@article{HintzMilojevicDupontCreutzigetal., author = {Hintz, Marie Josefine and Milojevic-Dupont, Nikola and Creutzig, Felix and Repke, Tim and Kaack, Lynn H.}, title = {A systematic map of machine learning for urban climate change mitigation}, series = {Nature Cities}, journal = {Nature Cities}, publisher = {Springer Science and Business Media LLC}, doi = {10.1038/s44284-025-00328-5}, abstract = {Many cities are interested in leveraging artificial intelligence and machine learning (ML) to help urban climate change mitigation (UCCM). Researchers and practitioners, however, are only beginning to understand how ML can contribute to achieving climate targets in cities. Here, we systematically map 2,300 peer-reviewed articles published between 1994 and 2024 that explore the use of ML in UCCM. We find that, despite fast growth in this research area, the use of generative artificial intelligence and large language models remains negligible, which contrasts to their increasing adoption in other urban domains. Among 40 identified application areas, ML research focuses predominantly on high-impact mitigation options denoted by the Intergovernmental Panel on Climate Change. This trend may partly be driven by data availability and commercial interest, which risk perpetuating geographic inequities and diverting efforts toward less impactful mitigation options. We therefore offer recommendations to guide the impactful deployment of ML solutions in UCCM.}, language = {en} } @techreport{KaiserRodriguesLimaAzevedoetal., type = {Working Paper}, author = {Kaiser, Silke K. and Rodrigues, Filipe and Lima Azevedo, Carlos and Kaack, Lynn H.}, title = {Spatio-Temporal Graph Neural Network for Urban Spaces: Interpolating Citywide Traffic Volume}, publisher = {arXiv}, doi = {10.48550/arXiv.2505.06292}, pages = {36}, abstract = {Reliable street-level traffic volume data, covering multiple modes of transportation, helps urban planning by informing decisions on infrastructure improvements, traffic management, and public transportation. Yet, traffic sensors measuring traffic volume are typically scarcely located, due to their high deployment and maintenance costs. To address this, interpolation methods can estimate traffic volumes at unobserved locations using available data. Graph Neural Networks have shown strong performance in traffic volume forecasting, particularly on highways and major arterial networks. Applying them to urban settings, however, presents unique challenges: urban networks exhibit greater structural diversity, traffic volumes are highly overdispersed with many zeros, the best way to account for spatial dependencies remains unclear, and sensor coverage is often very sparse. We introduce the Graph Neural Network for Urban Interpolation (GNNUI), a novel urban traffic volume estimation approach. GNNUI employs a masking algorithm to learn interpolation, integrates node features to capture functional roles, and uses a loss function tailored to zero-inflated traffic distributions. In addition to the model, we introduce two new open, large-scale urban traffic volume benchmarks, covering different transportation modes: Strava cycling data from Berlin and New York City taxi data. GNNUI outperforms recent, some graph-based, interpolation methods across metrics (MAE, RMSE, true-zero rate, Kullback-Leibler divergence) and remains robust from 90\% to 1\% sensor coverage. On Strava, for instance, MAE rises only from 7.1 to 10.5, on Taxi from 23.0 to 40.4, demonstrating strong performance under extreme data scarcity, common in real-world urban settings. We also examine how graph connectivity choices influence model accuracy.}, language = {en} } @techreport{XuSanchezCanalesFusarBassinietal., type = {Working Paper}, author = {Xu, Alice Lixuan and S{\´a}nchez Canales, Jorge and Fusar Bassini, Chiara and Kaack, Lynn H. and Hirth, Lion}, title = {Market power abuse in wholesale electricity markets}, publisher = {arXiv}, doi = {10.48550/arXiv.2506.03808}, pages = {39}, abstract = {In wholesale electricity markets, prices fluctuate widely from hour to hour and electricity generators price-hedge their output using longer-term contracts, such as monthly base futures. Consequently, the incentives they face to drive up the power prices by reducing supply has a high hourly specificity, and because of hedging, they regularly also face an incentive to depress prices by inflating supply. In this study, we explain the dynamics between hedging and market power abuse in wholesale electricity markets and use this framework to identify market power abuse in real markets. We estimate the hourly economic incentives to deviate from competitive behavior and examine the empirical association between such incentives and observed generation patterns. Exploiting hourly variation also controls for potential estimation bias that do not correlate with economic incentives at the hourly level, such as unobserved cost factors. Using data of individual generation units in Germany in a six-year period 2019-2024, we find that in hours where it is more profitable to inflate prices, companies indeed tend to withhold capacity. We find that the probability of a generation unit being withheld increases by about 1 \% per euro increase in the net profit from withholding one megawatt of capacity. The opposite is also true for hours in which companies benefit financially from lower prices, where we find units being more likely to be pushed into the market by 0.3 \% per euro increase in the net profit from capacity push-in. We interpret the result as empirical evidence of systematic market power abuse.}, language = {en} } @techreport{FusarBassiniXuSanchezCanalesetal., type = {Working Paper}, author = {Fusar Bassini, Chiara and Xu, Alice Lixuan and S{\´a}nchez Canales, Jorge and Hirth, Lion and Kaack, Lynn}, title = {Revealing the empirical flexibility of gas units through deep clustering}, publisher = {arXiv}, doi = {10.48550/arXiv.2504.16943}, pages = {19}, abstract = {The flexibility of a power generation unit determines how quickly and often it can ramp up or down. In energy models, it depends on assumptions on the technical characteristics of the unit, such as its installed capacity or turbine technology. In this paper, we learn the empirical flexibility of gas units from their electricity generation, revealing how real-world limitations can lead to substantial differences between units with similar technical characteristics. Using a novel deep clustering approach, we transform 5 years (2019-2023) of unit-level hourly generation data for 49 German units from 100 MWp of installed capacity into low-dimensional embeddings. Our unsupervised approach identifies two clusters of peaker units (high flexibility) and two clusters of non-peaker units (low flexibility). The estimated ramp rates of non-peakers, which constitute half of the sample, display a low empirical flexibility, comparable to coal units. Non-peakers, predominantly owned by industry and municipal utilities, show limited response to low residual load and negative prices, generating on average 1.3 GWh during those hours. As the transition to renewables increases market variability, regulatory changes will be needed to unlock this flexibility potential.}, language = {en} } @techreport{FusarBassiniXuSanchezCanalesetal., type = {Working Paper}, author = {Fusar Bassini, Chiara and Xu, Alice Lixuan and S{\´a}nchez Canales, Jorge and Hirth, Lion and Kaack, Lynn H.}, title = {Flexibility of German gas-fired generation: evidence from clustering empirical operation}, publisher = {arXiv}, doi = {10.48550/arXiv.2504.16943}, pages = {29}, abstract = {A key input to energy models are assumptions about the flexibility of power generation units, i.e., how quickly and often they can start up. These assumptions are usually calibrated on the technical characteristics of the units, such as installed capacity or technology type. However, even if power generation units technically can dispatch flexibly, service obligations and market incentives may constrain their operation. Here, we cluster over 60\% of German national gas generation (generation units of 100 MWp or above) based on their empirical flexibility. We process the hourly dispatch of sample units between 2019 and 2023 using a novel deep learning approach, that transforms time series into easy-to-cluster representations. We identify two clusters of peaker units and two clusters of non-peaker units, whose different empirical flexibility is quantified by cluster-level ramp rates. Non-peaker units, around half of the sample, are empirically less flexible than peakers, and make up for more than 83\% of sample must-run generation. Regulatory changes addressing the low market responsiveness of non-peakers are needed to unlock their flexibility.}, language = {en} } @techreport{SanchezCanalesXuFusarBassinietal., type = {Working Paper}, author = {S{\´a}nchez Canales, Jorge and Xu, Alice Lixuan and Fusar Bassini, Chiara and Kaack, Lynn H. and Hirth, Lion}, title = {An empirical estimate of the electricity supply curve from market outcomes}, publisher = {arXiv}, doi = {10.48550/arXiv.2511.23068}, pages = {33}, abstract = {Researchers and electricity sector practitioners frequently require the supply curve of electricity markets and the price elasticity of supply for purposes such as price forecasting, policy analyses or market power assessment. It is common practice to construct supply curves from engineering data such as installed capacity and fuel prices. In this study, we propose a data-driven methodology to estimate the supply curve of electricity market empirically, i.e. from observed prices and quantities without further modeling assumptions. Due to the massive swings in fuel prices during the European energy crisis, a central task is detecting periods of stable supply curves. To this end, we implement two alternative clustering methods, one based on the fundamental drivers of electricity supply and the other directly on observed market outcomes. We apply our methods to the German electricity market between 2019 and 2024. We find that both approaches identify almost identical regimes shifts, supporting the idea of stable supply regimes stemming from stable drivers. Supply conditions are often stable for extended periods, but evolved rapidly during the energy crisis, triggering a rapid succession of regimes. Fuel prices were the dominant drivers of regime shifts, while conventional plant availability and the nuclear phase-out play a comparatively minor role. Our approach produces empirical supply curves suitable for causal inference and counterfactual analysis of market outcomes.}, language = {en} } @techreport{SchmidCoroamăDumbravăetal., type = {Working Paper}, author = {Schmid, Nicolas and Coroamă, Vlad C. and Dumbravă, Oana and Eichler, Martin and Reisser, Moritz and Kaack, Lynn H. and Axenbeck, Janna and J{\"u}rg, F{\"u}ssler}, title = {Carbon leakage in AI-driven data center growth? An assessment of drivers and barriers to the localization of data center operations and investments with respect to carbon pricing policies}, number = {68/2025}, publisher = {German Environment Agency}, pages = {64}, abstract = {This study offers a comprehensive first assessment of the global carbon leakage potential associated with AI-driven data center operation and investment. The focus is on carbon leakage from costs imposed by emission trading systems (ETS) on data center electricity consumption. The study estimates AI's current and near-future electricity consumption and evaluates the technological feasibility as well as plausibility of shifting compute loads. Additionally, it maps global compute capacity against carbon intensities and the presence of ETS.}, language = {en} } @article{KaiserKleinKaack, author = {Kaiser, Silke K. and Klein, Nadja and Kaack, Lynn H.}, title = {From counting stations to city-wide estimates: data-driven bicycle volume extrapolation}, series = {Environmental Data Science}, volume = {4}, journal = {Environmental Data Science}, publisher = {Cambridge University Press (CUP)}, issn = {2634-4602}, doi = {10.1017/eds.2025.5}, abstract = {Shifting to cycling in urban areas reduces greenhouse gas emissions and improves public health. Access to street-level data on bicycle traffic would assist cities in planning targeted infrastructure improvements to encourage cycling and provide civil society with evidence to advocate for cyclists' needs. Yet, the data currently available to cities and citizens often only comes from sparsely located counting stations. This paper extrapolates bicycle volume beyond these few locations to estimate street-level bicycle counts for the entire city of Berlin. We predict daily and average annual daily street-level bicycle volumes using machine-learning techniques and various data sources. These include app-based crowdsourced data, infrastructure, bike-sharing, motorized traffic, socioeconomic indicators, weather, holiday data, and centrality measures. Our analysis reveals that crowdsourced cycling flow data from Strava in the area around the point of interest are most important for the prediction. To provide guidance for future data collection, we analyze how including short-term counts at predicted locations enhances model performance. By incorporating just 10 days of sample counts for each predicted location, we are able to almost halve the error and greatly reduce the variability in performance among predicted locations.}, language = {en} }