An auto-tuned hybrid deep learning approach for predicting fracture evolution

Abstract In this study, a novel auto-tuned hybrid deep learning approach composed of three base models, namely, long short-term memory, gated recurrent unit, and support vector regression, is developed to predict the fracture evolution process. The novelty framework lies in auto-determined hyperparameter configurations for each model based on Bayesian optimization technique, which guarantees fast easy implementation various practical applications. Moreover, ensemble modeling technique auto consolidates predictive capability generate final optimized model, offers better prediction overall pattern evolution, as demonstrated by case study. comparison different strategies exhibits that direct option than recursive prediction, particular longer distance. proposed may be applied sequential data predictions adopting adaptive scheme.