabyte-scale data volumes, in practice many applications require preprocessed datacubes that permit fast access to multi-year time series and image stacks. To serve near-real-time as well as offline land monitoring applications, we have created a Sentinel-1 backscatter datacube for all continents (except Antarctica) that is constantly being updated and maintained to ensure consistency and completeness of the data record over time. In this technical note, we present the technical specifications of the datacube, means of access and analysis capabilities, and its use in scientific and operational applications.
Collapse
|
3
|
Abstract
The development of analytical software for big Earth observation data faces several challenges. Designers need to balance between conflicting factors. Solutions that are efficient for specific hardware architectures can not be used in other environments. Packages that work on generic hardware and open standards will not have the same performance as dedicated solutions. Software that assumes that its users are computer programmers are flexible but may be difficult to learn for a wide audience. This paper describes sits, an open-source R package for satellite image time series analysis using machine learning. To allow experts to use satellite imagery to the fullest extent, sits adopts a time-first, space-later approach. It supports the complete cycle of data analysis for land classification. Its API provides a simple but powerful set of functions. The software works in different cloud computing environments. Satellite image time series are input to machine learning classifiers, and the results are post-processed using spatial smoothing. Since machine learning methods need accurate training data, sits includes methods for quality assessment of training samples. The software also provides methods for validation and accuracy measurement. The package thus comprises a production environment for big EO data analysis. We show that this approach produces high accuracy for land use and land cover maps through a case study in the Cerrado biome, one of the world’s fast moving agricultural frontiers for the year 2018.
Collapse
|