Spatioemporal variations of building sector carbon dioxide emissions from 2030 to 2060 in the GBA.

<b>Future building carbon emission maps with a spatial resolution of 500 meters under different SSP scenarios in the Guangdong-Hong Kong-Macao Greater Bay Area</b>This dataset provides high-resolution (500 meters) spatial distribution maps of building carbon emissions in the Guangdong-Hong Kong-Macao Greater Bay Area in the future (up to 2060) under different shared socio-economic path (SSP) scenarios. This study is based on an integrated modeling framework, which utilizes multi-source data such as urban form (LCZ) and population distribution, and through machine learning models like support vector regression (SVR), downscales the city-level multi-scenario (including business as business BAU and carbon Neutral CN) carbon emission prediction results to a 500-meter grid. It can accurately predict the spatial distribution pattern of future building carbon emissions under different development paths, providing data support for the research on urban carbon neutrality paths, sustainable planning and climate change mitigation strategies.<b>Future per capita building carbon emission maps with a spatial resolution of 500 meters under different SSP scenarios in the Guangdong-Hong Kong-Macao Greater Bay Area</b>This dataset provides high-resolution (500 meters) spatial distribution maps of per capita building carbon emissions in the Guangdong-Hong Kong-Macao Greater Bay Area in the future (up to 2060) under different shared socio-economic path (SSP) scenarios. This dataset is generated based on the prediction of total carbon emissions from buildings by dividing the predicted values of carbon emissions from each 500-meter grid by the high-resolution population prediction data within the corresponding grid. It can precisely reveal the carbon intensity and spatial equity of building usage in different regions in the future, providing key data support for formulating targeted emission reduction policies, evaluating sustainable urban development, and studying carbon neutrality strategies from the perspective of residents' lives.<br>

**粤港澳大湾区不同共享社会经济路径（Shared Socio-economic Pathway, SSP）情景下500米空间分辨率未来建筑碳排放地图**
本数据集提供了粤港澳大湾区未来（至2060年）不同共享社会经济路径情景下的高分辨率（500米）建筑碳排放空间分布图谱。本研究采用集成建模框架，融合局地气候分区（Local Climate Zone, LCZ）、人口分布等多源数据，并通过支持向量回归（Support Vector Regression, SVR）等机器学习模型，将城市尺度多情景（包括照常发展（Business As Usual, BAU）与碳中和（Carbon Neutral, CN）两类情景）下的建筑碳排放预测结果降尺度至500米网格单元。该数据集可精准预测不同发展路径下未来建筑碳排放的空间分布格局，为城市碳中和路径研究、可持续规划以及气候变化减缓策略制定提供数据支撑。

**粤港澳大湾区不同共享社会经济路径（Shared Socio-economic Pathway, SSP）情景下500米空间分辨率未来人均建筑碳排放地图**
本数据集提供了粤港澳大湾区未来（至2060年）不同共享社会经济路径情景下的高分辨率（500米）人均建筑碳排放空间分布图谱。该数据集通过将每个500米网格的建筑总碳排放预测值除以对应网格内的高分辨率人口预测数据，基于建筑总碳排放预测结果生成。其可精准揭示未来不同区域建筑使用的碳强度与空间公平性，为制定针对性减排政策、评估城市可持续发展水平以及从居民生活视角研究碳中和策略提供关键数据支撑。