This chapter presents an extensive review of methods for predicting both secondary and tertiary structures of nucleic acids, particularly focusing on RNA. Secondary structure prediction techniques are categorized into single sequence prediction and multiple sequence alignment prediction, encompassing methods like the minimum free energy approach, dynamic programming, statistical sampling, and associated tools. Additionally, tertiary structure prediction strategies, including homology modeling, ab initio modeling, and fragment assembly, are fully discussed. Notably, the application of artificial intelligence (AI) methods, such as deep learning and machine learning, in RNA structure prediction is also highlighted. These AI approaches leverage large datasets to enhance prediction accuracy and address complex sequence-structure relationships, showcasing their potential to transform the field of RNA structure prediction. Overall, this chapter encapsulates the diverse range of methods and tools currently employed in RNA structure prediction, emphasizing both traditional and AI-driven techniques.