Latest Tweets


downstream industry growth


→ expanding emerging demand

The objective is to develop data fusion and analytic capabilities integrating EO derived information with emerging data analytic capabilities in priority demand sectors, in particular those experiencing step change in information management, analysis functionality and performance. The objective is to embed EO analytics to the maximum extent possible within the information and analysis flows of the target demand sector so that the full value from geospatial information can be generated. This will enable a wide range of added value dimensions such as detecting spatial variation and elaborating disaggregation of core business information, characterizing environmental or situational risks on core business and integrating geospatial statistics with conventional strategic intelligence. This will support enhanced decision making, operational responsiveness to emerging issues and long term strategic planning.

Examples include:

  • integration of EO and conventional data to improve risk characterization and support the development of a sustainable risk management industry in SE Asia
  • combination of EO, airborne and in-situ sensors with operational monitoring and control information to improve oil spill preparedness and response for the oil and gas industry
  • integration of EO derived information with classical intelligence models to improve investigative analysis by the law enforcement community


→ catalyzing new opportunities and the emergence of new actors

This line of action addresses two main categories of emerging new opportunities:

  • bringing new technologies and tools together with EO datasets, opening up new markets, new approaches to creating and delivering information
  • working with small satellite and other novel data collection platform developers/operators to augment existing operational geo-information services


Examples include:

  • testing and verification of the utility and benefit from using leading edge data analytics and machine learning techniques. In particular the integration of deterministic information and data analytics driven outputs to characterize complex processes (eg human response to environmental drivers, ecosystem service characterization, disease propagation etc) and the application of ML techniques to combinations of static images and video data.
  • testing and assessing improvements in operational applications by integrating datasets and analysis from constellations of small satellites

In addition, a range of small studies are being carried out to assess the potential for new EO exploitation opportunities from a range of new developments including Blockchain, AI, quantum computing, Internet of Things as well as data processing paradigms such as TensorFlow


→ consolidating industrial best practices for EO

This line consists of a set of activities to address factors that inhibit wider uptake of EO derived information in priority market sectors. In particular, this addresses the situation where market sector or industry domain standards, working practices etc constrain the scope for using EO derived information that would otherwise be considered fit for purpose.

For each market sector, the range of situations will be elaborated where EO derived information can be used. In each use case, best practice guidelines will be tested and examples to support these guidelines will be generated. The output is a comprehensive characterization of best practices for using EO derived information within that market sector. At present, contracts have been started for the extractives industry and the agri-chemical sector. It is planned to address two market sectors each year.