Search for: All records

Abstract Compound climate hazards, such as co-occurring temperature and precipitation extremes, substantially impact people and ecosystems. Internal climate variability combines with the forced global warming response to determine both the magnitude and spatial distribution of these events, and their consequences can propagate from one country to another via many pathways. We examine how exposure to compound climate hazards in one country is transmitted internationally via agricultural trade networks by analyzing a large ensemble of climate model simulations and comprehensive trade data of four crops (i.e. wheat, maize, rice and soya). Combinations of variability-driven climate patterns and existing global agricultural trade give rise to a wide range of possible outcomes in the current climate. In the most extreme simulated year, 20% or more of the caloric supply in nearly one third of the world’s countries are exposed to compound heat and precipitation hazards. Countries with low levels of diversification, both in the number of suppliers and the regional climates of those suppliers, are more likely to import higher fractions of calories (up to 93%) that are exposed to these compound hazards. Understanding how calories exposed to climate hazards are transmitted through agricultural trade networks in the current climate can contribute to improved anticipatory capacity for national governments, international trade policy, and agricultural-sector resilience. Our results highlight the need for concerted effort toward merging cutting-edge seasonal-to-decadal climate prediction with international trade analysis in support of a new era of anticipatory Anthropocene risk management. 

Abstract Seasonal‐to‐decadal climate prediction is crucial for decision‐making in a number of industries, but forecasts on these timescales have limited skill. Here, we develop a data‐driven method for selecting optimal analogs for seasonal‐to‐decadal analog forecasting. Using an interpretable neural network, we learn a spatially‐weighted mask that quantifies how important each grid point is for determining whether two climate states will evolve similarly. We show that analogs selected using this weighted mask provide more skillful forecasts than analogs that are selected using traditional spatially‐uniform methods. This method is tested on two prediction problems using the Max Planck Institute for Meteorology Grand Ensemble: multi‐year prediction of North Atlantic sea surface temperatures, and seasonal prediction of El Niño Southern Oscillation. This work demonstrates a methodical approach to selecting analogs that may be useful for improving seasonal‐to‐decadal forecasts and understanding their sources of skill. 

Abstract We use neural networks and large climate model ensembles to explore predictability of internal variability in sea surface temperature (SST) anomalies on interannual (1–3 years) and decadal (1–5 and 3–7 years) timescales. We find that neural networks can skillfully predict SST anomalies at these lead times, especially in the North Atlantic, North Pacific, Tropical Pacific, Tropical Atlantic and Southern Ocean. The spatial patterns of SST predictability vary across the nine climate models studied. The neural networks identify “windows of opportunity” where future SST anomalies can be predicted with more certainty. Neural networks trained on climate models also make skillful SST predictions in reconstructed observations, although the skill varies depending on which climate model the network was trained. Our results highlight that neural networks can identify predictable internal variability within existing climate data sets and show important differences in how well patterns of SST predictability in climate models translate to the real world. 

Abstract Predictable internal climate variability on decadal timescales (2–10 years) is associated with large‐scale oceanic processes, however these predictable signals may be masked by the noisy climate system. One approach to overcoming this problem is investigating state‐dependent predictability—how differences in prediction skill depend on the initial state of the system. We present a machine learning approach to identify state‐dependent predictability on decadal timescales in the Community Earth System Model version 2 pre‐industrial control simulation by incorporating uncertainty estimates into a regression neural network. We leverage the network's prediction of uncertainty to examine state dependent predictability in sea surface temperatures by focusing on predictions with the lowest uncertainty outputs. In particular, we study two regions of the global ocean—the North Atlantic and North Pacific—and find that skillful initial states identified by the neural network correspond to particular phases of Atlantic multi‐decadal variability and the interdecadal Pacific oscillation. 

Abstract Neural networks have become increasingly prevalent within the geosciences, although a common limitation of their usage has been a lack of methods to interpret what the networks learn and how they make decisions. As such, neural networks have often been used within the geosciences to most accurately identify a desired output given a set of inputs, with the interpretation of what the network learns used as a secondary metric to ensure the network is making the right decision for the right reason. Neural network interpretation techniques have become more advanced in recent years, however, and we therefore propose that the ultimate objective of using a neural network can also be the interpretation of what the network has learned rather than the output itself. We show that the interpretation of neural networks can enable the discovery of scientifically meaningful connections within geoscientific data. In particular, we use two methods for neural network interpretation called backward optimization and layerwise relevance propagation, both of which project the decision pathways of a network back onto the original input dimensions. To the best of our knowledge, LRP has not yet been applied to geoscientific research, and we believe it has great potential in this area. We show how these interpretation techniques can be used to reliably infer scientifically meaningful information from neural networks by applying them to common climate patterns. These results suggest that combining interpretable neural networks with novel scientific hypotheses will open the door to many new avenues in neural network‐related geoscience research. 

Abstract Many problems in climate science require the identification of signals obscured by both the “noise” of internal climate variability and differences across models. Following previous work, we train an artificial neural network (ANN) to predict the year of a given map of annual‐mean temperature (or precipitation) from forced climate model simulations. This prediction task requires the ANN to learn forced patterns of change amidst a background of climate noise and model differences. We then apply a neural network visualization technique (layerwise relevance propagation) to visualize the spatial patterns that lead the ANN to successfully predict the year. These spatial patterns thus serve as “reliable indicators” of the forced change. The architecture of the ANN is chosen such that these indicators vary in time, thus capturing the evolving nature of regional signals of change. Results are compared to those of more standard approaches like signal‐to‐noise ratios and multilinear regression in order to gain intuition about the reliable indicators identified by the ANN. We then apply an additional visualization tool (backward optimization) to highlight where disagreements in simulated and observed patterns of change are most important for the prediction of the year. This work demonstrates that ANNs and their visualization tools make a powerful pair for extracting climate patterns of forced change.