A Large-Language-Model-Based Dataset of Plant Species for Green Roofs in China

As urbanization accelerates, a host of negative ecological impacts have become increasingly prominent. Green roofs, as a sustainable solution, can effectively mitigate the urban heat island effect and reduce carbon footprints. However, the lack of datasets on plant species suitable for green roofs in China has hindered the advancement of relevant research and practical applications. Therefore, this study constructed a diversified dataset of plant species for green roofs in China, using data sources from the China National Knowledge Infrastructure (CNKI) and Web of Science (WoS). Generated by integrating the Kimi large language model (Kimi LLM) API with knowledge graph technology, the dataset contains 2248 plant records. It specifically includes a statistical CSV file with detailed plant information, a CSV file of species combinations, a CSV file linking plant combinations to cities, and original plant data extracted from research papers. Technical experiments have validated the accuracy and efficiency of this dataset in acquiring plant species. Suitable for plant selection in green roof projects, this dataset will provide strong support for in-depth research and wider applications in the field of urban sustainability.