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.

Spontaneous water imbibition is an important mechanism in water-wet fractured reservoirs. For volume-fractured reservoirs, to evaluate the oil productivity and oil recovery through water counter-current imbibition, we propose an analytical method for optimizing the reservoir volume fracturing scheme. Based on the two-phase fluid flow differential equation for capillary force, a three-dimensional water imbibition productivity equation is derived analytically. The equation for the water imbibition productivity considering the fracture network is obtained. A numerical model is constructed to verify the validity of the average capillary diffusivity coefficient and the results of the analytical model. By applying this method to a low permeability reservoir, after volume fracturing and waterflooding huff and puff, the relationship between the tenth years oil recovery and oil production rate and the length, width, and density of the fracture network is predicted, which gives an optimization of the field fracturing construction scale. The results show that the length and width of the fracture network should be no less than 50 of the well spacing and row spacing to obtain a reasonable production. Considering the fracturing technique and economic feasibility, the higher the density of the fracture network, the better the production obtained. Through hydraulic volume fracturing and waterflooding huff and puff, water imbibition is brought into full play and the 10 year oil recovery is increased by 68 in this area.