早稲田大学 · 工学
Hung Vo Thanh教授の研究室は、炭素隔離・貯蔵（CCUS）やガス貯蔵技術の効率化を目的として、機械学習を活用した地下炭素・ガス貯蔵の性能予測と地質モデリングに注力しています。特に、人工ニューラルネットワークやランダムフォレストを用いた予測モデル開発、不確実性を伴う地質的条件下でのCO₂貯蔵容量の最適化が主な研究テーマです。実データと数値シミュレーションを統合した知的モデリング手法の構築が、CCUSプロジェクトの実用化を支援しています。
Figures are computed from collected data and may differ slightly.
Residual Oil Zones (ROZs) become potential formations for Carbon Capture, Utilization, and Storage (CCUS). Although the growing attention in ROZs, there is a lack of studies to propose the fast tool for evaluating the performance of a CO<sub>2</sub> injection process. In this paper, we introduce the application of artificial neural network (ANN) for predicting the oil recovery and CO<sub>2</sub> storage capacity in ROZs. The uncertainties parameters, including the geological factors and well ope
This study proposed a new geological modelling procedure for CO2 storage assessment in offshore Vietnam by integrating artificial neural networks, co-kriging and object-based methods. These methods could solve the limitations of well data that have not been addressed by conventional modelling. Petrel software was used to build a geological model for comparing conventional and new modelling workflows. Moreover, the Eclipse simulator was used for CO2 injection scenarios on the geological model of
Open papers in the app to read, cite, and organize with AI.
