SPEED2ZERO

Sustainable pathways towards net zero Switzerland

Started
September 1, 2023
Status
In Progress
Share this project

Abstract

Climate change increasingly affects society and ecosystems, including biodiversity, and also impacts energy security in Switzerland. Climate-related weather extremes of unprecedented levels and increased weather variability on different timescales may lead to the intermittency of energy supply. Combined with changes in hydropower, these require the design of more resilient future energy systems that operate reliably even in extreme situations and years. In the scope of the SPEED2ZERO initiative, we use state-of-the-art machine learning approaches, like generative adversarial networks (GANs), variational autoencoders (VAEs), normalizing flows, and diffusion models, to name a few, as well as Earth System Model emulators to model spatially explicit temperature, precipitation, and climate extremes, combined with sampling approaches that enable the emulation of high-dimensional density distributions. These models can learn from high-resolution climate model simulations and generate new weather patterns at much lower computational cost. The project will provide crucial inputs for modeling platforms and enable the generation of climate storylines, i.e., realizations of specific extremes and compound extremes, e.g., periods that are exceptionally hot and dry at the same time.

People

Collaborators

SDSC Team:
Maxim Samarin
Shirin Goshtasbpour
Michele Volpi
Guillaume Obozinski

PI | Partners:

ETH Zurich, Institute for Atmospheric and Climate Science:

  • Prof. Dr. Reto Knutti
  • Dr. Cyril Brunner

More info

ETH Zurich, Seminar for Statistics:

  • Prof. Dr. Nicolai Meinshausen
  • Maybritt Schillinger

More info

description

Motivation

Climate projections on regional scales are indispensable for deriving successful policies to address challenges related to energy, biodiversity, and climate change. However, typical global circulation models (GCMs) simulate climate variables like temperature or precipitation on spatial resolutions of 100 to 300 km and, thus, can only provide coarse estimates. To include regional-scale processes and local characteristics, regional climate models (RCMs) downscale outputs of GCMs to higher spatial resolutions of typically 10 to 30 km. Still, these RCM simulations can be computationally demanding and exhibit biases in the model prediction compared to actual temperature and other climate variable observations. To address these shortcomings, we develop multivariate generative downscaling approaches to generate regional-scale climate patterns from coarse-scale GCM inputs.

Proposed Approach / Solution

As a starting point for achieving the goals within the SPEED2ZERO initiative topic areas depicted in Figure 1, the SDSC's involvement focuses on developing multivariate generative downscaling approaches based on recent promising results in applying state-of-the-art architectures like GANs or diffusion models. As illustrated in Figure 2, the goal is to design an RCM emulator capable of providing several plausible climate pattern predictions, which are closer to actual observations of temperature and other climate variables.

Impact

Machine learning is increasingly becoming more important in climate modeling. In that regard, our projects will contribute state-of-the-art methods for working on challenges related to energy, biodiversity, and climate change. The SPEED2ZERO initiative will generate crucial scientific insight and develop technology, toolboxes, scenarios, and action plans with interactive visualizations to enable a sustainable transformation to a net zero greenhouse gases and biodiversity-positive Switzerland.

Figure 1: SPEED2ZERO focuses on the areas of net zero greenhouse gas emissions, energy, biodiversity, and climate change.
Figure 2: An important tool to achieve the goals in SPEED2ZERO is downscaling from coarse-scale global circulation model inputs to regional-scale outputs.

Gallery

Annexe

Additional resources

Bibliography

  1. Sun, Y., Deng, K., Ren, K., Liu, J., Deng, C., & Jin, Y. (2024). Deep learning in statistical downscaling for deriving high spatial resolution gridded meteorological data: A systematic review. ISPRS Journal of Photogrammetry and Remote Sensing. https://doi.org/10.1016/j.isprsjprs.2023.12.011
  2. Ling, F., Ouyang, L., Larbi, B. R., Luo, J.-J., Han, T., Zhong, X., & Bai, L. (2024). Is artificial intelligence providing the second revolution for weather forecasting? ArXiv. https://arxiv.org/abs/2401.16669
  3. Fischer, E. M., Beyerle, U., Bloin-Wibe, L., Gessner, C., Humphrey, V., Lehner, F., Pendergrass, A. G., Sippel, S., Zeder, J., & Knutti, R. (2023). Storylines for unprecedented heatwaves based on ensemble boosting. Nature Communications, 14(4643). https://doi.org/10.1038/s41467-023-40112-4
  4. Lam, R., Sanchez-Gonzalez, A., Willson, M., Wirnsberger, P., Fortunato, M., Alet, F., Ravuri, S., Ewalds, T., Eaton-Rosen, Z., Hu, W., Merose, A., Hoyer, S., Holland, G., Vinyals, O., Stott, J., Pritzel, A., Mohamed, S., & Battaglia, P. (2023). Learning skillful medium-range global weather forecasting. Science, 382(1416-1421). https://doi.org/10.1126/science.adi2336
  5. Price, I., Sanchez-Gonzalez, A., Alet, F., Andersson, T. R., El-Kadi, A., Masters, D., Ewalds, T., Stott, J., Mohamed, S., Battaglia, P., Lam, R., & Willson, M. (2023). GenCast: Diffusion-based ensemble forecasting for medium-range weather. ArXiv. https://arxiv.org/abs/2312.15796

Publications

More projects

IRMA

In Progress
Interpretable and Robust Machine Learning for Mobility Analysis
No items found.

Feature Learning for Bayesian Inference

In Progress
No items found.

STIMO

In Progress
Personalized epidural electrical stimulation of the lumbar spinal cord for clinically applicable therapy to restore mobility after paralyzing spinal cord injury
No items found.

LAMP

In Progress
Lensless Actinic Metrology for EUV Photomasks
No items found.

News

Latest news

Smartair | An active learning algorithm for real-time acquisition and regression of flow field data
May 1, 2024

Smartair | An active learning algorithm for real-time acquisition and regression of flow field data

Smartair | An active learning algorithm for real-time acquisition and regression of flow field data

We’ve developed a smart solution for wind tunnel testing that learns as it works, providing accurate results faster. It provides an accurate mean flow field and turbulence field reconstruction while shortening the sampling time.
The Promise of AI in Pharmaceutical Manufacturing
April 22, 2024

The Promise of AI in Pharmaceutical Manufacturing

The Promise of AI in Pharmaceutical Manufacturing

Innovation in pharmaceutical manufacturing raises key questions: How will AI change our operations? What does this mean for the skills of our workforce? How will it reshape our collaborative efforts? And crucially, how can we fully leverage these changes?
Efficient and scalable graph generation through iterative local expansion
March 20, 2024

Efficient and scalable graph generation through iterative local expansion

Efficient and scalable graph generation through iterative local expansion

Have you ever considered the complexity of generating large-scale, intricate graphs akin to those that represent the vast relational structures of our world? Our research introduces a pioneering approach to graph generation that tackles the scalability and complexity of creating such expansive, real-world graphs.

Contact us

Let’s talk Data Science

Do you need our services or expertise?
Contact us for your next Data Science project!