A Perspective on Foundation Models for the Electric Power Grid

no code implementations • 12 Jul 2024 • Hendrik F. Hamann, Thomas Brunschwiler, Blazhe Gjorgiev, Leonardo S. A. Martins, Alban Puech, Anna Varbella, Jonas Weiss, Juan Bernabe-Moreno, Alexandre Blondin Massé, Seong Choi, Ian Foster, Bri-Mathias Hodge, Rishabh Jain, Kibaek Kim, Vincent Mai, François Mirallès, Martin De Montigny, Octavio Ramos-Leaños, Hussein Suprême, Le Xie, El-Nasser S. Youssef, Arnaud Zinflou, Alexander J. Belvi, Ricardo J. Bessa, Bishnu Prasad Bhattari, Johannes Schmude, Stanislav Sobolevsky

Foundation models (FMs) currently dominate news headlines.

A 3D super-resolution of wind fields via physics-informed pixel-wise self-attention generative adversarial network

no code implementations • 20 Dec 2023 • Takuya Kurihana, Kyongmin Yeo, Daniela Szwarcman, Bruce Elmegreen, Karthik Mukkavilli, Johannes Schmude, Levente Klein

To mitigate global warming, greenhouse gas sources need to be resolved at a high spatial resolution and monitored in time to ensure the reduction and ultimately elimination of the pollution source.

Generative Adversarial Network Super-Resolution

AI Foundation Models for Weather and Climate: Applications, Design, and Implementation

no code implementations • 19 Sep 2023 • S. Karthik Mukkavilli, Daniel Salles Civitarese, Johannes Schmude, Johannes Jakubik, Anne Jones, Nam Nguyen, Christopher Phillips, Sujit Roy, Shraddha Singh, Campbell Watson, Raghu Ganti, Hendrik Hamann, Udaysankar Nair, Rahul Ramachandran, Kommy Weldemariam

In particular, we are witnessing the rise of AI foundation models that can perform competitively on multiple domain-specific downstream tasks.

Language Modelling Operator learning +4

TensorBank: Tensor Lakehouse for Foundation Model Training

no code implementations • 5 Sep 2023 • Romeo Kienzler, Leonardo Pondian Tizzei, Benedikt Blumenstiel, Zoltan Arnold Nagy, S. Karthik Mukkavilli, Johannes Schmude, Marcus Freitag, Michael Behrendt, Daniel Salles Civitarese, Naomi Simumba, Daiki Kimura, Hendrik Hamann

Storing and streaming high dimensional data for foundation model training became a critical requirement with the rise of foundation models beyond natural language.