Definition

The Knowledge-centred Earth Observation system (KEO) is a modular and scalable Component-based Processing Environment (CPE) which permits to:

1. • Ease the access to EO data and relevant information extracted from them
   

2. • Provide a large set of tools for EO data processing (bridging the gap between Data and Information)
   

3. • Expand the use of EO data by supporting and automating the identification and extraction of information relevant for users
   

4. • Encourage the use of a common scientific cooperative environment
   

Functionality

The KEO system permits users to interactively extract relevant features and information from EO data, either through a generic probabilistic technique (KIM subsystem) or by means of specific processing algorithms (CPE subsystem), and to provide outputs, i.e. valuable information extracted from data, in easily accessible formats.

The KIM (Knowledge-based Information Mining) subsystem permits interactive detection of features (with a size compatible with image and ingestion resolution: higher resolution for smaller features at the expense of larger storage). It is possible to train the system to explore image collections for specific features, to obtain relevant image identifiers or feature maps / objects, to store the training for reuse also by others. The trained "feature label" can be associated to a semantic term for its storage and retrieval.

The CPE (Component-based Processing Environment) subsystem permits to create, chain and execute, under the control of a workflow engine, new or available modules for the extraction of information form EO products. These modules can also be created by the system as result of trained "feature labels" (dynamic acquisition of new knowledge).

Applications

Within the KEO environment, the user can create and semantically identify Processing Components, and graphically chain them into more complex Processing Chains aiming at solving specific end-users applications. Several application domains have been explored so far, e.g. rapid flood monitoring, damage assessment, poppy field mapping, characterization of urban areas, algal bloom detection, forest monitoring and biomass estimation, hydrological hazards management, fire and burnt areas management, etc.

Interfaces

Users can access to all KEO functionalities through a unique user-oriented client application, KAOS (KEO Application Operating on Services). This graphical interface provides both administrator and users functions, also allowing system monitoring.

The Project

During last years ESA funded a series of projects (http://earth.eo.esa.int/rtd/Projects) in the field of Image Information Mining with the main objective of empowering users (e.g.: researchers, service providers, decision makers) with the capability to identify relevant information from EO (Earth Observation) data:

1. • Knowledge-based Information Mining (KIM)
   

2. • Knowledge-centred Earth Observation (KEO)
   

3. • Image Information Mining on Time Series (IIM-TS)
   

4. • KEO Extensions and Installations (KEI)
   

These efforts led during years to design and refine the Knowledge-centred Earth Observation (KEO) system in support to information extraction from EO images. The KEO environment permits to:

1. • Create & semantically identify internal / external Processing Components
   

2. • Create Processing Components from KIM training (also interactive use)
   

3. • Graphically chain Processing Components into more complex Processing Chains
   

4. • Store output into Web Servers (WFS, WMS, WCS)
   

5. • Create and publish Web Services (from Processing Chains or output)