The AIGS Pod

The AIGS Pod

The AIGS podcast tackling AI in earth system modeling and more.

Episodes

AI weather models independently learned physics

August 29, 2026 • 42 mins
Large data-driven physics models like DeepMind's weather model GraphCast have empirically succeeded in parameterizing time operators for complex dynamical systems with an accuracy reaching or in some cases exceeding that of traditional physics-based solvers. Unfortunately, how these data-driven models perform computations is largely unknown and whether their internal representations are interpretable or physically consistent is an ...
Listen
Watch
Mark as Played

GraphCast learns the laws of physics

August 28, 2026 • 20 mins
Large data-driven physics models like DeepMind's weather model GraphCast have empirically succeeded in parameterizing time operators for complex dynamical systems with an accuracy reaching or in some cases exceeding that of traditional physics-based solvers. Unfortunately, how these data-driven models perform computations is largely unknown and whether their internal representations are interpretable or physically consistent is an ...
Listen
Watch
Mark as Played

Walrus masters physics from stars to oceans

August 15, 2026 • 17 mins
Foundation models have reshaped language and vision, but physical simulation has resisted the same playbook: heterogeneous data, unstable long-term rollouts, and mismatched resolutions and dimensionalities make it hard to train one model across many kinds of physics. This paper introduces Walrus, a transformer-based foundation model for fluid-like continuum dynamics, built around a harmonic-analysis-based stabilization method, load...
Listen
Watch
Mark as Played

Walrus AI unifies nineteen physics scenarios

August 8, 2026 • 21 mins
Foundation models have reshaped language and vision, but physical simulation has resisted the same playbook: heterogeneous data, unstable long-term rollouts, and mismatched resolutions and dimensionalities make it hard to train one model across many kinds of physics. This paper introduces Walrus, a transformer-based foundation model for fluid-like continuum dynamics, built around a harmonic-analysis-based stabilization method, load...
Listen
Watch
Mark as Played

Teaching AI the laws of physics

August 1, 2026 • 18 mins
Foundation models have reshaped language and vision, but physical simulation has resisted the same playbook: heterogeneous data, unstable long-term rollouts, and mismatched resolutions and dimensionalities make it hard to train one model across many kinds of physics. This paper introduces Walrus, a transformer-based foundation model for fluid-like continuum dynamics, built around a harmonic-analysis-based stabilization method, load...
Listen
Watch
Mark as Played

Aurora AI beats multi-billion dollar supercomputers

July 25, 2026 • 45 mins
Aurora is a pioneering AI foundation model created by Microsoft to revolutionize Earth system forecasting by delivering high-resolution predictions with unprecedented speed and efficiency. Developed using a 3D Swin Transformer architecture, the model was pretrained on over one million hours of diverse geophysical data to learn the complex dynamics of the atmosphere. Through a process of fine-tuning, Aurora can be specialized for di...
Listen
Watch
Mark as Played

Microsoft Aurora outperforms traditional weather models

July 25, 2026 • 23 mins
Aurora is a pioneering AI foundation model created by Microsoft to revolutionize Earth system forecasting by delivering high-resolution predictions with unprecedented speed and efficiency. Developed using a 3D Swin Transformer architecture, the model was pretrained on over one million hours of diverse geophysical data to learn the complex dynamics of the atmosphere. Through a process of fine-tuning, Aurora can be specialized for di...
Listen
Watch
Mark as Played

Aurora AI beats traditional weather models

July 25, 2026 • 19 mins
Aurora is a pioneering AI foundation model created by Microsoft to revolutionize Earth system forecasting by delivering high-resolution predictions with unprecedented speed and efficiency. Developed using a 3D Swin Transformer architecture, the model was pretrained on over one million hours of diverse geophysical data to learn the complex dynamics of the atmosphere. Through a process of fine-tuning, Aurora can be specialized for di...
Listen
Watch
Mark as Played

NVIDIA ATLAS beats supercomputers on one GPU

July 20, 2026 • 22 mins
The recent revolution in data-driven methods for weather forecasting has lead to a fragmented landscape of complex, bespoke architectures and training strategies, obscuring the fundamental drivers of forecast accuracy. Here, we demonstrate that state-of-the-art probabilistic skill requires neither intricate architectural constraints nor specialized training heuristics. We introduce a scalable framework for learning multi-scale atmo...
Listen
Watch
Mark as Played

NVIDIA ATLAS beats global weather supercomputers

July 20, 2026 • 60 mins
The recent revolution in data-driven methods for weather forecasting has lead to a fragmented landscape of complex, bespoke architectures and training strategies, obscuring the fundamental drivers of forecast accuracy. Here, we demonstrate that state-of-the-art probabilistic skill requires neither intricate architectural constraints nor specialized training heuristics. We introduce a scalable framework for learning multi-scale atmo...
Listen
Watch
Mark as Played

Why climate AI needs synthetic data

July 14, 2026 • 21 mins
As deep learning for physical systems continues to grow in popularity, efforts to improve generalizability have primarily focused on designing architectures that embed physical constraints. However, for machine-learning surrogate climate models (emulators), research shows that the low structural diversity in existing scenarios commonly used to generate training data places a ceiling on predictive skill. This work examines whether t...
Listen
Watch
Mark as Played

The Tebaldi Test For Climate Emulators

July 5, 2026 • 20 mins
A comprehensive review of climate model emulation methods and their validation. This episode discusses the latest survey from Claudia Tebaldi, Noelle E. Selin, Rafael Ferrari, and Glenn Flierl, published in the Annual Review of Environment and Resources (2025). The paper surveys modern approaches to climate model emulation—surrogate models that replicate Earth System Model behavior at a fraction of the computational cost. Key...
Listen
Watch
Mark as Played

Solving climate emulator physics with random CO2

June 29, 2026 • 21 mins
Machine-learning weather-climate emulators like the Ai2 Climate Emulator (ACE) can reproduce the climate of recent decades, but they break down in unfamiliar conditions, producing unphysical results when asked to simulate a world with sea surface temperatures warmed by +4 K or an abrupt quadrupling of CO2. This research traces the problem to training data in which sea surface temperature (SST) and CO2 are tightly correlated, leavin...
Listen
Watch
Mark as Played

AI learns physics from Frankenstein climates

June 29, 2026 • 60 mins
Machine-learning weather-climate emulators like the Ai2 Climate Emulator (ACE) can reproduce the climate of recent decades, but they break down in unfamiliar conditions, producing unphysical results when asked to simulate a world with sea surface temperatures warmed by +4 K or an abrupt quadrupling of CO2. This research traces the problem to training data in which sea surface temperature (SST) and CO2 are tightly correlated, leavin...
Listen
Watch
Mark as Played

Why AI weather models fail climate emulation

May 25, 2026 • 19 mins
A look at the growing body of work questioning where AI weather and climate models fall short, and why physics-based simulation remains essential. Papers discussed: Zhang et al. (2026), Physics-based models outperform AI weather forecasts of record-breaking extremes, Science Advances, https://www.science.org/doi/full/10.1126/sciadv.aec1433 — Smith & Thorpe (2026), The Primacy of Physical Simulation in the Age of AI: A Cri...
Listen
Watch
Mark as Played

AI fixes climate model blind spots

April 27, 2026 • 62 mins
Climate simulations, at all grid resolutions, rely on approximations that encapsulate the forcing due to unresolved processes on resolved variables, known as parameterizations. Parameterizations often lead to inaccuracies in climate models, with significant biases in the physics of key climate phenomena. Advances in artificial intelligence (AI) are now directly enabling the learning of unresolved processes from data to improve the ...
Listen
Watch
Mark as Played

AI fixes systematic climate model bias

April 4, 2025 • 22 mins
Coarse resolution, imperfect parameterizations, and uncertain initial states and forcings limit Earth-system model (ESM) predictions. Traditional bias correction via data assimilation improves constrained simulations but offers limited benefit once models run freely. This research introduces an operator-learning framework that maps instantaneous model states to bias-correction tendencies and applies them online during integration. ...
Listen
Watch
Mark as Played

Why Tunnel Vision Fixes Climate AI

March 30, 2025 • 21 mins
This research introduces a modified machine-learning (ML) weather emulator designed to accurately predict fast radiative feedbacks in response to varying CO2 levels. While traditional emulators often struggle with global perturbations, the authors developed a column-local architecture for the Allen Institute for Artificial Intelligence Climate Emulator (ACE) to better represent atmospheric physics. By coupling this ML model with a ...
Listen
Watch
Mark as Played

AI weather models are stuck in 1998

March 28, 2025 • 20 mins
This research investigates a significant cold bias in modern AI weather and climate models, such as FourCastNet, Pangu, and ACE2, which stems from their reliance on historical training data. By evaluating these models on recent time periods outside of their training sets, the authors discovered that the predicted temperatures often reflect climatic conditions from 15 to 30 years ago rather than current warming trends. The study hig...
Listen
Watch
Mark as Played

Popular Podcasts

    Stuff You Should Know

    Stuff You Should Know

    If you've ever wanted to know about champagne, satanism, the Stonewall Uprising, chaos theory, LSD, El Nino, true crime and Rosa Parks, then look no further. Josh and Chuck have you covered.

    Betrayal Weekly

    Betrayal Weekly

    Betrayal Weekly is back for a new season. Every Thursday, Betrayal Weekly shares first-hand accounts of broken trust, shocking deceptions, and the trail of destruction they leave behind. Hosted by Andrea Gunning, this weekly ongoing series digs into real-life stories of betrayal and the aftermath. From stories of double lives to dark discoveries, these are cautionary tales and accounts of resilience against all odds. From the producers of the critically acclaimed Betrayal series, Betrayal Weekly drops new episodes every Thursday. If you would like to share your story, you can reach out to the Betrayal Team by emailing them at betrayalpod@gmail.com and follow us on Instagram at @betrayalpod and @glasspodcasts. Please join our Substack for additional exclusive content, curated book recommendations, and community discussions. Sign up FREE by clicking this link Beyond Betrayal Substack. Join our community dedicated to truth, resilience, and healing. Your voice matters! Be a part of our Betrayal journey on Substack.

    Dateline NBC

    Dateline NBC

    Current and classic episodes, featuring compelling true-crime mysteries, powerful documentaries and in-depth investigations. Follow now to get the latest episodes of Dateline NBC completely free, or subscribe to Dateline Premium for ad-free listening and exclusive bonus content: DatelinePremium.com

    The Joe Rogan Experience

    The Joe Rogan Experience

    The official podcast of comedian Joe Rogan.

    Love Trapped

    Love Trapped

    Former Bachelor Clayton Echard’s casual one-night fling turned into a paternity nightmare. When the news broke about the scandal, no one believed Clayton at first. He was a reality TV star, and an unpopular one at that. Clayton found himself trying to prove the truth, while trapped in a web of lies, manipulation, and threats. He would soon discover he was not the only one. At its core, this is a story about who you believe and why. It’s an epic battle that would take a group of strangers, citizen sleuths from across the world, to crack the case and finally hold someone accountable. New episodes of Love Trapped are released every Thursday, starting February 26th, 2026. If you would like to reach out to the Love Trapped team, email us at lovetrappedpod@gmail.com and follow along on Instagram @glasspodcasts.

Advertise With Us
Music, radio and podcasts, all free. Listen online or download the iHeart App.

Connect

Explore

iHeart

Live Radio

Podcasts

Artist Radio

Exclusives

News

Features

Events

Contests

Photos

Information

About

Advertise

Blog

Brand Guidelines

Contest Guidelines

Subscription Offers

Jobs

Get the App

Automotive

Home

Wearables

© 2026 iHeartMedia, Inc.

  • Help
  • Privacy Policy
  • Terms of Use
  • AdChoicesAd Choices