Historically trained ML weather emulators quantify fast precipitation changes from CO2 perturbations and produce results that agree with Earth System Models.
ACE: A fast, skillful learned global atmospheric model for climate prediction
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
representative citing papers
A GraphCast-based ocean emulator achieves skillful 10-15 day forecasts, with a Mahalanobis loss that accounts for variable correlations improving performance over MSE and acting as a statistical-dynamical regularizer.
A framework builds stable neural models of turbulent dynamics by enforcing energy-preserving nonlinearities and causal constraints in discrete-time flow maps, demonstrated on Charney-DeVore and Lorenz-96 systems.
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.
Image-to-image networks estimate parameters of non-stationary SAR models faster and more accurately than traditional methods by framing fields and parameters as images.
Adversarial optimal transport objectives train neural emulators with improved long-term statistical fidelity on chaotic systems.
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.
A PMP-based evaluation framework for testing deep-learning Earth system models on climate-relevant diagnostics beyond short-range forecasts.
citing papers explorer
-
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.
-
Skillful Global Ocean Emulation and the Role of Correlation-Aware Loss
A GraphCast-based ocean emulator achieves skillful 10-15 day forecasts, with a Mahalanobis loss that accounts for variable correlations improving performance over MSE and acting as a statistical-dynamical regularizer.
-
Physics and causally constrained discrete-time neural models of turbulent dynamical systems
A framework builds stable neural models of turbulent dynamics by enforcing energy-preserving nonlinearities and causal constraints in discrete-time flow maps, demonstrated on Charney-DeVore and Lorenz-96 systems.
-
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.
-
LatticeVision: Image to Image Networks for Modeling Non-Stationary Spatial Data
Image-to-image networks estimate parameters of non-stationary SAR models faster and more accurately than traditional methods by framing fields and parameters as images.
-
Learning to Emulate Chaos: Adversarial Optimal Transport Regularization
Adversarial optimal transport objectives train neural emulators with improved long-term statistical fidelity on chaotic systems.
-
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.
-
A PMP-inspired Evaluation Framework for Assessing Deep-Learning Earth System Models
A PMP-based evaluation framework for testing deep-learning Earth system models on climate-relevant diagnostics beyond short-range forecasts.