Statistical processing of building and neighborhood data considering energy ratings in Dublin, Ireland.

This paper presents a methodology aimed to enhance urban energy analysis through the utilization of geospatial data to collect and integrate not only building data but also data related to the urban context in which buildings are situated. Utilizing datasets like the GeoDirectory Building Energy Ratings (BER) dataset of Ireland, supplemented by data of Digital Landscape Models (DLM) Core Data from Tailte Éireann Surveying (PRIME2 Dataset), landscape map of Dublin, we acquire both geometric and non-geometric data related to buildings in Dublin at both building and neighborhood scales. These datasets enable us to perform effective neighborhood-scale analysis and built environment analysis within a geospatial context. Our methodology employs a diverse array of tools and software, including programming languages such as MATLAB and Python ( in the Jupyter Notebook interface), with libraries such as Geopandas, Pandas, NumPy, Seaborn, and Scikit-learn were used for data processing and analysing. In addition, we conduct geospatial analyses using the toolbox and plugins of the ArcGIS and QGIS software. Our data integration encompasses various parameters including building attributes, neighborhood characteristics, and urban-scale built environment metrics at both building and neighborhood scales. This comprehensive dataset provides valuable insights into building energy performance and urban energy dynamics. Researchers can leverage this data to develop data-driven approaches and predictive models for analyzing environmental factors, thereby formulating effective urban planning strategies for sustainability and energy analysis of buildings, neighborhoods, and residential zones in Dublin.