# Vectorized building rooftop prints of the Qinghai-Tibetan Plateau and its neighboring regions

## TL;DR

This paper presents the first high-resolution building footprint dataset for the Qinghai-Tibetan Plateau and surrounding regions, aiding urban planning and disaster risk research.

## Contribution

The study introduces the first vectorized building rooftop prints for the Qinghai-Tibetan Plateau using AI Earth platform and Google imagery.

## Key findings

- The dataset includes 13.09 million buildings covering 6092.7 km².
- Validation showed an overall accuracy of 87%, recall of 91.9%, and F1 score of 64.8%.
- The dataset provides a more detailed description of building distribution than the CBRA dataset.

## Abstract

Large-scale high-precision building distribution data is important fundation for regional urban planning and resource allocation and disaster risk research. The Qinghai-Tibetan Plateau is the third pole of the world. Although understanding local human–environment interactions in the Qinghai-Tibetan Plateau is critically important, this has been hindered by a lack of high-resolution building footprint data due to the vastness and remoteness of the area. In this study, we generated the first vectorized building rooftop prints of the Qinghai-Tibetan Plateau and its surrounding areas by using high-resolution Google imagery and the building contour extraction algorithm of the AI Earth platform. Our results include 13.09 million buildings covering 6092.7 km2, validated with a total of 250 × 1 km2 test samples. The data had an overall accuracy of 87%, a recall of 91.9%, and an F1 score of 64.8%, thus providing an advanced description of the building distribution of the study area as compared to CBRA. Our work has immense potential in facilitating exposure assessment for studies on disaster risk in this area.