OceanCBM is the first concept bottleneck model for spatiotemporal ocean prediction that uses mixed supervision on physical concepts and a free concept to deliver consistent mechanistic representations for mixed layer heat content forecasts.
Samudrace: Fast and accurate coupled climate modeling with 3d ocean and atmosphere emulators
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
Historically trained ML weather emulators quantify fast precipitation changes from CO2 perturbations and produce results that agree with Earth System Models.
HealDA supplies ML-based initial conditions for AI weather models that produce forecasts trailing ERA5-initialized runs by less than one day of effective lead time, with the skill gap arising mainly from initial error size.
With proper scaling and training convergence, a moderate-sized feedforward neural network can reproduce key aerosol concentration changes from the MAM4 microphysics module in E3SMv2.
AI methods can strengthen cross-domain interactions and support more coherent multi-component representations in Earth system models.
citing papers explorer
-
OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting
OceanCBM is the first concept bottleneck model for spatiotemporal ocean prediction that uses mixed supervision on physical concepts and a free concept to deliver consistent mechanistic representations for mixed layer heat content forecasts.
-
Examining Fast Radiatively Driven Responses Using Machine-Learning Weather Emulators
Historically trained ML weather emulators quantify fast precipitation changes from CO2 perturbations and produce results that agree with Earth System Models.
-
HealDA: Highlighting the importance of initial errors in end-to-end AI weather forecasts
HealDA supplies ML-based initial conditions for AI weather models that produce forecasts trailing ERA5-initialized runs by less than one day of effective lead time, with the skill gap arising mainly from initial error size.
-
Assessing Emulator Design and Training for Modal Aerosol Microphysics Parameterizations in E3SMv2
With proper scaling and training convergence, a moderate-sized feedforward neural network can reproduce key aerosol concentration changes from the MAM4 microphysics module in E3SMv2.
-
Toward Artificial Intelligence Enabled Earth System Coupling
AI methods can strengthen cross-domain interactions and support more coherent multi-component representations in Earth system models.