MOSAIC
An agentic scientific pipeline for discovering interpretable climate physics from observations.
Posts by Tag
- machine learning 7
- climate modeling 4
- aerosols 4
- shallow clouds 3
- satellite 3
- benchmarking 2
- emulation 2
- earth science 1
- ocean science 1
- differentiable 1
- equation discovery 1
- observations 1
machine learning
Detecting ship-tracks
Using machine learning to detect ship-tracks in satellite imagery and quantify how shipping emissions brighten clouds.
Pockets of open cells
A deep-learning census of 8,491 pockets of open cells across the Californian, Peruvian and Namibian stratocumulus decks.
JAX-GCM
A fully differentiable atmospheric model spanning fast SPEEDY physics to full ECHAM physics with online aerosol
GAIA Initiative
Harnessing AI to understand, forecast, and steward Earth’s complex systems
ClimateBench v1
Explore future warming under different emissions scenarios with an online emulator built on ClimateBench v1.
ClimateBench2
A probabilistic benchmark for evaluating physics-based, data-driven and hybrid climate models on an equal footing.
climate modeling
MOSAIC
An agentic scientific pipeline for discovering interpretable climate physics from observations.
JAX-GCM
A fully differentiable atmospheric model spanning fast SPEEDY physics to full ECHAM physics with online aerosol
Climate model emulation
Developing climate model emulators for better parameter estimation and calibration.
ClimateBench2
A probabilistic benchmark for evaluating physics-based, data-driven and hybrid climate models on an equal footing.
aerosols
Detecting ship-tracks
Using machine learning to detect ship-tracks in satellite imagery and quantify how shipping emissions brighten clouds.
Ship-track viewer
An interactive map of every ship-track detected by our machine learning algorithm, with MODIS timestamps for each track.
Pockets of open cells
A deep-learning census of 8,491 pockets of open cells across the Californian, Peruvian and Namibian stratocumulus decks.
JAX-GCM
A fully differentiable atmospheric model spanning fast SPEEDY physics to full ECHAM physics with online aerosol
shallow clouds
Detecting ship-tracks
Using machine learning to detect ship-tracks in satellite imagery and quantify how shipping emissions brighten clouds.
Ship-track viewer
An interactive map of every ship-track detected by our machine learning algorithm, with MODIS timestamps for each track.
Pockets of open cells
A deep-learning census of 8,491 pockets of open cells across the Californian, Peruvian and Namibian stratocumulus decks.
satellite
Detecting ship-tracks
Using machine learning to detect ship-tracks in satellite imagery and quantify how shipping emissions brighten clouds.
Ship-track viewer
An interactive map of every ship-track detected by our machine learning algorithm, with MODIS timestamps for each track.
Pockets of open cells
A deep-learning census of 8,491 pockets of open cells across the Californian, Peruvian and Namibian stratocumulus decks.
benchmarking
ClimateBench v1
Explore future warming under different emissions scenarios with an online emulator built on ClimateBench v1.
ClimateBench2
A probabilistic benchmark for evaluating physics-based, data-driven and hybrid climate models on an equal footing.
emulation
Climate model emulation
Developing climate model emulators for better parameter estimation and calibration.
ClimateBench v1
Explore future warming under different emissions scenarios with an online emulator built on ClimateBench v1.
earth science
GAIA Initiative
Harnessing AI to understand, forecast, and steward Earth’s complex systems
ocean science
GAIA Initiative
Harnessing AI to understand, forecast, and steward Earth’s complex systems
differentiable
JAX-GCM
A fully differentiable atmospheric model spanning fast SPEEDY physics to full ECHAM physics with online aerosol
equation discovery
MOSAIC
An agentic scientific pipeline for discovering interpretable climate physics from observations.
observations
MOSAIC
An agentic scientific pipeline for discovering interpretable climate physics from observations.