Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I'm Ashley Dickson, a final-year PhD candidate specialising in scalable machine learning and surrogate modelling for large-scale scientific problems. My work focuses on developing data-driven models that can emulate complex high-fidelity simulators while remaining computationally tractable. I'm eager to apply my modelling, optimisation, and software-engineering skills to real-world problems, translating rigorous research into practical solutions that drive scientific and engineering progress.…I'm Ashley Dickson, a final-year PhD candidate specialising in scalable machine learning and surrogate modelling for large-scale scientific problems. My work focuses on developing data-driven models that can emulate complex high-fidelity simulators while remaining computationally tractable. I'm eager to apply my modelling, optimisation, and software-engineering skills to real-world problems, translating rigorous research into practical solutions that drive scientific and engineering progress.

Ashley Dickson

Data Scientist, AI Engineer, AI Developer, +2





I'm Ashley Dickson, a final-year PhD candidate specialising in scalable machine learning and surrogate modelling for large-scale scientific problems. My work focuses on developing data-driven models that can emulate complex high-fidelity simulators while remaining computationally tractable. I'm eager to apply my modelling, optimisation, and software-engineering skills to real-world problems, translating rigorous research into practical solutions that drive scientific and engineering progress.…I'm Ashley Dickson, a final-year PhD candidate specialising in scalable machine learning and surrogate modelling for large-scale scientific problems. My work focuses on developing data-driven models that can emulate complex high-fidelity simulators while remaining computationally tractable. I'm eager to apply my modelling, optimisation, and software-engineering skills to real-world problems, translating rigorous research into practical solutions that drive scientific and engineering progress.

Available to hire

I’m Ashley Dickson, a final-year PhD candidate specialising in scalable machine learning and surrogate modelling for large-scale scientific problems. My work focuses on developing data-driven models that can emulate complex high-fidelity simulators while remaining computationally tractable.

I’m eager to apply my modelling, optimisation, and software-engineering skills to real-world problems, translating rigorous research into practical solutions that drive scientific and engineering progress.

Skills

Experience Level

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Intermediate

Language

English

Fluent

Work Experience

PhD Engineering at UK Atomic Energy Authority / Lancaster University

September 1, 2023 - Present

Designed and built a 7M+ sample training dataset using an automated distributed SLURM pipeline across high performance computer clusters (Python, Bash), leveraging both GPU and CPU resources. Trained scalable probabilistic Gaussian Process Regression model to emulate a high-fidelity simulator, enabling accurate prediction of radiation damage relevant to the nuclear fusion industry. Implemented Bayesian optimisation for hyperparameter tuning (PyTorch), improving RMSE by 10%. Benchmarked model performance, achieving a 200,000× speed-up over the ground-truth simulator with minimal accuracy loss; reduced computational complexity from O(N^3) to O(N). Applied Kernel principal component analysis and farthest-point sampling to reduce dataset size by 50% while maintaining predictive performance. Developed cross-validation and performance evaluation framework to ensure robust generalisation across large-scale datasets. Presented findings at international conferences, translating complex technic

Teaching Assistant at Lancaster University

October 1, 2024 - Present

Delivered hands-on workshops in C programming for engineering students. Hosted mathematics tutorials for groups of 15 students.

Research Internship at Murphy Materials Modelling Group

June 1, 2022 - September 30, 2022

Analysed time-series atomistic simulation data to explain diffusion of tritium in nuclear fusion materials.