Postdoc in Machine Learning for Wind-Flow Prediction in Coastal Dunes

Laplace Expert Ltd; Utrecht; Remote; EUR 41,000 - 64,000; Full time

Job summary

Utrecht University, Department of Physical Geography, invites applications for a postdoctoral researcher to develop machine-learning methods for wind-flow prediction in coastal dunes. The two-year project blends numerical modelling with data-driven approaches to improve coastal-dune models.

You will evaluate wind-field predictions against field measurements and CFD simulations, train surrogate models using PySR or neural networks, and validate the combined model on existing case studies.

Qualifications

• Applicants should hold a PhD in data science, computer science, physics, earth sciences, civil engineering or a related field by the start of the position.
• A strong background in data science, numerical modelling and machine learning is required; affinity with CFD, AeoLiS or aeolian field measurements is advantageous.

Responsibilities

• Develop machine-learning methods for wind-flow prediction in coastal dunes.
• Evaluate wind-field predictions against field measurements and CFD simulations.
• Train surrogate wind-field models using PySR or neural networks.
• Validate the combined model on existing case studies.

Skills

Machine learning

Numerical modelling

Python

AeoLiS

Computational fluid dynamics

PySR

Neural networks

Education

PhD in data science / related field

Tools

PySR

AeoLiS

CFD

Job description

Postdoc in Machine Learning for Wind-Flow Prediction in Coastal Dunes

Utrecht University · Department of Physical Geography, Faculty of Geosciences

Netherlands

Apply by 06 Nov 2026

About This Opportunity

Utrecht University is recruiting a postdoctoral researcher to develop machine-learning methods for wind-flow prediction in coastal dunes. Applications close on 6 November 2026 at 23:59 Europe/Amsterdam.

The two-year project improves coastal-dune models by combining numerical modelling and machine learning. The researcher will evaluate AeoLiS wind-field predictions against field measurements and CFD simulations, train surrogate wind-field models using approaches such as PySR or neural networks, and validate the combined model on existing case studies.

coastal dunes machine learning AeoLiS CFD wind flow

Level Postdoc

Time Commitment Full-time

Duration 24 months

Reference Code 5729

Field Machine Learning for Coastal Dune Dynamics

Organization Type University

Funding & Compensation

Amount EUR 3,706-5,760 / Per Month

Funding Type Salary

Funding Status Paid

Period Per Month

Requirements

Education

Applicants should hold a PhD in data science, computer science, physics, earth sciences, civil engineering or a related field by the start of the position.

Experience

A strong background in data science, numerical modelling and machine learning is required; affinity with CFD, AeoLiS or aeolian field measurements is advantageous.

Technical Skills

• Machine learning
• Numerical modelling
• Python
• AeoLiS
• Computational fluid dynamics
• PySR
• Neural networks

General Skills

• Collaboration
• Scientific communication
• Independent research