A global 150-m dataset of urban building heights around 2020

Here, we provide a 150-m global urban building heights dataset around 2020 by combining the spaceborne lidar (Global Ecosystem Dynamics Investigation, GEDI), multi-sourced data (Landsat-8, Sentinel-2, and Sentinel-1), and topographic data. The validation results revealed that the GEDI-estimated building height samples were effective in comparison to the reference data (Pearson's r = 0.81, RMSE = 3.58 m). The mapping product also demonstrated good performance, as indicated by its strong correlation with the reference data (Pearson's r = 0.71, RMSE = 4.73 m).The global dataset of our urban building heights is availably visible by following the website (https://nju-eco-lidar.projects.earthengine.app/view/gbh2020), powered by the Google Earth Engine (GEE).<br><br>

我们在此发布一套分辨率为150米、时序约为2020年的全球城市建筑高度数据集，该数据集通过融合全球生态系统动态调查（Global Ecosystem Dynamics Investigation，简称GEDI）星载激光雷达、多源遥感数据（Landsat-8、Sentinel-2及Sentinel-1）与地形数据构建得到。验证结果表明，相较于参考数据，经GEDI反演得到的建筑高度样本表现优异（皮尔逊相关系数（Pearson's r）=0.81，均方根误差（RMSE）=3.58米）；该制图产品同样具备出色性能，与参考数据间呈现显著相关性（皮尔逊相关系数（Pearson's r）=0.71，均方根误差（RMSE）=4.73米）。

本研究构建的全球城市建筑高度数据集可通过以下网站访问查看：https://nju-eco-lidar.projects.earthengine.app/view/gbh2020，该平台由谷歌地球引擎（Google Earth Engine，简称GEE）提供技术支持。

搜集汇总

背景与挑战

背景概述

该数据集提供了2020年全球150米分辨率的城市建筑高度数据，结合了GEDI激光雷达和多源遥感数据，验证显示其具有较高的准确性，并可通过Google Earth Engine平台访问。