New OGC Working Group aims to remove a major bottleneck to advanced Earth Observation science applications by defining a standard to document, store, and share Machine Learning sample data
15 April 2021: The Open Geospatial Consortium (OGC) seeks public comment on the formation of the new Sample Markup Language for Artificial Intelligence Machine Learning (SampleML-AI/ML) Standards Working Group (SWG), which will focus on developing the Sample Markup Language for AI/ML candidate standard for consideration by OGC membership for approval as an OGC Standard. Comments are due by May 5, 2021.
Artificial Intelligence (AI) is expected to play a crucial role in many domains and will revolutionize existing technologies. During the last decade, Machine Learning (ML) techniques, especially Deep Learning, have improved significantly due to an abundance of data and advancements in high-performance computing. ML reorients and transforms geographic information systems (GIS) and Remote Sensing (RS). ML-based applications are now being deployed across diverse markets to provide new solutions and increase human efficiency. Increasingly, the science community is also using these techniques to better harness the ever-increasing volume of Earth Observation (EO) data for geospatial analysis in various domains – such as smart cities, environmental management, and disaster management.
A key component of ML techniques and processes is sample data – data with known provenance, consistent metadata, and quality measurements that can be used to consistently tune and train ML applications. A lack of consistent and known sample data is becoming a bottleneck to advanced EO science applications. The lack of sample data is also causing reproducibility issues and making it difficult to compare results across studies.
Therefore, it is expected that the geospatial community should define stricter specifications and policies to enhance discovery and sharing sample data, in particular to develop a standard Sample Markup Language for AI/ML to document, store, and share the geospatial sample data following the FAIR data management principles of Findability, Accessibility, Interoperability, and Reusability.
The SampleML-AI/ML SWG will develop this Sample Markup Language. The geospatial sample data categories will initially include remote sensing imagery, moving features (typically vehicle trajectories), and related spatial content. The SWG will define a model and encodings to exchange and retrieve the sample data across the Web. The SWG will investigate the feasibility and interoperability of OGC standards to use and share geospatial sample data in ML applications and describe gaps and issues that can lead to a new geospatial standard.
Sample data should have sufficient metadata in a machine-readable standard format, include general spatiotemporal information and sample data-specific attributes to facilitate data discovery and query. Where available, the proposed standard will use existing industry standards commonly used by developers.
The SampleML-AI/ML SWG Draft Charter is available for review and comment on the OGC Portal. Comments are due by May 5, 2021, and should be submitted via the method outlined on the SampleML-AI/ML SWG Draft Charter public comment request page.
The Open Geospatial Consortium (OGC) is an international consortium of more than 500 businesses, government agencies, research organizations, and universities driven to make geospatial (location) information and services FAIR – Findable, Accessible, Interoperable, and Reusable.
OGC’s member-driven consensus process creates royalty free, publicly available geospatial standards. Existing at the cutting edge, OGC actively analyzes and anticipates emerging tech trends, and runs an agile, collaborative Research and Development (R&D) lab that builds and tests innovative prototype solutions to members’ use cases.
OGC members together form a global forum of experts and communities that use location to connect people with technology and improve decision-making at all levels. OGC is committed to creating a sustainable future for us, our children, and future generations.
Visit ogc.org for more info on our work.