Nicole Ludwig

Jannik Thuemmel, Matthias Karlbauer, Sebastian Otte et al.

Deep learning has gained immense popularity in the Earth sciences as it enables us to formulate purely data-driven models of complex Earth system processes. Deep learning-based weather prediction (DLWP) models have made significant progress in the last few years, achieving forecast skills comparable to established numerical weather prediction models with comparatively lesser computational costs. In order to train accurate, reliable, and tractable DLWP models with several millions of parameters, the model design needs to incorporate suitable inductive biases that encode structural assumptions about the data and the modelled processes. When chosen appropriately, these biases enable faster learning and better generalisation to unseen data. Although inductive biases play a crucial role in successful DLWP models, they are often not stated explicitly and their contribution to model performance remains unclear. Here, we review and analyse the inductive biases of state-of-the-art DLWP models with respect to five key design elements: data selection, learning objective, loss function, architecture, and optimisation method. We identify the most important inductive biases and highlight potential avenues towards more efficient and probabilistic DLWP models.

Nina Effenberger, Nicole Ludwig

Climate change will impact wind and therefore wind power generation with largely unknown effect and magnitude. Climate models can provide insights 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 and compare the aggregated predictions to actual power generation. Analyzing past climate model data supports the use of CMIP6 climate model data for multi-decadal wind power predictions and highlights the importance of being location-aware. Our predictions up to 2050 reveal only minor changes in yearly wind power generation. We find that wind power projections of 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 analysis also reveals larger uncertainty associated with Germany's coastal areas in the North as compared to Germany's South, motivating wind power expansion in regions where future wind is likely more reliable. Overall, our results indicate that wind energy will likely remain a reliable energy source in the future.

Nina Effenberger, Nicole Ludwig

Wind power and other forms of renewable energy sources play an ever more important role in the energy supply of today's power grids. Forecasting renewable energy sources has therefore become essential in balancing the power grid. While a lot of focus is placed on new forecasting methods, little attention is given on how to compare, reproduce and transfer the methods to other use cases and data. One reason for this lack of attention is the limited availability of open-source datasets, as many currently used datasets are non-disclosed and make reproducibility of research impossible. This unavailability of open-source datasets is especially prevalent in commercially interesting fields such as wind power forecasting. However, with this paper we want to enable researchers to compare their methods on publicly available datasets by providing the, to our knowledge, largest up-to-date overview of existing open-source wind power datasets, and a categorization into different groups of datasets that can be used for wind power forecasting. We show that there are publicly available datasets sufficient for wind power forecasting tasks and discuss the different data groups properties to enable researchers to choose appropriate open-source datasets and compare their methods on them.

Benedikt Heidrich, Andreas Bartschat, Marian Turowski et al.

Time series data are fundamental for a variety of applications, ranging from financial markets to energy systems. Due to their importance, the number and complexity of tools and methods used for time series analysis is constantly increasing. However, due to unclear APIs and a lack of documentation, researchers struggle to integrate them into their research projects and replicate results. Additionally, in time series analysis there exist many repetitive tasks, which are often re-implemented for each project, unnecessarily costing time. To solve these problems we present \texttt{pyWATTS}, an open-source Python-based package that is a non-sequential workflow automation tool for the analysis of time series data. pyWATTS includes modules with clearly defined interfaces to enable seamless integration of new or existing methods, subpipelining to easily reproduce repetitive tasks, load and save functionality to simply replicate results, and native support for key Python machine learning libraries such as scikit-learn, PyTorch, and Keras.

Florian Ebmeier, Nicole Ludwig, Jannik Thuemmel et al.

Solar thermal systems (STS) present a promising avenue for low-carbon heat generation, with a well-running system providing heat at minimal cost and carbon emissions. However, STS can exhibit faults due to improper installation, maintenance, or operation, often resulting in a substantial reduction in efficiency or even damage to the system. As monitoring at the individual level is economically prohibitive for small-scale systems, automated monitoring and fault detection should be used to address such issues. Recent advances in data-driven anomaly detection, particularly in time series analysis, offer a cost-effective solution by leveraging existing sensors to identify abnormal system states. Here, we propose a probabilistic reconstruction-based framework for anomaly detection. We evaluate our method on the publicly available PaSTS dataset of operational domestic STS, which features real-world complexities and diverse fault types. Our experiments show that reconstruction-based methods can detect faults in domestic STS both qualitatively and quantitatively, while generalizing to previously unseen systems. We also demonstrate that our model outperforms both simple and more complex deep learning baselines. Additionally, we show that heteroscedastic uncertainty estimation is essential to fault detection performance. Finally, we discuss the engineering overhead required to unlock these improvements and make a case for simple deep learning models.

Kornelius Raeth, Nicole Ludwig

Standard weather forecast evaluations focus on the forecaster's perspective and on a statistical assessment comparing forecasts and observations. In practice, however, forecasts are used to make decisions, so it seems natural to take the decision-maker's perspective and quantify the value of a forecast by its ability to improve decision-making. Decision calibration provides a novel framework for evaluating forecast performance at the decision level rather than the forecast level. We evaluate decision calibration to compare Machine Learning and classical numerical weather prediction models on various weather-dependent decision tasks. We find that model performance at the forecast level does not reliably translate to performance in downstream decision-making: some performance differences only become apparent at the decision level, and model rankings can change among different decision tasks. Our results confirm that typical forecast evaluations are insufficient for selecting the optimal forecast model for a specific decision task.

Jonathan Schmidt, Luca Schmidt, Felix Strnad et al.

Local climate information is crucial for impact assessment and decision-making, yet coarse global climate simulations cannot capture small-scale phenomena. Current statistical downscaling methods infer these phenomena as temporally decoupled spatial patches. However, to preserve physical properties, estimating spatio-temporally coherent high-resolution weather dynamics for multiple variables across long time horizons is crucial. We present a novel generative framework that uses a score-based diffusion model trained on high-resolution reanalysis data to capture the statistical properties of local weather dynamics. After training, we condition on coarse climate model data to generate weather patterns consistent with the aggregate information. As this predictive task is inherently uncertain, we leverage the probabilistic nature of diffusion models and sample multiple trajectories. We evaluate our approach with high-resolution reanalysis information before applying it to the climate model downscaling task. We then demonstrate that the model generates spatially and temporally coherent weather dynamics that align with global climate output.

Kibidi Neocosmos, Diego Baptista, Nicole Ludwig

In community detection, many methods require the user to specify the number of clusters in advance since an exhaustive search over all possible values is computationally infeasible. While some classical algorithms can infer this number directly from the data, this is typically not the case for graph neural networks (GNNs): even when a desired number of clusters is specified, standard GNN-based methods often fail to return the exact number due to the way they are designed. In this work, we address this limitation by introducing a flexible and principled way to control the number of communities discovered by GNNs. Rather than assuming the true number of clusters is known, we propose a framework that allows the user to specify a plausible range and enforce these bounds during training. However, if the user wants an exact number of clusters, it may also be specified and reliably returned.

Felix Strnad, Jonathan Schmidt, Fabian Mockert et al.

The European electricity power grid is transitioning towards renewable energy sources, characterized by an increasing share of off- and onshore wind and solar power. However, the weather dependency of these energy sources poses a challenge to grid stability, with so-called Dunkelflaute events -- periods of low wind and solar power generation -- being of particular concern due to their potential to cause electricity supply shortages. In this study, we investigate the impact of these events on the German electricity production in the years and decades to come. For this purpose, we adapt a recently developed generative deep learning framework to downscale climate simulations from the CMIP6 ensemble. We first compare their statistics to the historical record taken from ERA5 data. Next, we use these downscaled simulations to assess plausible future occurrences of Dunkelflaute events in Germany under the optimistic low (SSP2-4.5) and high (SSP5-8.5) emission scenarios. Our analysis indicates that both the frequency and duration of Dunkelflaute events in Germany in the ensemble mean are projected to remain largely unchanged compared to the historical period. This suggests that, under the considered climate scenarios, the associated risk is expected to remain stable throughout the century.

Paula Harder, Luca Schmidt, Francis Pelletier et al. · mila

Earth System Models (ESM) are our main tool for projecting the impacts of climate change. However, running these models at sufficient resolution for local-scale risk-assessments is not computationally feasible. Deep learning-based super-resolution models offer a promising solution to downscale ESM outputs to higher resolutions by learning from data. Yet, due to regional variations in climatic processes, these models typically require retraining for each geographical area-demanding high-resolution observational data, which is unevenly available across the globe. This highlights the need to assess how well these models generalize across geographic regions. To address this, we introduce RainShift, a dataset and benchmark for evaluating downscaling under geographic distribution shifts. We evaluate state-of-the-art downscaling approaches including GANs and diffusion models in generalizing across data gaps between the Global North and Global South. Our findings reveal substantial performance drops in out-of-distribution regions, depending on model and geographic area. While expanding the training domain generally improves generalization, it is insufficient to overcome shifts between geographically distinct regions. We show that addressing these shifts through, for example, data alignment can improve spatial generalization. Our work advances the global applicability of downscaling methods and represents a step toward reducing inequities in access to high-resolution climate information.

Oliver Neumann, Nicole Ludwig, Marian Turowski et al.

Deep Neural Networks are able to solve many complex tasks with less engineering effort and better performance. However, these networks often use data for training and evaluation without investigating its representation, i.e.~the form of the used data. In the present paper, we analyze the impact of data representations on the performance of Deep Neural Networks using energy time series forecasting. Based on an overview of exemplary data representations, we select four exemplary data representations and evaluate them using two different Deep Neural Network architectures and three forecasting horizons on real-world energy time series. The results show that, depending on the forecast horizon, the same data representations can have a positive or negative impact on the accuracy of Deep Neural Networks.