Application of Multi-Information Fracture Modeling Technology Constrained by the Stress Field in Shale Oil Development

Fractures are the main factors controlling the production of shale oil in the Mabei. Traditional well-seismic joint fracture modeling methods exhibit low accuracy and struggle to quantitatively characterize multi-scale, azimuthally distributed fractures. This paper innovates methods in the following aspects: (1) Azimuthal fracture modeling based on well data and azimuthal seismic information is conducted to enhance the pertinence; (2) Tectonic evolution analysis and multi-information-constrained stress field inversion are performed to reconstruct stress field across different periods, enabling the simulation of fracture development at different times driven by the stress field; (3) Through the method of deep learning, the fracture information from well logging, seismic data, and stress fields is effectively integrated into a unified framework, enabling precise characterization of fractures of different scales and periods. The application of these methods has significantly improved the prediction accuracy of natural fractures from the original 41% to over 80%. The results have delineated the distribution patterns of natural fractures in the Mabei, identified 26 square kilometers of favorable areas, supported the fracturing design of 6 wells in the M pilot area. The daily production capacity of wells has increased by more than 20%, contributing to cost reduction and efficiency enhancement in the oilfield.