Postdoc in Machine Learning within the H2020 project 'AIDA' on space missions data
Country/Region : Netherlands, The
Website : https://tinyurl.com/aida-CWI-job
Description
The AIDA H2020 Consortium funded by the European Commission is looking to cover several positions at the doctoral and postdoctoral level. The AIDA consortium is composed by KU Leuven in Belgium; CWI in The Netherlands; University of Calabria, University of Florence and CINECA in Italy; CNRS in France; IRIDA in Greece and by Space Consulting in USA.
The activities of AIDA (http://www.aida-space.eu) will focus on the development of modelling and data analysis from multiple space missions of processes in the solar corona (flares, CMEs), in the solar wind and in the Earth’s magnetosphere. The work will be primarily in the development of new methods for data analysis and simulation, focusing especially on machine learning and artificial intelligence but covering also more traditional data analysis methods. Knowledge of the python programming language is critical in most tasks. The work will be based on the extensive previous expertise in the field of high performance computing, space science and its application to space weather within the consortium
The position at CWI (Amsterdam) involves research in machine learning techniques and Bayesian inference. The aim of the project is to develop an open-source Python package to apply machine learning techniques to the vast amount of available date collected from space missions. The AIDA project will involve state-of-the-art numerical simulations, Bayesian parameters estimation, uncertainty quantification and machine learning techniques.
The successful candidate will work to: 1. develop a software package for classification and unsupervised learning which will be integrated into AIDA, 2. build a catalogue of relevant space physics events, 3. apply dimensionality reduction on the data, 4. apply clustering algorithms to the data, 5. use information theory to study causality between events.
At CWI, the postdoc will interact with the Machine Learning for Space Weather team (www.mlspaceweather.org), which is pioneering several Artificial Intelligence approaches to tackle the Space Weather problem.
More info at:
https://tinyurl.com/aida-CWI-job
http://www.aida-space.eu
The activities of AIDA (http://www.aida-space.eu) will focus on the development of modelling and data analysis from multiple space missions of processes in the solar corona (flares, CMEs), in the solar wind and in the Earth’s magnetosphere. The work will be primarily in the development of new methods for data analysis and simulation, focusing especially on machine learning and artificial intelligence but covering also more traditional data analysis methods. Knowledge of the python programming language is critical in most tasks. The work will be based on the extensive previous expertise in the field of high performance computing, space science and its application to space weather within the consortium
The position at CWI (Amsterdam) involves research in machine learning techniques and Bayesian inference. The aim of the project is to develop an open-source Python package to apply machine learning techniques to the vast amount of available date collected from space missions. The AIDA project will involve state-of-the-art numerical simulations, Bayesian parameters estimation, uncertainty quantification and machine learning techniques.
The successful candidate will work to: 1. develop a software package for classification and unsupervised learning which will be integrated into AIDA, 2. build a catalogue of relevant space physics events, 3. apply dimensionality reduction on the data, 4. apply clustering algorithms to the data, 5. use information theory to study causality between events.
At CWI, the postdoc will interact with the Machine Learning for Space Weather team (www.mlspaceweather.org), which is pioneering several Artificial Intelligence approaches to tackle the Space Weather problem.
More info at:
https://tinyurl.com/aida-CWI-job
http://www.aida-space.eu
Last modified: 2018-06-03 17:03:41