arXiv subjects

Laure Zanna

Publications and source records attributed to Laure Zanna.

50 records · Page 3Linked to original sources

arXiv2024

A data-driven framework for dimensionality reduction and causal inference in climate fields

We propose a data-driven framework to simplify the description of spatiotemporal climate variability into few entities and their causal linkages. Given a high-dimensional climate field, the methodology first reduces its dimensionality into a set of regionally constrained patterns. Time-dependent causal links are then inferred in the interventional sense through the fluctuation-response formalism, as shown in Baldovin et al. (2020). These two steps allow to explore how regional climate variability can influence remote locations. To distinguish between true and spurious responses, we propose a novel analytical null model for the fluctuation-dissipation relation, therefore allowing for uncertainty estimation at a given confidence level. Finally, we select a set of metrics to summarize the results, offering a useful and simplified approach to explore climate dynamics. We showcase the methodology on the monthly sea surface temperature field at global scale. We demonstrate the usefulness of the proposed framework by studying few individual links as well as "link maps", visualizing the cumulative degree of causation between a given region and the whole system. Finally, each pattern is ranked in terms of its "causal strength", quantifying its relative ability to influence the system's dynamics. We argue that the methodology allows to explore and characterize causal relationships in high-dimensional spatiotemporal fields in a rigorous and interpretable way.

physics.ao-ph↗

arXiv2024

Building Ocean Climate Emulators

The current explosion in machine learning for climate has led to skilled, computationally cheap emulators for the atmosphere. However, the research for ocean emulators remains nascent despite the large potential for accelerating coupled climate simulations and improving ocean forecasts on all timescales. There are several fundamental questions to address that can facilitate the creation of ocean emulators. Here we focus on two questions: 1) the role of the atmosphere in improving the extended skill of the emulator and 2) the representation of variables with distinct timescales (e.g., velocity and temperature) in the design of any emulator. In tackling these questions, we show stable prediction of surface fields for over 8 years, training and testing on data from a high-resolution coupled climate model, using results from four regions of the globe. Our work lays out a set of physically motivated guidelines for building ocean climate emulators.

physics.ao-ph↗

arXiv2023

Machine learning for online sea ice bias correction within global ice-ocean simulations

In this study we perform online sea ice bias correction within a GFDL global ice-ocean model. For this, we use a convolutional neural network (CNN) which was developed in a previous study (Gregory et al., 2023) for the purpose of predicting sea ice concentration (SIC) data assimilation (DA) increments. An initial implementation of the CNN shows systematic improvements in SIC biases relative to the free-running model, however large summertime errors remain. We show that these residual errors can be significantly improved with a data augmentation approach, in which sequential CNN and DA corrections are applied to a new simulation over the training period. This then provides a new training data set with which to refine the weights of the initial network. We propose that this machine-learned correction scheme could be utilized for generating improved initial conditions, and also for real-time sea ice bias correction within seasonal-to-subseasonal sea ice forecasts.

physics.ao-ph↗

arXiv2023

Parameterizing Vertical Mixing Coefficients in the Ocean Surface Boundary Layer using Neural Networks

Vertical mixing parameterizations in ocean models are formulated on the basis of the physical principles that govern turbulent mixing. However, many parameterizations include ad hoc components that are not well constrained by theory or data. One such component is the eddy diffusivity model, where vertical turbulent fluxes of a quantity are parameterized from a variable eddy diffusion coefficient and the mean vertical gradient of the quantity. In this work, we improve a parameterization of vertical mixing in the ocean surface boundary layer by enhancing its eddy diffusivity model using data-driven methods, specifically neural networks. The neural networks are designed to take extrinsic and intrinsic forcing parameters as input to predict the eddy diffusivity profile and are trained using output data from a second moment closure turbulent mixing scheme. The modified vertical mixing scheme predicts the eddy diffusivity profile through online inference of neural networks and maintains the conservation principles of the standard ocean model equations, which is particularly important for its targeted use in climate simulations. We describe the development and stable implementation of neural networks in an ocean general circulation model and demonstrate that the enhanced scheme outperforms its predecessor by reducing biases in the mixed-layer depth and upper ocean stratification. Our results demonstrate the potential for data-driven physics-aware parameterizations to improve global climate models.

physics.ao-ph↗

arXiv2023

Reliable coarse-grained turbulent simulations through combined offline learning and neural emulation

Integration of machine learning (ML) models of unresolved dynamics into numerical simulations of fluid dynamics has been demonstrated to improve the accuracy of coarse resolution simulations. However, when trained in a purely offline mode, integrating ML models into the numerical scheme can lead to instabilities. In the context of a 2D, quasi-geostrophic turbulent system, we demonstrate that including an additional network in the loss function, which emulates the state of the system into the future, produces offline-trained ML models that capture important subgrid processes, with improved stability properties.

physics.flu-dyn↗

arXiv2023

Background Pycnocline depth constrains Future Ocean Heat Uptake Efficiency

The Ocean Heat Uptake Efficiency (OHUE) quantifies the ocean's ability to mitigate surface warming through deep heat sequestration. Despite its importance, the main controls on OHUE, as well as its nearly two-fold spread across contemporary climate models, remain unclear. We argue that OHUE is primarily controlled by the strength of mid-latitude ventilation in the background climate, itself related to subtropical pycnocline depth and ocean stratification. This hypothesis is supported by a strong correlation between OHUE and pycnocline depth in the CMIP5 and CMIP6 under RCP85/SSP585, as well as in MITgcm. We explain these results through a regional OHUE decomposition, showing that the mid-latitudes largely account for both: (1) global heat uptake after increased radiative forcing and; (2) the correlation between pycnocline depth and OHUE. Coupled with the nearly equivalent inter-model spreads in OHUE/pycnocline depth, these results imply that mid-latitude ventilation also dominates the ensemble spread in OHUE. Our results provide a pathway towards observationally constraining OHUE, and thus future climate.

physics.ao-ph↗

arXiv2023

Discovering Causal Relations and Equations from Data

Physics is a field of science that has traditionally used the scientific method to answer questions about why natural phenomena occur and to make testable models that explain the phenomena. Discovering equations, laws and principles that are invariant, robust and causal explanations of the world has been fundamental in physical sciences throughout the centuries. Discoveries emerge from observing the world and, when possible, performing interventional studies in the system under study. With the advent of big data and the use of data-driven methods, causal and equation discovery fields have grown and made progress in computer science, physics, statistics, philosophy, and many applied fields. All these domains are intertwined and can be used to discover causal relations, physical laws, and equations from observational data. This paper reviews the concepts, methods, and relevant works on causal and equation discovery in the broad field of Physics and outlines the most important challenges and promising future lines of research. We also provide a taxonomy for observational causal and equation discovery, point out connections, and showcase a complete set of case studies in Earth and climate sciences, fluid dynamics and mechanics, and the neurosciences. This review demonstrates that discovering fundamental laws and causal relations by observing natural phenomena is being revolutionised with the efficient exploitation of observational data, modern machine learning algorithms and the interaction with domain knowledge. Exciting times are ahead with many challenges and opportunities to improve our understanding of complex systems.

physics.data-an↗

arXiv2023

Deep learning of systematic sea ice model errors from data assimilation increments

Data assimilation is often viewed as a framework for correcting short-term error growth in dynamical climate model forecasts. When viewed on the time scales of climate however, these short-term corrections, or analysis increments, can closely mirror the systematic bias patterns of the dynamical model. In this study, we use convolutional neural networks (CNNs) to learn a mapping from model state variables to analysis increments, in order to showcase the feasibility of a data-driven model parameterization which can predict state-dependent model errors. We undertake this problem using an ice-ocean data assimilation system within the Seamless system for Prediction and EArth system Research (SPEAR) model, developed at the Geophysical Fluid Dynamics Laboratory, which assimilates satellite observations of sea ice concentration every 5 days between 1982--2017. The CNN then takes inputs of data assimilation forecast states and tendencies, and makes predictions of the corresponding sea ice concentration increments. Specifically, the inputs are states and tendencies of sea ice concentration, sea-surface temperature, ice velocities, ice thickness, net shortwave radiation, ice-surface skin temperature, sea-surface salinity, as well as a land-sea mask. We find the CNN is able to make skillful predictions of the increments in both the Arctic and Antarctic and across all seasons, with skill that consistently exceeds that of a climatological increment prediction. This suggests that the CNN could be used to reduce sea ice biases in free-running SPEAR simulations, either as a sea ice parameterization or an online bias correction tool for numerical sea ice forecasts.

physics.ao-ph↗

arXiv2023

Exploring the non-stationarity of coastal sea level probability distributions

Studies agree on a significant global mean sea level rise in the 20th century and its recent 21st century acceleration in the satellite record. At regional scale, the evolution of sea level probability distributions is often assumed to be dominated by changes in the mean. However, a quantification of changes in distributional shapes in a changing climate is currently missing. To this end, we propose a novel framework quantifying significant changes in probability distributions from time series data. The framework first quantifies linear trends in quantiles through quantile regression. Quantile slopes are then projected onto a set of four $orthogonal$ polynomials quantifying how such changes can be explained by $independent$ shifts in the first four statistical moments. The framework proposed is theoretically founded, general and can be applied to any climate observable with close-to-linear changes in distributions. We focus on observations and a coupled climate model (GFDL-CM4). In the historical period, trends in coastal daily sea level have been driven mainly by changes in the mean and can therefore be explained by a shift of the distribution with no change in shape. In the modeled world, robust changes in higher order moments emerge with increasing CO2 concentration. Such changes are driven in part by ocean circulation alone and get amplified by sea level pressure fluctuations, with possible consequences for sea level extremes attribution studies.

physics.ao-ph↗

arXiv2023

Implementation and Evaluation of a Machine Learned Mesoscale Eddy Parameterization into a Numerical Ocean Circulation Model

We address the question of how to use a machine learned parameterization in a general circulation model, and assess its performance both computationally and physically. We take one particular machine learned parameterization \cite{Guillaumin1&Zanna-JAMES21} and evaluate the online performance in a different model from which it was previously tested. This parameterization is a deep convolutional network that predicts parameters for a stochastic model of subgrid momentum forcing by mesoscale eddies. We treat the parameterization as we would a conventional parameterization once implemented in the numerical model. This includes trying the parameterization in a different flow regime from that in which it was trained, at different spatial resolutions, and with other differences, all to test generalization. We assess whether tuning is possible, which is a common practice in general circulation model development. We find the parameterization, without modification or special treatment, to be stable and that the action of the parameterization to be diminishing as spatial resolution is refined. We also find some limitations of the machine learning model in implementation: 1) tuning of the outputs from the parameterization at various depths is necessary; 2) the forcing near boundaries is not predicted as well as in the open ocean; 3) the cost of the parameterization is prohibitively high on CPUs. We discuss these limitations, present some solutions to problems, and conclude that this particular ML parameterization does inject energy, and improve backscatter, as intended but it might need further refinement before we can use it in production mode in contemporary climate models.

physics.ao-ph↗

arXiv2023

Generative data-driven approaches for stochastic subgrid parameterizations in an idealized ocean model

Subgrid parameterizations of mesoscale eddies continue to be in demand for climate simulations. These subgrid parameterizations can be powerfully designed using physics and/or data-driven methods, with uncertainty quantification. For example, Guillaumin and Zanna (2021) proposed a Machine Learning (ML) model that predicts subgrid forcing and its local uncertainty. The major assumption and potential drawback of this model is the statistical independence of stochastic residuals between grid points. Here, we aim to improve the simulation of stochastic forcing with generative models of ML, such as Generative adversarial network (GAN) and Variational autoencoder (VAE). Generative models learn the distribution of subgrid forcing conditioned on the resolved flow directly from data and they can produce new samples from this distribution. Generative models can potentially capture not only the spatial correlation but any statistically significant property of subgrid forcing. We test the proposed stochastic parameterizations offline and online in an idealized ocean model. We show that generative models are able to predict subgrid forcing and its uncertainty with spatially correlated stochastic forcing. Online simulations for a range of resolutions demonstrated that generative models are superior to the baseline ML model at the coarsest resolution.

physics.ao-ph↗

arXiv2022

Deep Probability Estimation

Reliable probability estimation is of crucial importance in many real-world applications where there is inherent (aleatoric) uncertainty. Probability-estimation models are trained on observed outcomes (e.g. whether it has rained or not, or whether a patient has died or not), because the ground-truth probabilities of the events of interest are typically unknown. The problem is therefore analogous to binary classification, with the difference that the objective is to estimate probabilities rather than predicting the specific outcome. This work investigates probability estimation from high-dimensional data using deep neural networks. There exist several methods to improve the probabilities generated by these models but they mostly focus on model (epistemic) uncertainty. For problems with inherent uncertainty, it is challenging to evaluate performance without access to ground-truth probabilities. To address this, we build a synthetic dataset to study and compare different computable metrics. We evaluate existing methods on the synthetic data as well as on three real-world probability estimation tasks, all of which involve inherent uncertainty: precipitation forecasting from radar images, predicting cancer patient survival from histopathology images, and predicting car crashes from dashcam videos. We also give a theoretical analysis of a model for high-dimensional probability estimation which reproduces several of the phenomena evinced in our experiments. Finally, we propose a new method for probability estimation using neural networks, which modifies the training process to promote output probabilities that are consistent with empirical probabilities computed from the data. The method outperforms existing approaches on most metrics on the simulated as well as real-world data.

cs.LG↗

arXiv2017

Eddy-mixing entropy as a measure of turbulent disorder in barotropic ocean jets

Understanding the statistics of ocean geostrophic turbulence is of utmost importance in understanding its interactions with the global ocean circulation and the climate system as a whole. Here, a study of eddy-mixing entropy in a forced-dissipative barotropic ocean model is presented. Entropy is a concept of fundamental importance in statistical physics and information theory; motivated by equilibrium statistical mechanics theories of ideal geophysical fluids, we consider the effect of forcing and dissipation on eddy-mixing entropy, both analytically and numerically. By diagnosing the time evolution of eddy-mixing entropy it is shown that the entropy provides a descriptive tool for understanding three stages of the turbulence life cycle: growth of instability, formation of large scale structures and steady state fluctuations. Further, by determining the relationship between the time evolution of entropy and the maximum entropy principle, evidence is found for the action of this principle in a forced-dissipative flow. The maximum entropy potential vorticity statistics are calculated for the flow and are compared with numerical simulations. Deficiencies of the maximum entropy statistics are discussed in the context of the mean-field approximation for energy. This study highlights the importance entropy and statistical mechanics in the study of geostrophic turbulence.

physics.flu-dyn↗

arXiv2014

Optimisation of an idealised ocean model, stochastic parameterisation of sub-grid eddies

An optimisation scheme is developed to accurately represent the sub-grid scale forcing of a high dimensional chaotic ocean system. Using a simple parameterisation scheme, the velocity components of a 30km resolution shallow water ocean model are optimised to have the same climatological mean and variance as that of a less viscous 7.5km resolution model. The 5 day lag-covariance is also optimised, leading to a more accurate estimate of the high resolution response to forcing using the low resolution model. The system considered is an idealised barotropic double gyre that is chaotic at both resolutions. Using the optimisation scheme, we find and apply the constant in time, but spatially varying, forcing term that is equal to the time integrated forcing of the sub-mesoscale eddies. A linear stochastic term, independent of the large-scale flow, with no spatial correlation but a spatially varying amplitude and time scale is used to represent the transient eddies. The climatological mean, variance and 5 day lag-covariance of the velocity from a single high resolution integration is used to provide an optimisation target. No other high resolution statistics are required. Additional programming effort, for example to build a tangent linear or adjoint model, is not required either. The focus of this paper is on the optimisation scheme and the accuracy of the optimised flow. The method can be applied in future investigations into the physical processes that govern barotropic turbulence and it can perhaps be applied to help understand and correct biases in the mean and variance of a more realistic coarse or eddy-permitting ocean model. The method is complementary to current parameterisations and can be applied at the same time without modification.

physics.ao-ph↗