Large-scale atmospheric circulation patterns, so-called weather regimes, modulate the occurrence of extreme events such as heatwaves or extreme precipitation. In their role as mediators between long-range teleconnections and local impacts, weather regimes have demonstrated potential in improving long-term climate projections as well as sub-seasonal to seasonal forecasts. However, existing methods for identifying weather regimes are not specifically designed to capture the relevant physical processes responsible for variations in the impact variable in question. This paper introduces a novel probabilistic machine learning method, RMM-VAE, for identifying weather regimes targeted to a local-scale impact variable. Based on a variational autoencoder architecture, the method combines non-linear dimensionality reduction with a prediction task and probabilistic clustering in one coherent architecture. The new method is applied to identify circulation patterns over the Mediterranean region targeted to precipitation over Morocco and compared to three existing approaches: two established linear methods and another machine-learning approach. The RMM-VAE method identifies regimes that are more predictive of the target variable compared to the two linear methods, both in terms of terciles and extremes in precipitation, while also improving the reconstruction of the input space. Further, the regimes identified by the RMM-VAE method are also more robust and persistent compared to the alternative machine learning method. The results demonstrate the potential benefit of the new method for use in various climate applications such as sub-seasonal forecasting, and illustrate the trade-offs involved in targeted clustering.

Globally, forests are net carbon sinks that partly mitigates anthropogenic climate change. However, there is evidence of increasing weather-induced tree mortality, which needs to be better understood to improve forest management under future climate conditions. Disentangling drivers of tree mortality is challenging because of their interacting behavior over multiple temporal scales. In this study, we take a data-driven approach to the problem. We generate hourly temperate weather data using a stochastic weather generator to simulate 160,000 years of beech, pine, and spruce forest dynamics with a forest gap model. These data are used to train a generative deep learning model (a modified variational autoencoder) to learn representations of three-year-long monthly weather conditions (precipitation, temperature, and solar radiation) in an unsupervised way. We then associate these weather representations with years of high biomass loss in the forests and derive weather prototypes associated with such years. The identified prototype weather conditions are associated with 5–22% higher median biomass loss compared to the median of all samples, depending on the forest type and the prototype. When prototype weather conditions co-occur, these numbers increase to 10–25%. Our research illustrates how generative deep learning can discover compounding weather patterns associated with extreme impacts.

The Antarctic surface mass balance has been shown to be sensitive to the impacts of atmospheric rivers (ARs), which bring anomalous amounts of both moisture and heat from lower latitudes poleward. Therefore, describing the characteristics of ARs and their intensity and frequency in the Antarctic regions by applying detection algorithms became a key method to evaluating their impacts on the surface mass balance and melting events. Several intense AR events have influenced Antarctica during the year 2022, and here we report an event with a peak on 10 June 2022 that was detected at 84°S, having a potential impact on West Antarctica. The extreme warm event originated in the Southern Pacific subtropical region and evolved towards the Southern Ocean, crossing the northern Antarctic Peninsula, before reaching as far as most inland regions in Antarctica, different from other typical ARs that are mostly restricted to the continental coast.

It is often argued that governments take advantage of extreme events to expand their power to the detriment of the political opposition and citizens at large. Violations of constitutional constraints are a clear indication of such opportunistic behaviour. We study whether natural disasters, conflicts and other extreme events systematically diminish governments' compliance with constitutional constraints. Our results indicate that governments are most likely to overstep their competences or disregard their responsibilities during civil conflicts, at the onset of international sanctions or following successful coups d’état. Interestingly, Cold War interventions by the United States that installed or supported a political leader led to a decrease in constitutional compliance in the target country, whereas Soviet interventions had no such effect. In contrast, banking crises and natural disasters, which threaten societies at large, but not necessarily the political elite, do not cause a significant decline in constitutional compliance.

Wave transformation is an intrinsic dynamic process in coastal areas. An essential part of this process is the variation of water depth, which plays a dominant role in the propagation features of water waves, including a change in wave amplitude during shoaling and de-shoaling, breaking, celerity variation, refraction and diffraction processes. Fundamental theoretical studies have revolved around the development of analytical frameworks to accurately describe such shoaling processes and wave group hydrodynamics in the transition between deep- and shallow-water conditions since the 1970s. Very recent pioneering experimental studies in state-of-the-art water wave facilities provided proof of concept validations and improved understanding of the formed extreme waves’ physical characteristics and statistics in variable water depth. This review recaps the related most significant theoretical developments and groundbreaking experimental advances, which have particularly thrived over the last decade.

The idea of green infrastructure (GI) has generated great interest and creativity in addressing a range of challenging and expensive environmental problems, from coastal resilience to control of combined sewer overflows (CSOs). The appeal of GI stems from its cost savings compared to traditional “gray” infrastructure and the multiple benefits it provides, including biodiversity, aesthetics, and carbon sequestration. For example, a “green” approach to controlling CSOs in New York City saved $1.5 billion compared to a “gray” approach. Despite these advantages, GI still does not have detailed design and reliability specifications as compared to engineered gray infrastructure, potentially hindering its adoption. In this paper, we review some of the potential applications of GI in modern environmental science and discuss how reliability and associated (un)certainty in net benefits need to be addressed to realize the potential of this new approach.

Understanding the meteorological drivers of extreme impacts in social or environmental systems is important to better quantify current and project future climate risks. Impacts are typically an aggregated response to many different interacting drivers at various temporal scales, rendering such driver identification a challenging task. Machine learning–based approaches, such as deep neural networks, may be able to address this task but require large training datasets. Here, we explore the ability of Convolutional Neural Networks (CNNs) to predict years with extremely low gross primary production (GPP) from daily weather data in three different vegetation types. To circumvent data limitations in observations, we simulate 100,000 years of daily weather with a weather generator for three different geographical sites and subsequently simulate vegetation dynamics with a complex vegetation model. For each resulting vegetation distribution, we then train two different CNNs to classify daily weather data (temperature, precipitation, and radiation) into years with extremely low GPP and normal years. Overall, prediction accuracy is very good if the monthly or yearly GPP values are used as an intermediate training target (area under the precision-recall curve AUC $ \ge $ 0.9). The best prediction accuracy is found in tropical forests, with temperate grasslands and boreal forests leading to comparable results. Prediction accuracy is strongly reduced when binary classification is used directly. Furthermore, using daily GPP during training does not improve the predictive power. We conclude that CNNs are able to predict extreme impacts from complex meteorological drivers if sufficient data are available.