A learning-based data-driven forecast approach for predicting future reservoir performance

• Published in: Advances in water resources Vol. 118; no. C; pp. 95 - 109
• Main Authors: Jeong, Hoonyoung, Sun, Alexander Y., Lee, Jonghyun, Min, Baehyun
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01.08.2018; Elsevier Science Ltd; Elsevier
• Subjects: Algorithms; Artificial intelligence; Artificial neural network; Artificial neural networks; Calibration; Carbon capture and storage; Carbon dioxide; Carbon sequestration; Computer simulation; Constraint modelling; Data; Data processing; Data space inversion; Data-driven forecast; Economic forecasting; ENGINEERING; Forecasting techniques; Frameworks; Future reservoir performance; Genetic transformation; Geology; Iterative methods; Learning algorithms; Learning theory; Machine learning; Model matching; Neural networks; Oil production; oils; Performance prediction; prediction; Procedures; Regression analysis; Reservoir engineering; Reservoirs; Statistical analysis; Support vector machines; Support vector regression; Uncertainty; water resources; Workflow; Support vector regression; Data space inversion; Artificial neural network; Future reservoir performance; Data-driven forecast; Machine learning
• ISSN: 0309-1708; 1872-9657; 1872-9657
• DOI: 10.1016/j.advwatres.2018.05.015

•Data space inversion (DSI) methods enable fast prediction of system performance.•A new DSI method is developed based on machine learning and ensemble simulation.•Our method provided accurate forecast results and reasonable uncertainty intervals. Quantification of the predictive uncertainty of subsurface models has long been investigated. The traditional workflow is to calibrate prior models to match observed data, and then use the posterior models to simulate future system performance. Not only are these procedures computationally expensive, but they also have issues in maintaining geological model constraints during the calibration step. Data space inversion (DSI) was introduced recently to predict future system performance without the iterative history matching or model calibration step. In general, DSI approaches seek to establish a statistical relationship between the observed and forecast variables, as well as to quantify the predictive uncertainty of the forecast variables, by using an ensemble of uncalibrated prior models. Existing DSI approaches all require a number of complex transformation and mapping operations, which may deter their widespread use. In this study, we introduce a new and simpler DSI approach, the learning-based, data-driven forecast approach (LDFA), by combining dimension reduction and machine learning techniques to quickly provide accurate forecast results and reliably quantify corresponding uncertainty in the results. Our LDFA framework is demonstrated using two supervised learning algorithms, artificial neural network (ANN) and support vector regression (SVR), on two representative examples from reservoir engineering and geological carbon storage. Results suggest that our approach provides accurate forecast results (e.g., future oil production rate or cumulative injected CO2) and reasonable predictive uncertainty intervals. Our framework is generic and may be applied to other surface and subsurface problems.