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

2025-11-15

AI Summary

This study addresses the critical lack of high spatiotemporal resolution, continuous, and consistent data for global building dynamics monitoring. We propose the first multi-task deep learning framework designed for global-scale analysis, jointly estimating building density and height in an end-to-end manner by fusing quarterly PlanetScope satellite imagery (37.6 m spatial resolution) with building footprint and height annotations. The method achieves significantly improved temporal consistency—evidenced by a 0.96 correlation coefficient for five-year trend estimation—and attains F1 scores of 85%–88%, while substantially reducing computational cost. As the first of its kind, our framework generates a globally consistent, quarterly building change atlas spanning Q1 2018 to Q2 2025 at 37.6 m resolution. This dataset enables long-term, quantitative assessment of urbanization processes and climate adaptation strategies worldwide.

Technology Category

• Computer Vision: Scene Analysis & Understanding
• Machine Learning: Deep Neural Architectures and Foundation Models
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Web Mining and Content Analysis: Models for Web evolution

Abstract

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.

Problem

• Estimating global building density and height from satellite imagery
• Creating temporally resolved maps using deep learning models
• Monitoring urban development patterns and climate impacts quarterly

Innovation

• Uses deep learning for building density estimation
• Applies multi-task model to global satellite imagery
• Generates quarterly temporal maps at low cost