Skip to main content
Home
Department Of Physics text logo
  • Research
    • Our research
    • Our research groups
    • Our research in action
    • Research funding support
    • Summer internships for undergraduates
  • Study
    • Undergraduates
    • Postgraduates
  • Engage
    • For alumni
    • For business
    • For schools
    • For the public
  • Support
Menu
von Kármán vortex street over Canary Islands
Credit: NASA

Philip Stier

Professor of Atmospheric Physics

Research theme

  • Climate physics

Sub department

  • Atmospheric, Oceanic and Planetary Physics

Research groups

  • Climate processes
philip.stier@physics.ox.ac.uk
Telephone: 01865 (2)72887
Atmospheric Physics Clarendon Laboratory, room 103
  • About
  • Research
  • Teaching
  • CV
  • Publications

The sensitivity of cloud micro- and macrophysical properties to cloud microphysics parameterisations and simulation setup

Copernicus Publications (2024)

Authors:

Maor Sela, Philipp Weiss, Philip Stier
More details from the publisher

Contrasting effects of intensity and organisation on the structure and lifecycle of deep convective clouds

Copernicus Publications (2024)

Authors:

William Jones, Philip Stier
More details from the publisher

Simulating the Earth system with interactive aerosols at the kilometer scale

Copernicus Publications (2024)

Authors:

Philipp Weiss, Philip Stier
More details from the publisher

Physics-informed machine learning-based cloud microphysics parameterization for earth system models

12th International Conference on Learning Representations (ICLR 2024) International Conference on Learning Representations (2024)

Authors:

Ellen Sarauer, Mierk Schwabe, Philipp Weiss, Axel Lauer, Philip Stier, Veronika Eyring

Abstract:

In this study, we develop a physics-informed machine learning (ML)-based cloud microphysics parameterization for the ICON model. By training the ML parameterization on high-resolution simulation data, we aim to improve Earth System Models (ESMs) in comparison to traditional parameterization schemes. We investigate the usage of a multilayer perceptron (MLP) with feature engineering and physics-constraints, and use explainability techniques to understand the relationship between input features and model output. Our novel approach yields promising results, with the physics-informed ML-based cloud microphysics parameterization achieving an R2 score up to 0.777 for an individual feature. Additionally, we demonstrate a notable improvement in the overall performance in comparison to a baseline MLP, increasing its average R2 score from 0.290 to 0.613 across all variables. This approach to improve the representation of cloud microphysics in ESMs promises to enhance climate projections, contributing to a better understanding of climate change.

Details from ORA

Towards Downscaling Global AOD with Machine Learning

(2024)

Authors:

Josh Millar, paula Harder, Lilli Freischem, Philipp Weiss, Philip STIER

Pagination

  • First page First
  • Previous page Prev
  • …
  • Page 10
  • Page 11
  • Page 12
  • Page 13
  • Current page 14
  • Page 15
  • Page 16
  • Page 17
  • Page 18
  • …
  • Next page Next
  • Last page Last

Footer Menu

  • Contact us
  • Giving to the Dept of Physics
  • Work with us
  • Media

User account menu

  • Log in

Follow us

FIND US

Clarendon Laboratory,

Parks Road,

Oxford,

OX1 3PU

CONTACT US

Tel: +44(0)1865272200

University of Oxfrod logo Department Of Physics text logo
IOP Juno Champion logo Athena Swan Silver Award logo

© University of Oxford - Department of Physics

Cookies | Privacy policy | Accessibility statement

Built by: Versantus

  • Home
  • Research
  • Study
  • Engage
  • Our people
  • News & Comment
  • Events
  • Our facilities & services
  • About us
  • Giving to Physics
  • Current students
  • Staff intranet