Production Capacity Prediction of Fractured Horizontal Wells Based on XGBoost

Abstract

Accurate prediction of the productivity of tight gas fracturing horizontal wells has important practical significance for optimizing development strategies and improving production efficiency. In view of the limitations of traditional methods in terms of assumptions and lack of historical data, as well as the complex nonlinear relationship between geological and engineering parameters, this paper takes the tight gas fracturing horizontal wells in Block S of Ordos Basin as an example, and uses Spearman correlation analysis to determine the main control factors of post fracturing production; Combining geological and engineering parameters, a horizontal well fracturing productivity prediction model is established based on XGBoost algorithm. The results show that the average error is 11.47%, which can better realize the accurate prediction of post fracturing productivity and provide an important scientific basis for the economic development of tight gas fields.