Maike Sonnewald

Mariana C. A. Clare, Maike Sonnewald, Redouane Lguensat et al.

The trustworthiness of neural networks is often challenged because they lack the ability to express uncertainty and explain their skill. This can be problematic given the increasing use of neural networks in high stakes decision-making such as in climate change applications. We address both issues by successfully implementing a Bayesian Neural Network (BNN), where parameters are distributions rather than deterministic, and applying novel implementations of explainable AI (XAI) techniques. The uncertainty analysis from the BNN provides a comprehensive overview of the prediction more suited to practitioners' needs than predictions from a classical neural network. Using a BNN means we can calculate the entropy (i.e. uncertainty) of the predictions and determine if the probability of an outcome is statistically significant. To enhance trustworthiness, we also spatially apply the two XAI techniques of Layer-wise Relevance Propagation (LRP) and SHapley Additive exPlanation (SHAP) values. These XAI methods reveal the extent to which the BNN is suitable and/or trustworthy. Using two techniques gives a more holistic view of BNN skill and its uncertainty, as LRP considers neural network parameters, whereas SHAP considers changes to outputs. We verify these techniques using comparison with intuition from physical theory. The differences in explanation identify potential areas where new physical theory guided studies are needed.

William Yik, Maike Sonnewald, Mariana C. A. Clare et al.

Complex ocean systems such as the Antarctic Circumpolar Current play key roles in the climate, and current models predict shifts in their strength and area under climate change. However, the physical processes underlying these changes are not well understood, in part due to the difficulty of characterizing and tracking changes in ocean physics in complex models. Using the Antarctic Circumpolar Current as a case study, we extend the method Tracking global Heating with Ocean Regimes (THOR) to a mesoscale eddy permitting climate model and identify regions of the ocean characterized by similar physics, called dynamical regimes, using readily accessible fields from climate models. To this end, we cluster grid cells into dynamical regimes and train an ensemble of neural networks, allowing uncertainty quantification, to predict these regimes and track them under climate change. Finally, we leverage this new knowledge to elucidate the dynamical drivers of the identified regime shifts as noted by the neural network using the 'explainability' methods SHAP and Layer-wise Relevance Propagation. A region undergoing a profound shift is where the Antarctic Circumpolar Current intersects the Pacific-Antarctic Ridge, an area important for carbon draw-down and fisheries. In this region, THOR specifically reveals a shift in dynamical regime under climate change driven by changes in wind stress and interactions with bathymetry. Using this knowledge to guide further exploration, we find that as the Antarctic Circumpolar Current shifts north under intensifying wind stress, the dominant dynamical role of bathymetry weakens and the flow intensifies.

Sanah Suri, Kieran Ringel, Maike Sonnewald

Extreme ocean phenomena are challenging not only to predict but to diagnose, as accurate forecasts alone do not reveal the underlying physical drivers. While recent machine learning approaches achieve strong predictive skill, they remain largely opaque and provide limited guarantees of fidelity to ground-truth physics. We introduce OceanCBM, the first concept bottleneck model (CBM) for spatiotemporal prediction and mechanistic interrogation of ocean dynamics. OceanCBM uses mixed supervision to predict mixed layer heat content, a key precursor of marine heatwaves, while routing information through an intermediate layer of prescribed concepts derived from geophysical fluid dynamics and a 'free' concept. This design imposes soft physical structure without over-constraining the model, and the free concept both regularizes concept predictions and captures residual physical processes. Across ensemble initializations, we show that mixed supervision yields consistent mechanistic representations, whereas prediction-only and prescription-only baselines learn highly variable latent structures despite similar predictive performance. OceanCBM achieves interpretable, physically grounded representations without sacrificing skill, explicitly characterizing the interpretability-performance trade-off.

Yvonne Jenniges, Maike Sonnewald, Sebastian Maneth et al.

Defining ocean regions and water masses helps to understand marine processes and can serve downstream tasks such as defining marine protected areas. However, such definitions often result from subjective decisions potentially producing misleading, unreproducible outcomes. Here, the aim was to objectively define regions of the North Atlantic through systematic comparison of clustering methods within the Native Emergent Manifold Interrogation (NEMI) framework (Sonnewald, 2023). About 300 million measured salinity, temperature, and oxygen, nitrate, phosphate and silicate concentration values served as input for various clustering methods (k-Means, agglomerative Ward, and Density-Based Spatial Clustering of Applications with Noise (DBSCAN)). Uniform Manifold Approximation and Projection (UMAP) emphasised (dis-)similarities in the data while reducing dimensionality. Based on systematic validation of clustering methods and their hyperparameters using internal, external and relative validation techniques, results showed that UMAP-DBSCAN best represented the data. Strikingly, internal validation metrics proved systematically unreliable for comparing clustering methods. To address stochastic variability, 100 UMAP-DBSCAN clustering runs were conducted and aggregated following NEMI, yielding a final set of 321 clusters. Reproducibility was evaluated via ensemble overlap ($88.81\pm1.8\%$) and mean grid cell-wise uncertainty ($15.49\pm20\%$). Case studies of the Mediterranean Sea, deep Atlantic waters and Labrador Sea showed strong agreement with common water mass definitions. This study revealed a more detailed regionalisation compared to previous concepts such as the Longhurst provinces through systematic clustering method comparison. The applied method is objective, efficient and reproducible and will support future research on biogeochemical differences and changes in oceanic regions.

Simon Dräger, Maike Sonnewald

Machine Learning has become a pervasive tool in climate science applications. However, current models fail to address nonstationarity induced by anthropogenic alterations in greenhouse emissions and do not routinely quantify the uncertainty of proposed projections. In this paper, we model the Atlantic Meridional Overturning Circulation (AMOC) which is of major importance to climate in Europe and the US East Coast by transporting warm water to these regions, and has the potential for abrupt collapse. We can generate arbitrarily extreme climate scenarios through arbitrary time scales which we then predict using neural networks. Our analysis shows that the AMOC is predictable using neural networks under a diverse set of climate scenarios. Further experiments reveal that MLPs and Deep Ensembles can learn the physics of the AMOC instead of imitating its progression through autocorrelation. With quantified uncertainty, an intriguing pattern of "spikes" before critical points of collapse in the AMOC casts doubt on previous analyses that predicted an AMOC collapse within this century. Our results show that Bayesian Neural Networks perform poorly compared to more dense architectures and care should be taken when applying neural networks to nonstationary scenarios such as climate projections. Further, our results highlight that big NN models might have difficulty in modeling global Earth System dynamics accurately and be successfully applied in nonstationary climate scenarios due to the physics being challenging for neural networks to capture.

Jason C. Furtado, Maria J. Molina, Marybeth C. Arcodia et al.

Artificial intelligence (AI) -- and specifically machine learning (ML) -- applications for climate prediction across timescales are proliferating quickly. The emergence of these methods prompts a revisit to the impact of data preprocessing, a topic familiar to the climate community, as more traditional statistical models work with relatively small sample sizes. Indeed, the skill and confidence in the forecasts produced by data-driven models are directly influenced by the quality of the datasets and how they are treated during model development, thus yielding the colloquialism "garbage in, garbage out." As such, this article establishes protocols for the proper preprocessing of input data for AI/ML models designed for climate prediction (i.e., subseasonal to decadal and longer). The three aims are to: (1) educate researchers, developers, and end users on the effects that preprocessing has on climate predictions; (2) provide recommended practices for data preprocessing for such applications; and (3) empower end users to decipher whether the models they are using are properly designed for their objectives. Specific topics covered in this article include the creation of (standardized) anomalies, dealing with non-stationarity and the spatiotemporally correlated nature of climate data, and handling of extreme values and variables with potentially complex distributions. Case studies will illustrate how using different preprocessing techniques can produce different predictions from the same model, which can create confusion and decrease confidence in the overall process. Ultimately, implementing the recommended practices set forth in this article will enhance the robustness and transparency of AI/ML in climate prediction studies.

Katherine A. Rosenfeld, Maike Sonnewald, Sonia J. Jindal et al.

We introduce a framework for the use of large language models (LLMs) in Building Understandable Messaging for Policy and Evidence Review (BUMPER). LLMs are proving capable of providing interfaces for understanding and synthesizing large databases of diverse media. This presents an exciting opportunity to supercharge the translation of scientific evidence into policy and action, thereby improving livelihoods around the world. However, these models also pose challenges related to access, trust-worthiness, and accountability. The BUMPER framework is built atop a scientific knowledge base (e.g., documentation, code, survey data) by the same scientists (e.g., individual contributor, lab, consortium). We focus on a solution that builds trustworthiness through transparency, scope-limiting, explicit-checks, and uncertainty measures. LLMs are rapidly being adopted and consequences are poorly understood. The framework addresses open questions regarding the reliability of LLMs and their use in high-stakes applications. We provide a worked example in health policy for a model designed to inform measles control programs. We argue that this framework can facilitate accessibility of and confidence in scientific evidence for policymakers, drive a focus on policy-relevance and translatability for researchers, and ultimately increase and accelerate the impact of scientific knowledge used for policy decisions.

Bryan Kaiser, Tailin Wu, Maike Sonnewald et al.

Nobel laureate Philip Anderson and Elihu Abrahams once stated that, "even if machines did contribute to normal science, we see no mechanism by which they could create a Kuhnian revolution and thereby establish a new physical law." In this Perspective, we draw upon insights from the philosophies of science and artificial intelligence (AI) to propose necessary conditions of precisely such a mechanism for generating revolutionary mathematical theories. Recent advancements in AI suggest that satisfying the proposed necessary conditions by machines may be plausible; thus, our proposed necessary conditions also define a moonshot challenge. We also propose a heuristic definition of the intelligibility of mathematical theories to accelerate the development of machine theorists.

Bryan E. Kaiser, Juan A. Saenz, Maike Sonnewald et al.

The advent of big data has vast potential for discovery in natural phenomena ranging from climate science to medicine, but overwhelming complexity stymies insight. Existing theory is often not able to succinctly describe salient phenomena, and progress has largely relied on ad hoc definitions of dynamical regimes to guide and focus exploration. We present a formal definition in which the identification of dynamical regimes is formulated as an optimization problem, and we propose an intelligible objective function. Furthermore, we propose an unsupervised learning framework which eliminates the need for a priori knowledge and ad hoc definitions; instead, the user need only choose appropriate clustering and dimensionality reduction algorithms, and this choice can be guided using our proposed objective function. We illustrate its applicability with example problems drawn from ocean dynamics, tumor angiogenesis, and turbulent boundary layers. Our method is a step towards unbiased data exploration that allows serendipitous discovery within dynamical systems, with the potential to propel the physical sciences forward.

Maike Sonnewald, Redouane Lguensat, Daniel C. Jones et al.

Progress within physical oceanography has been concurrent with the increasing sophistication of tools available for its study. The incorporation of machine learning (ML) techniques offers exciting possibilities for advancing the capacity and speed of established methods and also for making substantial and serendipitous discoveries. Beyond vast amounts of complex data ubiquitous in many modern scientific fields, the study of the ocean poses a combination of unique challenges that ML can help address. The observational data available is largely spatially sparse, limited to the surface, and with few time series spanning more than a handful of decades. Important timescales span seconds to millennia, with strong scale interactions and numerical modelling efforts complicated by details such as coastlines. This review covers the current scientific insight offered by applying ML and points to where there is imminent potential. We cover the main three branches of the field: observations, theory, and numerical modelling. Highlighting both challenges and opportunities, we discuss both the historical context and salient ML tools. We focus on the use of ML in situ sampling and satellite observations, and the extent to which ML applications can advance theoretical oceanographic exploration, as well as aid numerical simulations. Applications that are also covered include model error and bias correction and current and potential use within data assimilation. While not without risk, there is great interest in the potential benefits of oceanographic ML applications; this review caters to this interest within the research community.

Christopher Irrgang, Niklas Boers, Maike Sonnewald et al.

We outline a perspective of an entirely new research branch in Earth and climate sciences, where deep neural networks and Earth system models are dismantled as individual methodological approaches and reassembled as learning, self-validating, and interpretable Earth system model-network hybrids. Following this path, we coin the term "Neural Earth System Modelling" (NESYM) and highlight the necessity of a transdisciplinary discussion platform, bringing together Earth and climate scientists, big data analysts, and AI experts. We examine the concurrent potential and pitfalls of Neural Earth System Modelling and discuss the open question whether artificial intelligence will not only infuse Earth system modelling, but ultimately render them obsolete.