Ryan Chan

I’m a senior research associate focusing on end-to-end machine learning for environmental forecasting based in the Machine Learning Group at the University of Cambridge (in Richard Turner's group). I’m working on Project Cumulus, an initiative to develop bespoke data-driven weather subseasonal forecasting systems tailored for farming communities in West Africa.

I have a background in statistics, machine learning and software engineering. I hold a PhD in Statistics from the University of Warwick, supervised by Professor Gareth Roberts and Professor Murray Pollock. In my PhD, I focused on developing Monte Carlo methods for combining distributed statistical analyses (Fusion). I completed my undergraduate studies at the University of Leeds, where I was awarded a first class honours MMath Mathematics degree and received the Royal Statistical Society Prize.

Research & Projects

I am interested in applying machine learning to environment and sustainability problems and currently focusing on end-to-end data-driven weather forecasting.

Current

• Project Cumulus — Data-driven forecasting systems to support farming communities in West Africa. Leading development of observationally driven models for global sub-seasonal forecasting. [Press release]

Previous

• FastNet: AI for Numerical Weather Prediction — A Graph Neural Network for medium-range weather forecasting, developed in collaboration between the Met Office and The Alan Turing Institute. [Technical report] [Pre-print]
• Project t0 — Lean language models using knowledge retrieval and fine-tuning for reasoning and test-time scaling. [Blog] [Technical report] [Code]
• prompto — Open source software for reproducible experiments on LLMs at scale, supporting self-hosted and API-based models. [NAACL 2025]
• Rough Paths — Software and applications of rough path theory and path signatures for complex data streams, with applications in NLP.
  • nlpsig: Python library for constructing paths of transformer embeddings.
  • sig-networks: PyTorch library for signature neural networks for longitudinal NLP. [EACL 2024]
  • SigMahaKNN: Anomaly detection on multivariate streams using path signatures. [Paper]
• IceNet — Probabilistic deep learning sea ice forecasting system led by British Antarctic Survey and The Alan Turing Institute. [Nature Communications] Nominated for the Arctic Circle Frederik Paulsen Award.

Miscellaneous

• Maya — Multilingual multimodal model based on Cohere’s Aya and LLaVA, part of C4AI’s Expedition Aya 2024. Won the Most Promising Award. [CVPR 2025 Workshop]
• Reginald — LLM chatbot for The Alan Turing Institute using RAG and llama-index, deployed on the Turing’s Slack workspace.
• AIrsenal & AIrgentina — Machine learning for Fantasy Premier League and World Cup prediction. AIrgentina came 6th in @Futbolmetrix1’s WC2022 contest, outperforming FiveThirtyEight, Opta, and Betfair. [Blog] [New Scientist]
• Podcast recommendation systems — Topic modelling and collaborative filtering for podcast discovery, with Entale at ATI Data Study Group (April 2021). [Report]
• Bayesian Sports Modelling — Bayesian hierarchical models for football match prediction (masters project). [Code]

Selected Publications

• Daub, E. G. et al. Technical overview and architecture of the FastNet Machine Learning weather prediction model, version 1.0. 2025. [Report]
• Dunston, T. et al. FastNet: Improving the physical consistency of machine-learning weather prediction models through loss function design. 2025. [Pre-print]
• Chan, R.S.Y., Nanni, F., Lazauskas, T., Wood, R., Yong, P., Tarassenko, L., Girolami, M., Geddes, J., Duncan, A. Retrieval-augmented reasoning with lean language models. 2025. [Report]
• Bowler, E. et al. AI sea ice forecasts for Arctic conservation: A case study predicting the timing of caribou sea ice migrations. 2025. Ecological Solutions and Evidence. [Paper]
• Chan, R.S.Y., Nanni, F., Brown, E., Chapman, E., Williams, A.R., Bright, J., Gabasova, E. Prompto: An open source library for asynchronous querying of LLM endpoints. 2025. In Proceedings of NAACL 2025. [Paper]
• Williams, A.R., Burke-Moore, L., Chan, R.S.Y. et al. Large language models can consistently generate high-quality content for election disinformation operations. 2025. PLoS ONE. [Paper]
• Alam, N. et al. Maya: Multimodal Aya. 2025. In CVPR 2025 Workshop Vision Language Models For All. [Paper]
• Tseriotou, T., Chan, R.S.Y., Tsakalidis, A., Bilal, I.M., Kochkina, E., Lyons, T., Liakata, M. Sig-Networks Toolkit: Signature Networks for Longitudinal Language Modelling. 2024. In Proceedings of EACL 2024. [Paper]
• Mougan, C. et al. How to Data in Datathons. 2023. In NeurIPS 2023 Datasets and Benchmarks Track. [Paper]
• Chan, R.S.Y., Johansen, A.M., Pollock, M., and Roberts, G.O. Divide-and-Conquer Fusion. 2023. Journal of Machine Learning Research. [Paper]

Talks, Conferences & Awards

Awards

• C4AI Expedition Aya 2024: Most Promising Award for Maya: Multimodal Aya
• The Alan Turing Institute Doctoral Studentship (2018–2022)
• The Royal Statistical Society Prize (2018)
• The Top 10 Scholarship, School of Mathematics, University of Leeds (2015, 2016, 2017)
• Summer Vacation Bursary Scheme, School of Mathematics, University of Leeds (2016, 2017)

Presentations

• Robots in Disguise: Mechanistic Interpretability III — Sparse Autoencoders. 20/11/24
• Robots in Disguise: Mechanistic Interpretability II — Circuits and Superposition. 02/10/24
• Robots in Disguise: Mechanistic Interpretability I — Introduction. 23/09/24
• Robots in Disguise: An overview of Llama 3.1. 12/08/24
• Robots in Disguise: Vision Transformers. 07/08/23
• Robots in Disguise: GPT. 24/07/23
• Robots in Disguise: BERT. 07/07/23
• Greek Stochastics Nu [Naxos]. 07/07/23
• Robots in Disguise: Transformer Encoder and Decoder models. 26/06/23
• Robots in Disguise: Sequence-to-sequence models Part II. 03/05/23
• Robots in Disguise: Sequence-to-sequence models Part I. 17/04/23
• AIUK Demo (IceNet) [London]. 21/03/23
• Lunchtime Tech Talk [The Alan Turing Institute]. 25/10/22
• 2022 World Meeting of the International Society for Bayesian Analysis [Montreal]. 28/06/22
• Data Study Group (April 2021) Entale [The Alan Turing Institute]. 29/04/21
• Young Researchers’ Meetings [University of Warwick]. 09/02/21
• Statistics Group Seminar [Newcastle University]. 10/07/20
• RSS Discussion Meeting — “Quasi-stationary Monte Carlo and ScaLE” [The Royal Statistical Society]. 24/06/20 [Video]
• The Student Seminar Series [The Alan Turing Institute]. 21/04/20
• University of Warwick Departmental Conference [Gregynog]. 24/03/20
• Algorithms & Computationally Intensive Inference Seminar [University of Warwick]. 08/03/19
• Student Seminar [University of Leeds]. 22/05/18 [Handout]

Posters

• 2022 World Meeting of the International Society for Bayesian Analysis [Montreal]. 28/06/22
• Bayes at CIRM 2021 [Marseille]. 25/10/21
• 2021 World Meeting of the International Society for Bayesian Analysis [Online]. 28/06/21
• The Turing Research Showcase [Online]. 24/09/20 [Video]
• Greek Stochastics Lambda [Corfu]. 28/08/19
• O’Bayes 2019 [University of Warwick]. 29/06/19

Miscellaneous

• Cycling from Manchester to London for Ambitious for Autism
• PhD Thesis: Monte Carlo methods for combining sample approximations of distributions; examined by Professor Nicolas Chopin and Dr. Krzysztof Łatuszyński
• Advent of Code 2022 with Julia
• R package for Fusion methodologies: DCFusion
• R package for layered Brownian bridges: layeredBB
• Advent of Code 2021 with R
• Masters Thesis: Bayesian Sports Modelling
• Undergraduate project: Automatic Puzzle Solving
• Fundraising for FareShare: Cycling challenge