@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{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{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} }