BlackSky has secured a multi-phase, multi-year research contract from the Intelligence Advanced Research Projects Activity (IARPA), which leads research programmes to address different challenges relevant to the US intelligence community.

Under the contract, BlackSky will support the development of IARPA’s Space-based Machine Automated Recognition Technique (SMART) programme.

The programme seeks to automate the quantitative analysis of space-based imagery to carry out broad-area searches for natural and other man-made events using time-series imagery.

BlackSky will leverage its Spectra AI platform to develop a responsive system capable of monitoring large-scale construction of critical infrastructure such as military bases and airports, automatically.

Work will include the development of open-source, supervised and semi-supervised learning algorithms to determine data patterns specific to large-scale construction projects.

BlackSky CEO Brian O’Toole said: “This is a tremendous breakthrough in unsupervised learning for our Spectra AI platform and an unprecedented step toward the future of global monitoring.

“The IARPA SMART programme is a natural fit for BlackSky given our deep expertise in geospatial analytics and our proven ability to deliver first-to-know insights.”

The project will utilise the resources of Nasa’s and US Geological Survey Landsat’s constellation and European space agency’s constellation called Sentinel.

BlackSky focuses on providing global monitoring services and geospatial insights. It specifically monitors activities and facilities worldwide utilising emerging sensor networks and its own satellite constellation.

According to the company, it uses new techniques including machine learning, artificial intelligence, computer vision, and natural language processing for providing monitoring services.