Key points are not available for this paper at this time.
This study reviews the research on global photovoltaic power station site selection, using bibliometric analysis and inductive summary methods to construct a research framework of "literature collection - data integration - multi-dimensional analysis - inductive summary". This study employed the ChatGPT artificial intelligence model in conjunction with the Consensus plugin to conduct collaborative literature retrieval, and utilized the IMA knowledge base in combination with the DeepSeek large language model for analysis, examining the theoretical and technical frameworks of photovoltaic site selection. The study finds that since 2001, photovoltaic power station site selection methods have evolved from single economic goal optimization to multiple criteria decision making, integrating environmental, technological, and social dimensions. In recent years, the machine learning and optimization algorithms have become widespread, improving decision-making accuracy and efficiency. However, a structured overview to guide method selection and indicator optimization remains lacking. This study aims to: (1) identify trends and evolution paths in photovoltaic site selection research; (2) summarize the construction logic of the site selection evaluation index system; (3) outline the technical framework of multi-method collaborative decision-making. The findings provide theoretical support for dynamic weight optimization and cross-disciplinary method integration in photovoltaic site selection.
Liang et al. (Fri,) studied this question.