Postdoc: Machine learning for wind flow prediction in coastal dunes

Utrecht University; Netherlands; On-site; EUR 41,000 - 64,000; Full time

Benefits offered by this job

Pension scheme

Holiday pay

Year-end bonus

Job summary

Utrecht University seeks a data-driven postdoctoral researcher to advance coastal dune modelling. You will combine numerical wind-field models with ML on CFD data to create fast, surrogate wind predictors that enhance AeoLiS-based simulations.

Requirements include a PhD in a relevant field and strong Python skills. The role includes stakeholder outreach, conference presentations, and journal publications in a collaborative environment.

Qualifications

• In-depth data science and ML experience applied to physical systems.
• Strong numerical modelling background and programming (Python).
• Experience with wind-field or coastal dune modelling is a plus.
• Clear communication; proficiency in English.

Responsibilities

• Develop surrogate wind-field models to feed coastal dune models.
• Evaluate AeoLiS wind field predictions against CFD/ field data.
• Train ML models on CFD data for fast predictions.
• Contribute to field data collection and disseminate results in meetings and journals.

Skills

Data science

Machine learning

Python

Education

PhD in Data Sciences

PhD in Computer Sciences

PhD in Physics

PhD in Earth Sciences

PhD in Civil Engineering

Tools

PySR

Neural networks

CFD simulations

AeoLiS

Job description

Environmental science » Natural resources management

Organisation/Company Utrecht University Research Field Engineering » Civil engineering Engineering » Simulation engineering Environmental science » Earth science Environmental science » Natural resources management Researcher Profile Recognised Researcher (R2) Application Deadline 6 Nov 2026 - 22:59 (UTC) Country Netherlands Type of Contract Temporary Job Status Not Applicable Hours Per Week 40.0 Is the job funded through the EU Research Framework Programme? Not funded by a EU programme Is the Job related to staff position within a Research Infrastructure? No

Offer Description

Coastal dunes are dynamic landforms that provide flood protection and crucial habitat in the Netherlands and across the world. Coastal dunes are formed by sand transport, which strongly relies on the interaction between wind and dune shape. Recent improvements in airflow modelling and coastal dune modelling are promising. However, getting accurate wind field predictions remains challenging, especially in dunes with complex topography.
Your job
In this 2-year postdoc position, you will use numerical modelling and machine learning techniques to increase the accuracy of coastal dune models. As a result, your project will inform and enhance decision-making in coastal dune management.

The ultimate goal of this project is to build a surrogate wind field model that can feed accurate wind field predictions into numerical coastal dune models. You will start by evaluating current wind field predictions from the coastal dune model AeoLiS by comparing model output with existing field measurements and/or Computational Fluid Dynamics (CFD) simulations. Specifically, you will assess where simplified assumptions in the model fall short. You will then train a machine learning model (such as PySR or neural networks) on CFD data to develop a fast, data-driven wind field predictor. You will combine this surrogate model with AeoLiS and evaluate the accuracy of the new model setup by applying it to existing case studies. Where needed, you will contribute to field data collection to support model validation. You will share your results in stakeholder meetings, scientific conferences, and academic journals.

You have a strong background in data science and experience applying machine learning and other AI techniques. You are interested in applying these techniques to physical systems, in this case, to coastal dunes, wind flow dynamics and wind-driven sand transport.
You have an open, collaborative and curious attitude. You enjoy exploring new approaches and you combine this with the pragmatism that is needed to move a project forward.

• By the time the position starts, you have obtained a PhD degree in Data Sciences, Computer Sciences, Physics, Earth Sciences, Civil Engineering, or a related field.
• You have a strong background in numerical modelling and programming (preferably Python). You will collaborate with colleagues who are AeoLiS and CFD specialists, so affinity with these techniques is a plus but not required.
• Affinity with the collection and analysis of (aeolian) field measurements is a plus.
• You communicate clearly and have a strong command of the English language.

Additional Information

We offer:

• a position (1.0 FTE) for 24 months.
• a working week of 36 - 40 hours and a gross monthly salary between €3.706 and €5.760 (salary scale 10 under the Collective Labour Agreement for Dutch Universities (CAO NU)). The salary is based on a 38-hour working week;
• 8% holiday pay and 8.3% year-end bonus;
• a pension scheme, partially paid parental leave and flexible terms of employment based on the CAO NU.

In addition to the terms of employment set out in our collective labour agreement, we offer attractive additional benefits, including opportunities for personal and professional growth , flexible leave arrangements, and extra vacation days. Through the UU Terms of Employment Options Model, you can tailor your employment package to your needs. In this way, we encourage you to grow in what you do, both in your work and in your development. Read more about our terms of employment .

Selection process

At Utrecht University, we strive to be a place where everyone feels at home. We value colleagues with different backgrounds, perspectives and identities, including differences in culture, religion or ethnicity, gender, sexual orientation, neurodiversity, disability and age. We are committed to creating a safe and inclusive environment where everyone can thrive and contribute. Read more about our commitment to diversity and inclusion. If you have any questions about accessibility, for example regarding your workplace Vening Meineszgebouw A , the application process or your work, please contact us via our HR contact page .

Knowledge security screening can be part of the selection procedures of academic staff. We do this, among other things, to prevent the unwanted transfer of sensitive knowledge and technology.

The first interview is online via MS Teams in the week of 23 November. If applicable, the second interview is in the week of 30 November.

If you have an international (non-Dutch) Master’s diploma, you will be requested to provide your Bachelor’s and Master’s diplomas as well as the corresponding grade lists (in English) if you are selected for this position.

The preferred start date is 1 January 2027, but this is flexible. Regardless of the start date, the contract needs to end at or before 31 December 2028. This means that if the contract starts later than 1 January 2027, it will be shorter than 2 years; if it starts earlier, it may be longer than 2 years (depending on available funding).

Note that international candidates that need a visa/work permit for the Netherlands require at least four months processing time after selection and acceptance. This will be arranged with help of the International Service Desk (ISD) of our university. Finding appropriate housing in or near Utrecht is your own responsibility, but the ISD may be able to advise you therewith. Unfortunately, we must warn that it is a tight market at the moment. In case of general questions about working and living in The Netherlands, please consult the Dutch Mobility Portal .

For more information about this position, please contact Dr Christa van IJzendoorn at [e-mail] . Candidates for this vacancy will be recruited by Utrecht University.