Keynote Lectures

Geographic Knowledge Engineering for Territorial Intelligence
Robert Laurini, Knowledge Systems Institute, France, France

Hyperspectral Remote Sensing Data Analysis
José Bioucas Dias, ECE, , Portugal, Portugal

eARTh Observation - A World to Be Sensed
Jordi Corbera, Independent Researcher, Spain, Spain

Why the Map of the Future Will Not Look like a Map
Ed Parsons, Independent Researcher, United Kingdom, United Kingdom

Abstract

In a lot of applications from agriculture to zoology, from environmental planning to territorial intelligence, actual systems of artificial intelligence are not very efficient, essentially because of a naïve representation of space.
As spatial knowledge corresponds to conventional geometric and topological knowledge, geographic knowledge corresponds to knowledge about geographic features in the real world even if real features can have spatial relationships between them. In other words, spatial knowledge is based on topological, projective and distance relations; but if applied to geographic features, one must take earth rotundity and other characteristics (demography, physical geographic, economic geography, etc.) into account.
After a rapid presentation of geographic relations and their properties, this paper will detail the 12 principles governing geographic knowledge. First emphasis will be given to various forms of geography knowledge, such as located facts, geographic clusters, flows, co-location rules and topological constraints.
Then, based on ribbon theory spatial relations and earth rotundity, geographic relations will be defined. For instance, let us consider two features in the real world associated with a DISJOINT relation; when down-scaling, those objects can be associated with a TOUCHES relation. As a consequence, any reasoning mechanism must be transformed accordingly.
Territorial intelligence is what business intelligence is for companies. Territorial intelligence can be defined as a cross-fertilization of human intelligence and artificial intelligence for sustainable development of any territory, countries, regions, cities, etc.

Abstract
Hyperspectral remote sensing technology has advanced significantly in the past two decades. Current sensors onboard airborne and spaceborne platforms cover large areas of the Earth surface with unprecedented spectral, spatial, and temporal resolutions. These characteristics enable a myriad of applications requiring fine identification of materials or estimation of physical parameters. Very often, these applications rely on sophisticated and complex data analysis methods. The sources of difficulties are, namely, the high dimensionality and size of the hyperspectral data,   the spectral mixing (linear and nonlinear), and the degradation mechanisms associated to the measurement process such as noise, blur, and  atmospheric effects.  In this talk, I will present an overview cross section of some relevant hyperspectral data analysis methods and algorithms, namely,  data fusion, unmixing, classification, target detection, physical parameter retrieval, and fast computing.  For each topic, I will summarize the mathematical problem involved, give relevant pointers to state-of-the-art algorithm to address these problems, and illustrate experimentally the potentialities and limitations of these algorithms.

Abstract
Geoinformation of specific regions, territories and ecosystems requires tools operating on a stable and integrity basis. Earth Observation Platforms are nowadays a mature tehnology, allowing continous, high quality terrain observations. Consequently, space and air- borne EO is progressively becoming more affordable for new actors. The lecturer describe the main EO challenges and current added value experiences based on more than 30 years of EO at the Institute Cartographic and Geological of Catalonia, in particular addressed to provide geoinformation layers for sustainable and eficience urban areas (Smart City concept). The key note will revise the main drivers, elements, challenges and technologies to be considered when designing Geoinformation programs from Earth Observation assets. The analysis of the added value chain to transform data into knowledge and information is a paramount issue as well as to measure the social, environmental and economic impact of the potential products and services generated. A critical view of main applications in terms of energy efficiency, environmental/health and risk analysis will be discussed from a technical, operational and benefits point of view.

Abstract
Until very recently rich geographical information has been a valuable, but highly specialized,  corner of the Web.  With the widespread adoption of Web Mapping and the growth of consumer applications built around location technology maps have become mainstream. In the near future however the most widespread use of geospatial information will be to provide context for applications of the linked web. A linked Web that understands geographical concepts will  immediately make much of the Web more useful to the developers of Web  applications and will provide an important foundation for the emerging Internet  of Things.