Dr Daniel Pitchforth (he/him)
School of Mechanical, Aerospace and Civil Engineering
Research Associate
Full contact details
School of Mechanical, Aerospace and Civil Engineering
Mining Block, RC08
Sir Frederick Mappin Building
Mappin Street
Sheffield
S1 3JD
- Profile
-
Daniel Pitchforth is a research associate in the dynamics group at the University of Sheffield. His research interests focus on the integration of physical knowledge within machine learners, directed toward answering a few favourite questions: How can we most effectively combine physics and data for a particular task? What benefits can physics-informed models provide over purely data/physics-based approaches? How can we reap such benefits with application to structural dynamics?
During his PhD, he developed physics-informed models for offshore structures, with a specific focus on wave loading prediction. Currently, his research role involves working with industrial partners to implement PIML on real-world engineering challenges. Throughout his research career, an enthusiasm has grown for Gaussian processes, Kernel design and Autoregressive modelling.
- Research interests
-
Physics-informed machine learning, Gaussian processes, Autoregressive modelling, Structural dynamics
- Publications
-
Journal articles
- Physics-informed kernel mixtures for structural dynamics. Mechanical Systems and Signal Processing, 254. View this article in WRRO
- Gaussian process kernels for partial physical insight. Proceedings of the 10th European Workshop on Structural Health Monitoring (EWSHM 2024), 29(7). View this article in WRRO
- Physically-informed change-point kernels for variable levels of physical knowledge inclusion in Gaussian processes. Proceedings of the 10th European Workshop on Structural Health Monitoring (EWSHM 2024), 29(7). View this article in WRRO
- A spectrum of physics-informed Gaussian processes for regression in engineering. Data-Centric Engineering, 5(11). View this article in WRRO
- Grey-box models for wave loading prediction. Mechanical Systems and Signal Processing, 159. View this article in WRRO
Book chapters
- Making the Most of Data in Offshore Wind Energy: From Population to Physics‐informed Modeling (pp. 29-48). Wiley
- Physics-informed machine learning for structural health monitoring In Cury A, Ribeiro D, Ubertini F & Todd MD (Ed.), Structural Health Monitoring Based on Data Science Techniques (pp. 347-367). Springer Cham View this article in WRRO
Conference proceedings
- PHYSICALLY-INFORMED CHANGE-POINT KERNELS FOR INTERMITTENT INCLUSION OF PHYSICA LKNOWLEDGE. Proceedings of the 6th International Conference on Uncertainty Quantification in Computational Sciences and Engineering (UNCECOMP) (pp 112-121), 15 June 2025 - 18 June 2025.
- Physics-informed Gaussian processes - a guide to what physics where?. Proceedings of ISMA 2024 International Conference on Noise and Vibration Engineering and Usd 2024 International Conference on Uncertainty in Structural Dynamics (pp 4469-4481)
- PARTIALLY STRUCTURED GAUSSIAN PROCESSES FOR GREY-BOX LEARNING IN SHM. Proceedings of the 14th International Workshop on Structural Health Monitoring
- PHYSICS-INFORMED GAUSSIAN PROCESSES FOR WAVE LOADING PREDICTION. Proceedings of the 14th International Workshop on Structural Health Monitoring
- Physically-informed kernels for wave loading prediction. 11th International Conference on Structural Health Monitoring of Intelligent Infrastructure, Vol. 2022 (pp 452-457). Montreal, Canada, 8 August 2022 - 8 August 2022. View this article in WRRO
- Incorporation of partial physical knowledge within Gaussian processes. Proceedings of ISMA 2022 International Conference on Noise and Vibration Engineering and Usd 2022 International Conference on Uncertainty in Structural Dynamics (pp 4865-4877)
- A grey-box model for wave loading prediction with uncertainty propagation. Proceedings of ISMA 2020 International Conference on Noise and Vibration Engineering and Usd 2020 International Conference on Uncertainty in Structural Dynamics (pp 3611-3622)
Preprints
- Physics-informed kernel mixtures for structural dynamics. Mechanical Systems and Signal Processing, 254. View this article in WRRO
- Research group
-
Dynamics Research Group