Publisher
source

University of Birmingham

Top university

Just Landed

PhD Studentship in Machine Learning and Uncertainty Quantification for Complex Scientific Systems University of Birmingham in United Kingdom

Degree Level

PhD

Field of study

Computer Science

Funding

Tuition funding will be available for UK-based applicants. Outstanding international students may also be considered. No stipend amount or additional funding details are stated.

Deadline

Feb 18, 2027

Country flag

Country

United Kingdom

University

University of Birmingham

Apply for this position

Free with an ApplyKite account: the application link, the deadline in your tracker and a check of your fit.

Keywords

Computer Science
Mathematics
Artificial Intelligence
Computational Science
Uncertainty Analysis
Statistics
Statistical Modelling
Applied Mathematic

More like this

Suggested positions

Publisher
source

University of Birmingham

Country flag

United Kingdom

[Tuition funding will be available for UK-based applicants; outstanding international students may also be considered. No stipend or additional funding amount is specified.] This PhD studentship explores how machine learning and uncertainty quantification can be used to understand, model and predict complex scientific systems. The project addresses situations in which processes are uncertain, dynamic and only partially observable, while measurements may be noisy, incomplete or collected across d...

Computer Science
Mathematics
Stochastic Processes
+9 more

Posted Yesterday

Publisher
source

University of Birmingham

Country flag

United Kingdom

[CENTA3 DLA funding from the Natural Environment Research Council covers an annual stipend, tuition fees at the home-fee level, and a Research Training Support Grant. International students are eligible for studentships to a maximum of 30% of the cohort. Funding does not cover additional costs relating to moving to or residing in the UK.] This PhD project will develop next-generation methods for predicting the magnitude of UK pollen seasons months in advance. Although daily pollen forecasting ha...

Computer Science
Environmental Science
Mathematics
+6 more

6 days ago

Publisher
source

National Laboratory of the Rockies

Country flag

United States

The National Laboratory of the Rockies is seeking a postdoctoral researcher for a cross-disciplinary project on uncertainty quantification and prediction reliability . The work is based in the Artificial Learning and Intelligent Systems group within NLR’s Computational Science Center in Golden, Colorado. The project addresses the challenge of making reliable predictions across multiple scales, from laboratory-scale to pilot-scale applications relevant to critical minerals and energy innovation. ...

Computer Science
Mathematics
Statistical Inference
+6 more

1 week ago

Publisher
source

University of Cambridge

Country flag

United Kingdom

Funded PhD opportunity at the University of Cambridge in collaboration with AstraZeneca: Machine Learning for Drug Discovery . This four-year, AstraZeneca-funded PhD studentship focuses on physics-guided representation learning and other machine learning approaches for drug discovery. The project offers access to rich proprietary drug-discovery datasets and close collaboration with scientists at AstraZeneca. Likely research areas include machine learning , statistics , mathematics , scientific c...

Computer Science
Chemistry
Biomedical Engineering
+7 more

1 month ago

Publisher
source

University of Birmingham

Country flag

United Kingdom

[Funded through the CENTA3 DLA by the Natural Environment Research Council (NERC). Funding covers an annual stipend, tuition fees at home-fee level, and a Research Training Support Grant.] This PhD studentship focuses on understanding and modelling extreme precipitation events in Europe under a warming climate. The project addresses the challenge of estimating very rare, high-impact rainfall events whose frequency and intensity are difficult to assess in both the current climate and future warmi...

Computer Science
Environmental Science
Mathematics
+8 more

1 week ago

About this position

This PhD studentship will develop reliable mathematical, statistical, and machine learning methods for complex scientific systems. The project addresses real-world settings in which processes are uncertain, dynamic, and only partially observable, while measurements may be noisy, incomplete, or collected across different spatial and temporal scales.

The research sits at the interface of scientific machine learning, uncertainty quantification, stochastic modelling, and data-driven inference. Possible directions include learning from noisy and high-dimensional observations, modelling complex stochastic dynamics, quantifying uncertainty in data-driven predictions, and developing statistically reliable methods for scientific applications.

A central aim is to bridge modern machine learning with the mathematical principles required for trustworthy scientific inference. Rather than using machine learning solely as a black-box prediction tool, the project will explore methods that capture uncertainty, reveal underlying dynamics, and generate meaningful insight into complex processes.

Potential applications include understanding cellular and molecular dynamics, analysing noisy biological measurements, learning stochastic dynamical systems in physics and engineering, reconstructing physical processes from imperfect observations, and analysing high-dimensional, time-dependent, and spatially structured scientific data. The precise direction will be shaped by the successful candidate’s interests and background, with opportunities for both fundamental methodological work and applications using real scientific data.

The project will be supervised by Dr Mingtao Xia at the University of Birmingham, providing an interdisciplinary research environment combining mathematical theory, machine learning, and scientific applications.

Funding details

Tuition funding will be available for UK-based applicants. Outstanding international students may also be considered. No stipend amount or additional funding details are stated.

What's required

Applicants should have a strong background in applied mathematics, mathematics, statistics, machine learning, computational science, or a closely related discipline. An interest in probability, stochastic processes, statistical inference, optimisation, or scientific computing is particularly valuable. Applicants should be enthusiastic about mathematical and computational research and interested in developing methods motivated by real-world scientific problems. Prior experience in biological or medical research is not required.

How to apply

Review the full vacancy details and submit an application through the jobs.ac.uk advert. The project is supervised by Dr Mingtao Xia.

ApplyKite TwinLearns as you apply

Make your next move.

Prepare your application

Review drafts and confirm requirements with the university.