Generation of Synthetic Data for the Analysis of the Physical Stability of Tailing Dams through Artificial Intelligence

In this research, we address the problem of evaluating physical stability (PS) to close tailings dams (TD) from medium-sized Chilean mining using artificial intelligence (AI) algorithms. The PS can be analyzed through study critical variables TD that allow estimating different potential failure mechanisms (PFM): seismic liquefaction, slope instability, static overtopping, and piping, which may occur in type storage facilities a seismically active country such as Chile. Thus, article proposes use four machine learning algorithms, namely random forest (RF), support vector (SVM), neural networks (ANN), extreme gradient boosting (XGBoost), estimate five possible PFM. addition, due scarcity data train generative adversarial (GAN) is proposed create synthetic increase database used. Therefore, novelty consists PFM for generating GAN. results show that, when GAN, result obtained by ML models increases F1-score metric 30 percentage points, obtaining 97.4%, 96.3%, 96.7%, 97.3% RF, SVM, ANN, XGBoost, respectively.