Generative adversarial networks review in earthquake-related engineering fields

Abstract Within seismology, geology, civil and structural engineering, deep learning (DL), especially via generative adversarial networks (GANs), represents an innovative, engaging, advantageous way to generate reliable synthetic data that represent actual samples’ characteristics, providing a handy augmentation tool. Indeed, in many practical applications, obtaining significant number of high-quality information is demanding. Data generally based on artificial intelligence (AI) machine data-driven models. The DL GAN-based approach for generating seismic signals revolutionized the current paradigm. This study delivers critical state-of-art review, explaining recent research into AI-based GAN generation ground motion or events, also with comprehensive insight seismic-related geophysical studies. may be relevant, earth planetary science, geology oil gas exploration, other hand assessing response buildings infrastructures, detection tasks, general engineering applications. Furthermore, highlighting strengths limitations studies applied seismology help guide efforts next future toward most promising directions.