About ETRO  |  News  |  Events  |  Vacancies  |  Contact  
Home Research Education Industry Publications About ETRO

Master theses

Current and past ideas and concepts for Master Theses.

Big data and machine learning techniques to improve the forecast of water levels


Every day, the Hydrological Information Centre (HIC) at Flanders Hydraulics Research (Flemish Government) has to deliver forecasts for the (high and low) water levels along the tidally influenced River Scheldt (e.g. near Antwerp). In particular for very high-water level conditions (e.g. due to springtide and/or storm events), it is of the utmost importance that the forecasts are reliable and precise, in order to be able to take precautions against the possible impact of floods and, hence, protect the population.
The actual water levels in the tidal area of the Scheldt basin are influenced by a number of factors. E.g. the water levels at the North Sea and the wind along the River Scheldt have an important impact on the final water levels. On the other hand, it is also observed that other, unknown factors have an influence on the system, as the water levels are sometimes over- or underestimated. As an example, the influence of the current state and history of the system on the next high water is poorly understood.

Kind of work

The objective of this MSc thesis is therefore to use big data (e.g., proprietary and online data mining) and machine learning (deep learning) techniques and algorithms to (1) identify and (2) define a relation between on the one hand, the difference in water levels near Vlissingen and near resp. Terneuzen, Hansweert, Prosperpolder and Antwerp, and on the other hand, all possible factors that might influence these differences.

Framework of the Thesis

Such relation can provide new insights in the system and the factors that are determining the water levels in the Scheldt basin and can be an interesting tool for improving the forecasts of the Hydrological Information Centre (in particular during storm-conditions).
All necessary data (e.g. water levels, wind speed, wind directions,…) will be provided by Flanders Hydraulics Research. Moreover, the research will be carried out in collaboration with Flanders Hydraulics Research.

The thesis will be supervised by Dr. ir. Jiri Nossent

Number of Students


Expected Student Profile

- Computer Science / Engineering / Mathematics
- Good programming skills in Python and Matlab
- Good understanding of machine learning, mathematics (linear algebra, calculus) and optimisation


Prof. Dr. Ir. Nikolaos Deligiannis

+32 (0)2 629 1683

more info


Picture taken at Antwerp during the storm in January 2018.

- Contact person




- Contact person

- Thesis proposals

- ETRO Courses

- Contact person

- Spin-offs

- Know How

- Journals

- Conferences

- Books

- Vacancies

- News

- Events

- Press


ETRO Department

Tel: +32 2 629 29 30

©2019 • Vrije Universiteit Brussel • ETRO Dept. • Pleinlaan 2 • 1050 Brussels • Tel: +32 2 629 2930 (secretariat) • Fax: +32 2 629 2883 • WebmasterDisclaimer