Michael S. Pritchard

    flowchart
    A[Michael S. Pritchard]
    AC["Associated Concepts (23)"]
    AW["Authored Works (14)"]
    CA["Linked Co-Authors (12)"]
    CI["Linked Collaborating Institutions (10)"]
    A== dcterms:relation ==>AC
    AW== author ==>A
    AW== author ==>CA
    AW== affil ==>CI
    click AC "#associated-concepts"
    click AW "#authored-works"
    click CA "#co-authors"
    click CI "#collaborating-institutions"

    NI["add incoming edge"]
    NO["add outgoing edge"]
    NI-- ? -->A
    A-- ? -->NO
    click NI "#add-incoming-edge"
    click NO "#add-outgoing-edge"
    style NI stroke-width:2px,stroke-dasharray: 5 5
    style NO stroke-width:2px,stroke-dasharray: 5 5

ORCiD

https://orcid.org/0000-0002-0340-6327

OpenAlex ID

https://openalex.org/A5004092533 (API record)

Associated Concepts [?]

• Computer science
• Political science
• Engineering
• Law
• Physics
• Philosophy
• Geography
• Biology
• Psychology
• Geology
• Sociology
• Meteorology
• Epistemology
• Mathematics
• Environmental science
• Thermodynamics
• Engineering ethics
• Ecology
• Oceanography
• Quantum mechanics
• Economics
• Climatology
• Atmospheric sciences

Authored Works

sorted by decreasing year, and then by display-name

• Understanding the Monthly Variation in the Upstream Enhancement of Indian Summer Monsoon Precipitation Near the Western Ghats
• Towards Digital Twins for NVIDIA's Earth-2 Initiative: Pushing the Limits of Deep Auto-regressive Fourier Neural Operator and Transformer models for Earth System Emulation
• Sensitivity of Deep Convection to Vertical Resolution in a CRM
• Physics to machine learning, and machine learning back to physics
• Non-Linear Dimensionality Reduction with a Variational Encoder Decoder to Understand Convective Processes in Climate Models
• NVIDIA's Earth-2: The "Hop, Skip, Tune, Leap" strategy for accelerated km-scale hybrid ML-physics climate prediction
• Machine Learning-Based Causally Informed Atmospheric Parametrizations for Climate Models
• Low-cloud Feedbacks in an Ultra-parameterized GCM with Improved Computational Efficiency and Fidelity
• Confronting the offline vs. online skill dilemma via prognostic testing of neural network convection parameterizations at a computationally ambitious scale
• Comparing Storm Resolving Models and Climates via Unsupervised Machine Learning
• Unsupervised Organization of Turbulent Updraft Regimes and their Global Response to Warming
• Understanding cloud impacts on Amazonia carbon cycle via radiation and precipitation using convection-parameterized and resolved GCMs
• Making regionalized high intensity physics calculations flexible with anew geographic load-balancing scheme to enable hybridsuperparameterization
• Machine learning-based parametrizations for the ICON model

Linked Co-Authors

• Andrea M. Jenney
• Fernando Iglesias‐Suarez
• Jane W. Baldwin
• Kara D. Lamb
• Karthik Kashinath
• Nana Liu
• Peter N. Blossey
• Pierre Gentine
• Sara Shamekh
• Savannah L. Ferretti
• Tom Beucler
• Veronika Eyring

Linked Collaborating Institutions

• Columbia University, New York
• German Aerospace Center, Wessling
• Lawrence Berkeley National Laboratory, California
• Lawrence Livermore National Laboratory, California
• Massachusetts Institute of Technology
• Max-Planck-Institute for Meteorology, Hamburg
• University of California, Berkeley
• University of California, Irvine
• University of Lausanne, Switzerland
• University of Washington, Seattle

Add Incoming Edge

Login via ORCiD to contribute.

Add Outgoing Edge

Login via ORCiD to contribute.