Cargando…
A learning-based algorithm for generation of synthetic participatory mapping data in 2D and 3D
Public participation GIS (PPGIS) is a kind of spatial data that is collected through map-based surveys in which participants create map features and express their experiences and opinions associated with various places. PPGIS is widely used in urban and environmental research. PPGIS is often impleme...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Elsevier
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9535123/ https://www.ncbi.nlm.nih.gov/pubmed/36211594 http://dx.doi.org/10.1016/j.mex.2022.101871 |
Sumario: | Public participation GIS (PPGIS) is a kind of spatial data that is collected through map-based surveys in which participants create map features and express their experiences and opinions associated with various places. PPGIS is widely used in urban and environmental research. PPGIS is often implemented through online surveys and points are the most common mapped features. PPGIS data provide invaluable experiential spatial knowledge. Nevertheless, collection of this data for purely methodological purposes may be costly and unnecessary. Therefore, we developed a context-aware method that can learn from previously collected PPGIS data and create a realistic dataset that can be used for methodological development purposes. The synthetic data can be generated for any desired geographical extent in both 2D and 3D, i.e. with Z coordinates. The latter is particularly important as 3D PPGIS is an emerging frontier and limited infrastructures currently exist for collection of such data. Hence, while the relevant technology is developing, spatial analytical developments can also advance using such synthetic data. This method: • Learns from existing 2D and 3D PPGIS data in relation to the geographical context. • Creates a realistic and context-aware simulated PPGIS point dataset. The paper concludes by addressing the limitations and envisioning future research directions. |
---|