TEMPO: Global Temporal Building Density and Height Estimation from Satellite Imagery

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Glazer, Tammy, Hacheme, Gilles Q., Zaytar, Akram, Marotti, Luana, Michaels, Amy, Tadesse, Girmaw Abebe, White, Kevin, Dodhia, Rahul, Zolli, Andrew, Becker-Reshef, Inbal, Ferres, Juan M. Lavista, Robinson, Caleb
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917083163394048
author Glazer, Tammy
Hacheme, Gilles Q.
Zaytar, Akram
Marotti, Luana
Michaels, Amy
Tadesse, Girmaw Abebe
White, Kevin
Dodhia, Rahul
Zolli, Andrew
Becker-Reshef, Inbal
Ferres, Juan M. Lavista
Robinson, Caleb
author_facet Glazer, Tammy
Hacheme, Gilles Q.
Zaytar, Akram
Marotti, Luana
Michaels, Amy
Tadesse, Girmaw Abebe
White, Kevin
Dodhia, Rahul
Zolli, Andrew
Becker-Reshef, Inbal
Ferres, Juan M. Lavista
Robinson, Caleb
contents We present TEMPO, a global, temporally resolved dataset of building density and height derived from high-resolution satellite imagery using deep learning models. We pair building footprint and height data from existing datasets with quarterly PlanetScope basemap satellite images to train a multi-task deep learning model that predicts building density and building height at a 37.6-meter per pixel resolution. We apply this model to global PlanetScope basemaps from Q1 2018 through Q2 2025 to create global, temporal maps of building density and height. We validate these maps by comparing against existing building footprint datasets. Our estimates achieve an F1 score between 85% and 88% on different hand-labeled subsets, and are temporally stable, with a 0.96 five-year trend-consistency score. TEMPO captures quarterly changes in built settlements at a fraction of the computational cost of comparable approaches, unlocking large-scale monitoring of development patterns and climate impacts essential for global resilience and adaptation efforts.
format Preprint
id arxiv_https___arxiv_org_abs_2511_12104
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TEMPO: Global Temporal Building Density and Height Estimation from Satellite Imagery
Glazer, Tammy
Hacheme, Gilles Q.
Zaytar, Akram
Marotti, Luana
Michaels, Amy
Tadesse, Girmaw Abebe
White, Kevin
Dodhia, Rahul
Zolli, Andrew
Becker-Reshef, Inbal
Ferres, Juan M. Lavista
Robinson, Caleb
Computer Vision and Pattern Recognition
Machine Learning
We present TEMPO, a global, temporally resolved dataset of building density and height derived from high-resolution satellite imagery using deep learning models. We pair building footprint and height data from existing datasets with quarterly PlanetScope basemap satellite images to train a multi-task deep learning model that predicts building density and building height at a 37.6-meter per pixel resolution. We apply this model to global PlanetScope basemaps from Q1 2018 through Q2 2025 to create global, temporal maps of building density and height. We validate these maps by comparing against existing building footprint datasets. Our estimates achieve an F1 score between 85% and 88% on different hand-labeled subsets, and are temporally stable, with a 0.96 five-year trend-consistency score. TEMPO captures quarterly changes in built settlements at a fraction of the computational cost of comparable approaches, unlocking large-scale monitoring of development patterns and climate impacts essential for global resilience and adaptation efforts.
title TEMPO: Global Temporal Building Density and Height Estimation from Satellite Imagery
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2511.12104