Search for: All records

Global storm-resolving models (GSRMs) have gained widespread interest because of the unprecedented detail with which they resolve the global climate. However, it remains difficult to quantify objective differences in how GSRMs resolve complex atmospheric formations. This lack of comprehensive tools for comparing model similarities is a problem in many disparate fields that involve simulation tools for complex data. To address this challenge we develop methods to estimate distributional distances based on both nonlinear dimensionality reduction and vector quantization. Our approach automatically learns physically meaningful notions of similarity from low-dimensional latent data representations that the different models produce. This enables an intercomparison of nine GSRMs based on their high-dimensional simulation data (2D vertical velocity snapshots) and reveals that only six are similar in their representation of atmospheric dynamics. Furthermore, we uncover signatures of the convective response to global warming in a fully unsupervised way. Our study provides a path toward evaluating future high-resolution simulation data more objectively.

 

Projecting climate change is a generalization problem: We extrapolate the recent past using physical models across past, present, and future climates. Current climate models require representations of processes that occur at scales smaller than model grid size, which have been the main source of model projection uncertainty. Recent machine learning (ML) algorithms hold promise to improve such process representations but tend to extrapolate poorly to climate regimes that they were not trained on. To get the best of the physical and statistical worlds, we propose a framework, termed “climate-invariant” ML, incorporating knowledge of climate processes into ML algorithms, and show that it can maintain high offline accuracy across a wide range of climate conditions and configurations in three distinct atmospheric models. Our results suggest that explicitly incorporating physical knowledge into data-driven models of Earth system processes can improve their consistency, data efficiency, and generalizability across climate regimes.

 

Climate models are essential to understand and project climate change, yet long‐standing biases and uncertainties in their projections remain. This is largely associated with the representation of subgrid‐scale processes, particularly clouds and convection. Deep learning can learn these subgrid‐scale processes from computationally expensive storm‐resolving models while retaining many features at a fraction of computational cost. Yet, climate simulations with embedded neural network parameterizations are still challenging and highly depend on the deep learning solution. This is likely associated with spurious non‐physical correlations learned by the neural networks due to the complexity of the physical dynamical system. Here, we show that the combination of causality with deep learning helps removing spurious correlations and optimizing the neural network algorithm. To resolve this, we apply a causal discovery method to unveil causal drivers in the set of input predictors of atmospheric subgrid‐scale processes of a superparameterized climate model in which deep convection is explicitly resolved. The resulting causally‐informed neural networks are coupled to the climate model, hence, replacing the superparameterization and radiation scheme. We show that the climate simulations with causally‐informed neural network parameterizations retain many convection‐related properties and accurately generate the climate of the original high‐resolution climate model, while retaining similar generalization capabilities to unseen climates compared to the non‐causal approach. The combination of causal discovery and deep learning is a new and promising approach that leads to stable and more trustworthy climate simulations and paves the way toward more physically‐based causal deep learning approaches also in other scientific disciplines.

 

Abstract Neural networks are a promising technique for parameterizing subgrid-scale physics (e.g., moist atmospheric convection) in coarse-resolution climate models, but their lack of interpretability and reliability prevents widespread adoption. For instance, it is not fully understood why neural network parameterizations often cause dramatic instability when coupled to atmospheric fluid dynamics. This paper introduces tools for interpreting their behavior that are customized to the parameterization task. First, we assess the nonlinear sensitivity of a neural network to lower-tropospheric stability and the midtropospheric moisture, two widely studied controls of moist convection. Second, we couple the linearized response functions of these neural networks to simplified gravity wave dynamics, and analytically diagnose the corresponding phase speeds, growth rates, wavelengths, and spatial structures. To demonstrate their versatility, these techniques are tested on two sets of neural networks, one trained with a superparameterized version of the Community Atmosphere Model (SPCAM) and the second with a near-global cloud-resolving model (GCRM). Even though the SPCAM simulation has a warmer climate than the cloud-resolving model, both neural networks predict stronger heating/drying in moist and unstable environments, which is consistent with observations. Moreover, the spectral analysis can predict that instability occurs when GCMs are coupled to networks that support gravity waves that are unstable and have phase speeds larger than 5 m s −1 . In contrast, standing unstable modes do not cause catastrophic instability. Using these tools, differences between the SPCAM-trained versus GCRM-trained neural networks are analyzed, and strategies to incrementally improve both of their coupled online performance unveiled. 

While cloud-resolving models can explicitly simulate the details of small-scale storm formation and morphology, these details are often ignored by climate models for lack of computational resources. Here, we explore the potential of generative modeling to cheaply recreate small-scale storms by designing and implementing a Variational Autoencoder (VAE) that performs structural replication, dimension- ality reduction, and clustering of high-resolution vertical velocity fields. Trained on ∼ 6 · 106 samples spanning the globe, the VAE successfully reconstructs the spatial structure of convection, per- forms unsupervised clustering of convective organization regimes, and identifies anomalous storm activity, confirming the potential of generative modeling to power stochastic parameterizations of convection in climate models. 

On small scales, the tropical atmosphere tends to be either moist or very dry. This defines two states that, on large scales, are separated by a sharp margin, well identified by the antimode of the bimodal tropical column water vapor distribution. Despite recent progress in understanding physical processes governing the spatiotemporal variability of tropical water vapor, the behavior of this margin remains elusive, and we lack a simple framework to understand the bimodality of tropical water vapor in observations. Motivated by the success of coarsening theory in explaining bimodal distributions, we leverage its methodology to relate the moisture field's spatial organization to its time evolution. This results in a new diagnostic framework for the bimodality of tropical water vapor, from which we argue that the length of the margin separating moist from dry regions should evolve toward a minimum in equilibrium. As the spatial organization of moisture is closely related to the organization of tropical convection, we hereby introduce a new convective organization index (BLW) measuring the ratio of the margin's length to the circumference of a well‐defined equilibrium shape. Using BLW, we assess the evolution of self‐aggregation in idealized cloud‐resolving simulations of radiative‐convective equilibrium and contrast it to the time evolution of the Atlantic Intertropical Convergence Zone (ITCZ) in the ERA5 meteorological reanalysis product. We find that BLW successfully captures aspects of convective organization ignored by more traditional metrics, while offering a new perspective on the seasonal cycle of convective organization in the Atlantic ITCZ.

 

Tropical precipitation extremes are expected to strengthen with warming, but quantitative estimates remain uncertain because of a poor understanding of changes in convective dynamics. This uncertainty is addressed here by analyzing idealized convection-permitting simulations of radiative–convective equilibrium in long-channel geometry. Across a wide range of climates, the thermodynamic contribution to changes in instantaneous precipitation extremes follows near-surface moisture, and the dynamic contribution is positive and small but is sensitive to domain size. The shapes of mass flux profiles associated with precipitation extremes are determined by conditional sampling that favors strong vertical motion at levels where the vertical saturation specific humidity gradient is large, and mass flux profiles collapse to a common shape across climates when plotted in a moisture-based vertical coordinate. The collapse, robust to changes in microphysics and turbulence schemes, implies a thermodynamic contribution that scales with near-surface moisture despite substantial convergence aloft and allows the dynamic contribution to be defined by the pressure velocity at a single level. Linking the simplified dynamic mode to vertical velocities from entraining plume models reveals that the small dynamic mode in channel simulations ([Formula: see text]2% K⁻¹) is caused by opposing height dependences of vertical velocity and density, together with the buffering influence of cloud-base buoyancies that vary little with surface temperature. These results reinforce an emerging picture of the response of extreme tropical precipitation rates to warming: a thermodynamic mode of about 7% K⁻¹dominates, with a minor contribution from changes in dynamics.

 

There is no consensus on the physical mechanisms controlling the scale at which convective activity organizes near the Equator. Here, we introduce a diagnostic framework relating the evolution of the length‐scale of convective aggregation to the net radiative heating, the surface enthalpy flux, and horizontal energy transport. We evaluate these expansion tendencies of convective aggregation in 20 high‐resolution cloud‐permitting simulations of radiative‐convective equilibrium. While both radiative fluxes contribute to convective aggregation, the net long‐wave radiative flux operates at large scales (1,000–5,000 km) and stretches the size of moist and dry regions, while the net short‐wave flux operates at smaller scales (500–2,000 km) and shrinks it. The surface flux expansion tendency is dominated by convective gustiness, which acts to aggregate convective activity at smaller scales (500–3,000 km).