====== Efficient Data Compression ======

| Begin | Anytime |
| Supervisor | [[about:people:julian kunkel]] |
| Collaboration | ECMWF |

This work will be embedded in the [[https://aces.cs.reading.ac.uk/|ACES research group]] and conducted in tight collaboration with ECMWF.

If you are interested in this topic or similar topics, contact [[about:people:julian kunkel]].

===== Description =====
Efficient data compression is mandatory to deal with the data deluge of data-intensive science like climate/weather. In this work, we investigate the state of the practice at ECMWF, explore if and how existing compression schemes could improve upon this situation, and aim to develop a model that approximates the compression behavior depending on data characteristics. 

===== Methods =====
Firstly, the current practice at ECMWF is researched and a test environment with used compression tools and example data files is setup. Next, the performance and compression ratio of compression schemes is measured and analyzed. Finally, a (machine-learning) model is developed to estimate performance and ratio depending on the data characteristics.

===== Beneficial Knowledge =====

While all skills needed to complete this project can be obtained during the time of the project, some skills are beneficial:
  * Basic knowledge about machine learning methods
  * Programming languages: C (basic level)
  * Linux (intermediate)

An MSc candidate is expected to bring soft skills (in decreasing order of importance):
  * Communication
  * Problem-Solving
  * Time management