Complex physical processes that are inherent to rainfall lead to the challenging task of its prediction. To contribute to the improvement of rainfall prediction, artificial neural network (ANN) models were developed using a multilayer perceptron (MLP) approach to predict monthly rainfall 2 months in advance for six geographically diverse weather stations across the Benin Republic. For this purpose, 12 lagged values of atmospheric data were used as predictors. The models were trained using data from 1959 to 2017 and tested for 4 years (2018–2021). The proposed method was compared to long short-term memory (LSTM) and climatology forecasts (CFs). The prediction performance was evaluated using five statistical measures: root mean square error, mean absolute error, mean absolute percentage error, coefficient of determination, and Nash–Sutcliffe efficiency (NSE) coefficient. Furthermore, Taylor diagrams, violin plots, box error, and Kruskal–Wallis test were used to assess the robustness of the model’s forecast. The results revealed that MLP gives better results than LSTM and CF. The NSE obtained with the MLP, LSTM, and CF models during the test period ranges from 0.373 to 0.885, 0.297 to 0.875, and 0.335 to 0.845, respectively, depending on the weather station. Rainfall predictability was more accurate, with 0.512 improvement in NSE using MLP at higher latitudes across the country, showing the effect of geographic regions on prediction model results. In summary, this research has revealed the potential of ANN techniques in predicting monthly rainfall 2 months ahead, supplying valuable insights for decision-makers in the Republic of Benin.

In order to enable widespread integration of solar energy into the power system, there is an increasing need to reduce the uncertainty associated with solar power output which requires major improvements in solar irradiance forecasting. While most recent works have addressed short-term (minutes or hours ahead) forecasting, through this work, we propose using deep sequence learning models for forecasting at longer lead times such as a week in advance, as this can play a significant role in future power system storage applications. Along with point forecasts, we also produce uncertainty estimates through probabilistic prediction and showcase the potential of our machine learning frameworks for a new and important application of longer lead time forecasting in this domain. Our study on the SURFRAD data over seven US cities compares various deep sequence models and the results are encouraging, demonstrating their superior performance against most benchmarks from the literature and a current machine learning-based probabilistic prediction baseline (previously applied to short-term solar forecasting).

Precipitation is one of the most relevant weather and climate processes. Its formation rate is sensitive to perturbations such as by the interactions between aerosols, clouds, and precipitation. These interactions constitute one of the biggest uncertainties in determining the radiative forcing of climate change. High-resolution simulations such as the ICOsahedral non-hydrostatic large-eddy model (ICON-LEM) offer valuable insights into these interactions. However, due to exceptionally high computation costs, it can only be employed for a limited period and area. We address this challenge by developing new models powered by emerging machine learning approaches capable of forecasting autoconversion rates—the rate at which small droplets collide and coalesce becoming larger droplets—from satellite observations providing long-term global spatial coverage for more than two decades. In particular, our approach involves two phases: (1) we develop machine learning models which are capable of predicting autoconversion rates by leveraging high-resolution climate model data, (2) we repurpose our best machine learning model to predict autoconversion rates directly from satellite observations. We compare the performance of our machine learning models against simulation data under several different conditions, showing from both visual and statistical inspections that our approaches are able to identify key features of the reference simulation data to a high degree. Additionally, the autoconversion rates obtained from the simulation output and satellite data (predicted) demonstrate statistical concordance. By efficiently predicting this, we advance our comprehension of one of the key processes in precipitation formation, crucial for understanding cloud responses to anthropogenic aerosols and, ultimately, climate change.

Outdoor air pollution is estimated to cause a huge number of premature deaths worldwide. It catalyzes many diseases on a variety of time scales, and it has a detrimental effect on the environment. In light of these impacts, it is necessary to obtain a better understanding of the dynamics and statistics of measured air pollution concentrations, including temporal fluctuations of observed concentrations and spatial heterogeneities. Here, we present an extensive analysis for measured data from Europe. The observed probability density functions (PDFs) of air pollution concentrations depend very much on the spatial location and the pollutant substance. We analyze a large number of time series data from 3544 different European monitoring sites and show that the PDFs of nitric oxide ($ NO $), nitrogen dioxide ($ {NO}_2 $), and particulate matter ($ {PM}_{10} $ and $ {PM}_{2.5} $) concentrations generically exhibit heavy tails. These are asymptotically well approximated by $ q $-exponential distributions with a given entropic index $ q $ and width parameter $ \lambda $. We observe that the power-law parameter $ q $ and the width parameter $ \lambda $ vary widely for the different spatial locations. We present the results of our data analysis in the form of a map that shows which parameters $ q $ and $ \lambda $ are most relevant in a given region. A variety of interesting spatial patterns is observed that correlate to the properties of the geographical region. We also present results on typical time scales associated with the dynamical behavior.

Atmospheric processes involve both space and time. Thus, humans looking at atmospheric imagery can often spot important signals in an animated loop of an image sequence not apparent in an individual (static) image. Utilizing such signals with automated algorithms requires the ability to identify complex spatiotemporal patterns in image sequences. That is a very challenging task due to the endless possibilities of patterns in both space and time. Here, we review different concepts and techniques that are useful to extract spatiotemporal signals from meteorological image sequences to expand the effectiveness of AI algorithms for classification and prediction tasks. We first present two applications that motivate the need for these approaches in meteorology, namely the detection of convection from satellite imagery and solar forecasting. Then we provide an overview of concepts and techniques that are helpful for the interpretation of meteorological image sequences, such as (a) feature engineering methods using (i) meteorological knowledge, (ii) classic image processing, (iii) harmonic analysis, and (iv) topological data analysis; (b) ways to use convolutional neural networks for this purpose with emphasis on discussing different convolution filters (2D/3D/LSTM-convolution); and (c) a brief survey of several other concepts, including the concept of “attention” in neural networks and its utility for the interpretation of image sequences and strategies from self-supervised and transfer learning to reduce the need for large labeled datasets. We hope that presenting an overview of these tools—many of which are not new but underutilized in this context—will accelerate progress in this area.

Thermohaline staircases are a widespread stratification feature that impacts the vertical transport of heat and nutrients and are consistently observed throughout the Canada Basin of the Arctic Ocean. Observations of staircases from the same time period and geographic region form clusters in temperature-salinity (T–S) space. Here, for the first time, we use an automated clustering algorithm called the hierarchical density-based spatial clustering of applications with noise to detect and connect individual well-mixed staircase layers across profiles from ice-tethered profilers. Our application only requires an estimate of the typical layer thickness and expected salinity range of staircases. We compare this method to two previous studies that used different approaches to detect layers and reproduce several results, including the mean lateral density ratio $ {R}_L $ and that the difference in salinity between neighboring layers is a magnitude larger than the salinity variance within a layer. We find that we can accurately and automatically track individual layers in coherent staircases across time and space between different profiles. In evaluating the algorithm’s performance, we find evidence of different physical features, namely splitting or merging layers and remnant intrusions. Further, we find a dependence of $ {R}_L $ on pressure, whereas previous studies have reported constant $ {R}_L $. Our results demonstrate that clustering algorithms are an effective and parsimonious method of identifying staircases in ocean profile data.

We compared climatic relationships to insurance loss across the inland Pacific Northwest region of the United States, using a design matrix methodology, to identify optimum temporal windows for climate variables by county in relationship to wheat insurance loss due to drought. The results of our temporal window construction for water availability variables (precipitation, temperature, evapotranspiration, and the Palmer drought severity index [PDSI]) identified spatial patterns across the study area that aligned with regional climate patterns, particularly with regards to drought-prone counties of eastern Washington. Using these optimum time-lagged correlational relationships between insurance loss and individual climate variables, along with commodity pricing, we constructed a regression-based random forest model for insurance loss prediction and evaluation of climatic feature importance. Our cross-validated model results indicated that PDSI was the most important factor in predicting total seasonal wheat/drought insurance loss, with wheat pricing and potential evapotranspiration having noted contributions. Our overall regional model had a $ {R}^2 $ of 0.49, and a RMSE of $30.8 million. Model performance typically underestimated annual losses, with moderate spatial variability in terms of performance between counties.

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.

Surface ozone is an air pollutant that contributes to hundreds of thousands of premature deaths annually. Accurate short-term ozone forecasts may allow improved policy actions to reduce the risk to human health. However, forecasting surface ozone is a difficult problem as its concentrations are controlled by a number of physical and chemical processes that act on varying timescales. We implement a state-of-the-art transformer-based model, the temporal fusion transformer, trained on observational data from three European countries. In four-day forecasts of daily maximum 8-hour ozone (DMA8), our novel approach is highly skillful (MAE = 4.9 ppb, coefficient of determination $ {\mathrm{R}}^2=0.81 $) and generalizes well to data from 13 other European countries unseen during training (MAE = 5.0 ppb, $ {\mathrm{R}}^2=0.78 $). The model outperforms other machine learning models on our data (ridge regression, random forests, and long short-term memory networks) and compares favorably to the performance of other published deep learning architectures tested on different data. Furthermore, we illustrate that the model pays attention to physical variables known to control ozone concentrations and that the attention mechanism allows the model to use the most relevant days of past ozone concentrations to make accurate forecasts on test data. The skillful performance of the model, particularly in generalizing to unseen European countries, suggests that machine learning methods may provide a computationally cheap approach for accurate air quality forecasting across Europe.

Patterns of underwater human-generated noise events and durations of noise-free intervals (NFIs) are soundscape metrics that can potentially affect animal communication and behavior. Due to the arduous task of manual analysis, these metrics have not been described in Glacier Bay National Park and Preserve (GBNP). To surmount this challenge, we created a machine-learning (ML) model trained on 18 hr of labeled audio samples from a hydrophone operating in GBNP since 2000. The validated convolutional neural net transfer-learning model (GBNP-CNN) was used to classify several categories of sound sources in nearly 9,000 hours of data from the same hydrophone, enabling our study of vessel noise between 2017 and 2020. We focused on the occurrence and duration of NFI and the hourly proportion (HP) of vessel noise. As expected, shorter NFI and higher HP were found during daytime hours. The GBNP-CNN F1 score was 75%, largely due to the model’s confusion of vessel noise with harbor seal roars. Therefore, NFI lengths should be considered minimum estimates, but the errors do not qualitatively affect diurnal or seasonal patterns. In 2018, mean daytime NFI during peak tourism months (June–August) was less than half the duration compared to May and September (1.3 min vs. 2.9 min). In 2020, when large-vessel tourism was substantially reduced but small-craft activity continued, we found that HP decreased in June–August. In conjunction with other soundscape metrics, monitoring NFI trends using ML models such as GBNP-CNN will provide crucial information for management and conservation of acoustic habitats and sensitive species in GBNP.

Carbon credits from the reducing emissions from deforestation and degradation (REDD+) projects have been criticized for issuing junk carbon credits due to invalid ex-ante baselines. Recently, the concept of ex-post baseline has been discussed to overcome the criticism, while ex-ante baseline is still necessary for project financing and risk assessment. To address this issue, we propose a Bayesian state-space model that integrates ex-ante baseline projection and ex-post dynamic baseline updating in a unified manner. Our approach provides a tool for appropriate risk assessment and performance evaluation of REDD+ projects. We apply the proposed model to a REDD+ project in Brazil and show that it may have had a small, positive effect but has been overcredited. We also demonstrate that the 90% predictive interval of the ex-ante baseline includes the ex-post baseline, implying that our ex-ante estimation can work effectively.

Nature-based solutions are becoming increasingly recognized as effective tools for addressing various environmental problems. This study presents a novel approach to selecting optimal blue–green infrastructure (BGI) solutions tailored to the unique environmental and climatic challenges of Istanbul, Türkiye. The primary objective is to utilize a Bayesian Belief Network (BBN) model for assisting in the identification of the most effective BGI solutions, considering the city’s distinct environmental conditions and vulnerabilities to climate change. Our methodology integrates comprehensive data collection, including meteorological and land use data, and employs a BBN model to analyze and weigh the complex network of factors influencing BGI suitability. Key findings reveal the model’s capacity to effectively predict BGI applicability across diverse climate scenarios, with quantitative results demonstrating a notable enhancement in decision-making processes for urban sustainability. Quantitative results from our model reveal a significant improvement in decision-making accuracy, with a predictive accuracy rate of 82% in identifying suitable BGI solutions for various urban scenarios. This enhancement is particularly notable in densely populated districts, where our model predicted a 25% greater efficiency in stormwater management and urban heat island mitigation compared to traditional planning methods. The study also acknowledges the limitations, such as data scarcity and the need for further model refinement. The results highlight the model’s potential for application in other complex urban areas, making it a valuable tool for improving urban sustainability and climate change adaptation. This study shows the importance of incorporating detailed meteorological and local climate zones data into urban planning processes and suggests that similar methodologies could be beneficial for addressing environmental challenges in diverse urban settings.

Determining an accurate picture of ocean currents is an important societal challenge for oceanographers, aiding our understanding of the vital role currents play in regulating Earth’s climate, and in the dispersal of marine species and pollutants, including microplastics. The geodetic approach, which combines satellite observations of sea level and Earth’s gravity, offers the only means to estimate the dominant geostrophic component of these currents globally. Unfortunately, however, geodetically-determined geostrophic currents suffer from high levels of contamination in the form of geodetic noise. Conventional approaches use isotropic spatial filters to improve the signal-to-noise ratio, though this results in high levels of attenuation. Hence, the use of deep learning to improve the geodetic determination of the ocean currents is investigated. Supervised machine learning typically requires clean targets from which to learn. However, such targets do not exist in this case. Therefore, a training dataset is generated by substituting clean targets with naturally smooth climate model data and generative machine learning networks are employed to replicate geodetic noise, providing noisy input and clean target pairs. Prior knowledge of the geodetic noise is exploited to develop a more realistic training dataset. A convolutional denoising autoencoder (CDAE) is then trained on these pairs. The trained CDAE model is then applied to unseen real geodetic ocean currents. It is demonstrated that our method outperforms conventional isotropic filtering in a case study of four key regions: the Gulf Stream, the Kuroshio Current, the Agulhas Current, and the Brazil-Malvinas Confluence Zone.

High-resolution simulations such as the ICOsahedral Non-hydrostatic Large-Eddy Model (ICON-LEM) can be used to understand the interactions among aerosols, clouds, and precipitation processes that currently represent the largest source of uncertainty involved in determining the radiative forcing of climate change. Nevertheless, due to the exceptionally high computing cost required, this simulation-based approach can only be employed for a short period within a limited area. Despite the potential of machine learning to alleviate this issue, the associated model and data uncertainties may impact its reliability. To address this, we developed a neural network (NN) model powered by evidential learning, which is easy to implement, to assess both data (aleatoric) and model (epistemic) uncertainties applied to satellite observation data. By differentiating whether uncertainties stem from data or the model, we can adapt our strategies accordingly. Our study focuses on estimating the autoconversion rates, a process in which small droplets (cloud droplets) collide and coalesce to become larger droplets (raindrops). This process is one of the key contributors to the precipitation formation of liquid clouds, crucial for a better understanding of cloud responses to anthropogenic aerosols and, subsequently, climate change. We demonstrate that incorporating evidential regression enhances the model’s credibility by accounting for uncertainties without compromising performance or requiring additional training or inference. Additionally, the uncertainty estimation shows good calibration and provides valuable insights for future enhancements, potentially encouraging more open discussions and exploration, especially in the field of atmospheric science.

Environmental data science for spatial extremes has traditionally relied heavily on max-stable processes. Even though the popularity of these models has perhaps peaked with statisticians, they are still perceived and considered as the “state of the art” in many applied fields. However, while the asymptotic theory supporting the use of max-stable processes is mathematically rigorous and comprehensive, we think that it has also been overused, if not misused, in environmental applications, to the detriment of more purposeful and meticulously validated models. In this article, we review the main limitations of max-stable process models, and strongly argue against their systematic use in environmental studies. Alternative solutions based on more flexible frameworks using the exceedances of variables above appropriately chosen high thresholds are discussed, and an outlook on future research is given. We consider the opportunities offered by hybridizing machine learning with extreme-value statistics, highlighting seven key recommendations moving forward.