Cities often report how much green space they contain, but those statistics rarely distinguish between parks that anyone can use and green spaces that are private or inaccessible. That distinction matters when planners are trying to understand equitable access to nature.
As evidence continues to show the benefits of green spaces for physical and mental well-being, they are receiving growing attention from policymakers, urban planners, and the public.
Understanding who has access to these areas is essential for ensuring that the benefits of green space are shared more equitably rather than reinforcing existing socioeconomic inequalities. Statistical and deep learning methods that combine satellite imagery with open GIS data are helping researchers map public green spaces more accurately.
Mapping private versus public green spaces
Sentinel-2 imagery can identify green spaces, but it cannot determine whether those spaces are publicly or privately accessible. Combining OpenStreetMap (OSM) and Sentinel-2 data can help urban planners distinguish public green spaces from private ones. In a 2021 study, researchers mapped public green spaces by first identifying land use polygons derived from OpenStreetMap data.
Combining satellite imagery with OpenStreetMap data
While OpenStreetMap (OSM) data can provide insights into public access by examining connections between spaces and streets, Sentinel-2 imagery is used to assess the ‘greenness’ of a specific area based on visual data.
In the approach, OSM data and Sentinel-2 satellite imagery are fused, and green spaces are determined through a probabilistic Dempster–Shafer theory. The method first estimates vegetation using the normalized difference vegetation index (NDVI) derived from Sentinel-2 imagery before applying Dempster-Shafer theory to estimate the probability that each area is truly green space.
This helps account for uncertainty caused by Sentinel-2’s spatial resolution and by pixels that fall between clearly vegetated and non-vegetated classes.
Subsequently, the OpenStreetMap (OSM) tag data, which indicates whether an area is ‘green,’ is utilized to refine the results, allowing for more accurate classification of land as ‘green.
Using OpenStreetMap indicators to determine if a green space is public
Even though this helps determine a green space, the results also need to classify public access and determine if something is truly public. This was done probabilistically using Bayesian logistic regression in classifying if given OSM data indicate public access.
Indicators such as ‘parks’, ‘village green’, or playgrounds would suggest public areas, this was not always the case so a probabilistic model is needed.
In a Bayesian hierarchical approach, if given indicators or tags from the OSM data would suggest public space, then that would mean the space is likely public but there is some probability it would not be classified as such; the model is not strictly deterministic given errors from map data.
The results are also validated using 300 land use polygons selected by hand and compared to the machine-based results.
The final step entails fusing results of green spaces and public access using Dempster-Shafer theory once again. This effectively combined rules that allowed both green and public spaces to be defined and fused in the final classification.
95% overall accuracy in identifying public green space
Overall accuracy did reach 95% when data were combined and checked manually.[1]
This demonstrates that the methodology is fairly accurate but uncertainty remains in places, in part driven by unclear results that can be derived from OSM data given that public spaces are not always clear.
Other approaches to mapping public green space
The approach represents a simpler, perhaps less machine-intensive way in which public green spaces can be determined.
Other approaches have included using deep learning classification, which not only require more data but require training a given model on what a public green space is. One can select from imagery and train a model to know that given areas on imagery would represent a public green space rather than something that was not public.
In this approach, classification from training areas using convolutional neural networks (CNN) helps to determine what is a public green space.
In some parts of the world, however, training a deep learning model may require additional local knowledge to accurately identify public green spaces. Such an approach may also require high resolution imagery to capture spaces, given that Sentinel-2’s resolution is 10 m this may not work as well with such imagery.[2]
Statistical and deep learning methods for mapping public green space
Both statistical and deep learning approaches can accurately map public green spaces when sufficient training data are available. In both cases, combining satellite imagery with OpenStreetMap data improves classification by reducing the uncertainty inherent in each dataset alone. More importantly, mapping public green spaces provides better estimates of public access, particularly for people living in densely urbanized areas.
References
[1] For more on using belief function and probabilistic methods to determine public green spaces from satellite imagery and OSM data, see: Ludwig C, Hecht R, Lautenbach S, et al. (2021) Mapping Public Urban Green Spaces Based on OpenStreetMap and Sentinel-2 Imagery Using Belief Functions. ISPRS International Journal of Geo-Information 10(4): 251. DOI: 10.3390/ijgi10040251.
[2] For more on a deep learning approach to mapping public green spaces, see: Huerta RE, Yépez FD, Lozano-GarcÃa DF, et al. (2021) Mapping Urban Green Spaces at the Metropolitan Level Using Very High Resolution Satellite Imagery and Deep Learning Techniques for Semantic Segmentation. Remote Sensing 13(11): 2031. DOI: 10.3390/rs13112031.
