The current configuration of the ocean overturning involves upwelling predominantly in the Southern Ocean and sinking predominantly in the Atlantic basin. The reasons for this remain unclear, as both models and paleoclimatic observations suggest that sinking can sometimes occur in the Pacific. We present a six-box model of the overturning in which temperature, salinity and low-latitude pycnocline depths are allowed to vary prognostically in both the Atlantic and Pacific. The overturning is driven by temperature, winds, and mixing and modulated by the hydrological cycle. In each basin there are three possible flow regimes, depending on whether low-latitude water flowing into northern surface boxes is transformed into dense deep water, somewhat lighter intermediate water, or light water that is returned at the surface. The resulting model combines insights from a number of previous studies and allows for nine possible global flow regimes. For the modern ocean, we find that although the interbasin atmospheric freshwater flux suppresses Pacific sinking, the equator-to-pole flux enhances it. When atmospheric temperatures are held fixed, seven possible flow regimes can be accessed by changing the amplitude and configuration of the modern hydrological cycle . North Pacific overturning can strengthen with either increases or decreases in the hydrological cycle, as well as under reversal of the interbasin freshwater flux. Tipping-point behavior of both transient and equilibrium states is modulated by parameters such as the poorly constrained lateral diffusive mixing. If hydrological cycle amplitude is varied consistently with global temperature, northern polar amplification is necessary for the Atlantic overturning to collapse.

In the modern ocean, the transformation of light surface waters to dense deep waters primarily occurs in the Atlantic basin rather than in the North Pacific or Southern Oceans. The reasons for this remain unclear, as both models and paleoclimatic observations suggest that sinking can sometimes occur in the Pacific. We present a six-box model of overturning that combines insights from a number of previous studies. A key determinant of the overturning configuration in our model is whether the Antarctic Intermediate Waters are denser than the northern subpolar waters, something that de-pends on the magnitude and configuration of atmospheric freshwater transport. For the modern ocean, we find that al-though the interbasin atmospheric freshwater flux suppresses Pacific sinking, the poleward atmospheric freshwater flux out of the subtropics enhances it. When atmospheric temperatures are held fixed, North Pacific overturning can strengthen with either increases or decreases in the hydrological cycle, as well as under reversal of the interbasin freshwater flux. Tipping-point behavior, where small changes in the hydrological cycle may cause the dominant location of densification of light waters to switch between basins and the magnitude of overturning within a basin to exhibit large jumps, is seen in both transient and equilibrium states. This behavior is modulated by parameters such as the poorly constrained lateral dif-fusive mixing coefficient. If hydrological cycle amplitude is varied consistently with global temperature, northern polar amplification is necessary for the Atlantic overturning to collapse. Certain qualitative insights incorporated in the model can be validated using a fully coupled climate model.

We describe a new multidisciplinary effort to understand how Artificial Intelligence (AI) could be used to improve climate tipping point discovery using the collapse of the Atlantic Meridional Overturning Circulation (AMOC) as a case study. Our methodology includes an AI simulated environment where a Generative Adversarial Network (GAN) is used to play an adversarial game between two deep networks. One network, the generator, tries to invoke an AMOC collapse tipping point. The other network, the discriminator, tries to predict which model configurations lead to an AMOC collapse, and which do not. The discriminator uses a climate surrogate model to run model configurations suggested by the generator network. In this study we have explored using a well-researched reduced oceanography four-box model (Gnanadesikan et al. 2018) as the surrogate. In addition, we introduce a new type of surrogate model that is used for expanding to larger models, which is based on modeling stochastic differential equations to estimate bifurcation escape times, enabling a deeper understanding of the unstable areas and how to escape them. We describe how we apply this method to larger Global Circulation Models (GCMs) by means of a CESM2-calibrated dataset. Included in this methodology is a neuro-symbolic representation of the model configurations that translates into natural language questions enabling climate modelers to ask questions of the learned adversarial space and to provide explainability. We describe the results of applying this method to study the AMOC, and evaluate our method by comparing how well it learns to predict AMOC collapse, how well it learns the area of uncertainty in state space, and how effective the neuro-symbolic language is in providing a natural language interface into the adversarial game.

In 2018, the IPCC summarized in a special report the potential risks surrounding climate tipping point. In 2019, Lenton et al. highlighted climate tipping points that could contribute to irreversible changes to our world including ice melt, deforestation, and circulation slowing. In this work we describe a study of the Atlantic Meridional Overturning Circulation (AMOC), and the use of an Artificial Intelligence (AI) assisted climate model methodology capable of performing unsupervised tipping point discovery to discover conditions which could lead to AMOC collapse.

We developed a novel AI generative adversarial network (GAN), where a set of deep learning generators attempt to invoke AMOC collapse by perturbing a constrained set of parameters, while another deep learning network, the discriminator, tries to learn how to avoid AMOC collapse. A surrogate model is used to run model configurations to test this adversarial method. We show that our methodology can be used to discover areas in model space that are consistent with fold bifurcations where the system moves from an on state to an off state. We measured the performance of this method by comparing it to an AMOC four box model and experiments described in (Gnanadesikan 2018) which uses the four box model to understand overturning stability.

We have found that the deep learning method can be used to exploit the area of uncertainty that is consistent with the area that separates the two stable states in a fold bifurcation model. When we compared the results of the adversarial network to the Gnanadesikan experiments we observed that when incorporating information regarding the uncertainty in the loss function, increasing the number of AI generators caused the AI agents to become more focused on this area of uncertainty. This area of uncertainty is consistent with what is described as the separatrix. In this study, we show the benefit of using this novel unsupervised approach as part of an AI assisted climate modeling methodology.

We propose a hybrid Artificial Intelligence (AI) climate modeling approach that enables climate modelers in scientific discovery using a climate-targeted simulation methodology based on a novel combination of deep neural networks and mathematical methods for modeling dynamical systems. The simulations are grounded by a neuro-symbolic language that both enables question answering of what is learned by the AI methods and provides a means of explainability. We describe how this methodology can be applied to the discovery of climate tipping points and, in particular, the collapse of the Atlantic Meridional Overturning Circulation (AMOC). We show how this methodology is able to predict AMOC collapse with a high degree of accuracy using a surrogate climate model for ocean interaction. We also show preliminary results of neuro-symbolic method performance when translating between natural language questions and symbolically learned representations. Our AI methodology shows promising early results, potentially enabling faster climate tipping point related research that would otherwise be computationally infeasible.

This study examines the applicability of the Gnanadesikan four-box model of the Atlantic Meridional Overturning Circulation to a global earth system model. The Community Earth System Model 2 (CESM2) is used to quantify the extent to which pycnocline depth and AMOC strength as predicted by the four-box model from regional densities and Southern Ocean fluxes match CESM2 values. The dynamics of a reduced meridional density difference driving a deepening pycnocline and weakening AMOC are qualitatively matched between the 4-box model and CESM2. We will quantify the fraction of variability in the CESM2 Large Ensemble of historical and SSP3-7.0 runs that is explained by the 4-box model; initial results suggest about two-thirds of the variability in AMOC is explained and over 90% of the variability in the pycnocline depth. This analysis may be repeated for any CMIP6 model, and a comparison of SSP5-8.5 across a handful of models is included as a demonstration.

Arctic sea ice has declined rapidly in recent decades. The faster than projected retreat suggests that free-running large-scale climate models may not be accurately representing some key processes. The small-scale turbulent entrainment of heat from the mixed layer could be one such process. To better understand this mechanism, we model the Arctic Ocean's Canada Basin, which is characterized by a perennial anomalously warm Pacific Summer Water (PSW) layer residing at the base of the mixed layer and a summertime Near-Surface Temperature Maximum (NSTM) within the mixed layer trapping heat from solar radiation. We use large eddy simulation (LES) to investigate heat entrainment for different ice-drift velocities and different initial temperature profiles. The value of LES is that the resolved turbulent fluxes are greater than the subgrid-scale fluxes for most of our parameter space. The results show that the presence of the NSTM enhances heat entrainment from the mixed layer. Additionally there is no PSW heat entrained under the parameter space considered. We propose a scaling law for the ocean-to-ice heat flux which depends on the initial temperature anomaly in the NSTM layer and the ice-drift velocity. A case study of “The Great Arctic Cyclone of 2012” gives a turbulent heat flux from the mixed layer that is approximately 70% of the total ocean-to-ice heat flux estimated from the PIOMAS model often used for short-term predictions. Present results highlight the need for large-scale climate models to account for the NSTM layer.