The efficient and safe operation of CO2 injection wells during geological sequestration is crucial for successful carbon capture and storage (CCS) projects. This study explores the application of machine learning in creating a data-driven model for simultaneous prediction of the location and size of potential leak incidents along an active CO2 injection well based on wellhead and bottom-hole pressure and temperature data. Five different well-established machine learning algorithms were selected for predictive model development, including Support Vector Regression (SVR), K-Nearest Neighbor Regression (KNNR), Decision Tree Regression (DTR), Random Forest Regression (RFR), and Artificial Neural Network (ANN). A series of numerical simulations were performed to create a dataset based on a CO2 injection well model in a southern North Sea saline aquifer reservoir, accounting for various leak scenarios with different locations and sizes. The dataset includes three input features of wellhead pressure, bottom-hole pressure, and bottom-hole temperature, paired with two output variables of leak location and leak size. The research findings demonstrate that all models perform well in effectively pinpointing leak locations, but they face difficulties when it comes to detecting small leaks, particularly those with a CO2 leakage rate below 0.01 kg/s. The results obtained indicated that, with regard to model performance, the SVR and KNNR models tended to outperform the others during the testing phase. More precisely, the SVR model demonstrated exceptional performance in the context of leak localization, particularly when dealing with smaller datasets. Conversely, KNNR consistently showcased superior performance in the detection of leak size, regardless of the dataset size. The outcomes of this research can provide valuable insights into the behavior of leaky CO2 injection wells during geological sequestration and highlight the efficacy of supervised machine learning in detecting and predicting leakage in CO2 injection wells.

You can access this article if you purchase or spend a download.