PhD Position in Physics-Informed Generative AI for Energy Data Synthesis at Radboud University

Physicists and Astronomers

PhD Position in Physics-Informed Generative AI for Energy Data Synthesis

Radboud University

Nijmegen, Gelderland, Netherlands

3,204 – 4,051 / month

Hybrid

Entry

Starts as soon as possible

posted 27 days ago

Vacancy Summary

Join the NWO-funded SHARE project to develop AI models that generate synthetic energy data, aiding the Dutch energy transition. Collaborate with real-world data from Alliander and publish your findings in leading machine learning venues while making a tangible impact on the energy sector.

Required skills

DSO

PYTHON

Pytorch

Innovation

Flow

modeling

planning

Energy Systems

Gaussian

Tools

Artificial Intelligence (AI)

Law

Governance

Grid

Electrical

Bootstrap (Framework)

Forecasting

SOLID

Computer Science

Data Analysis

Motivation

Data Science

Deep Learning

Generative Models

Dutch

Temporal

English

Privacy Engineering

Generative AI

Machine Learning

Applied Mathematics

Programming

Real-World Data

Research

Support

Academic Writing

Access

Synthesis

Evaluation

Energy Transition

CAN

Training

Performance

Graph

Neural Networks

AI Models

Time Series Analysis

Development

Teaching

receiving

Modelling

English level

Fluent

Languages

English

Can you help unlock the data needed for the energy transition? In the NWO-funded SHARE project, you will develop AI models that generate realistic, privacy-preserving synthetic energy data for grid planning and decision-making. Working with real-world data from Alliander, you will publish at leading machine learning venues while building tools with tangible impact on the Dutch energy sector.

About the Company

The SHARE consortium, funded by the NWO Knowledge and Innovation Covenant programme, includes Radboud University, the Dutch Open University, DSO Alliander, national metrology institute VSL, Zenmo, Bronscode, and the Municipality of Nijmegen, focusing on AI, privacy engineering, energy systems, law, and governance.

The Role

As a PhD candidate, you will develop physics-informed, domain-constrained generative models for energy-system data, contributing to the SHARE project (Work Package 3). Your work will involve:

Designing and comparing deep generative approaches, including UAEs, GANs, diffusion models, and Gaussian processes for realistic load, generation, and voltage time series.
Embedding physical constraints into generation, such as power-flow consistency (Kirchhoff's laws), operational bounds, and network topology through graph neural network architectures.
Building validated benchmark datasets and an evaluation framework covering statistical fidelity, temporal and spatial structure, physical plausibility, and downstream task performance.
Collaborating with a fellow PhD candidate and a postdoctoral researcher on integrating differential privacy into the generative pipeline.
Contributing to an open-source synthetic data toolbox for use by DSOs, municipalities, and researchers across the Netherlands.

This research has a direct route to impact, involving real operational data from Alliander with regular on-site visits and direct access to practitioners who will use your models for congestion forecasting and spatial energy planning. You will also be expected to spend up to 10% of your time on teaching activities.

About Radboud University

Radboud University

De Radboud Universiteit draagt bij aan een gezonde, vrije wereld met gelijke kansen voor iedereen en is zowel regionaal als internationaal van betekenis

Locations

Nijmegen, NL

Website

Still searching manually?

Let us do the work for you.

TotaMatch works for you

We scan thousands of jobs daily and notify you when there is a match. No searching needed.

Anonymous, safe and free

Your profile stays anonymous. Your employer will not see it. You choose when to become visible.

Ready in 3 minutes

Answer a few questions and create your profile in minutes. No commitment.

About TotaMatch

TotaMatch helps professionals find work that truly fits their work happiness. We believe work is more than just an income. It is a source of fulfillment, growth, and pride. Instead of endlessly scrolling through job boards, TotaMatch works for you. Our platform continuously analyzes thousands of opportunities and identifies roles that align with what truly matters to you. You focus on your work and the people around you. We make sure you never miss a better opportunity.