An official website of the United States government
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.
more »
« less
Comparing storm resolving models and climates via unsupervised machine learning
Abstract 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.
more »
« less
- PAR ID:
- 10550287
- Publisher / Repository:
- Nature
- Date Published:
- Journal Name:
- Scientific Reports
- Volume:
- 13
- Issue:
- 1
- ISSN:
- 2045-2322
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Current and upcoming cosmological surveys will produce unprecedented amounts of high-dimensional data, which require complex high-fidelity forward simulations to accurately model both physical processes and systematic effects which describe the data generation process. However, validating whether our theoretical models accurately describe the observed datasets remains a fundamental challenge. An additional complexity to this task comes from choosing appropriate representations of the data which retain all the relevant cosmological information, while reducing the dimensionality of the original dataset. In this work we present a novel framework combining scale-dependent neural summary statistics with normalizing flows to detect model misspecification in cosmological simulations through Bayesian evidence estimation. By conditioning our neural network models for data compression and evidence estimation on the smoothing scale, we systematically identify where theoretical models break down in a data-driven manner. We demonstrate a first application of our approach using simulated total matter and gas density fields from three hydrodynamic simulation suites with different subgrid physics implementations.more » « less
-
Abstract Future changes in the Beaufort Gyre liquid freshwater content (LFWC) are important for the local and global climate. However, traditional climate models cannot resolve oceanic and atmospheric eddies that are critical to the LFWC variations. In this study, we investigate physical processes controlling Beaufort Gyre LFWC changes in an eddy‐resolving simulation. The model simulation largely reproduces the observed LFWC changes, and projects a long‐term LFWC increase with an intensification of its decadal variability during the 21st century. Freshwater budget analysis suggests that future LFWC changes are strongly influenced by sea ice melt. The conversion from solid to liquid phase provides more liquid freshwater into the ocean. Meanwhile, sea ice loss enhances the efficiency of air‐sea momentum transfer, leading to increased wind‐driven freshwater convergence and its variability. The decadal variation of the LFWC will regulate Arctic freshwater exports and coincident with an O (0.5 Sv) change in the meridional overturning circulation.more » « less
-
Abstract Detailed knowledge of chemical processes in the atmosphere is key to our understanding of regional air pollution and global climate change. However, a complete description of all atmospheric chemical reactions is still out of reach. This necessitates the discovery of new reactions for improved predictability and process understanding. Here, we propose a data‐driven, chemical kinetics‐oriented approach for atmospheric chemical reaction discovery. Our approach leverages time series of species abundances and an incomplete chemical mechanism to predict the existence of new chemistry by “completing” the mechanism. Species abundances and the incomplete mechanism serve as inputs to a variant of graph neural networks known as graph autoencoders (GAEs). The GAE learns a low‐dimensional representation of the chemical system to predict the existence of pairwise chemical interactions occurring between species. We assess our model using GEOS‐Chem, a widely used atmospheric chemical mechanism that represents the complex set of chemical interactions in the atmosphere. Our reaction discovery model achieves high predictive performance (0.9085 mean AUC; 90.06% average precision) in recovering unseen reactions and outperforms other competitive baselines. The success of this method solidifies its promise in discovering unknown chemical reactions and warrants further application to additional atmospheric chemistry contexts.more » « less
-
Abstract As modeling tools and approaches become more advanced, ecological models are becoming more complex. Traditional sensitivity analyses can struggle to identify the nonlinearities and interactions emergent from such complexity, especially across broad swaths of parameter space. This limits understanding of the ecological mechanisms underlying model behavior. Machine learning approaches are a potential answer to this issue, given their predictive ability when applied to complex large datasets. While perceptions that machine learning is a “black box” linger, we seek to illuminate its interpretive potential in ecological modeling. To do so, we detail our process of applying random forests to complex model dynamics to produce both high predictive accuracy and elucidate the ecological mechanisms driving our predictions. Specifically, we employ an empirically rooted ontogenetically stage-structured consumer-resource simulation model. Using simulation parameters as feature inputs and simulation output as dependent variables in our random forests, we extended feature analyses into a simple graphical analysis from which we reduced model behavior to three core ecological mechanisms. These ecological mechanisms reveal the complex interactions between internal plant demography and trophic allocation driving community dynamics while preserving the predictive accuracy achieved by our random forests.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript
- Journal Article:
- https://doi.org/10.1038/s41598-023-49455-w
