Abstract This work shows that the GBDT algorithms are a better choice to predict the Start date while the ANN algorithms have better prediction performances on predicting the End date and Duration values. Utilizing a machine-learning algorithm to directly predict the Start date value is better than utilizing two algorithms to predict the End date and […]
Abstract In this work, it has been shown that a mixture SDS/CnDMAA can be used as the switchable surfactants. A COMPASS forcefield is one of the successful options in this study. Molecular simulation has the potential to predict inter- and intra-molecular interactions. The results showed that CnDMAA can significantly affect the interfacial behavior of SDS surfactant in an […]
Abstract In this work, a Transformer model was built based on Encoder-Decoder architecture to evaluate the performance of reservoirs integrating production data, geological data, and dynamic data. Structure changes are made in the Transformer model to utilize various data types to improve the accuracy of prediction. More data sets (i.e., simulations and field cases) will be applied […]
Abstract This work shows that the asphaltene architecture, resin and surfactant structures significantly affect surfactant-asphaltene interactions. A benzene ring in the surfactant structure can improve the interaction between surfactant and asphaltenes. Having sulfur heteroatoms in the resin structure can increase an interaction between SDBS and asphaltenes for both archipelago and island architectures. However, resin with sulfur […]
Abstract This work shows that the deep learning method can solve the problem of a PDE system effectively and accurately (error: less than 0.7%); The deep learning method can accurately handle the estimation problem of a PDE system (error: less than 0.5%); Shale gas production can be divided into three stages, and they are dominated by free […]