PhD Position Physics-Aware Foundation Models for Climate Research

PhD Position Physics-Aware Foundation Models for Climate Research

Are you passionate about applying AI to climate challenges? Join our innovative PhD project at TU Delft!

Job description

The rise of general-purpose AI systems—known as foundation models (FMs), such as GPT-n, Llama for language, and DALL-E for images—has opened exciting new possibilities in artificial intelligence. Yet, when applied to critical domains like climate, the environment, and renewable energy, these models often fall short in interpretability and trustworthiness. This is largely due to their purely data-driven design. To make real-world impact, it is essential to align these models with physical laws and domain knowledge—ensuring they not only generate accurate predictions, but also reflect the underlying dynamics of the systems they aim to model.

In this PhD project, you will explore how to bring physical consistency and sustainability into foundation models for climate science. You’ll tackle three key challenges:

• Developing physically grounded foundation models
  You will work on integrating atmosphere, surface, and subsurface earth observations to build large-scale FMs that are physically consistent. This includes incorporating physical laws into the model architecture, training process, or loss functions—making the models better reflect real-world climate dynamics.
• Balancing interpretability with generalization
  Physical constraints can enhance model interpretability and reliability—but may also limit flexibility. You’ll investigate how to strike a fundamental balance: creating models that are both grounded in physics and able to adapt to diverse datasets and novel scenarios.
• Improving sustainability in AI
  Training large models often requires significant energy resources. You will explore how to reduce the environmental footprint of these models—contributing directly to sustainable AI development and climate goals.

Join our passionate and collaborative research team

Your home base will be the Pattern Recognition Lab (PRLab) within the Computer Science department at TU Delft. You will be supervised by Dr. Jing Sun and collaborate closely with experts in both AI and geophysics. The PRLab is an open, inclusive, and collaborative research group, where knowledge-sharing, personal growth, and innovation are central. You’ll be working in a friendly and interdisciplinary environment, alongside fellow PhD students, postdocs, and academic staff who are passionate about using AI to tackle real-world challenges. Together, the team fosters a culture of support, curiosity, and shared ambition to make meaningful impact in science and society.

What makes this position exciting, unique, and impactful?

• You’ll work on a socially relevant topic: improving AI models for climate research with a strong focus on sustainability.
• You’ll combine cutting-edge technology (foundation models) with domain knowledge from (geo)physics.
• You’ll have plenty of room for initiative and interdisciplinary collaboration with experts at the intersection of AI and geophysics.
• You’ll be part of a strong international network and receive excellent.

Job requirements

What makes you a great fit?

We’re looking for a motivated and curious candidate who is eager to contribute to interdisciplinary research at the intersection of AI and climate science. Ideally, you have:

• A Master’s degree (or are close to finishing one) in Computer Science, Artificial Intelligence, Data Science, Geophysics, Applied Physics, Computational Physics, or a closely related field.
• A solid theoretical understanding of Machine Learning and Deep Learning fundamentals.
• Basic knowledge of, and a genuine interest in, applied (geo)physics and earth system science.
• Strong programming skills—preferably in Python—and hands-on experience with machine learning frameworks and tools.
• The ability to work independently with creativity and initiative, as well as collaboratively across diverse disciplines (including geophysics).
• Strong interpersonal and communication skills, and a collaborative mindset.
• Proficiency in English, both spoken and written.

We welcome candidates from all backgrounds. Diversity makes us stronger – no matter who you are or where you come from, you are welcome at EEMCS.

TU Delft (Delft University of Technology)

Delft University of Technology is built on strong foundations. As creators of the world-famous Dutch waterworks and pioneers in biotech, TU Delft is a top international university combining science, engineering and design. It delivers world class results in education, research and innovation to address challenges in the areas of energy, climate, mobility, health and digital society. For generations, our engineers have proven to be entrepreneurial problem-solvers, both in business and in a social context.

At TU Delft we embrace diversity as one of our core values and we actively engage to be a university where you feel at home and can flourish. We value different perspectives and qualities. We believe this makes our work more innovative, the TU Delft community more vibrant and the world more just. Together, we imagine, invent and create solutions using technology to have a positive impact on a global scale. That is why we invite you to apply. Your application will receive fair consideration.
Challenge. Change. Impact!

Faculty Electrical Engineering, Mathematics and Computer Science

The Faculty of Electrical Engineering, Mathematics and Computer Science (EEMCS) brings together three scientific disciplines. Combined, they reinforce each other and are the driving force behind the technology we all use in our daily lives. Technology such as the electricity grid, which our faculty is helping to make completely sustainable and future-proof. At the same time, we are developing the chips and sensors of the future, whilst also setting the foundations for the software technologies to run on this new generation of equipment – which of course includes AI. Meanwhile we are pushing the limits of applied mathematics, for example mapping out disease processes using single cell data, and using mathematics to simulate gigantic ash plumes after a volcanic eruption. In other words: there is plenty of room at the faculty for ground-breaking research. We educate innovative engineers and have excellent labs and facilities that underline our strong international position. In total, more than 1000 employees and 4,000 students work and study in this innovative environment.

Conditions of employment

Doctoral candidates will be offered a 4-year period of employment in principle, but in the form of 2 employment contracts. An initial 1,5 year contract with an official go/no go progress assessment within 15 months. Followed by an additional contract for the remaining 2,5 years assuming everything goes well and performance requirements are met.
Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities, increasing from € 2901 per month in the first year to € 3707 in the fourth year. As a PhD candidate you will be enrolled in the TU Delft Graduate School. The TU Delft Graduate School provides an inspiring research environment with an excellent team of supervisors, academic staff and a mentor. The Doctoral Education Programme is aimed at developing your transferable, discipline-related and research skills. The TU Delft offers a customisable compensation package, discounts on health insurance, and a monthly work costs contribution. Flexible work schedules can be arranged.

Additional information

If you would like more information about this vacancy or the selection procedure, please contact Dr. Jing Sun, via jing.sun@tudelft.nl