Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tarver, Benjamin, Law, Noelle, Getz, Sasha, Miura, Yuki
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2505.19358
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914605880573952
author Tarver, Benjamin
Law, Noelle
Getz, Sasha
Miura, Yuki
author_facet Tarver, Benjamin
Law, Noelle
Getz, Sasha
Miura, Yuki
contents Building-level exposure data are critical to natural hazard risk modeling, yet most global inventories describe where buildings are located rather than what they are made of. Roof material is a critical but poorly documented attribute for assessing vulnerability to wildfires, wind hazards, urban heat, floods, and earthquakes. To address this gap, we introduce RoofNet, a global dataset that maps 49,662 georeferenced building instances from 101 countries to 14 key roofing material classes using Earth observation (EO) imagery (redistributed where permitted) and associated geospatial metadata. RoofNet contributes (1) climatographically and architecturally diverse coverage of roof material labels, (2) a scalable annotation pipeline combining SME-guided manual labeling with vision-language model (VLM)-assisted classification, rule-based validation, and human-in-the-loop verification, and (3) a resource for evaluating subtle, geographically variable material-level identification in EO imagery and its implications for material-aware hazard risk modeling. Evaluation on a manually labeled hold-out set shows that zero-shot Remote Contrastive Language-Image Pre-Training (RemoteCLIP) struggles with roof material classification, while fine-tuning with RoofNet improves top-1 accuracy from 4.9% to 47.7%. We use RoofNet in an illustrative hazard case study to demonstrate how material-aware exposure data can change vulnerability estimates relative to material-naive inventories. RoofNet provides a missing material layer for global building attribute mapping and scalable hazard risk assessment.
format Preprint
id arxiv_https___arxiv_org_abs_2505_19358
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RoofNet: A Global Multimodal Dataset for Roof Material Identification from Earth Observation
Tarver, Benjamin
Law, Noelle
Getz, Sasha
Miura, Yuki
Computational Engineering, Finance, and Science
Building-level exposure data are critical to natural hazard risk modeling, yet most global inventories describe where buildings are located rather than what they are made of. Roof material is a critical but poorly documented attribute for assessing vulnerability to wildfires, wind hazards, urban heat, floods, and earthquakes. To address this gap, we introduce RoofNet, a global dataset that maps 49,662 georeferenced building instances from 101 countries to 14 key roofing material classes using Earth observation (EO) imagery (redistributed where permitted) and associated geospatial metadata. RoofNet contributes (1) climatographically and architecturally diverse coverage of roof material labels, (2) a scalable annotation pipeline combining SME-guided manual labeling with vision-language model (VLM)-assisted classification, rule-based validation, and human-in-the-loop verification, and (3) a resource for evaluating subtle, geographically variable material-level identification in EO imagery and its implications for material-aware hazard risk modeling. Evaluation on a manually labeled hold-out set shows that zero-shot Remote Contrastive Language-Image Pre-Training (RemoteCLIP) struggles with roof material classification, while fine-tuning with RoofNet improves top-1 accuracy from 4.9% to 47.7%. We use RoofNet in an illustrative hazard case study to demonstrate how material-aware exposure data can change vulnerability estimates relative to material-naive inventories. RoofNet provides a missing material layer for global building attribute mapping and scalable hazard risk assessment.
title RoofNet: A Global Multimodal Dataset for Roof Material Identification from Earth Observation
topic Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2505.19358