Map of built-up expansion ("nedbygging") over Norway 2017-2024 with year of loss

1. Dataset description This is an updated version of the dataset found here: https://zenodo.org/records/12566926 In this version, we made the following changes: Refined the algorithm used to detect built-up expansion from Dynamic World - see a brief description of the methods in this NRK article Extended the timeframe to cover 2017-2024. Identified the year in which built-up expansion occurred for each polygon Description: The data contains polygons outlining potential “nedbygging” (hereafter translated to “built-up expansion” in English) events between 2017 and 2024 over Norway. The built-up expansion polygons were identified using a combination of Sentinel-2 satellite imagery, a fully convolutional neural network (a type of AI model) from Google called Dynamic World and NINA’s time series analysis thereof. The method to create the map will be published by NINA at a later date. It is important to note that the map is a result of AI and has errors in it. Therefore, users are encouraged to read the sections on data quality and usage information below. Users can refer to Venter et al. (2024) for details on the scientific best practice which the NRK journalists followed to ensure that their reported area estimates in the article were not biased. There are also many instances of built-up expansion which will be missed in the map such as forestry road development, building of small cabins etc. 2. File Details - Format: GeoJSON - Size: 188.6 MB 3. Geospatial Information - Coordinate System: EPSG:25832 - ETRS89 / UTM zone 32N - Spatial Resolution: 10m - Geographical Coverage: Norway mainland (excludes Svalbard) - Temporal Coverage: 2017 to 2024 4. Data Content - Attributes Included: - *id*: unique identity number for each polygon - *year*: the year in which the built-up expansion occurred as defined by the crowdsourcing volunteers - *area*: area in meters squared 5. Data Quality The overall User's Accuracy of the map is 82% = commission error of 18%. This means that the map incorrectly identified built-up expansion 18% of the time. We derived this from (1) a stratified random sample of 10x10m pixels within the area mapped as built-up expansion which were labelled by experts, and (2) a crowdsourcing campaign described here. The overall Producer's Accuracy of the map is 38% = omission error of 62%. This means that the map misses true cases of built-up expansion 62% of the time. We derived this by measuring the spatial overlap between our map and all buildings developed in SSB-bygg during the same timeframe. We found that many of the true cases (ie. buildings) were not detected by our map. In addition, we manually processed a random sample of 2868 buildings from SSB-bygg to identify the exact year at which land was cleared for decelopment. Here are the year-specific balanced accuracies of our map: 80.6% for 2018; 81.8 for 2019; 82.2 for 2020; 84% for 2021; 86% for 2022; 95% for 2023. 6. Usage Information - Use Limitations: Considering the map error described above, users should proceed with caution when analysing the map to derive area statistics or overlays with other maps. As described in Venter et al. (2024), simply adding the areas of the polygons (or “pixel counting” with maps formatted as images) without accounting for the error in the map will lead to incorrect area statistics. We recommend that users validate the map for their municipality or study area before proceeding with analysis. It is likely that the margin of error is highly variable between municipalities. For example, although we have not quantified it, we noticed many AI mistakes in mountainous regions due to snow and ice interference and therefore high-altitude municipalities might have more errors than low-altitude ones. 7. Acknowledgements This product was developed with support from the Norwegian Space Agency (Norsk Romsenter følgemidler 2024 kontrakt ON/2023/118).