Dataset
GLAMOUR: Global building morphology dataset for urban climate modelling (2020)
Abstract
The GLobAl building MOrphology dataset for URban hydroclimate modelling (GLAMOUR) is derived from open-source Sentinel imagery that captures the average building height and footprint at a resolution of 0.0009° across urbanized areas worldwide (approximately 100 m at the equator) across 13189 urban areas globally from 01/01/2020 to 31/12/2020. This dataset optimally leverages multi-task DL (MTDL) models, publicly accessible satellite images in conjunction with the Google Cloud ecosystem to enable efficient and accurate large-scale mapping. This building morphology dataset provides an unprecedented possibility for enabling various urban hydroclimate applications at a global scale, including human thermal comfort simulation, building energy modelling, 3D flood risk analysis among others.
Data are netCDF formatted and contain the following variables:
- BH: building height (m)
- BF: building footprint (m2 m-2)
Each file is named following the convention: `GLAMOUR_{lon_start}_{lon_end}_{lat_start}_{lat_end}.nc`, where:
- {lon_start} and {lon_end} are the longitude coordinates of the lower-left and upper-right corners of the grid, respectively.
- {lat_start} and {lat_end} are the latitude coordinates of the lower-left and upper-right corners of the grid, respectively.
Details
| Previous Info: |
No news update for this record
|
|---|---|
| Previously used record identifiers: |
No related previous identifiers.
|
| Access rules: |
Public data: access to these data is available to both registered and non-registered users.
Use of these data is covered by the following licence(s): http://www.nationalarchives.gov.uk/doc/open-government-licence/version/3/ When using these data you must cite them correctly using the citation given on the CEDA Data Catalogue record. |
| Data lineage: |
GLAMOUR is produced using a multi-task deep learning model SHAFTS based on Sentinel-1 and Sentinel-2 satellite images. The SHAFTS model is trained on a large-scale dataset of building footprints and heights from OpenStreetMap and Google Earth Engine. The SHAFTS model is then used to predict building footprints and heights for urban areas identified based population density outlined by the Gridded Population of the World, Version 4 (GPWv4) dataset and the Global Human Settlement-Urban Centre Database (GHS-UCDB). |
| Data Quality: |
The GLAMOUR dataset is derived from open-source Sentinel imagery that captures the average building height and footprint at a resolution of 0.0009° across urbanized areas worldwide. Validated in 18 cities, GLAMOUR exhibits superior accuracy with median root mean square errors of 7.5 m and 0.14 for building height and footprint estimations, indicating better overall performance against existing published datasets.
|
| File Format: |
NetCDF
|
Process overview
| Title | Simultaneous building Height And FootprinT extraction from Sentinel imagery (SHAFTS) |
| Abstract | A multi-task deep-learning-based Python package SHAFTS (Simultaneous building Height And FootprinT extraction from Sentinel imagery) to extract the average building height and footprint from Sentinel imagery. Evaluation in 46 cities worldwide shows that SHAFTS achieves significant improvement over existing machine-learning-based methods. |
| Input Description | None |
| Output Description | None |
| Software Reference | None |
- units: 1
- var_id: BF
- long_name: Building Footprint
- units: m
- var_id: BH
- long_name: Building Height
- units: degrees_north
- var_id: latitude
- long_name: Latitude
- units: degrees_east
- var_id: longitude
- long_name: Longitude
- var_id: time
- long_name: Time
- units: hours
- var_id: spatial_ref
Co-ordinate Variables
Temporal Range
2020-01-01T00:00:00
2020-12-31T00:00:00
Geographic Extent
72.0000° |
||
-180.0000° |
180.0000° |
|
-55.0000° |