Inferring CO₂ saturation from seismic data is important when seismic methods are applied at CO₂ sequestration sites for verification and accounting purposes, such as verifying the total injected CO₂ volume, comparing with model predictions for concordance evaluation, tracking the migration of CO₂ plume, and detecting possible leakage from the storage reservoir. In this work, we infer CO₂ saturation levels at three depths from simulated surface seismic, downhole pressure and total dissolved solids (TDS) data using machine learning (ML) methods. The simulated monitoring data are based on 6000 numerical multi-phase flow simulations of hypothetical wellbore CO₂ and brine leakage from a legacy well into shallow aquifers at a model CO₂ storage site. We conduct rock physics modeling to estimate changes in seismic velocity due to the simulated CO₂ and brine leakage at each time step in the flow simulation outputs, resulting in 120,000 forward seismic velocity models. 2D finite-difference acoustic wave modeling is performed for each velocity model to generate synthetic shot gathers, along a sparse 2D seismic line with only 5 shots and 40 receivers. We extract 6 time-lapse seismic attribute anomalies from each trace in the time window relevant to each geologic layer, and use the seismic features, together with downhole pore pressure, TDS features to train the machine learning algorithms. The impact of seismic noise on the performance of the trained machine learning models has also been investigated. Inferred CO₂ saturations from the trained classifiers are in good agreement with observations. Direct pressure and TDS measurements from downhole monitoring can increase the accuracy of the inferred CO₂ saturation class from the forward modeled 2D surface seismic data. Our ML workflow represents a promising way to combine measurements from multiple monitoring techniques, together with seismic monitoring to achieve more accurate seismic quantitative interpretation.

从地震数据中推断出CO ₂饱和度是很重要的，这是因为在将CO ₂隔离地点采用地震方法进行验证和核算时，例如验证总注入CO ₂量，与模型预测进行比较以进行一致性评估，跟踪CO ₂羽流的迁移，并检测是否可能从储水箱漏水。在这项工作中，我们使用机器学习（ML）方法从模拟的表面地震，井下压力和总溶解固体（TDS）数据推断出三个深度处的CO ₂饱和度水平。模拟的监测数据基于假设的井筒CO _2的6000数值多相流模拟和盐水从旧式井泄漏到模型CO ₂储存地点的浅层含水层中。我们进行岩石物理建模，以估算由于模拟的CO ₂引起的地震速度变化流模拟输出中每个时间步的盐水泄漏和盐水泄漏，产生了120,000个正向地震速度模型。对每个速度模型执行2D有限差分声波建模，以沿着只有5个炮弹和40个接收器的稀疏2D地震线生成合成炮弹集。我们从与每个地质层相关的时间窗口中的每条迹线中提取6个时移地震属性异常，并使用地震特征以及井下孔隙压力TDS特征来训练机器学习算法。还研究了地震噪声对训练后的机器学习模型的性能的影响。推断CO ₂经过训练的分类器的饱和度与观测值非常吻合。井下监测的直接压力和TDS测量可以提高正向建模的2D地面地震数据推断的CO ₂饱和度等级的准确性。我们的ML工作流程代表了一种将多种监测技术的测量结果与地震监测结合起来以实现更准确的地震定量解释的有前途的方式。