Search for: All records

Abstract Global climate models parameterize a range of atmospheric‐oceanic processes, including gravity waves (GWs), clouds, moist convection, and turbulence, that cannot be sufficiently resolved. These subgrid‐scale closures for unresolved processes are a substantial source of model uncertainty. Here, we present a new approach to developing machine learning (ML) parameterizations of small‐scale climate processes by fine‐tuning a pre‐trained AI foundation model (FM). FMs are largely unexplored in climate research. A pre‐trained encoder‐decoder from a 2.3 billion parameter FM (NASA and IBM Research's Prithvi WxC)—which contains a latent probabilistic representation of atmospheric evolution—is fine‐tuned (or reused) to create a deep learning parameterization for atmospheric gravity waves (GWs); a process unseen during pre‐training. The parameterization captures GW effects for a coarse‐resolution climate model by learning the fluxes from an atmospheric reanalysis with 10 times finer resolution. A comparison of monthly averages and instantaneous evolution with a machine learning model baseline (an Attention U‐Net) reveals superior predictive performance of the FM parameterization throughout the atmosphere, even in regions excluded during pre‐training. This performance boost is quantified using the Hellinger distance, which is 0.11 for the baseline and 0.06 for the fine‐tuned model. Our findings emphasize the versatility and reusability of FMs, which could be used to accomplish a range of atmosphere‐ and climate‐related applications, leading the way for the creation of observations‐driven and physically accurate parameterizations for more earth system processes. 

Abstract Gravity waves (GWs) make crucial contributions to the middle atmospheric circulation. Yet, their climate model representation remains inaccurate, leading to key circulation biases. This study introduces a set of three neural networks (NNs) that learn to predict GW fluxes (GWFs) from multiple years of high‐resolution ERA5 reanalysis. The three NNs: a ANN, a ANN‐CNN, and an Attention UNet embed different levels of horizontal nonlocality in their architecture and are capable of representing nonlocal GW effects that are missing from current operational GW parameterizations. The NNs are evaluated offline on both time‐averaged statistics and time‐evolving flux variability. All NNs, especially the Attention UNet, accurately recreate the global GWF distribution in both the troposphere and the stratosphere. Moreover, the Attention UNet most skillfully predicts the transient evolution of GWFs over prominent orographic and nonorographic hotspots, with the model being a close second. Since even ERA5 does not resolve a substantial portion of GWFs, this deficiency is compensated by subsequently applying transfer learning on the ERA5‐trained ML models for GWFs from a 1.4 km global climate model. It is found that the re‐trained models both (a) preserve their learning from ERA5, and (b) learn to appropriately scale the predicted fluxes to account for ERA5's limited resolution. Our results highlight the importance of embedding nonlocal information for a more accurate GWF prediction and establish strategies to complement abundant reanalysis data with limited high‐resolution data to develop machine learning‐driven parameterizations for missing mesoscale processes in climate models. 

Abstract We investigate a scaling relationship between global tropical cyclone (TC) frequency and the latitude of the intertropical convergence zone (ITCZ) in simulations performed with a 50‐km‐resolution aquaplanet version of the Geophysical Fluid Dynamics Laboratory Atmosphere Model 4.0. The simulations use fixed, zonally symmetric sea surface temperature distributions, including some with uniform warming and cooling perturbations. We find that TC frequency per unit area is proportional to the Coriolis parameter at the ITCZ, following the same scaling introduced in a previous study. We hypothesize that TCs in these simulations originate as precursor disturbances at the ITCZ and intensify into TCs upon reaching sufficiently warm SSTs. We test this interpretation by tracking TC precursors, with different methods based on precipitation and vorticity, and comparing TC precursor frequency with TC frequency and ITCZ latitude. Both tracking methods show that precursors predominantly originate around the poleward edge of the ITCZ, consistent with our hypothesized TC genesis pathway. We also verify that most TC genesis events are immediately preceded by the occurrence of a precursor in the same area. However, precursor frequency is only weakly correlated with the Coriolis parameter at the ITCZ and precursor frequency. The correlation is stronger for vorticity‐based precursors than for precipitation‐based precursors. These mixed results provide partial, but not complete, support for our hypothesized interpretation. They also illustrate how results can depend on the choice of precursor tracking scheme, underlining a need for improved understanding of how best to define and track TC precursors. 

Abstract We discuss the emerging advances and opportunities at the intersection of machine learning (ML) and climate physics, highlighting the use of ML techniques, including supervised, unsupervised, and equation discovery, to accelerate climate knowledge discoveries and simulations. We delineate two distinct yet complementary aspects: (a) ML for climate physics and (b) ML for climate simulations. Although physics-free ML-based models, such as ML-based weather forecasting, have demonstrated success when data are abundant and stationary, the physics knowledge and interpretability of ML models become crucial in the small-data/nonstationary regime to ensure generalizability. Given the absence of observations, the long-term future climate falls into the small-data regime. Therefore, ML for climate physics holds a critical role in addressing the challenges of ML for climate simulations. We emphasize the need for collaboration among climate physics, ML theory, and numerical analysis to achieve reliable ML-based models for climate applications. 

Abstract Subgrid‐scale processes, such as atmospheric gravity waves (GWs), play a pivotal role in shaping the Earth's climate but cannot be explicitly resolved in climate models due to limitations on resolution. Instead, subgrid‐scale parameterizations are used to capture their effects. Recently, machine learning (ML) has emerged as a promising approach to learn parameterizations. In this study, we explore uncertainties associated with a ML parameterization for atmospheric GWs. Focusing on the uncertainties in the training process (parametric uncertainty), we use an ensemble of neural networks to emulate an existing GW parameterization. We estimate both offline uncertainties in raw NN output and online uncertainties in climate model output, after the neural networks are coupled. We find that online parametric uncertainty contributes a significant source of uncertainty in climate model output that must be considered when introducing NN parameterizations. This uncertainty quantification provides valuable insights into the reliability and robustness of ML‐based GW parameterizations, thus advancing our understanding of their potential applications in climate modeling. 

Abstract The study presents (a) a 44‐year wintertime climatology of resolved gravity wave (GW) fluxes and forcing in the extratropical stratosphere using ERA5, and (b) their composite evolution around gradual (final warming) and abrupt (sudden warming) transitions in the wintertime circulation, focusing on lateral fluxes. The transformed Eulerian mean equations are leveraged to provide a glimpse of the importance of GW lateral propagation (i.e., horizontal propagation) toward driving the wintertime stratospheric circulation by analyzing the relative contribution of the vertical versus meridional flux dissipation. The relative contribution from lateral propagation is found to be notable, especially in the Austral winter stratosphere where lateral (vertical) momentum flux convergence provides a peak climatological forcing of up to −0.5 (−3.5) m/s/day around 60°S at 40–45 km altitude. Prominent lateral propagation in the wintertime midlatitudes also contributes to the formation of belts of GW activity in both hemispheres. 

Abstract We present estimates of gravity wave momentum fluxes calculated from Project Loon superpressure balloon data collected between 2013 and 2021. In total, we analyzed more than 5,000 days of data from balloon flights in the lower stratosphere, flights often over regions or during times of the year without any previous in‐situ observations of gravity waves. Maps of mean momentum fluxes show significant regional variability; we analyze that variability using the statistics of the momentum flux probability distributions for six regions: the Southern Ocean, the Indian Ocean, and the tropical and extratropical Pacific and Atlantic Oceans. The probability distributions are all approximately log‐normal, and using their geometric means and geometric standard deviations we statistically explain the sign and magnitude of regional mean and 99th percentile zonal momentum fluxes and regional momentum flux intermittencies. We study the dependence of the zonal momentum flux on the background zonal wind and argue that the increase of the momentum flux with the wind speed over the Southern Ocean is likely due to a varying combination of both wave sources and filtering. Finally, we show that as the magnitude of the momentum flux increases, the fractional contributions by high‐frequency waves increases, waves which need to be parameterized in large‐scale models of the atmosphere. In particular, the near‐universality of the log‐normal momentum flux probability distribution, and the relation of its statistical moments to the mean momentum flux and intermittency, offer useful checks when evaluating parameterized or resolved gravity waves in models. 

Abstract Breaking atmospheric gravity waves (GWs) in the tropical stratosphere are essential in driving the roughly 2‐year oscillation of zonal winds in this region known as the Quasi‐Biennial Oscillation (QBO). As Global Climate Models (GCM)s are not typically able to directly resolve the spectrum of waves required to drive the QBO, parameterizations are necessary. Such parameterizations often require knowledge of poorly constrained physical parameters. In the case of the spectral gravity parameterization used in this work, these parameters are the total equatorial GW stress and the half width of phase speed distribution. Radiosonde observations are used to obtain the period and amplitude of the QBO, which are compared against values obtained from a GCM. We utilize two established calibration techniques to obtain estimates of the range of plausible parameter values: History matching & Ensemble Kalman Inversion (EKI). History matching is found to reduce the size of the initial range of plausible parameters by a factor of 98%, requiring only 60 model integrations. EKI cannot natively provide any uncertainty quantification but is able to produce a single best estimate of the calibrated values in 25 integrations. When directly comparing the approaches using the Calibrate, Emulate, Sample method to produce a posterior estimate from EKI, history matching produces more compact posteriors with fewer model integrations at lower ensemble sizes compared to EKI; however, these differences become less apparent at higher ensemble sizes. 

Abstract Neural networks (NNs) are increasingly used for data‐driven subgrid‐scale parameterizations in weather and climate models. While NNs are powerful tools for learning complex non‐linear relationships from data, there are several challenges in using them for parameterizations. Three of these challenges are (a) data imbalance related to learning rare, often large‐amplitude, samples; (b) uncertainty quantification (UQ) of the predictions to provide an accuracy indicator; and (c) generalization to other climates, for example, those with different radiative forcings. Here, we examine the performance of methods for addressing these challenges using NN‐based emulators of the Whole Atmosphere Community Climate Model (WACCM) physics‐based gravity wave (GW) parameterizations as a test case. WACCM has complex, state‐of‐the‐art parameterizations for orography‐, convection‐, and front‐driven GWs. Convection‐ and orography‐driven GWs have significant data imbalance due to the absence of convection or orography in most grid points. We address data imbalance using resampling and/or weighted loss functions, enabling the successful emulation of parameterizations for all three sources. We demonstrate that three UQ methods (Bayesian NNs, variational auto‐encoders, and dropouts) provide ensemble spreads that correspond to accuracy during testing, offering criteria for identifying when an NN gives inaccurate predictions. Finally, we show that the accuracy of these NNs decreases for a warmer climate (4 × CO₂). However, their performance is significantly improved by applying transfer learning, for example, re‐training only one layer using ∼1% new data from the warmer climate. The findings of this study offer insights for developing reliable and generalizable data‐driven parameterizations for various processes, including (but not limited to) GWs. 

Abstract The climate model hierarchy encompasses models of varying complexity along different axes, ranging from idealized models that elegantly describe isolated mechanisms to fully coupled Earth system models that aspire to provide useable climate projections. Based on the second Model Hierarchies Workshop, which took place in 2022, we present perspectives on how this field has evolved since the first Model Hierarchies Workshop in 2016. In this period, we have witnessed a dramatic increase in the use of (a) machine learning in climate modeling and (b) climate models to estimate risks and influence decision making under climate change. Here, we discuss the implications of these growing areas of research and how we expect them to become integrated into the model hierarchies framework.