Solar energy is considered one of the most important renewable energy sources and is recognized as the fastest-growing energy source worldwide. The power generated in solar energy facilities primarily depends on the amount of radiation reaching the surface of photovoltaic (PV) panels. Prior knowledge of solar radiation is crucial for reliable planning and efficient design of solar energy systems. Therefore, solar radiation forecasting is a highly significant topic. Various techniques can be employed for solar radiation prediction, including fundamental physical and statistical methods, as well as ensemble methods obtained by combining different approaches. However, the remarkable success of artificial neural networks, a form of artificial intelligence application that enhances learning algorithms, in various applications has attracted researchers to this field. The promising potential of this field is evident in the richness of proposed methods and the increasing number of publications. The main objective of this study is to review artificial intelligence-based techniques found in the literature for solar radiation prediction and to identify research gaps by examining radiation predictions using machine learning-based methods and hybrid models created by their combination with other techniques, which have gained popularity recently. Additionally, the aim is to provide an analysis that guides future improvements and understanding of recent advancements in this field. To facilitate and enhance research in this area, a comprehensive review of various artificial intelligence-based prediction methods employed in solar radiation prediction studies, particularly focusing on the most commonly used artificial intelligence-based approach published recently, is presented. Furthermore, information on the required data parameters in solar radiation prediction studies is provided. All research details, fundamental features, and specifics are summarized in tabular and shape formats for a comprehensive overview.