Climate change poses an existential threat, necessitating effective climate policies to enact impactful change. Decisions in this domain are incredibly complex, involving conflicting entities and evidence. In the last decades, policymakers increasingly use simulations and computational methods to guide some of their decisions. Integrated Assessment Models (IAMs) are one of such methods, which combine social, economic, and environmental simulations to forecast potential policy effects. For example, the UN uses outputs of IAMs for their recent Intergovernmental Panel on Climate Change (IPCC) reports. Traditionally these have been solved using recursive equation solvers, but have several shortcomings, e.g. struggling at decision making under uncertainty. Recent preliminary work using Reinforcement Learning (RL) as an alternative to traditional solvers shows promising results in decision making in uncertain and noisy scenarios. We extend on this work by introducing multiple interacting RL agents as a preliminary analysis on modelling the complex interplay of socio-interactions between various stakeholders or nations that drives much of the current climate crisis. Our findings show that cooperative agents in this framework can consistently chart pathways towards more desirable futures in terms of reduced carbon emissions and improved economy. However, upon introducing competition between agents, for instance by using opposing reward functions, desirable climate futures are rarely reached. Modelling competition is key to increased realism in these simulations, as such we employ policy interpretation by visualizing what states lead to more uncertain behavior, to understand algorithm failure. Finally, we highlight the current limitations and avenues for further work to ensure future technology uptake for policy derivation.

Good air quality is a critical determinant of public health, influencing life expectancy, respiratory health, work productivity, and the prevention of chronic diseases. This study presents a novel approach to classifying the Air Quality Index (AQI) using deep learning techniques, specifically convolutional neural networks (CNNs). We collected and curated a dataset comprising 11,000 digital images from three distinct regions in Indonesia—Jakarta, Malang, and Semarang—ensuring uniformity through standardized acquisition settings. The images were categorized into four air quality classes: good, moderate, unhealthy for sensitive groups, and unhealthy. We designed and implemented a CNN architecture optimized for AQI classification. The model achieved an impressive accuracy of 99.81% using K-fold cross-validation. In addition, the model’s interpretative capabilities were examined using techniques such as Grad-CAM, providing valuable insights into how the CNN identifies and classifies air quality conditions based on image features. These findings underscore the effectiveness of CNNs for AQI classification and highlight the potential for future work to incorporate a more diverse set of digital images captured from various perspectives to enhance dataset complexity and model robustness. The dataset is publicly accessible at https://doi.org/10.5281/zenodo.15727522.

Accurate prediction of nondispatchable renewable energy sources is essential for grid stability and price prediction. Regional power supply forecasts are usually indirect through a bottom-up approach of plant-level forecasts, incorporate lagged power values, and do not use the potential of spatially resolved data. This study presented a comprehensive methodology for predicting solar and wind power production at a country scale in France using machine learning models trained with spatially explicit weather data combined with spatial information about production sites’ capacity. A dataset is built spanning from 2012 to 2023, using daily power production data from Réseau de Transport d’Electricité (the national grid operator) as the target variable, with daily weather data from ECMWF Re-Analysis v5, production sites capacity and location, and electricity prices as input features. Three modeling approaches are explored to handle spatially resolved weather data: spatial averaging over the country, dimension reduction through principal component analysis, and a computer vision architecture to exploit complex spatial relationships. The study benchmarks state-of-the-art machine learning models as well as hyperparameter tuning approaches based on cross-validation methods on daily power production data. Results indicate that cross-validation tailored to time series is best suited to reach low error. We found that neural networks tend to outperform traditional tree-based models, which face challenges in extrapolation due to the increasing renewable capacity over time. Model performance ranges from 4% to 10% in normalized root-mean-squared error for midterm horizon, achieving similar error metrics to local models established at a single-plant level, highlighting the potential of these methods for regional power supply forecasting.

Water resources from the Indus Basin sustain over 270 million people. However, water security in this region is threatened by climate change. This is especially the case for the upper Indus Basin, where most frozen water reserves are expected to decrease significantly by the end of the century, leaving rainfall as the main driver of river flow. However, future precipitation estimates from global climate models differ greatly for this region. To address this uncertainty, this paper explores the feasibility of using probabilistic machine learning to map large-scale circulation fields, better represented by global climate models, to local precipitation over the upper Indus Basin. More specifically, Gaussian processes are trained to predict monthly ERA5 precipitation data over a 15-year horizon. This paper also explores different Gaussian process model designs, including a non-stationary covariance function to learn complex spatial relationships in the data. Going forward, this approach could be used to make more accurate predictions from global climate model outputs and better assess the probability of future precipitation extremes.

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.

Reliably identifying and understanding temporal precursors to extreme wind gusts is crucial for early warning and mitigation. This study proposes a simple data-driven approach to extract key predictors from a dataset of historical extreme European winter windstorms and derive simple equations linking these precursors to extreme gusts over land. A major challenge is the limited training data for extreme events, increasing the risk of model overfitting. Testing various mitigation strategies, we find that combining dimensionality reduction, careful cross-validation, feature selection, and a nonlinear transformation of maximum wind gusts informed by Generalized Extreme Value distributions successfully reduces overfitting. These measures yield interpretable equations that generalize across regions while maintaining satisfactory predictive skill. The discovered equations reveal the association between a steady drying low-troposphere before landfall and wind gust intensity in Northwestern Europe.