Martin Andrae

I’m a WASP PhD student at the Division of Statistics and Machine Learning at Linköping University, Sweden. My supervisors are Fredrik Lindsten and Tomas Landelius.

My main research interest is in probabilistic spatio-temporal modeling with applications in the physical sciences. In particular, I’m interested in applying tools from generative modelling to weather forecasting and data assimilation.

I have a BSc in Engineering Physics and a MSc in Applied Mathematics both from KTH.

Outside of work I enjoy rock climbing both in- and outdoors.

Don’t hesitate to reach out if you want to chat about research or climb together!

News

Apr 22, 2025	I’m attending ICLR 2025 in Singapore. Let me know if you want to meet up!
Apr 07, 2025	I attended the Generative Modeling Summer School / Statlearn in Sophia Antipolis, France.
Jan 22, 2025	“Continuous Ensemble Weather Forecasting with Diffusion models” has been accepted to ICLR 2025!
Aug 29, 2024	I presented our work on probabilistic weather forecasting at the “Large-Scale Deep Learning for the Earth System” workshop in Bonn.

Selected publications

Continuous Ensemble Weather Forecasting with Diffusion models

Martin Andrae, Tomas Landelius, Joel Oskarsson, and Fredrik Lindsten

In The Thirteenth International Conference on Learning Representations, 2025

Abs Bib PDF Blog Code Poster

Weather forecasting has seen a shift in methods from numerical simulations to data-driven systems. While initial research in the area focused on deterministic forecasting, recent works have used diffusion models to produce skillful ensemble forecasts. These models are trained on a single forecasting step and rolled out autoregressively. However, they are computationally expensive and accumulate errors for high temporal resolution due to the many rollout steps. We address these limitations with Continuous Ensemble Forecasting, a novel and flexible method for sampling ensemble forecasts in diffusion models. The method can generate temporally consistent ensemble trajectories completely in parallel, with no autoregressive steps. Continuous Ensemble Forecasting can also be combined with autoregressive rollouts to yield forecasts at an arbitrary fine temporal resolution without sacrificing accuracy. We demonstrate that the method achieves competitive results for global weather forecasting with good probabilistic properties.
@inproceedings{andrae2025continuous, title = {Continuous Ensemble Weather Forecasting with Diffusion models}, author = {Andrae, Martin and Landelius, Tomas and Oskarsson, Joel and Lindsten, Fredrik}, booktitle = {The Thirteenth International Conference on Learning Representations}, year = {2025}, }