@article{KaackRolnickReischetal., author = {Kaack, Lynn and Rolnick, David and Reisch, Lucia A. and Joppa, Lucas and Howson, Peter and Gil, Artur and Alevizou, Panayiota and Michaelidou, Nina and Appiah-Campbell, Ruby and Santarius, Tilman and K{\"o}hler, Susanne and Pizzol, Massimo and Schweizer, Pia-Johanna and Srinivasan, Dipti and Kaack, Lynn and Donti, Priya L.}, title = {Digitizing a sustainable future}, series = {One Earth}, volume = {4}, journal = {One Earth}, number = {6}, doi = {10.1016/j.oneear.2021.05.012}, pages = {768 -- 771}, abstract = {Digital technologies have a crucial role in facilitating transitions toward a sustainable future. Yet there remain challenges to overcome and pitfalls to avoid. This Voices asks: how do we leverage the digital transformation to successfully support a sustainability transition?}, language = {en} } @techreport{HintzMilojevicDupontCreutzigetal., type = {Working Paper}, author = {Hintz, Marie Josefine and Milojevic-Dupont, Nikola and Creutzig, Felix and Kaack, Lynn}, title = {A systematic map of machine learning in urban climate change mitigation}, publisher = {Research Square}, doi = {10.21203/rs.3.rs-4242075/v1}, abstract = {To tackle the climate crisis, cities must reduce greenhouse gas (GHG) emissions rapidly. To aid these efforts, many cities are interested in leveraging artificial intelligence and machine learning (ML). Researchers and practitioners, however, only begin to understand how ML can contribute to achieving climate targets in urban contexts. To provide an overview of application areas, and the potential leverage of ML to reduce GHG emissions, we systematically map research conducted over the past three decades. We identify 1,206 relevant peer-reviewed records, and discover that research involving ML is expanding more rapidly than the literature on urban climate mitigation more broadly. The research focus largely aligns with urban mitigation options that the Intergovernmental Panel on Climate Change assessed as having high impact. We also find that research concentrates on the ML-strong regions Eastern Asia, Europe, and Northern America. This regional focus can influence research agendas, and we observed signs that this can lead to bias regarding which ML applications are pursued in urban climate action.}, language = {en} } @article{ChevanceNieuwenhuijsenBragaetal., author = {Chevance, Guillaume and Nieuwenhuijsen, Mark and Braga, Kaue and Clifton, Kelly and Hoadley, Suzanne and Kaack, Lynn H. and Kaiser, Silke K. and Lampkowski, Marcelo and Lupu, Iuliana and Radics, Mikl{\´o}s and Vel{\´a}zquez-Cort{\´e}s, Daniel and Williams, Sarah and Woodcock, James and Tonne, Cathryn}, title = {Data gaps in transport behavior are bottleneck for tracking progress towards healthy sustainable transport in European cities}, series = {Environmental Research Letters}, volume = {19}, journal = {Environmental Research Letters}, number = {5}, doi = {10.1088/1748-9326/ad42b3}, language = {en} } @article{CreutzigAcemogluBaietal., author = {Creutzig, Felix and Acemoglu, Daron and Bai, Xuemei and Edwards, Paul N. and Hintz, Marie Josefine and Kaack, Lynn and Kilkis, Siir and Kunkel, Stefanie and Luers, Amy and Milojevic-Dupont, Nikola and Rejeski, Dave and Renn, J{\"u}rgen and Rolnick, David and Rosol, Christoph and Russ, Daniela and Turnbull, Thomas and Verdolini, Elena and Wagner, Felix and Wilson, Charlie and Zekar, Aicha and Zumwald, Marius}, title = {Digitalization and the Anthropocene}, series = {Annual Review of Environment and Resources}, volume = {47}, journal = {Annual Review of Environment and Resources}, doi = {10.1146/annurev-environ-120920-100056}, pages = {479 -- 509}, abstract = {Great claims have been made about the benefits of dematerialization in a digital service economy. However, digitalization has historically increased environmental impacts at local and planetary scales, affecting labor markets, resource use, governance, and power relationships. Here we study the past, present, and future of digitalization through the lens of three interdependent elements of the Anthropocene: (a) planetary boundaries and stability, (b) equity within and between countries, and (c) human agency and governance, mediated via (i) increasing resource efficiency, (ii) accelerating consumption and scale effects, (iii) expanding political and economic control, and (iv) deteriorating social cohesion. While direct environmental impacts matter, the indirect and systemic effects of digitalization are more profoundly reshaping the relationship between humans, technosphere and planet. We develop three scenarios: planetary instability, green but inhumane, and deliberate for the good. We conclude with identifying leverage points that shift human-digital-Earth interactions toward sustainability.}, language = {en} } @techreport{CluttonBrockRolnickDontietal., type = {Working Paper}, author = {Clutton-Brock, Peter and Rolnick, David and Donti, Priya L. and Kaack, Lynn}, title = {Climate Change and AI. Recommendations for Government Action}, pages = {94}, abstract = {The report, Climate Change and AI: Recommendations for Government, highlights 48 specific recommendations for how governments can both support the application of AI to climate challenges and address the climate-related risks that AI poses.}, language = {en} } @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} } @article{MilojevicDupontWagnerNachtigalletal., author = {Milojevic-Dupont, Nikola and Wagner, Felix and Nachtigall, Florian and Hu, Jiawei and Br{\"u}ser, Geza Boi and Zumwald, Marius and Biljecki, Filip and Heeren, Niko and Kaack, Lynn and Pichler, Peter-Paul and Creutzig, Felix}, title = {EUBUCCO v0.1: European building stock characteristics in a common and open database for 200+ million individual buildings}, series = {Scientific Data}, volume = {10}, journal = {Scientific Data}, doi = {10.1038/s41597-023-02040-2}, abstract = {Building stock management is becoming a global societal and political issue, inter alia because of growing sustainability concerns. Comprehensive and openly accessible building stock data can enable impactful research exploring the most effective policy options. In Europe, efforts from citizen and governments generated numerous relevant datasets but these are fragmented and heterogeneous, thus hindering their usability. Here, we present EUBUCCO v0.1, a database of individual building footprints for ~202 million buildings across the 27 European Union countries and Switzerland. Three main attributes - building height, construction year and type - are included for respectively 73\%, 24\% and 46\% of the buildings. We identify, collect and harmonize 50 open government datasets and OpenStreetMap, and perform extensive validation analyses to assess the quality, consistency and completeness of the data in every country. EUBUCCO v0.1 provides the basis for high-resolution urban sustainability studies across scales - continental, comparative or local studies - using a centralized source and is relevant for a variety of use cases, e.g., for energy system analysis or natural hazard risk assessments.}, language = {en} } @article{KaackDontiStrubelletal., author = {Kaack, Lynn and Donti, Priya L. and Strubell, Emma and Kamiya, George and Creutzig, Felix and Rolnick, David}, title = {Aligning artificial intelligence with climate change mitigation}, series = {Nature Climate Change}, volume = {12}, journal = {Nature Climate Change}, doi = {10.1038/s41558-022-01377-7}, pages = {518 -- 527}, abstract = {There is great interest in how the growth of artificial intelligence and machine learning may affect global GHG emissions. However, such emissions impacts remain uncertain, owing in part to the diverse mechanisms through which they occur, posing difficulties for measurement and forecasting. Here we introduce a systematic framework for describing the effects of machine learning (ML) on GHG emissions, encompassing three categories: computing-related impacts, immediate impacts of applying ML and system-level impacts. Using this framework, we identify priorities for impact assessment and scenario analysis, and suggest policy levers for better understanding and shaping the effects of ML on climate change mitigation.}, language = {en} } @article{Kaack, author = {Kaack, Lynn}, title = {Machine learning enables global solar-panel detection}, series = {Nature}, volume = {598}, journal = {Nature}, number = {7882}, doi = {10.1038/d41586-021-02875-y}, pages = {567 -- 568}, abstract = {An inventory of the world's solar-panel installations has been produced with the help of machine learning, revealing many more than had previously been recorded. The results will inform efforts to meet global targets for solar-energy use.}, language = {en} } @article{KaackRolnickDontietal., author = {Kaack, Lynn and Rolnick, David and Donti, Priya L. and Kochanski, Kelly and Lacoste, Alexandre and Sankaran, Kris and Ross, Andrew S. and Milojevic-Dupont, Nikola and Jaques, Natasha and Waldman-Brown, Anna and Luccioni, Alexandra S. and Maharaj, Tegan and Sherwin, Evan D. and Mukkavilli, Karthik and Kording, Konrad P. and Gomes, Carla P. and Ng, Andrew Y. and Hassabis, Demis and Platt, John C. and Creutzig, Felix and Chayes, Jennifer and Bengio, Yoshua}, title = {Tackling Climate Change with Machine Learning}, series = {ACM Computing Surveys}, volume = {55}, journal = {ACM Computing Surveys}, number = {2}, doi = {10.1145/3485128}, pages = {1 -- 96}, abstract = {Climate change is one of the greatest challenges facing humanity, and we, as machine learning experts, may wonder how we can help. Here we describe how machine learning can be a powerful tool in reducing greenhouse gas emissions and helping society adapt to a changing climate. From smart grids to disaster management, we identify high impact problems where existing gaps can be filled by machine learning, in collaboration with other fields. Our recommendations encompass exciting research questions as well as promising business opportunities. We call on the machine learning community to join the global effort against climate change.}, language = {en} } @article{SewerinKaackKuetteletal., author = {Sewerin, Sebastian and Kaack, Lynn and K{\"u}ttel, Joel and Sigurdsson, Fride and Martikainen, Onerva and Esshaki, Alisha and Hafner, Fabian}, title = {Towards understanding policy design through text-as-data approaches: The policy design annotations (POLIANNA) dataset}, series = {Scientific Data}, volume = {10}, journal = {Scientific Data}, doi = {10.1038/s41597-023-02801-z}, abstract = {Despite the importance of ambitious policy action for addressing climate change, large and systematic assessments of public policies and their design are lacking as analysing text manually is labour-intensive and costly. POLIANNA is a dataset of policy texts from the European Union (EU) that are annotated based on theoretical concepts of policy design, which can be used to develop supervised machine learning approaches for scaling policy analysis. The dataset consists of 20,577 annotated spans, drawn from 18 EU climate change mitigation and renewable energy policies. We developed a novel coding scheme translating existing taxonomies of policy design elements to a method for annotating text spans that consist of one or several words. Here, we provide the coding scheme, a description of the annotated corpus, and an analysis of inter-annotator agreement, and discuss potential applications. As understanding policy texts is still difficult for current text-processing algorithms, we envision this database to be used for building tools that help with manual coding of policy texts by automatically proposing paragraphs containing relevant information.}, 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{YaakoubiDontiKaacketal., type = {Working Paper}, author = {Yaakoubi, Yassine and Donti, Priya L. and Kaack, Lynn H. and Rolnick, David and Dunietz, Jesse and Malik, Muneeb and Afolabi, Temilola and Kuhne, Paul and Ndzimande, Onezwa and Chinyamakobvu, Mutsa and Gombakomba, Ruvimbo and Chibvongodze, Vongai and Leslie, Timothy and Bj{\"a}rby, Effuah and Letuka, Teboho}, title = {Grand Challenge Initiatives in AI for Climate \& Nature: Landscape Assessment and Recommendations}, publisher = {Climate Change AI (CCAI)}, language = {en} } @techreport{KaiserKleinKaack, type = {Working Paper}, author = {Kaiser, Silke K. and Klein, Nadja and Kaack, Lynn}, title = {Predicting cycling traffic in cities: Is bikesharing data representative of the cycling volume?}, doi = {10.48462/opus4-4942}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:b1570-opus4-49429}, pages = {5}, abstract = {A higher share of cycling in cities can lead to a reduction in greenhouse gas emissions, a decrease in noise pollution, and personal health benefits. Data-driven approaches to planning new infrastructure to promote cycling are rare, mainly because data on cycling volume are only available selectively. By leveraging new and more granular data sources, we predict bicycle count measurements in Berlin, using data from free-floating bike-sharing systems in addition to weather, vacation, infrastructure, and socioeconomic indicators. To reach a high prediction accuracy given the diverse data, we make use of machine learning techniques. Our goal is to ultimately predict traffic volume on all streets beyond those with counters and to understand the variance in feature importance across time and space. Results indicate that bike-sharing data are valuable to improve the predictive performance, especially in cases with high outliers, and help generalize the models to new locations.}, language = {de} } @article{HintzGrossCreutzigetal., author = {Hintz, Marie Josefine and Gross, Milena and Creutzig, Felix and Kaack, Lynn H.}, title = {Practical implementation of artificial intelligence for climate change mitigation in cities - priorities, collaborations and challenges}, series = {Energy Research \& Social Science}, volume = {131}, journal = {Energy Research \& Social Science}, publisher = {Elsevier BV}, doi = {10.1016/j.erss.2025.104498}, abstract = {European cities are increasingly exploring artificial intelligence (AI) applications to achieve their climate goals. Yet, how European city administrations implement AI-for-climate projects remains unclear. To address this gap, we interviewed city staff and urban innovation experts (n=15 interviewees) from Amsterdam, Berlin, Copenhagen, Greater Paris, Helsinki, and Vienna about their motivations, challenges, solutions, and partnerships when deploying AI tools. We found that city administrations were driven by different priorities that extend beyond accelerating climate action, such as improving decision-making, providing better services to residents, reducing costs, and showcasing innovation. We also identified implementation challenges for city administrations, for instance, socio-technical interoperability with existing systems or increasing AI literacy among city staff who work on climate action. We characterized three implementation arrangements through which cities deployed AI, highlighting the plural roles of city administrations in shaping AI deployment. Our analysis indicates that the European Commission, start-ups, researchers, and innovation labs were key partners for implementation, unlike civil society and large technology firms. Our study also reveals substantial challenges even for large, affluent cities, creating doubt about the applicability of AI projects for climate change mitigation in small and medium-sized cities.}, 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} } @article{KaackVaishnavGrangerMorganetal., author = {Kaack, Lynn and Vaishnav, Parth and Granger Morgan, M and Azevedo, In{\^e}s and Rai, Srijana}, title = {Decarbonizing intraregional freight systems with a focus on modal shift}, series = {Environmental Research Letters}, volume = {13}, journal = {Environmental Research Letters}, number = {8}, doi = {10.1088/1748-9326/aad56c}, abstract = {Road freight transportation accounts for around 7\% of total world energy-related carbon dioxide emissions. With the appropriate incentives, energy savings and emissions reductions can be achieved by shifting freight to rail or water modes, both of which are far more efficient than road. We briefly introduce five general strategies for decarbonizing freight transportation, and then focus on the literature and data relevant to estimating the global decarbonization potential through modal shift. We compare freight activity (in tonne-km) by mode for every country where data are available. We also describe major intraregional freight corridors, their modal structure, and their infrastructure needs. We find that the current world road and rail modal split is around 60:40. Most countries are experiencing strong growth in road freight and a shift from rail to road. Rail intermodal transportation holds great potential for replacing carbon-intense and fast-growing road freight, but it is essential to have a targeted design of freight systems, particularly in developing countries. Modal shift can be promoted by policies targeting infrastructure investments and internalizing external costs of road freight, but we find that not many countries have such policies in place. We identify research needs for decarbonizing the freight transportation sector both through improvements in the efficiency of individual modes and through new physical and institutional infrastructure that can support modal shift.}, language = {en} } @article{KaackKatul, author = {Kaack, Lynn and Katul, Gabriel}, title = {Fifty years to prove Malthus right}, series = {Proceedings of the National Academy of Sciences}, journal = {Proceedings of the National Academy of Sciences}, doi = {10.1073/pnas.1301246110}, abstract = {A major question confronting sustainability research today is to what extent our planet, with a finite environmental resource base, can accommodate the faster than exponentially growing human population. Although these concerns are generally attributed to Malthus (1766-1834), early attempts to estimate the maximum sustainable population (ergo, the carrying capacity K) were reported by van Leeuwenhoek (1632-1723) to be at 13 billion people (1). Since then, the concept of carrying capacity has evolved to accommodate many resource limitations originating from available water, energy, and other ecosystem goods and services (1, 2). In PNAS, Suweis et al.(3) apply the concept of carrying capacity using fresh water availability on a national scale as the limiting resource to infer the global K. They estimate a decline in global human population by the middle of this century. We ask to what extent models that are …}, language = {en} } @article{KaackAptGrangerMorganetal., author = {Kaack, Lynn and Apt, Jay and Granger Morgan, M. and McSharry, Patrick}, title = {Empirical prediction intervals improve energy forecasting}, series = {Proceedings of the National Academy of Sciences}, volume = {114}, journal = {Proceedings of the National Academy of Sciences}, number = {33}, doi = {10.1073/pnas.1619938114}, pages = {8752 -- 8757}, abstract = {Hundreds of organizations and analysts use energy projections, such as those contained in the US Energy Information Administration (EIA)'s Annual Energy Outlook (AEO), for investment and policy decisions. Retrospective analyses of past AEO projections have shown that observed values can differ from the projection by several hundred percent, and thus a thorough treatment of uncertainty is essential. We evaluate the out-of-sample forecasting performance of several empirical density forecasting methods, using the continuous ranked probability score (CRPS). The analysis confirms that a Gaussian density, estimated on past forecasting errors, gives comparatively accurate uncertainty estimates over a variety of energy quantities in the AEO, in particular outperforming scenario projections provided in the AEO. We report probabilistic uncertainties for 18 core quantities of the AEO 2016 projections. Our work frames how to produce, evaluate, and rank probabilistic forecasts in this setting. We propose a log transformation of forecast errors for price projections and a modified nonparametric empirical density forecasting method. Our findings give guidance on how to evaluate and communicate uncertainty in future energy outlooks.}, language = {en} } @incollection{KaackChenGrangerMorgan, author = {Kaack, Lynn and Chen, George and Granger Morgan, M}, title = {Truck traffic monitoring with satellite images}, series = {Proceedings of the 2nd ACM SIGCAS Conference on Computing and Sustainable Societies}, booktitle = {Proceedings of the 2nd ACM SIGCAS Conference on Computing and Sustainable Societies}, publisher = {Association for Computing Machinery}, address = {New York}, doi = {10.1145/3314344}, publisher = {Hertie School}, pages = {155 -- 164}, abstract = {The road freight sector is responsible for a large and growing share of greenhouse gas emissions, but reliable data on the amount of freight that is moved on roads in many parts of the world are scarce. Many low-and middle-income countries have limited ground-based traffic monitoring and freight surveying activities. In this proof of concept, we show that we can use an object detection network to count trucks in satellite images and predict average annual daily truck traffic from those counts. We describe a complete model, test the uncertainty of the estimation, and discuss the transfer to developing countries.}, language = {de} } @article{MilojevicDupontHansKaacketal., author = {Milojevic-Dupont, Nikola and Hans, Nicolai and Kaack, Lynn and Zumwald, Marius and Andrieux, Fran{\c{c}}ois and de Barros Soares, Daniel and Lohrey, Steffen and Pichler, Peter-Paul and Creutzig, Felix}, title = {Learning from urban form to predict building heights}, series = {Plos one}, volume = {15}, journal = {Plos one}, number = {12}, doi = {10.1371/journal.pone.0242010}, abstract = {Understanding cities as complex systems, sustainable urban planning depends on reliable high-resolution data, for example of the building stock to upscale region-wide retrofit policies. For some cities and regions, these data exist in detailed 3D models based on real-world measurements. However, they are still expensive to build and maintain, a significant challenge, especially for small and medium-sized cities that are home to the majority of the European population. New methods are needed to estimate relevant building stock characteristics reliably and cost-effectively. Here, we present a machine learning based method for predicting building heights, which is based only on open-access geospatial data on urban form, such as building footprints and street networks. The method allows to predict building heights for regions where no dedicated 3D models exist currently. We train our model using building data from four European countries (France, Italy, the Netherlands, and Germany) and find that the morphology of the urban fabric surrounding a given building is highly predictive of the height of the building. A test on the German state of Brandenburg shows that our model predicts building heights with an average error well below the typical floor height (about 2.5 m), without having access to training data from Germany. Furthermore, we show that even a small amount of local height data obtained by citizens substantially improves the prediction accuracy. Our results illustrate the possibility of predicting missing data on urban infrastructure; they also underline the value of open government data and volunteered geographic information for scientific applications, such as contextual but scalable strategies to mitigate climate change.}, language = {en} } @unpublished{KaackFriederichLuccionietal., author = {Kaack, Lynn and Friederich, David and Luccioni, Alexandra and Steffen, Bjarne}, title = {Automated Identification of Climate Risk Disclosures in Annual Corporate Reports}, abstract = {It is important for policymakers to understand which financial policies are effective in increasing climate risk disclosure in corporate reporting. We use machine learning to automatically identify disclosures of five different types of climate-related risks. For this purpose, we have created a dataset of over 120 manually-annotated annual reports by European firms. Applying our approach to reporting of 337 firms over the last 20 years, we find that risk disclosure is increasing. Disclosure of transition risks grows more dynamically than physical risks, and there are marked differences across industries. Country-specific dynamics indicate that regulatory environments potentially have an important role to play for increasing disclosure.}, language = {en} } @techreport{KaackDontiStrubelletal., type = {Working Paper}, author = {Kaack, Lynn and Donti, Priya and Strubell, Emma and Rolnick, David}, title = {Artificial Intelligence and Climate Change: Opportunities, considerations, and policy levers to align AI with climate change goals}, abstract = {With the increasing deployment of artificial intelligence (AI) technologies across society, it is important to understand in which ways AI may accelerate or impede climate progress, and how various stakeholders can guide those developments. On the one hand, AI can facilitate climate change mitigation and adaptation strategies within a variety of sectors, such as energy, manufacturing, agriculture, forestry, and disaster management. On the other hand, AI can also contribute to rising greenhouse gas emissions through applications that benefit high-emitting sectors or drive increases in consumer demand, as well as via energy use associated with AI itself. Here, we provide a brief overview of AI's multi-faceted relationship with climate change, and recommend policy levers to align the use of AI with climate change mitigation and adaptation pathways.}, 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} } @techreport{KaiserKleinKaack, type = {Working Paper}, author = {Kaiser, Silke K. and Klein, Nadja and Kaack, Lynn}, title = {From Counting Stations to City-Wide Estimates: Data-Driven Bicycle Volume Extrapolation}, doi = {10.48550/arXiv.2406.18454}, pages = {30}, abstract = {Shifting to cycling in urban areas reduces greenhouse gas emissions and improves public health. Street-level bicycle volume information would aid 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 bicycle volume for the entire city of Berlin. We predict daily and average annual daily street-level bicycle volumes using machine-learning techniques and various public data sources. These include app-based crowdsourced data, infrastructure, bike-sharing, motorized traffic, socioeconomic indicators, weather, and holiday data. Our analysis reveals that the best-performing model is XGBoost, and crowdsourced cycling and infrastructure data are most important for the prediction. We further simulate how collecting short-term counts at predicted locations improves performance. By providing ten days of such sample counts for each predicted location to the model, we are able to halve the error and greatly reduce the variability in performance among predicted locations.}, language = {en} }