Increasing penetration of variable and intermittent renewable energy resources on the energy grid poses a challenge for reliable and efficient grid operation, necessitating the development of algorithms that are robust to this uncertainty. However, standard algorithms incorporating uncertainty for generation dispatch are computationally intractable when costs are nonconvex, and machine learning-based approaches lack worst-case guarantees on their performance. In this work, we propose a learning-augmented algorithm, RobustML, that exploits the good average-case performance of a machine-learned algorithm for minimizing dispatch and ramping costs of dispatchable generation resources while providing provable worst-case guarantees on cost. We evaluate the algorithm on a realistic model of a combined cycle cogeneration plant, where it exhibits robustness to distribution shift while enabling improved efficiency as renewables penetration increases.

Peat is formed by the accumulation of organic material in water-saturated soils. Drainage of peatlands and peat extraction contribute to carbon emissions and biodiversity loss. Most peat extracted for commercial purposes is used for energy production or as a growing substrate. Many countries aim to reduce peat usage but this requires tools to detect its presence in substrates. We propose a decision support system based on deep learning to detect peat-specific testate amoeba in microscopy images. We identified six taxa that are peat-specific and frequent in European peatlands. The shells of two taxa (Archerella sp. and Amphitrema sp.) were well preserved in commercial substrate and can serve as indicators of peat presence. Images from surface and commercial samples were combined into a training set. A separate test set exclusively from commercial substrates was also defined. Both datasets were annotated and YOLOv8 models were trained to detect the shells. An ensemble of eight models was included in the decision support system. Test set performance (average precision) reached values above 0.8 for Archerella sp. and above 0.7 for Amphitrema sp. The system processes thousands of images within minutes and returns a concise list of crops of the most relevant shells. This allows a human operator to quickly make a final decision regarding peat presence. Our method enables the monitoring of peat presence in commercial substrates. It could be extended by including more species for applications in restoration ecology and paleoecology.

How areas of land are allocated for different uses, such as forests, urban areas, and agriculture, has a large effect on the terrestrial carbon balance and, therefore, climate change. Based on available historical data on land-use changes and a simulation of the associated carbon emissions and removals, a surrogate model can be learned that makes it possible to evaluate the different options available to decision-makers efficiently. An evolutionary search process can then be used to discover effective land-use policies for specific locations. Such a system was built on the Project Resilience platform and evaluated with the Land-Use Harmonization dataset LUH2 and the bookkeeping model BLUE. It generates Pareto fronts that trade off carbon impact and amount of land-use change customized to different locations, thus providing a proof-of-concept tool that is potentially useful for land-use planning.

The growing need for agricultural products and the challenges posed by environmental and economic factors have created a demand for enhanced agricultural systems management. Machine learning has increasingly been leveraged to tackle agricultural optimization problems, and in particular, reinforcement learning (RL), a subfield of machine learning, seems a promising tool for data-driven discovery of future farm management policies. In this work, we present the development of CropGym, a Gymnasium environment, where a reinforcement learning agent can learn crop management policies using a variety of process-based crop growth models. As a use case, we report on the discovery of strategies for nitrogen application in winter wheat. An RL agent is trained to decide weekly on applying a discrete amount of nitrogen fertilizer, with the aim of achieving a balance between maximizing yield and minimizing environmental impact. Results show that close to optimal strategies are learned, competitive with standard practices set by domain experts. In addition, we evaluate, as an out-of-distribution test, whether the obtained policies are resilient against a change in climate conditions. We find that, when rainfall is sufficient, the RL agent remains close to the optimal policy. With CropGym, we aim to facilitate collaboration between the RL and agronomy communities to address the challenges of future agricultural decision-making.

The main goal of this study is to investigate if the publicly available sea state forecasts for the Aran Islands region in the Republic of Ireland can be improved. This improvement is achieved by using the combination of local scale sea state forecasts and Bayesian Model Averaging techniques. The question of a good forecast has been around since the start of forecasting. With current state-of-the-art numerical models, computational power, and vast data availability, we consider whether it is possible to improve model forecasts only by using the combination of publicly available forecasts, free open-source software, and very moderate computational power. It is shown that it is possible to improve the sea state forecast by at least $ 1\% $, and in some cases up to $ 8\% $. The reduction of error is between $ 6\% $ and $ 48\% $. With a more careful and specific selection of training parameters, it is possible to improve the forecast accuracy even more. The possibility of extending this local improvement to the whole coastal area around the island of Ireland is explored. Unfortunately, it is currently impossible, due to a lack of live data buoys in the coastal waters. Nonetheless, it is shown that the proposed process is simple and can be implemented by anyone whose livelihood depends on an accurate sea state forecast. It does not require large computational power, model forecasts are publicly available, and there is minimal to no training in forecasting and statistics required to enable one to perform such improvements for one’s area of interest, provided one has access to live wave data.

Measuring and attributing greenhouse gas (GHG) emissions remains a challenging problem as the world strives toward meeting emissions reductions targets. As a significant portion of total global emissions, the road transportation sector represents an enormous challenge for estimating and tracking emissions at a global scale. To meet this challenge, we have developed a hybrid approach for estimating road transportation emissions that combines the strengths of machine learning and satellite imagery with localized emissions factors data to create an accurate, globally scalable, and easily configurable GHG monitoring framework.

Climate change will impact wind and, therefore, wind power generation with largely unknown effects and magnitude. Climate models can provide insight and should be used for long-term power planning. In this work, we use Gaussian processes to predict power output given wind speeds from a global climate model. We validate the aggregated predictions from past climate model data with actual power generation, which supports using CMIP6 climate model data for multi-decadal wind power predictions and highlights the importance of being location-aware. We find that wind power projections for the two in-between climate scenarios, SSP2–4.5 and SSP3–7.0, closely align with actual wind power generation between 2015 and 2023. Our location-aware future predictions up to 2050 reveal only minor changes in yearly wind power generation. Our analysis also reveals larger uncertainty associated with Germany’s coastal areas in the North than Germany’s South, motivating wind power expansion in regions where the future wind is likely more reliable. Overall, our results indicate that wind energy will likely remain a reliable energy source.

Airborne radar sensors capture the profile of snow layers present on top of an ice sheet. Accurate tracking of these layers is essential to calculate their thicknesses, which are required to investigate the contribution of polar ice cap melt to sea-level rise. However, automatically processing the radar echograms to detect the underlying snow layers is a challenging problem. In our work, we develop wavelet-based multi-scale deep learning architectures for these radar echograms to improve snow layer detection. These architectures estimate the layer depths with a mean absolute error of 3.31 pixels and 94.3% average precision, achieving higher generalizability as compared to state-of-the-art snow layer detection networks. These depth estimates also agree well with physically drilled stake measurements. Such robust architectures can be used on echograms from future missions to efficiently trace snow layers, estimate their individual thicknesses, and thus support sea-level rise projection models.

Accurate geospatial information about the causes and consequences of climate change, including energy systems infrastructure, is critical to planning climate change mitigation and adaptation strategies. When up-to-date spatial data on infrastructure is lacking, one approach to fill this gap is to learn from overhead imagery using deep-learning-based object detection algorithms. However, the performance of these algorithms can suffer when applied to diverse geographies, which is a common case. We propose a technique to generate realistic synthetic overhead images of an object (e.g., a generator) to enhance the ability of these techniques to transfer across diverse geographic domains. Our technique blends example objects into unlabeled images from the target domain using generative adversarial networks. This requires minimal labeled examples of the target object and is computationally efficient such that it can be used to generate a large corpus of synthetic imagery. We show that including these synthetic images in the training of an object detection model improves its ability to generalize to new domains (measured in terms of average precision) when compared to a baseline model and other relevant domain adaptation techniques.

We developed a cloud microphysics parameterization for the icosahedral nonhydrostatic modeling framework (ICON) model based on physics-informed machine learning (ML). By training our ML model on high-resolution simulation data, we enhance the representation of cloud microphysics in Earth system models (ESMs) compared to traditional parameterization schemes, in particular by considering the influence of high-resolution dynamics that are not resolved in coarse ESMs. We run a global, kilometer-scale ICON simulation with a one-moment cloud microphysics scheme, the complex graupel scheme, to generate 12 days of training data. Our ML approach combines a microphysics trigger classifier and a regression model. The microphysics trigger classifier identifies the grid cells where changes due to the cloud microphysical parameterization are expected. In those, the workflow continues by calling the regression model and additionally includes physical constraints for mass positivity and water mass conservation to ensure physical consistency. The microphysics trigger classifier achieves an F1 score of 0.93 on classifying unseen grid cells. The regression model reaches an $ {R}^2 $ score of 0.72 averaged over all seven microphysical tendencies on simulated days used for validation only. This results in a combined offline performance of 0.78. Using explainability techniques, we explored the correlations between input and output features, finding a strong alignment with the graupel scheme and, hence, physical understanding of cloud microphysical processes. This parameterization provides the foundation to advance the representation of cloud microphysical processes in climate models with ML, leading to more accurate climate projections and improved comprehension of the Earth’s climate system.

In climate modeling, the stratospheric ozone layer is typically only considered in a highly simplified form due to computational constraints. For climate projections, it would be of advantage to include the mutual interactions between stratospheric ozone, temperature, and atmospheric dynamics to accurately represent radiative forcing. The overarching goal of our research is to replace the ozone layer in climate models with a machine-learned neural representation of the stratospheric ozone chemistry that allows for a particularly fast, but accurate and stable simulation. We created a benchmark data set from pairs of input and output variables that we stored from simulations of the ATLAS Chemistry and Transport Model. We analyzed several variants of multilayer perceptrons suitable for physical problems to learn a neural representation of a function that predicts 24-h ozone tendencies based on input variables. We performed a comprehensive hyperparameter optimization of the multilayer perceptron using Bayesian search and Hyperband early stopping. We validated our model by replacing the full chemistry module of ATLAS and comparing computation time, accuracy, and stability. We found that our model had a computation time that was a factor of 700 faster than the full chemistry module. The accuracy of our model compares favorably to the full chemistry module within a 2-year simulation run, also outperforms a previous polynomial approach for fast ozone chemistry, and reproduces seasonality well in both hemispheres. In conclusion, the neural representation of stratospheric ozone chemistry in simulation resulted in an ozone layer that showed a high accuracy, significant speed-up, and stability in a long-term simulation.

Land cover classification (LCC) and natural disaster response (NDR) are important issues in climate change mitigation and adaptation. Existing approaches that use machine learning with Earth observation (EO) imaging data for LCC and NDR often rely on fully annotated and segmented datasets. Creating these datasets requires a large amount of effort, and a lack of suitable datasets has become an obstacle in scaling the use of machine learning for EO. In this study, we extend our prior work on Scene-to-Patch models: an alternative machine learning approach for EO that utilizes Multiple Instance Learning (MIL). As our approach only requires high-level scene labels, it enables much faster development of new datasets while still providing segmentation through patch-level predictions, ultimately increasing the accessibility of using machine learning for EO. We propose new multi-resolution MIL architectures that outperform single-resolution MIL models and non-MIL baselines on the DeepGlobe LCC and FloodNet NDR datasets. In addition, we conduct a thorough analysis of model performance and interpretability.

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.

Both energy performance certificates (EPCs) and thermal infrared (TIR) images play key roles in mapping the energy performance of the urban building stock. In this paper, we developed parametric building archetypes using an EPC database and conducted temperature clustering on TIR images acquired from drones and satellite datasets. We evaluated 1,725 EPCs of existing building stock in Cambridge, UK, to generate energy consumption profiles. Drone-based TIR images of individual buildings in two Cambridge University colleges were processed using a machine learning pipeline for thermal anomaly detection and investigated the influence of two specific factors that affect the reliability of TIR for energy management applications: ground sample distance (GSD) and angle of view (AOV). The EPC results suggest that the construction year of the buildings influences their energy consumption. For example, modern buildings were over 30% more energy-efficient than older ones. In parallel, older buildings were found to show almost double the energy savings potential through retrofitting compared to newly constructed buildings. TIR imaging results showed that thermal anomalies can only be properly identified in images with a GSD of 1 m/pixel or less. A GSD of 1-6 m/pixel can detect hot areas of building surfaces. We found that a GSD > 6 m/pixel cannot characterize individual buildings but does help identify urban heat island effects. Additional sensitivity analysis showed that building thermal anomaly detection is more sensitive to AOV than to GSD. Our study informs newer approaches to building energy diagnostics using thermography and supports decision-making for large-scale retrofitting.

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.

Feature selection is an important component of machine learning for researchers that are confronted with high dimensional data. In the field of economics, researchers are often faced with high dimensional data, particularly in the studies that aim to understand the channels through which climate change affects the welfare of countries. This work reviews the current literature that introduces various feature selection algorithms that may be useful for applications in this area of study. The article first outlines the specific problems that researchers face in understanding the effects of climate change on countries’ macroeconomic outcomes, and then provides a discussion regarding different categories of feature selection. Emphasis is placed on two main feature selection algorithms: Least Absolute Shrinkage and Selection Operator and causality-based feature selection. I demonstrate an application of feature selection to discover the optimal heatwave definition for economic outcomes, enhancing our understanding of extreme temperatures’ impact on the economy. I argue that the literature in computer science can provide useful insights in studies concerned with climate change as well as its economic outcomes.

Extreme precipitation events are projected to increase both in frequency and intensity due to climate change. High-resolution climate projections are essential to effectively model the convective phenomena responsible for severe precipitation and to plan any adaptation and mitigation action. Existing numerical methods struggle with either insufficient accuracy in capturing the evolution of convective dynamical systems, due to the low resolution, or are limited by the excessive computational demands required to achieve kilometre-scale resolution. To fill this gap, we propose a novel deep learning regional climate model (RCM) emulator called graph neural networks for climate downscaling (GNN4CD) to estimate high-resolution precipitation. The emulator is innovative in architecture and training strategy, using graph neural networks (GNNs) to learn the downscaling function through a novel hybrid imperfect framework. GNN4CD is initially trained to perform reanalysis to observation downscaling and then used for RCM emulation during the inference phase. The emulator is able to estimate precipitation at very high resolution both in space ($ 3 $km) and time ($ 1 $h), starting from lower-resolution atmospheric data ($ \sim 25 $km). Leveraging the flexibility of GNNs, we tested its spatial transferability in regions unseen during training. The model trained on northern Italy effectively reproduces the precipitation distribution, seasonal diurnal cycles, and spatial patterns of extreme percentiles across all of Italy. When used as an RCM emulator for the historical, mid-century, and end-of-century time slices, GNN4CD shows the remarkable ability to capture the shifts in precipitation distribution, especially in the tail, where changes are most pronounced.

Drought forecasting is a critical tool for mitigating the severe impacts of water scarcity, particularly in regions like North Benin, where agriculture is a cornerstone of livelihoods. Despite the vital importance of its accurate prediction in resource management, the ability to quantify uncertainties in forecasts is a significant pain point to enable more informed and trustworthy decision-making. So, this study aims to develop an uncertainty-aware prediction model for drought forecasting in six key localities within the Alibori department—Banikoara, Gogounou, Kandi, Karimama, Malanville, and Segbana—each facing unique challenges due to drought. To achieve this, we conducted a comprehensive experiment involving six machine learning models (linear regression, ridge regression, random forest, Xgboost, LightGBM, and SVM) and four deep learning models (Conv1D, LSTM, GRU, and Conv1D-LSTM) using the Standardized Precipitation Index at a 6-month scale. To address the uncertainty quantification challenge, we employed the Ensemble Batch Prediction Interval, a conformal prediction method specifically designed for time series data. Our comparative analysis, framed within the Borda count methodology, utilized performance metrics such as R2, RMSE, MSE, and carbon footprint, as well as uncertainty quantification metrics, including empirical coverage and the width of prediction intervals. The top-performing models achieved $ {R}^2 $ scores of 98.29, 97.84, 97.76, 97.42, 96.61, and 97.07%, and prediction interval coverages of 0.94, 0.79, 0.93, 0.77, 0.73, and 0.93, respectively, for Banikoara, Gogounou, Malanville, Kandi, Segbana, and Karimama. The Conv1D-LSTM model stood out as the most effective, offering an optimal balance between predictive accuracy and uncertainty coverage.

Language models (LMs) have attracted the attention of researchers from the natural language processing (NLP) and machine learning (ML) communities working in specialized domains, including climate change. NLP and ML practitioners have been making efforts to reap the benefits of LMs of various sizes, including large language models, in order to both simplify and accelerate the processing of large collections of text data, and in doing so, help climate change stakeholders to gain a better understanding of past and current climate-related developments, thereby staying on top of both ongoing changes and increasing amounts of data. This paper presents a brief history of language models and ties LMs’ beginnings to them becoming an emerging technology for analysing and interacting with texts in the specialized domain of climate change. The paper reviews existing domain-specific LMs and systems based on general-purpose large language models for analysing climate change data, with special attention being paid to the LMs’ and LM-based systems’ functionalities, intended use and audience, architecture, the data used in their development, the applied evaluation methods, and their accessibility. The paper concludes with a brief overview of potential avenues for future research vis-à-vis the advantages and disadvantages of deploying LMs and LM-based solutions in a high-stakes scenario such as climate change research. For the convenience of readers, explanations of specialized terms used in NLP and ML are provided.