Deep learning in earth observation for better data
Earth observation (EO) is changing considerably because of the large amounts of observations obtained from remote sensing and in-situ sensor networks that acquire very precise localised measurements. Novel solutions are needed to obtain data from spaceborne and ground-based instruments for estimating geophysical parameters. To better understand multisource EO data, the EU-funded CALCHAS project will gather observations from different sources, combine sampling scales associated with spaceborne and in-situ measurements and analyse time series of dynamic observations. Mathematical tools will be used to extend the present capacity of single-source data analysis. The project will analyse time series of measurements from active and passive microwave and multispectral spaceborne imaging instruments, and in-situ sensor measurements.
Fields of science
- engineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringsensorssmart sensors
- engineering and technologyenvironmental engineeringremote sensing
- natural sciencescomputer and information sciencesartificial intelligencemachine learningdeep learning
- engineering and technologyenvironmental engineeringnatural resources managementwater management
- natural sciencescomputer and information sciencesartificial intelligencecomputational intelligence
Call for proposalSee other projects for this call
Funding SchemeMSCA-IF-GF - Global Fellowships
See on map
Partner organisations contribute to the implementation of the action, but do not sign the Grant Agreement.
90089 5013 Los Angeles Ca
See on map