Abstract: In this paper we present different approaches to multi-source data integration for the solution of complex applied problems, in particular flood mapping and vegetation state estimation using satellite, modelling and in-situ data. Since these applications are data- and computation-intensive, we use Grid computing technologies. In such a case computational and informational resources are geographically distributed and may belong to different organisations. For this purpose, we also investigate benefits of different approaches to the integration of satellite-based monitoring systems.

Keywords: data integration, Earth observation, flood mapping, inverse modelling, neural network, Grid technologies, information system, geospatial information.

ACM Classification Keywords: I.5.1 Pattern Recognition Models – Neural nets; G.1.8 Numerical Analysis Partial Differential Equations - Inverse problems; D.2.12 Software Engineering Interoperability; F.1.2 Theory of Computation Modes of Computation - Parallelism and concurrency; F.1.1 Models of Computation - Probabilistic computation; G.4 Mathematical Software - Parallel and vector implementations; H.1.1 Information Systems Models and Principles - Systems and Information Theory; H.3.5 Information Storage and Retrieval Online Information Services; I.4.6 Image Processing and Computer Vision Segmentation - Pixel classification; I.4.8 Scene Analysis - Sensor fusion; J.2 Computer Applications Physical Sciences and Engineering - Earth and Atmospheric Sciences

Link:

HIGH-PERFORMANCE INTELLIGENT COMPUTATIONS FOR ENVIRONMENTAL AND DISASTER MONITORING

Nataliia Kussul, Andrii Shelestov, Sergii Skakun, Oleksii Kravchenko

http://foibg.com/ijitk/ijitk-vol03/IJITK03-2-p03.pdf