Zoo & Phytoplankton EOV Products: Big data and machine learning methods to enhance biodiversity data

     
10:00 CET
Online

Zoo & Phytoplankton EOV Products: Big data and machine learning methods to enhance biodiversity data

On 12 February 2021, Blue-Cloud will be introducing "Zoo and Phytoplankton EOV Products", the demonstrator developed by the Flanders Marine Institute (VLIZ), in collaboration with the Faculty of Science and Engineering at Sorbonne University.

The demonstrator will compile and process several data resources that are available under different European marine networks, data systems and research infrastructures and apply big data analysis and machine learning (e.g. neural networks) methods to create fit for purpose data products, using an open transparent methodology that runs in the Blue Cloud. It will focus on biological Essential Ocean Variables (EOV’s) on plankton.

A method for creating gridded climatologies from zooplankton observations, developed by the GHER of the University of Liège using the variational inverse method and a neural network, will also be presented.

Alexander Barth (University of Liège) a FNRS researcher working in the physical oceanography group GHER (GeoHydrodynamics and Environment Research), and PHIDIAS use case 3 partner will be presenting on this event.

Visit the official webinar page to register.

Speakers

Alexander Barth

Alexander Barth

ORGANISATION: Université de Liège

Alexander Barth (University of Liège) is a FNRS researcher working in the physical oceanography group GHER (GeoHydrodynamics and Environment Research). He is mainly interested in ocean modelling, data analysis and data assimilation. The GHER develops various tools for data analysis for satellite data (DINEOF, Data Interpolating Empirical Orthogonal Functions) and in situ observations (DIVAnd, Data-Interpolating Variational Analysis in n dimensions). Recently Alexander Barth developed a method to reconstruct missing data in satellite observations using a deep neural network called DINCAE (Data-Interpolating Convolutional Auto-Encoder). He is currently focusing his work to combine classical data analysis techniques with neural networks.

Funded by

disclaimer
The PHIDIAS project has received funding from the European Union’s Connecting Europe Facility under grant agreement n° INEA/CEF/ICT/ A2018/1810854.
READ MORE...

news

Final PHIDIAS Impact Webinar: The path toward new services to increase HPC and Data capacities

The PHIDIAS’s final impact webinar took place last 12 July which aimed at presenting the tangible outputs achieved by the PHIDIAS HPC initiative at the service of the European HPC and Research community, including main features, concrete impact, and prospective advantages for Research & HPC ecosphere. Here are the brief key takeaways from the event: • A simple web access to a world-class supercomputer, yet with a kind of magic • From 5% of data analysis to 45% for scientists (data access and computing) on the road to 80% • Two portals to find and access the available data • Already available results for Earth Science Systems (detection of extreme events, pollution, nutrients or ocean oxygen measures, etc.) • Security by design is key in creating such an infrastructure (Security Committee) • PHIDIAS is also a prototype to evaluate costs • Metadata is a key point.

Events

Get in touch with us

The 30-months project NGIatlantic.eu will push the Next Generation Internet a step further by providing cascade funding to EU-based researchers and innovators in carrying out Next Generation Internet related experiments in collaboration with US research teams.




contact action add button