<b>PS4GR-CN:</b><b> </b><b>A dataset of plant species for green roofs in China based on a large language model</b>

As urbanization accelerates, many negative ecological impacts become more prominent. Green roofs offer a sustainable solution to mitigate the urban heat island effect and reduce the carbon footprint. However, the lack of plant species datasets for green roofs in China limits research and practice. Therefore, this study constructs a diversified dataset of plant species for green roofs in China using China National Knowledge Infrastructure (CNKI) and Web of Science (WoS) as data sources. The dataset is generated by integrating the Kimi large language model(Kimi LLM) API with knowledge graph technology, resulting in 2,248 plant records. It includes a statistical CSV file of plant details, a CSV file of species combinations, a CSV file linking plant combinations to cities, and original plant data from papers. The accuracy and efficiency of the dataset in acquiring plant species are validated through technical experiments. This dataset applies to plant selection for green roofs, facilitating in-depth research and broader applications in urban sustainability.<br>