Prediction of Permeability of Various Geotechnical Materials under Different Temperatures Based on Physical Characteristics and Machine Learning

Accurately and efficiently predicting permeability at different temperatures is crucial in the fuel science, as it enables optimization of production efficiency, and ensures safety and stability during storage and transportation. There remains a deficiency in predictive methods using comprehensive and reasonable training datasets and validating their applicability across different materials, particularly when considering stress and temperature. This study presents a machine learning-based method to predict permeability, incorporating physical characteristics such as microscopic image features and damage factors. The image sample data augmentation method was improved for a sufficient and meaningful training dataset, and gas permeability of sandstone under different pressure conditions after various temperature treatments were obtained. After summarizing the variation patterns of each characteristic with temperature, the necessity of using selected predictive features was validated, and sample sets were constructed. We trained an extreme learning machine neural network for sandstone’s permeability under different conditions, and the relative error was compared with other representative machine learning methods. Subsequently, the same data acquisition and prediction process were applied to granite and bentonite to validate the proposed method's applicability. The findings indicate that the proposed predictive method can stably provide accurate gas permeability predictions for various geomaterials, with relatively small prediction error rates (sandstone-4.1782%, granite-4.1782%, bentonite-3.2479%). Moreover, the stability of the relative error is steadily better than other representative machine learning methods. This approach achieves an effective prediction of gas permeability under various conditions, and can potentially simulate the evolution of gas permeability for fuel sector.