Development of a statistical approach to representatively “collocate” in-situ data and earth observation data product which allow identifying bias, disruption, and missing algorithms parameters in global models in a context of supervised M. learning.
What is the data science project’s research question? How to reliably train models to uptake obstacles the lack of labeling on earth observation product.
What data will be worked on? Satellite data product provided by NASA and ESA and available at World Data Center and Copernicus platform.
What tasks will this project involve? Development and validation of a statistical method for spatio-temporal collocation of in-situ data that can represent the upscaled data product in the product grid cell.
What makes this project interesting to work on? Data disruption is a newly emerging issue and neural network data checking methods with a solid statistical background can allow to track and validate data products.
What is the expected outcome? Contribution to research paper
What infrastructure, programs and tools will be used? Can they be used remotely? The program would be entirely remote, basically would evolve discussion of method and skills exchange.
What skills are necessary for this project? Data analytics / statistics, Scientific computation, Computational models, Data mining / Machine learning
Is the data open source? Yes
Interested candidates should be at Master level. Danilo Custódio is looking for 2 visiting scientists, working on the project together with the team.