Xiaopeng Ma
China University of Petroleum
18 Papers
Xiaopeng Ma is an academic researcher from China University of Petroleum. The author has contributed to research in topics: Computer science & Surrogate model. The author has an hindex of 5, co-authored 10 publications.
Chat about Author
Papers
Data-Driven Niching Differential Evolution with Adaptive Parameters Control for History Matching and Uncertainty Quantification
TL;DR: A novel data-driven niching differential evolution algorithm with adaptive parameter control for nonuniqueness of inversion, called DNDE-APC, designed to balance exploration and convergence in solving the multimodal inverse problems is proposed.
97
Parameter prediction of hydraulic fracture for tight reservoir based on micro-seismic and history matching
TL;DR: In this article, micro-seismic source location is used to describe the basic shape of hydraulic fractures and secondary modeling is considered to calibrate the parameters information of hydraulic fracture by using DFM (discrete fracture model) and history matching method.
61
A fractal discrete fracture network model for history matching of naturally fractured reservoirs
TL;DR: The distribution of fractures is highly uncertain in naturally fractured reservoirs and may be predicted by using the assisted-history-matching (AHM) that calibrates the reservoir model.
52
Fourier Neural Operator for Solving Subsurface Oil/Water Two-Phase Flow Partial Differential Equation
Kai Zhang,Yuande Zuo,Hanjun Zhao,Xiaopeng Ma,Jian Wei Gu,Jian Wang,Yongmei Yang,Chuanjin Yao,Jun Yao +8 more
TL;DR: A deep-learning-based model is developed to solve three categories of problems controlled by the subsurface 2D oil/water two-phase flow PDE based on the FNO, a recently proposed high-efficiency PDE solution architecture that overcomes the shortcomings of popular algorithms such as physics-informed neural networks and fully convolutional network.
42
A novel hybrid recurrent convolutional network for surrogate modeling of history matching and uncertainty quantification
Xiaopeng Ma,Kai Zhang,Jinding Zhang,Yanzhong Wang,Liming Zhang,Piyang Liu,Yongmei Yang,Jian Wang +7 more
TL;DR: In this paper , a hybrid recurrent convolutional network (HRCN) model is proposed for surrogate modeling of numerical simulation used in automatic history matching (AHM), which is end-to-end trainable for predicting the well production data of high-dimensional parameter fields.
28