GraphCSVAE is a new probabilistic framework that builds graph representations from satellite data to model and audit spatiotemporal changes in physical vulnerability using categorical inference and expert priors.
A., Marcos, J
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Mapping buildings and roads automatically with remote sensing typically requires high-resolution imagery, which is expensive to obtain and often sparsely available. In this work we demonstrate how multiple 10 m resolution Sentinel-2 images can be used to generate 50 cm resolution building and road segmentation masks. This is done by training a `student' model with access to Sentinel-2 images to reproduce the predictions of a `teacher' model which has access to corresponding high-resolution imagery. While the predictions do not have all the fine detail of the teacher model, we find that we are able to retain much of the performance: for building segmentation we achieve 79.0\% mIoU, compared to the high-resolution teacher model accuracy of 85.5\% mIoU. We also describe two related methods that work on Sentinel-2 imagery: one for counting individual buildings which achieves $R^2 = 0.91$ against true counts and one for predicting building height with 1.5 meter mean absolute error. This work opens up new possibilities for using freely available Sentinel-2 imagery for a range of tasks that previously could only be done with high-resolution satellite imagery.
representative citing papers
A rule-based grid score (median building area / building count) from open building footprints classifies Indian urban neighborhoods into affluence tiers that correlate with loan delinquency and visually match informal settlements.
citing papers explorer
-
GraphCSVAE: Graph Categorical Structured Variational Autoencoder for Spatiotemporal Auditing of Physical Vulnerability Towards Sustainable Post-Disaster Risk Reduction
GraphCSVAE is a new probabilistic framework that builds graph representations from satellite data to model and audit spatiotemporal changes in physical vulnerability using categorical inference and expert priors.
-
Life Style Levels: Neighborhood Delineation using Geospatial Data
A rule-based grid score (median building area / building count) from open building footprints classifies Indian urban neighborhoods into affluence tiers that correlate with loan delinquency and visually match informal settlements.