Events

Hi everyone,

We’ll have our Stormtracks group meeting this Wednesday (20.05) from 14:00 to 15:00 at Skybar (BCCR 3180). This week Hari will give a talk on How the background climate state modulates the storm track response to mesoscale SST features?

The meeting will be hybrid and you can join remotely via Zoom: https://uib.zoom.us/j/62886269543?pwd=ajWbi97zr0hbniaoQdZkUtD2EUSSri.1
Meeting ID: 628 8626 9543 | Password: qSKTfKU3

The meeting schedule for this semester is in the following google doc: https://docs.google.com/document/d/1F9hy45DSeS9qrXl-3l4cNzCPSE9OuBBVqdCu3VY240U/edit?usp=sharing

See you all there! :)

Cheers,
Birgit and Yangfan

Qidi holder prøveforelesning 22. mai kl. 10.15 over oppgitt emne: “Origins and evolution of weather forecasting before the age of operational numerical weather prediction”.  

I prøveforelesningskomitéen er:

Harald Sodemann, leder

Costijn Zwart

Helene Asbjørnsen

Veiledere:

Thomas Spengler (hovedveileder)

Clemens Spensberger (biveileder)

Linus Magnusson (biveileder)

Prøveforelesningen holdes på Foredragssal 200.

Studenter er også velkomne!

Dear all,

The next BCCR Seminar will be given by Will Chapman from the University of Colorado, Boulder. 

He will present his work on Towards coupled data-driven Earth system prediction.

As next Monday is a public holiday, the seminar will be held next Wednesday in the usual BCCR seminar room (4th floor of the West wing) at 11:00.

We hope to see you there!

Best regards,

Fiona and Johannes

 
Abstract

Recent advances in machine learning have enabled data driven models for weather and climate prediction that are approaching the skill of traditional numerical weather prediction systems. These approaches, ranging from hybrid physics and machine learning methods to full model emulation, offer dramatic reductions in computational cost and open the door to new experiments, large ensembles, and interactive workflows.

In this talk, the speakers present recent work within NCAR’s CREDIT, Community Research Earth Digital Twin, framework, focusing on stable decadal scale autoregressive prediction. They introduce CAMulator, a data driven emulator of the NSF NCAR Community Atmosphere Model, CAM, and examine its architecture, training strategy, and long horizon behavior. Results show that the model reproduces key atmospheric dynamics while maintaining stability over extended forecasts.

They then explore a pathway toward coupled data driven Earth system modeling by coupling CAMulator with a process based ocean model. This required building a robust interface between legacy Fortran infrastructure and modern Python based machine learning systems. They discuss both the technical challenges and the solutions that enabled this hybrid coupling, and present early results demonstrating the potential of such systems to accelerate Earth system prediction and experimentation.

Speaker information

Dr. William (Will) Chapman is an Assistant Professor in the Department of Atmospheric and Oceanic Sciences at the University of Colorado Boulder in Boulder, Colorado, USA. His research focuses on climate predictability, machine learning, and coupled Earth system dynamics, with an emphasis on improving weather and climate prediction through data-driven methods and numerical modeling. He leads research efforts machine learning for coupled Earth system modeling and has contributed to the development of advanced AI frameworks for climate model emulation and bias correction. He received his Ph.D. in Atmospheric Science from the Scripps Institution of Oceanography in 2022 and a B.S. in Environmental Engineering from the University of California San Diego. Dr. Chapman has held research positions at the National Center for Atmospheric Research (NCAR), including as a Project Scientist and Advanced Studies Program Postdoctoral Fellow, and collaborates broadly on advancing machine learning applications for Earth system science, including work on emulation frameworks and next-generation climate prediction systems.

_________________________________________________________________________________________

Zoom link:     https://uib.zoom.us/j/68304284910?pwd=2IgsDMWHuJlQw3XFHSTo3OoGBsRrhz.1

Meeting ID:   683 0428 4910

Password:       7pwZK4mG

As a part of the BCCR Training Programme in Machine Learning, there will be a seminar on AI/ML research at the BCCR on Monday, June 1st from 11:00 to 14:00. We will have two sessions of two talks each, with a free lunch provided in between. The speakers will present their work using neural networks, with a focus on what type of neural network they use and how they help them solve their problems.

Please sign up for a free lunch here:

https://forms.cloud.microsoft/pages/responsepage.aspx?id=vCSKZI2pJUCcYEjBmhQgaemxD9CtoRROnJCKyVCOholURTRMWUtRNkdHN0xCMUpNVzhEU1ZNSUdOTS4u&route=shorturl

Here is the current programme:

11:00 - 11:30 - Kamilla Wergeland from NORCE and Småkraft AS: Improving Day-Ahead Production Forecasts for Run-of-River Hydropower Using Long Short-Term Neural Networks.

11:30 - 12:00 - Antoine Bernigaud from NERSC: Super-resolution of sea surface height: U-net VS GAN.

12:00 - 13:00 - Lunch break

13:00 - 13:30 - Yangfan Zhou from GFI: Using deep learning for precipitation downscaling in Norway.

13:30 - 14:00 - Julien Brajard from NERSC: End-to-end AI forecasting of Arctic Sea Ice from observations.

Bjerknes Climate Prediction Unit (BCPU), plan to have our seminar on Tuesday 2 June 2026, from 13:00-15:00.

Program:

13:00-13:20 RA1: Wolfgang Müller (MPI): Sub-decadal North Atlantic climate variability: Imprints in European extreme summer temperatures and predictions

13:20-13:40 William Eric Chapman: title TBD

13:40-14:00 RA2: Akhilesh Nair (UiO & NERSC): Understanding Groundwater Droughts Across Europe

14:00-14:20 RA3: Filippa Fransner (UiB & BCCR): title TBD

14:20-14:40 RA4: Richard Davy (NERSC & BCCR): Co-developing Downscaled Climate Prediction Services for Norway’s National Parks

14:40- Mingling and Open Agenda (for those who wish to share or discuss)

*RA stands for Research Area

This informal discussion space is open to all Bjerknes members and guests.

Please feel free to join us and we welcome contributions from all.

Hazards Discussion Meeting Series 2026 – Your science and society

What?

Science talk on a paper or project, followed by an open discussion on how the presented science can reach “society”.

In the open discussion we will address the target “society” audience for the paper/project, how the main outcomes can be best communicated, and who at BCCR can help.

Who can attend?

Open to all BCCR.

When?

Every second Wednesday of the month, 11–12h, in Bjerknes Meeting Room (3rd floor).

10 June

Victoria Miles (NSERC)

Urban climate hazards

FTI

Hi all,

We are excited to announce an upcoming workshop, "Technological Advances in Climate Modelling", taking place June 15–19 at Bjerknes. We have invited five climate model developers to lead a mix of talks and hands-on sessions throughout the week.

The current program is as follows (subject to change):

• Monday morning: Introduction to Julia and script-based and interactive ESM modelling

• Monday afternoon: Introduction to GPU modelling

• Tuesday morning: Hands-on experiments using Oceananigans (ocean), SpeedyWeather (atmosphere), and Terrarium (land surface)

• Tuesday afternoon: TBD – possibly biogeochemistry-focused

• Wednesday morning: Hybrid physics–ML modelling, differentiable ESM modelling, and more

• Wednesday afternoon: A bit of continuation from the morning, and afterwards we will have a couple of hours for discussions and general questions of everything introduced since Monday

• Thursday morning: Coupled ocean–atmosphere simulations using script-based and interactive ESM modelling (it can be easier than you think!)

• Thursday afternoon: Coupled atmosphere–ocean large eddy simulation (LES) / nonhydrostatic modelling, with examples such as prescribed sea-ice leads or complex topography

• Friday: TBD; more discussion time

This workshop is designed to cater to a wide range of experience levels — from those running their first ocean, atmosphere, or land surface simulation, to seasoned modellers looking to deepen their knowledge of GPU computing, hybrid physics–ML approaches, and more. The introduction and hands-on sessions on Monday and Tuesday in particular are aiming to be beginner friendly, even if you have never approached a model, or Julia/GPUs, before. You are welcome to join only the sessions most relevant to you; there is no expectation to attend the full week. Our guest experts will be around for most of the week and will be available to discuss and help you get started.

We are also in discussions with Sigma2 about using their new supercomputer Olivia, which is equipped with the latest-generation GPUs and opens up exciting new possibilities for climate modelling.

A sign-up sheet will be circulated after Easter, once the program is finalised. In the meantime, we encourage you to block the week in your calendar if you are interested in joining.

Do not hesitate to get in touch if you have any questions — we look forward to seeing many of you there!

Best regards,

Kjersti Daae, Guillaume Boutin, and Andreas Klocker

Save the dates!

Save the dates!