Search

IntroductionRapid reductions in Arctic sea ice in response to warming have led to increased interest in using the Arctic Ocean for commercial shipping. As the world warms, however, different strategies are being considered to stabilize or reduce surface temperatures in order to prevent critical climate change impacts. One such strategy is stratospheric aerosol injection (SAI), a form of solar climate intervention. Projected changes to Arctic sea ice under SAI with specific regards to shipping have not yet been assessed.MethodsWe compare output from two SAI simulations that have different global mean temperature targets with a non-SAI control simulation to provide the first assessment of Arctic Ocean navigability under potential SAI scenarios.ResultsWe find that sea ice concentration and thickness quickly stabilize or increase after SAI deployment. When sea ice thickness stabilizes in response to SAI, the number of days when the Arctic Ocean is navigable remains fairly constant, but increasing sea ice thickness leads to reduced navigability compared to the non-SAI simulation. From 2035-2069, both the Northwest Passage and Northern Sea Route are accessible from July-November in all three simulations, but there are no navigable routes under either SAI scenario from April-June. When the Arctic is navigable, it can take 2-12 days longer to cross the Arctic Ocean in the SAI simulations than in the non-SAI control simulation, and there are large year-to-year variations in travel time.DiscussionOverall, Arctic shipping may take longer and be more difficult in an SAI vs a non-SAI world because of relatively thicker sea ice, but the degree to which Arctic shipping may change in response to SAI is dependent on the particular climate intervention strategy.

The Madden–Julian oscillation (MJO) is a major tropical weather system and one of the largest sources of predictability for subseasonal-to-seasonal weather forecasts. Skillful prediction of the MJO has been a highly active area of research due to its large socio-economic impacts. Silini et al., herein S21, developed a machine learning model to predict the MJO, which they claimed to have an MJO prediction skill of 26–27 days over all seasons and 45 days for December–February (DJF) winter. If true, this would make the skill of their model competitive with that of the state-of-the-art dynamical MJO prediction systems at 20–35 days. However, here we show that the MJO prediction was calculated incorrectly in S21, which spuriously increased the performance of their model. Correctly computed skill of their model was substantially lower than that reported in S21; the skill for all seasons drops to 11–12 days and the skill for forecasts initialized during DJF drops to 15 days. Our findings clarify that the S21 machine learning model is not competitive with state-of-the-art numerical weather prediction models in predicting the MJO.

Abstract Stratospheric aerosol injection is a potential method of climate intervention to reduce climate risk as decarbonization efforts continue. However, possible ecosystem impacts from the strategic design of hypothetical intervention scenarios are poorly understood. Two recent Earth system model simulations depict policy-relevant stratospheric aerosol injection scenarios with similar global temperature targets, but a 10-year delay in intervention deployment. Here we show this delay leads to distinct ecological risk profiles through climate speeds, which describe the rate of movement of thermal conditions. On a planetary scale, climate speeds in the simulation where the intervention maintains temperature are not statistically distinguishable from preindustrial conditions. In contrast, rapid temperature reduction following delayed deployment produces climate speeds over land beyond either a preindustrial baseline or no-intervention climate change with present policy. The area exposed to threshold climate speeds places different scenarios in context to their relative ecological risks. Our results support discussion of tradeoffs and timescales in future scenario design and decision-making.

Abstract Earth system models are powerful tools to simulate the climate response to hypothetical climate intervention strategies, such as stratospheric aerosol injection (SAI). Recent simulations of SAI implement a tool from control theory, called a controller, to determine the quantity of aerosol to inject into the stratosphere to reach or maintain specified global temperature targets, such as limiting global warming to 1.5°C above pre‐industrial temperatures. This work explores how internal (unforced) climate variability can impact controller‐determined injection amounts using the Assessing Responses and Impacts of Solar climate intervention on the Earth system with Stratospheric Aerosol Injection (ARISE‐SAI) simulations. Since the ARISE‐SAI controller determines injection amounts by comparing global annual‐mean surface temperature to predetermined temperature targets, internal variability that impacts temperature can impact the total injection amount as well. Using an offline version of the ARISE‐SAI controller and data from Earth system model simulations, we quantify how internal climate variability and volcanic eruptions impact injection amounts. While idealized, this approach allows for the investigation of a large variety of climate states without additional simulations and can be used to attribute controller sensitivities to specific modes of internal variability.

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.

Background The right ventricle (RV) is at risk in patients with complex congenital heart disease involving right‐sided obstructive lesions. We have shown that capillary rarefaction occurs early in the pressure‐loaded RV. Here we test the hypothesis that microRNA (miR)‐34a, which is induced in RV hypertrophy and RV failure (RVF), blocks the hypoxia‐inducible factor‐1α‐vascular endothelial growth factor (VEGF) axis, leading to the attenuated angiogenic response and increased susceptibility to RV failure. Methods and Results Mice underwent pulmonary artery banding to induce RV hypertrophy and RVF. Capillary rarefaction occurred immediately. Although hypoxia‐inducible factor‐1α expression increased (0.12±0.01 versus 0.22±0.03, P=0.05), VEGF expression decreased (0.61±0.03 versus 0.22±0.05, P=0.01). miR‐34a expression was most upregulated in fibroblasts (4‐fold), but also in cardiomyocytes and endothelial cells (2‐fold). Overexpression of miR‐34a in endothelial cells increased cell senescence (10±3% versus 22±2%, P

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 Stratospheric aerosol injection (SAI) has been proposed as a possible response option to limit global warming and its societal consequences. However, the climate impacts of such intervention are unclear. Here, an explainable artificial intelligence (XAI) framework is introduced to quantify how distinguishable an SAI climate might be from a pre‐deployment climate. A suite of neural networks is trained on Earth system model data to learn to distinguish between pre‐ and post‐deployment periods across a variety of climate variables. The network accuracy is analogous to the “climate distinguishability” between the periods, and the corresponding distinctive patterns are identified using XAI methods. For many variables, the two periods are less distinguishable under SAI than under a no‐SAI scenario, suggesting that the specific intervention modeled decelerates future climatic changes and leads to a less novel climate than the no‐SAI scenario. Other climate variables for which the intervention has negligible effect are also highlighted.

Abstract Stratospheric aerosol injection (SAI) is a proposed form of climate intervention that would release reflective particles into the stratosphere, thereby reducing solar insolation and cooling the planet. The climate response to SAI is not well understood, particularly on short‐term time horizons frequently used by decision‐makers and planning practitioners to assess climate information. We demonstrate two framings to explore the climate response in the decade after SAI deployment in modeling experiments with parallel SAI and no‐SAI simulations. The first framing, which we call a snapshot around deployment, displays change over time within the SAI scenarios and applies to the question “What happens before and after SAI is deployed in the model?” The second framing, the intervention impact, displays the difference between the SAI and no‐SAI simulations, corresponding to the question “What is the impact of a given intervention relative to climate change with no intervention?” We apply these framings to annual mean 2 m temperature, precipitation, and a precipitation extreme during the 10 yr after deployment in two large ensembles of Earth system model simulations that comprehensively represent both the SAI injection process and climate response, and connect these results to implications for other climate variables. We show that SAI deployment robustly reduces changes in many high‐impact climate variables even on these short timescales where the forced response is relatively small, but that details of the climate response depend on the model version, greenhouse gas emissions scenario, and other aspects of the experimental design.

A simple method for adding uncertainty to neural network regression tasks in earth science via estimation of a general probability distribution is described. Specifically, we highlight the sinh-arcsinh-normal distributions as particularly well suited for neural network uncertainty estimation. The methodology supports estimation of heteroscedastic, asymmetric uncertainties by a simple modification of the network output and loss function. Method performance is demonstrated by predicting tropical cyclone intensity forecast uncertainty and by comparing two other common methods for neural network uncertainty quantification (i.e., Bayesian neural networks and Monte Carlo dropout). The simple approach described here is intuitive and applicable when no prior exists and one just wishes to parameterize the output and its uncertainty according to some previously defined family of distributions. The authors believe it will become a powerful, go-to method moving forward.

Abstract Different spring and early summer North Atlantic sea surface temperature anomalies (SSTAs) have been shown to precede recent European summer heatwaves (EuSHWs). So far, the limited number of observed events associated with several physical mechanisms has prevented a robust identification of SSTAs as precursors. Here, we extend beyond previous studies by combining 100 historical simulations (1850–2005) of the MPI Grand‐Ensemble with an explainable neural‐network method. We find that the spring tripolar North Atlantic pattern with positive SSTAs in the Subtropical Gyre is a precursor of EuSHWs. In addition, positive SSTAs west of the Iberian Peninsula, and in the North Sea, the Baltic Sea and the Mediterranean Sea relate to distinct early summer soil moisture anomaly patterns and are precursors of western and southeastern EuSHWs, respectively. While the phase of the tripolar North Atlantic pattern indicates whether a EuSHW might emerge, regional SSTAs indicate the spatial characteristics of EuSHWs.

The aim of this work is to provide an overview of the current state of additive manufacturing (AM), commonly known as 3D printing, within superficial brachytherapy (BT). Several comprehensive database searches were performed to find publications linked to AM in superficial BT. Twenty-eight core publications were found, which can be grouped under general categories of clinical cases, physical and dosimetric evaluations, proof-of-concept cases, design process assessments, and economic feasibility studies. Each study demonstrated a success regarding AM implementation and collectively, they provided benefits over traditional applicator fabrication techniques. Publications of AM in superficial BT have increased significantly in the last 5 years. This is likely due to associated efficiency and consistency benefits; though, more evidences are needed to determine the true extent of these benefits.

Abstract Evaluating historical simulations from global climate models (GCMs) remains an important exercise for better understanding future projections of climate change and variability in rapidly warming regions, such as the Arctic. As an alternative approach for comparing climate models and observations, we set up a machine learning classification task using a shallow artificial neural network (ANN). Specifically, we train an ANN on maps of annual mean near‐surface temperature in the Arctic from a multi‐model large ensemble archive in order to classify which GCM produced each temperature map. After training our ANN on data from the large ensembles, we input annual mean maps of Arctic temperature from observational reanalysis and sort the prediction output according to increasing values of the ANN's confidence for each GCM class. To attempt to understand how the ANN is classifying each temperature map with a GCM, we leverage a feature attribution method from explainable artificial intelligence. By comparing composites from the attribution method for every GCM classification, we find that the ANN is learning regional temperature patterns in the Arctic that are unique to each GCM relative to the multi‐model mean ensemble. In agreement with recent studies, we show that ANNs can be useful tools for extracting regional climate signals in GCMs and observations.

Abstract Assessing forced climate change requires the extraction of the forced signal from the background of climate noise. Traditionally, tools for extracting forced climate change signals have focused on one atmospheric variable at a time, however, using multiple variables can reduce noise and allow for easier detection of the forced response. Following previous work, we train artificial neural networks to predict the year of single‐ and multi‐variable maps from forced climate model simulations. To perform this task, the neural networks learn patterns that allow them to discriminate between maps from different years—that is, the neural networks learn the patterns of the forced signal amidst the shroud of internal variability and climate model disagreement. When presented with combined input fields (multiple seasons, variables, or both), the neural networks are able to detect the signal of forced change earlier than when given single fields alone by utilizing complex, nonlinear relationships between multiple variables and seasons. We use layer‐wise relevance propagation, a neural network explainability tool, to identify the multivariate patterns learned by the neural networks that serve as reliable indicators of the forced response. These “indicator patterns” vary in time and between climate models, providing a template for investigating inter‐model differences in the time evolution of the forced response. This work demonstrates how neural networks and their explainability tools can be harnessed to identify patterns of the forced signal within combined fields.

Abstract Few studies have utilized machine learning techniques to predict or understand the Madden‐Julian oscillation (MJO), a key source of subseasonal variability and predictability. Here, we present a simple framework for real‐time MJO prediction using shallow artificial neural networks (ANNs). We construct two ANN architectures, one deterministic and one probabilistic, that predict a real‐time MJO index using maps of tropical variables. These ANNs make skillful MJO predictions out to ∼18 days in October‐March and ∼11 days in April‐September, outperforming conventional linear models and efficiently capturing aspects of MJO predictability found in more complex, dynamical models. The flexibility and explainability of simple ANN frameworks are highlighted through varying model input and applying ANN explainability techniques that reveal sources and regions important for ANN prediction skill. The accessibility, performance, and efficiency of this simple machine learning framework is more broadly applicable to predict and understand other Earth system phenomena.

Despite the increasingly successful application of neural networks to many problems in the geosciences, their complex and nonlinear structure makes the interpretation of their predictions difficult, which limits model trust and does not allow scientists to gain physical insights about the problem at hand. Many different methods have been introduced in the emerging field of eXplainable Artificial Intelligence (XAI), which aims at attributing the network’s prediction to specific features in the input domain. XAI methods are usually assessed by using benchmark datasets (such as MNIST or ImageNet for image classification). However, an objective, theoretically derived ground truth for the attribution is lacking for most of these datasets, making the assessment of XAI in many cases subjective. Also, benchmark datasets specifically designed for problems in geosciences are rare. Here, we provide a framework, based on the use of additively separable functions, to generate attribution benchmark datasets for regression problems for which the ground truth of the attribution is known a priori. We generate a large benchmark dataset and train a fully connected network to learn the underlying function that was used for simulation. We then compare estimated heatmaps from different XAI methods to the ground truth in order to identify examples where specific XAI methods perform well or poorly. We believe that attribution benchmarks as the ones introduced herein are of great importance for further application of neural networks in the geosciences, and for more objective assessment and accurate implementation of XAI methods, which will increase model trust and assist in discovering new science.

Abstract It remains difficult to disentangle the relative influences of aerosols and greenhouse gases on regional surface temperature trends in the context of global climate change. To address this issue, we use a new collection of initial‐condition large ensembles from the Community Earth System Model version 1 that are prescribed with different combinations of industrial aerosol and greenhouse gas forcing. To compare the climate response to these external forcings, we adopt an artificial neural network (ANN) architecture from previous work that predicts the year by training on maps of near‐surface temperature. We then utilize layer‐wise relevance propagation (LRP) to visualize the regional temperature signals that are important for the ANN's prediction in each climate model experiment. To mask noise when extracting only the most robust climate patterns from LRP, we introduce a simple uncertainty metric that can be adopted to other explainable artificial intelligence (AI) problems. We find that the North Atlantic, Southern Ocean, and Southeast Asia are key regions of importance for the neural network to make its prediction, especially prior to the early‐21st century. Notably, we also find that the ANN predictions based on maps of observations correlate higher to the actual year after training on the large ensemble experiment with industrial aerosols held fixed to 1920 levels. This work illustrates the sensitivity of regional temperature signals to changes in aerosol forcing in historical simulations. By using explainable AI methods, we have the opportunity to improve our understanding of (non)linear combinations of anthropogenic forcings in state‐of‐the‐art global climate models.

Abstract Increases in vapor pressure deficit (VPD) have been hypothesized as the primary driver of future fire changes. The Coupled Model Intercomparison Project Phase 5 (CMIP5) models agree that western U.S. surface temperatures and associated dryness of air as defined by the VPD will increase in the 21st century for Representative Concentration Pathways (RCPs) 4.5 and 8.5. However, we find that averaged over seasonal and regional scales, other environmental variables demonstrated to be relevant to flammability, moisture abundances, and aridity—such as precipitation, evaporation, relative humidity, root zone soil moisture, and wind speed—can be used to explain observed variance in wildfire burn area as well or better than VPD. However, the magnitude and sign of the change of these variables in the 21st century are less certain than the predicted changes in VPD. Our work demonstrates that when objectively selecting environmental variables to maximize predictive skill of linear regressions (minimize square error on unseen data) VPD is not always selected and when it is not, the magnitude of future increases in burn area becomes less certain. Hence, this work shows that future burn area predictions are sensitive to what environmental predictors are chosen to drive burn area.

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.

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.

Introduction. Merkel cell carcinoma is a rare form of non-melanoma skin cancer of neuroendocrine origin. Optimal management of patients is controversial and the role of radiotherapy is unclear. Purpose. The purpose of this study was to review the efficacy of RT in the treatment of both local and distant metastatic disease from MCC. Methods. A literature search was conducted in MEDLINE (1946—January Week 1 2012) and Embase (1980–2012 Week 2). Articles of interest analyze the efficacy of radiotherapy for treatment of metastatic MCC and did not exclude case reports. Results. All articles except one focusing on the role of radiotherapy were of retrospective origin or case series. Significant limitations applied in all studies due to limited sample sizes and the retrospective nature of these studies. Radiotherapy improves locoregional control in the adjuvant setting, and many series suggest an improvement in overall survival. In cases where surgery is not possible, definitive radiotherapy may be an as-efficacious alternative. The radiosensitive nature of MCC coupled with existing reports suggests that treatment via current protocols for other primary tumors is adequate. Conclusion. Further studies should be conducted prospectively to clarify the true role of radiotherapy in metastatic MCC.