Climate processes

Abstract:

Neural operators (NOs) have emerged as effective tools for modeling complex physical systems in scientific machine learning. In NOs, a central characteristic is to learn the governing physical laws directly from data. In contrast to other machine learning applications, partial knowledge is often known a priori about the physical system at hand whereby quantities such as mass, energy and momentum are exactly conserved. Currently, NOs have to learn these conservation laws from data and can only approximately satisfy them due to finite training data and random noise. In this work, we introduce conservation law-encoded neural operators (clawNOs), a suite of NOs that endow inference with automatic satisfaction of such conservation laws. ClawNOs are built with a divergence-free prediction of the solution field, with which the continuity equation is automatically guaranteed. As a consequence, clawNOs are compliant with the most fundamental and ubiquitous conservation laws essential for correct physical consistency. As demonstrations, we consider a wide variety of scientific applications ranging from constitutive modeling of material deformation, incompressible fluid dynamics, to atmospheric simulation. ClawNOs significantly outperform the state-of-the-art NOs in learning efficacy, especially in small-data regimes. Our code and data accompanying this paper are available at https: //github.com/ningliu-iga/clawNO.

Abstract:

General circulation models' (GCMs) estimates of the liquid water path adjustment to anthropogenic aerosol emissions differ in sign from other lines of evidence. This reduces confidence in estimates of the effective radiative forcing of the climate by aerosol–cloud interactions (ERFaci). The discrepancy is thought to stem in part from GCMs' inability to represent the turbulence–microphysics interactions in cloud-top entrainment, a mechanism that leads to a reduction in liquid water in response to an anthropogenic increase in aerosols. In the real atmosphere, enhanced cloud-top entrainment is thought to be the dominant adjustment mechanism for liquid water path, weakening the overall ERFaci. We show that the latest generation of GCMs includes models that produce a negative correlation between the present-day cloud droplet number and liquid water path, a key piece of observational evidence supporting liquid water path reduction by anthropogenic aerosols and one that earlier-generation GCMs could not reproduce. However, even in GCMs with this negative correlation, the increase in anthropogenic aerosols from preindustrial to present-day values still leads to an increase in the simulated liquid water path due to the parameterized precipitation suppression mechanism. This adds to the evidence that correlations in the present-day climate are not necessarily causal. We investigate sources of confounding to explain the noncausal correlation between liquid water path and droplet number. These results are a reminder that assessments of climate parameters based on multiple lines of evidence must carefully consider the complementary strengths of different lines when the lines disagree.

Abstract:

Anthropogenic aerosols are a primary source of uncertainty in future climate projections. Changes to aerosol concentrations modify cloud radiative properties, radiative fluxes and precipitation from the micro to the global scale. Due to computational constraints, we have been unable to explicitly simulate cloud dynamics, leaving key processes, such as convective updrafts parameterized. This has significantly limited our understanding of aerosol impacts on convective clouds and climate. However, new state-of-the-art climate models running on exascale supercomputers are capable of representing these scales. In this study, we use the kilometre-scale earth system model ICON to explore, for the first time, the global response of clouds and precipitation to anthropogenic aerosol via aerosol-cloud-interactions (ACI) and aerosol-radiation-interactions (ARI). In our month-long simulations, we find that the aerosol impact on clouds and precipitation exhibits strong regional dependence, highlighting the complex interplay with atmospheric dynamics. The impact of ARI and ACI on clouds in isolation shows some consistent behaviour, but the magnitude and additive nature of the effects are regionally dependent. This behaviour suggests that the findings of isolated case studies from regional simulations may not be representative, and that ARI and ACI processes should both be accounted for in modelling studies. The simulations also highlight some limitations to be considered in future studies. Differences in internal variability between the simulations makes large-scale comparison difficult after the initial 10 – 15 days. Longer averaging periods or ensemble simulations will be beneficial for perturbation experiments in future kilometre-scale model simulations.