I lead scientific AI research at King's College London, coordinate the Machine Learning Working Group at the ESA Ariel Space Mission, and direct the Ariel Data Challenge. I go by Gordon Yip and publish under Kai Hou Yip (K. H. Yip).
Surrogates & Physics
AI for Science & Neural Emulation
Physics-informed neural surrogates that accelerate 3D fluid, radiative transfer, and chemical network simulations by orders of magnitude.
Neural surrogates
Physics-informed ML
3D simulation emulation
Differentiable models
Bayesian Inference
Probabilistic ML & Inverse Problems
Simulation-Based Inference (SBI), variational inference, and normalising flows for rapid, amortised posterior estimation from noisy sensor data.
Simulation-based inference
Normalising flows
Variational inference
State-space filtering
Benchmarks & UQ
AI Evaluation, Safety & Reliability
International benchmark architecture (NeurIPS & Kaggle), calibrated uncertainty quantification, out-of-distribution diagnostics, and explainable AI.
NeurIPS & Kaggle benchmarks
Uncertainty calibration
OOD diagnostics
Explainable AI
Missions & Systems
Space Systems & Open-Source Software
Coordinating the ESA Ariel Machine Learning Working Group and co-developing the modular TauREx Python framework for forward modelling and retrieval.
ESA Ariel ML
TauREx framework
PyTorch & JAX
Distributed HPC
-
Machine Learning Lead Coordinator, ESA Ariel Space Mission (2020 to present)
Open Ariel mission ↗
-
Principal Investigator & Lead Organiser, The Ariel Data Challenge (NeurIPS & Kaggle) (2022 to present)
Open challenge site ↗
Kaggle 24 ↗
Kaggle 25 ↗
-
Guest editor, Ariel: mission, science & community engagement. RAS Techniques and Instruments (RASTI), Oxford University Press (2024 to present)
RASTI special issue ↗
-
STEM for Britain finalist at the Houses of Parliament (Apr 2026). Presented the Ariel Data Challenge to MPs and the Parliamentary and Scientific Committee.
UK Parliament ↗
-
The Conversation & AAS Journal Author Series (2021). Article and AAS interview on interpreting deep learning models for exoplanet spectra.
Public writing & AAS ↗
-
Lecturer in Physics (AI), King's College London (2025 to present). Department of Physics, Faculty of Natural, Mathematical & Engineering Sciences
King's profile ↗
-
Senior Research Fellow & Associate Lecturer, University College London (2024 to 2025). Department of Physics and Astronomy
-
Postdoctoral Research Fellow, University College London (2021 to 2024). Department of Physics and Astronomy
-
Ph.D. in Data Intensive Science (Astrophysics), University College London (2017 to 2021). Thesis: "Expect the Unexpected: Deciphering Exoplanetary Signals with Machine Learning Techniques." Supervised by Prof. Ingo Waldmann and Prof. Giovanna Tinetti.
-
M.Sci. in Astrophysics (First Class Honours), University College London (2013 to 2017)
-
Vojteková & Tahseen (2027). PhD students (jointly supervised)
-
Davey (2026). PhD student (jointly supervised)
-
Pan & You (2022 to 2023). MSci Astrophysics students, University College London
-
Kohlhofer (2022 to 2023). MSc student, University of Vienna
-
Ballard (2021 to 2022). MSci Astrophysics student, University College London
-
Ignat & Skaf (2019 to 2020). MSci students, University College London & Imperial College London
-
4CCP1987: Introduction to Astrophysics. Lecturer, Department of Physics, King's College London (2025/26 to present)
-
Programming in Action. Lecturer, Department of Physics, King's College London (2025/26 to present)