Marsh
@mrshll.com
high-tech skills, low-tech ambitions.
---
For work, I run https://upstream.tech, an org that forecasts the future of rivers and monitors natural and conserved spaces. I also started https://dynamical.org to make weather data more fun to work with.
---
For work, I run https://upstream.tech, an org that forecasts the future of rivers and monitors natural and conserved spaces. I also started https://dynamical.org to make weather data more fun to work with.
Had a great time visiting my "local" hydropower powerhouses: Oak Ridge National Lab and TVA's River Forecast Center.
Got to see the Frontier supercomputer (the computer-building kid in me squealed - it's the world's first exascale supercomputer) and the super cool control room at TVA.
Got to see the Frontier supercomputer (the computer-building kid in me squealed - it's the world's first exascale supercomputer) and the super cool control room at TVA.
November 27, 2025 at 2:37 AM
Had a great time visiting my "local" hydropower powerhouses: Oak Ridge National Lab and TVA's River Forecast Center.
Got to see the Frontier supercomputer (the computer-building kid in me squealed - it's the world's first exascale supercomputer) and the super cool control room at TVA.
Got to see the Frontier supercomputer (the computer-building kid in me squealed - it's the world's first exascale supercomputer) and the super cool control room at TVA.
🌤️ weathering 003: NeuralGCM and the Hybrid Approach
the debate of theory vs machine learning is nothing new. Not quite "age old" but certainly "off the age".
NeuralGCM, like a good negotiator and meme appreciator says "why not both" but in a pretty spectactular way.
the debate of theory vs machine learning is nothing new. Not quite "age old" but certainly "off the age".
NeuralGCM, like a good negotiator and meme appreciator says "why not both" but in a pretty spectactular way.
July 30, 2025 at 1:05 AM
🌤️ weathering 003: NeuralGCM and the Hybrid Approach
the debate of theory vs machine learning is nothing new. Not quite "age old" but certainly "off the age".
NeuralGCM, like a good negotiator and meme appreciator says "why not both" but in a pretty spectactular way.
the debate of theory vs machine learning is nothing new. Not quite "age old" but certainly "off the age".
NeuralGCM, like a good negotiator and meme appreciator says "why not both" but in a pretty spectactular way.
Jack Silverman @ urban cowboy; 2025-01-20
January 21, 2025 at 2:07 PM
Jack Silverman @ urban cowboy; 2025-01-20