Abstract
Predictive analysis of the reservoir surveillance data is crucial for the high-efficiency management of oil and gas reservoirs. Here we introduce a new approach to reservoir surveillance that uses the machine learning tree boosting method to forecast production data. In this method, the prediction target is the decline rate of oil production at a given time for one well in the low-permeability carbonate reservoir. The input data to train the model includes reservoir production data (e.g., oil rate, water cut, gas oil ratio (GOR)) and reservoir operation data (e.g., history of choke size and shut-down activity) of 91 producers in this reservoir for the last 20 years. The tree boosting algorithm aims to quantitatively uncover the complicated hidden patterns between the target prediction parameter and other monitored data of a high variety, through state-of-the-art automatic classification and multiple linear regression algorithms. We also introduce a segmentation technique that divides the multivariate time-series production and operation data into a sequence of discrete segments. This feature extraction technique can transfer key features, based on expert knowledge derived from the in-reservoir surveillance, into a data form that is suitable for the machine learning algorithm. Compared with traditional methods, the approach proposed in this article can handle surveillance data in a multivariate time-series form with different strengths of internal correlation. It also provides capabilities for data obtained in multiple wells, measured from multiple sources, as well as of multiple attributes. Our application results indicate that this approach is quite promising in capturing the complicated patterns between the target variable and several other explanatory variables, and thus in predicting the daily oil production rate.