Physical Science and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, 23955, Saudi Arabia.
Physical Science and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, 23955, Saudi Arabia.
Chemosphere. 2023 Dec;345:140469. doi: 10.1016/j.chemosphere.2023.140469. Epub 2023 Oct 17.
Effectively storing carbon dioxide (CO) in geological formations synergizes with algal-based removal technology, enhancing carbon capture efficiency, leveraging biological processes for sustainable, long-term sequestration while aiding ecosystem restoration. On the other hand, geological carbon storage effectiveness depends on the interactions and wettability of rock, CO, and brine. Rock wettability during storage determines the CO/brine distribution, maximum storage capacity, and trapping potential. Due to the high CO reactivity and damage risk, an experimental assessment of the CO wettability on storage/caprocks is challenging. Data-driven machine learning (ML) models provide an efficient and less strenuous alternative, enabling research at geological storage conditions that are impossible or hazardous to achieve in the laboratory. This study used robust ML models, including fully connected feedforward neural networks (FCFNNs), extreme gradient boosting, k-nearest neighbors, decision trees, adaptive boosting, and random forest, to model the wettability of the CO/brine and rock minerals (quartz and mica) in a ternary system under varying conditions. Exploratory data analysis methods were used to examine the experimental data. The GridSearchCV and K cross-validation approaches were implemented to augment the performance abilities of the ML models. In addition, sensitivity plots were generated to study the influence of individual parameters on the model performance. The results indicated that the applied ML models accurately predicted the wettability behavior of the mineral/CO/brine system under various operating conditions, where FCFNN performed better than other ML techniques with an R above 0.98 and an error of less than 3%.
有效地将二氧化碳（CO）储存在地质构造中与基于藻类的去除技术协同作用，提高碳捕获效率，利用生物过程进行可持续的长期封存，同时有助于生态系统恢复。另一方面，地质碳封存的有效性取决于岩石、CO 和盐水之间的相互作用和润湿性。储存过程中的岩石润湿性决定了 CO/盐水的分布、最大储存容量和捕集潜力。由于 CO 反应性高且有损坏风险，因此对储存/封存用岩石的 CO 润湿性进行实验评估具有挑战性。基于数据的机器学习 (ML) 模型提供了一种高效且不费力的替代方法，使研究能够在实验室中无法或危险地实现的地质封存条件下进行。本研究使用了强大的 ML 模型，包括全连接前馈神经网络 (FCFNN)、极端梯度提升、k 最近邻、决策树、自适应增强和随机森林，以在不同条件下对 CO/盐水和岩石矿物（石英和云母）在三元体系中的润湿性进行建模。使用探索性数据分析方法来检查实验数据。实施了 GridSearchCV 和 K 交叉验证方法来增强 ML 模型的性能能力。此外，还生成了敏感性图来研究单个参数对模型性能的影响。结果表明，所应用的 ML 模型准确预测了在各种操作条件下矿物/CO/盐水系统的润湿性行为，其中 FCFNN 比其他 ML 技术表现更好，R 值高于 0.98，误差小于 3%。
