An Intelligent Inversion Method for Complex Fractures Using Ensemble Neural Network

Abstract

Abstract Proper characterization of fractures is critical for evaluating the effectiveness of fracturing jobs and optimizing well performance in unconventional reservoirs, geothermal energy production, and other areas. However, accurately determining the size, shape, and orientation of these fractures solely from microseismic events is challenging due to weak signals and noise. To address this challenge, this study proposes a novel workflow that directly builds accurate fracture models from microseismic events using the DBSCAN clustering algorithm and ensemble neural network. The first step is to filter the noise in microseismic events using the DBSCAN clustering algorithm. Next, a 3D planar equation is employed to construct the fracture plane. Based on the results of this step, reservoir simulations are performed iteratively using an embedded discrete fracture model (EDFM) and proxy. Multiple representation models are obtained to capture calibration uncertainty and enable subsequent studies of long-term well performance, such as history matching for production. Finally, an integrated neural network incorporating the ES-MDA history auto-fitting algorithm is utilized to find the most appropriate fracture model for matching field production data through iterative processes. The developed complex fracture inversion method was implemented on a representative shale gas horizontal well. The results demonstrate that the DBSCAN clustering algorithm effectively reduces noise in microseismic activity and ensures the accuracy of fracture geometry. A large number of different fracture models can be quickly generated by the proxy model to capture calibration uncertainty. An integrated neural network with a history auto-fitting algorithm is utilized to optimize the fracture model and identify the optimal solution. The fracture models constructed using this method exhibit fracture half-lengths and fracture heights that are 20%-40% smaller than those estimated by microseismic monitoring. Furthermore, the high level of historical fit for this horizontal well indicates that the complex fracture model is realistic for the mine site. This study introduces a new approach to building a complex fracture network. By using microseismic data, and implementing an automatic history matching system, this method provides a practical solution. The proposed workflow shows a significant improvement in both the accuracy of fracture network prediction and computational efficiency compared to traditional fracture inversion methods, which are often plagued by high multi-solution, high computational cost, and difficulties with convergence.