Development of Visual Prediction Model for Shale Gas Well Production Based on Screening Main Controlling Factors

Abstract

The clarification of the main controlling factors of production and estimated ultimate recovery (EUR) with high accuracy is necessary for shale gas development. Sixteen key parameters were selected as the most influential factors through a sensitivity analysis study: the reservoir parameters, hydraulic fracturing parameters, production parameters. The importance was sorted based on the key parameters by distance correlation coefficient, and then the main controlling factors that affect the EUR are clarified. A visual forecasting model of EUR was then developed using least squares support vector machine (LSSVM) in terms of the main controlling factors. The visual models established by the response surface method and the simple neural network were compared and analyzed. The field application results of the model indicate that the model based on the LSSVM has the best field application effect. The proposed model is a serviceable tool for EUR prediction of shale gas wells. Furthermore, the use of the model is efficient and convenient, and only six main controlling factors can be used to achieve the prediction of EUR. The results of this study can be extended as the main controlling factors analysis and the development of EUR visual model of shale gas wells in other blocks.