Search academic texts

Information × Registration Number 0120U104869, ( 0220U104289  ) R & D request Title Deep learning methods and models for applied problems of satellite monitoring Head Kussul Nataliia M., д.т.н. Registration Date 12-11-2020 Organization Space Research Institute of National Academy od Science and State Space Agency of Ukraine popup.description1 Improvement of the existing and development of the new deep learning methods and models to solve problems of economy indicators monitoring and business intelligence based on the fusion of the heterogenous satellite data and data obtained from different sources with the high spatial and temporal resolution. The developed methods will differ from the existing ones by outputs in the form of a multidimensional time series and by possibility of applying them to other time series of data using transfer learning, which allow to solve applied problems of the satellite monitoring. Spatial resolution upscaling for the satellite data and harmonization of the geospatial products with the high and low spatial resolution will be carried out using generative adversarial networks and recurrent neural networks regression models. This will increase the accuracy of identification and localization of objects, which allows to increase the accuracy of the economic monitoring activities based on the geospatial data. popup.nrat_date 2024-12-10 Close