GIS Ostrava 2022 – Earth Observation for Smart City and Smart Region March 16 - 18, 2022 MAPPING URBAN GREEN SPACE DYNAMICS: A SEMANTIC EARTH OBSERVATION DATA CUBE APPROACH Dirk TIEDE 1 , Martin SUDMANNS 1 , Hannah AUGUSTIN 1 , Larisa PAULESCU 1 , Andrea BARALDI 2 1 Department of Geoinformatics, University of Salzburg, Salzburg, 5020, Austria ²Spatial Services GmbH, Salzburg, 5020, Austria Correspondence to: Dirk TIEDE 1 (dirk.tiede@plus.ac.at) https://doi.org/10.31490/9788024846026-13 Abstract Urban green space mapping based on satellite imagery is now possible more frequently and over shorter timespans thanks to dense time-series of open and free Earth observation (EO) images (e.g. the Copernicus Sentinel-2 mission). Despite this data availability, many approaches still focus on identifying the annual maximum extent of urban green spaces instead of utilising the entire dense image stack to characterise seasonal dynamics. We aim to temporally inform urban green space delineations, which could be relevant for applications like urban heat mitigation or citizens’ urban green perception. We present a semantic EO data cube approach that allows ad-hoc, browser-based vegetation mapping for custom areas and timespans using transferable semantic models. We demonstrate the approach using a Sentinel-2 semantic EO data cube covering Austria, which makes use of every available Sentinel-2 observation since 2015 and where non-valid observations (e.g. cloud) can be masked out on an individual pixel basis to increase the number of valid observations for shorter timespans rather than relying on image-wide metadata. While we show results for the city of Vienna, the approach is transferrable to anywhere in Austria using the same infrastructure, or any other similar semantic EO data cube worldwide. Keywords: urban green space, semantic EO data cube, semantic enrichment, semantic models, time series analysis INTRODUCTION Urban green space (UGS) is valuable for wellbeing and health and provides environmental benefits, such as mitigating urban heat or retaining storm water (Lee et al., 2015). There is a need for permanently monitoring urban green space and relevant changes in line with the United Nations Sustainable Development Goals (SDG), especially SDG 11, to improve availability of green spaces in cities and strengthen UGS’s role in climate change mitigation. UGS mapping based on satellite imagery is now possible at a higher spatial resolution and over more frequent and shorter timespans than ever before due to the availability of open and free Earth observation (EO) images (e.g. Copernicus Sentinel-2 data, Landsat mission). Nevertheless, most approaches that map UGS mainly focus on the maximum spatial extent during a year. For example, Huang et al. (2021) analysed UGS for an enormous amount of 1039 cities worldwide, making use of the greenest pixel compositing method looking for the maximum extents of vegetation cover based on machine learning methods. Corbane et al. (2020) used annual greenest pixel composites for Landsat data on the Google Earth Engine