NESYM combines AI and Earth models for new climate insights.
problem Replacing traditional Earth models with AI.
method Neural Earth System Modelling (NESYM) integrating AI and climate models.
result Artificial intelligence may render traditional models obsolete.
A new method estimates time-varying parameters in earth system models using offline and online data assimilation.
problem Estimating time-varying parameters in complex earth system models.
method Hybrid Offline Online Parameter Estimation with Particle Filtering (HOOPE-PF)
result HOOPE-PF outperforms existing methods, especially with small ensemble sizes.
Efficient surrogate model reduces ESM evaluation time.
problem Reducing computational time for large-scale ESM simulations.
method SVD for dimensionality reduction followed by Bayesian optimization for neural network surrogate.
result 20 ESM simulations build a 42660-variable surrogate with 93% consistency and 2% MSE.
Blueprint for ESMs that learn from observations and high-res simulations.
problem Large uncertainties in climate projections due to parameterized processes.
method Integrates global observations and high-resolution simulations through machine learning and data assimilation.
result ESMs can learn from both global and high-resolution data, reducing uncertainties.
TerraNova models Earth and societies as a unified system.
problem Modeling the physical Earth and human societies as a coupled system.
method TerraNova integrates physical Earth fields and societal indicators in their native geometries using encoders, cross-modal transformers, and a hypernetwork.
result TerraNova represents the physical Earth and societies without lossy averaging over borders, achieving competitive performance and spanning axes not represented by purpose-built encoders.
Generative models emulate climate model outputs for impact assessment.
problem Outdated climate model projections hinder adaptation and mitigation planning.
method Score-based diffusion on a spherical mesh, trained on monthly ESM fields.
result Generative models produce distributions closely matching ESM outputs.
Kernel methods' derivatives make complex models more interpretable.
problem Interpreting complex kernel models.
method Deriving kernel functions' derivatives and applying them to various kernel methods.
result Derivatives of kernel functions can be computed and applied to improve model interpretation.
Deep learning models match traditional surrogate models in accuracy and speed for satellite remote sensing.
problem Limited computational power hinders high-resolution numerical model simulations.
method Deep learning framework applied to satellite remote sensing data.
result Deep learning models can accurately and efficiently emulate numerical models.
DecoR estimates causal effects in confounded time series data.
problem Estimating causal effects in time series with unobserved confounders.
method Robust regression in the frequency domain.
result Proves upper bounds for estimation error of DecoR, implying consistency.
The paper applies Gaussianization to analyze Earth data, simplifying complex multivariate distributions.
problem Challenges in accurately estimating information content in high-dimensional, heterogeneous Earth data.
method Multivariate Gaussianization for robust probability density estimation.
result Validates the method for estimating information-theoretic measures in Earth system data.
Machine learning predicts seasonal precipitation for East Africa.
problem Predicting seasonal precipitation for East Africa using machine learning.
method Dimension reduction via EOFs, large-scale climate variability indices as features, interpretable ML algorithm.
result The ML approach shows significant positive skill in predicting precipitation for OND season, comparable to ECMWF forecasts.
A new method for faster spatial modeling on exascale computers.
problem Scalable, memory-efficient machine learning for spatially distributed data.
method Partitioned Sparse Variational Gaussian Process (PSVGP) with decentralized communication.
result Improved spatial predictions and better model fit with minimal overhead.
FaIRGP model improves climate emulation with physical interpretability.
problem Lack of physical interpretability in data-driven emulators.
method Bayesian approach to a data-driven emulator of energy balance equations.
result Demonstrates skillful emulation of global and spatial surface temperatures.
Reservoir Computing enhances climate predictability studies.
problem Improving climate predictability using machine learning.
method Reservoir Computing applied to climate data.
result Reservoir Computing outperforms traditional LIM in predicting climate variables.
Deep learning improves aerosol optical depth predictions from reanalysis data.
problem Biases in reanalysis datasets like MERRA-2 against ground truth AOD measurements.
method A hybrid CNN model combining MERRA-2 reanalysis with deep learning.
result The CNN-based model provides better AOD estimates than MERRA-2 alone.
Extends DRFGP to make GPs more robust and adaptive for dynamic, noisy data.
problem Limited scalability, static targets, and brittleness to outliers in GPs.
method Introduces robust-filtering update and dynamic adaptation mechanism.
result Enhanced stability and accuracy in modeling dynamic, noisy data.
Generative AI predicts Arctic sea ice dynamics over decades.
problem Reproducing realistic sea ice dynamics from days to decades is computationally challenging.
method Introduced GenSIM, a generative AI model trained on 20 years of sea-ice-ocean simulation data.
result Generative AI predicts realistic sea ice evolution for 30 years, capturing long-term trends and physical consistency.
HECT tests climate model outputs for reproducibility.
problem Ensuring climate models accurately reflect physical processes.
method Probabilistic classifiers for high-dimensional spatio-temporal data.
result A principled way to assess statistical reproducibility of climate models.
This paper corrects climate model biases using a factor model approach.
problem Systematic biases in GCM outputs due to unobserved confounders.
method Factor model approach to learn latent confounders from historical data and apply them to enhance bias correction.
result Significant improvements in the accuracy of precipitation outputs.
A hybrid model combines physics and machine learning to predict unknown processes in numerical models.
problem Unknown or poorly represented processes in numerical models of the Earth System.
method Combining a physical model with a neural-net trained on observations.
result The hybrid model accurately predicts unknown processes with high correlation (close to 1).
Future projection of climate is typically obtained by combining outputs from multiple Earth System Models (ESMs) for several climate variables such as temperature and precipitation. While IPCC has traditionally used a simple model output average, recent work has illustrated potential advantages of using a multitask lea…
ClimART dataset benchmarks ML emulators for atmospheric RT in climate models.
problem Lack of a comprehensive dataset and standardized practices for ML benchmarking in climate models.
method Builds ClimART, a large dataset with over 10 million samples, and presents novel baselines.
result Indicates shortcomings of prior datasets and network architectures.
Machine learning improves chaotic dynamical system simulations with empirical error correction.
problem Improving chaotic dynamical system simulations using machine learning.
method Combining machine learning with physically-derived models to correct timestep errors.
result The approach yields stable models with improved long-term statistics and single time-step tendencies.
SPF uses a hierarchical approach to efficiently emulate climate changes.
problem Slow and unstable climate emulation for long horizons.
method Spatiotemporal Pyramid Flows (SPF) model data hierarchically across spatial and temporal scales.
result SPF outperforms flow matching baselines and pre-trained models on ClimateBench.
Deep learning improves climate models by capturing sub-grid processes efficiently.
problem Uncertainty in climate models due to sub-grid processes, especially clouds.
method Trained a deep neural network to represent atmospheric sub-grid processes in a climate model.
result The neural network accurately reproduces climate and variability features from a cloud-resolving model.
Neural networks improve geoscience by enabling interpretable decision pathways.
problem Lack of methods to interpret neural networks' learning and decision-making.
method Backwards optimization and layerwise relevance propagation.
result Interpretation techniques reveal meaningful connections in geoscientific data.
ACI identifies cause-effect relationships and causal influence ranges in dynamical systems.
problem Detecting and quantifying causal influence ranges in complex systems.
method Bayesian data assimilation and assimilative causal inference (ACI) to trace causes back from observed effects.
result Mathematically rigorous formulations of forward and backward causal influence ranges (CIRs) for nonlinear dynamical systems.