High-resolution reservoir characterization using deep learning-aided elastic full-waveform inversion: The North Sea field data example

Abstract

<jats:p> Reservoir characterization is an essential component of oil and gas production, as well as exploration. Classic reservoir characterization algorithms, deterministic and stochastic, are typically based on stacked images and rely on simplifications and approximations to the subsurface (e.g., assuming linearized reflection coefficients). Elastic full-waveform inversion (FWI), which aims to match the waveforms of prestack seismic data, potentially provides more accurate high-resolution reservoir characterization from seismic data. However, FWI can easily fail to characterize deep-buried reservoirs due to illumination limitations. We have developed a deep learning-aided elastic FWI strategy using observed seismic data and available well logs in the target area. Five facies are extracted from the well and then connected to the inverted P- and S-wave velocities using trained neural networks, which correspond to the subsurface facies distribution. Such a distribution is further converted to the desired reservoir-related parameters such as velocities and anisotropy parameters using a weighted summation. Finally, we update these estimated parameters by matching the resulting simulated wavefields to the observed seismic data, which corresponds to another round of elastic FWI aided by the a priori knowledge gained from the predictions of machine learning. A North Sea field data example, the Volve Oil Field data set, indicates that the use of facies as prior knowledge helps resolve the deep-buried reservoir target better than the use of only seismic data. </jats:p>

Seismic Inversion by Hybrid Machine Learning

“…Sun and Alkhalifah (2020a) trained an RNN to learn an optimization algorithm to improve the FWI convergence. Zhang and Alkhalifah (2020) developed a Deep Neural Network (DNN)‐assisted FWI to invert a high‐resolution reservoir by using the DNN to statistically connect surface seismic data with facies information from a well. Sun and Alkhalifah (2020b) proposed a framework for learning a robust misfit function, entitled ML‐misfit, for FWI using meta‐learning.…”

Advances in seismic imaging of magma and crystal mush

“…This method has been used successfully to constrain melt fractions beneath mid-ocean ridges (e.g., Singh et al, 1998). More recently, the exploration industry has embraced full-waveform inversion, which can simultaneously provide high-resolution structural constraints and robust reservoir parameters (Prieux et al, 2013;Warner et al, 2013;Zhang and Alkhalifah, 2020). Where these methods have been applied to magma imaging, they have been successful in revealing small melt bodies and constraining melt fractions more robustly than possible with traditional methods.…”

Wavefield Reconstruction Inversion via Physics-Informed Neural Networks

“…Neural network (NN) and its variation forms (e.g., deep/convolutional/recurrent NN) are becoming more powerful in pattern recognition, image processing and image segmentation for large-scale data. Deep NNs have shown effectiveness in picking first arrivals from raw seismic data [27], improve seismic image resolution by approximating a Hessian matrix inverse [28] and FWI inverted velocity models by using well-log information [29], [30], [31]. Convolutional NN (CNN) has strong capabilities in extracting features from a large number of images, and it has been effectively applied to detect salt bodies [32], horizons, and faults from seismic images [33], predict low-frequency components from highfrequency data [34].…”