1 August 2019 in Interpretation
An inversion algorithm is commonly used to estimate the elastic properties, such as P-wave velocity ([ ]), S-wave velocity ([ ]), and density ([ ]) of the earth’s subsurface. Generally, the seismic inversion problem is solved using one of the traditional optimization algorithms. These algorithms start with a given model and update the model at each iteration, following a physics-based rule. The algorithm is applied at each common depth point (CDP) independently to estimate the elastic parameters. Here, we have developed a technique using the convolutional neural network (CNN) to solve the same problem. We perform two critical steps to take advantage of the generalization capability of CNN and the physics to generate synthetic data for a meaningful representation of the subsurface. First, rather than using CNN as in a classification type of problem, which is the standard approach, we modified the CNN to solve a regression problem to estimate the elastic properties. Second, again unlike the conventional CNN, which is trained by supervised learning with predetermined label (elastic parameter) values, we use the physics of our forward problem to train the weights. There are two parts of the network: The first is the convolution network, which takes the input as seismic data to predict the elastic parameters, which is the desired intermediate result. In the second part of the network, we use wave-propagation physics and we use the output of the CNN to generate the predicted seismic data for comparison with the actual data and calculation of the error. This error between the true and predicted seismograms is then used to calculate gradients, and update the weights in the CNN. After the network is trained, only the first part of the network can be used to estimate elastic properties at remaining CDPs directly. We determine the application of physics-guided CNN on prestack and poststack inversion problems. To explain how the algorithm works, we examine it using a conventional CNN workflow without any physics guidance. We first implement the algorithm on a synthetic data set for prestack and poststack data and then apply it to a real data set from the Cana field. In all the training examples, we use a maximum of 20% of data. Our approach offers a distinct advantage over a conventional machine-learning approach in that we circumvent the need for labeled data sets for training.
5 August 2019 in Interpretation
Machine learning (ML) has recently gained immense popularity because of its successful application in complex problems. It develops an abstract relation between the input and output. We have evaluated the application of ML to the most basic seismic processing of normal moveout (NMO) correction. The arrival times of reflection events in a common midpoint (CMP) gather follow a hyperbolic trajectory; thus, they require a correction term to flatten the CMP gather before stacking. This correction term depends on an rms velocity, also referred to as the NMO velocity. In general, NMO velocity is estimated using the semblance measures and picking the peaks in the velocity panel. This process requires a lot of human intervention and computation time. We have developed a novel method using one of the tools based on an ML- approach and applied to the NMO velocity estimation problem. We use the recurrent neural network (RNN) to estimate the NMO velocity directly from the seismic data. The input to the network is a seismic gather and corresponding precalculated NMO velocity (as prelabeled data set) to flatten the gather. We first train the network to develop a relationship between the input gathers (before NMO correction) and the corresponding NMO velocities for a few CMPs as a supervised learning process. Adam optimization algorithm is used to train the RNN. The output from the network is then compared against the correct NMO velocity. The error between the two velocities is then used to update the weight of the neurons and to minimize the mean-squared error between the two velocities. After the network is trained, it can be used to calculate the NMO velocity for the rest of the seismic gathers. We evaluate our method on a noisy data set from Poland. We used only 10% of the CMPs to train the network, and then we used the trained network to predict NMO velocity for the remaining CMP locations. The stack section obtained by using RNN-generated NMO velocities is nearly identical to that obtained by the conventional semblance method.
4 November 2014 in Bulletin of the Seismological Society of America
20 March 2023 in Geophysical Prospecting
1 August 2022 in The Leading Edge
Commercial and low-saturation gas (also called paleoresidual gas [PRG]) show similar strong amplitude signatures on P-wave seismic data. This poses an exploration risk in gas reservoir regions. However, density correlates inversely with gas saturation and can differentiate a zone of full gas saturation from PRG. This can improve the chances of success in terms of predrill prediction of gas saturation. Amplitude-variation-with-offset (AVO) inversion using prestack seismic data is the most commonly used technique that can estimate elastic parameters such as P-wave velocity, S-wave velocity, and density. Out of these three parameters, extracting density from seismic data is the most challenging due to its weak sensitivity to seismic reflection amplitude and the lack of good quality seismic data at far offsets. However, with recent improvements in seismic data acquisition and processing technology, which produces reliable AVO gathers, density estimates have improved. This requires that strong density sensitivity to AVO exists. Note that multiple density models may fit the data equally well. Therefore, quantifying uncertainty is crucial for interpretation and risk assessment. We apply a recently developed stochastic approach based on the Bayesian framework to solve the problem in a transdimensional framework, where the number of model parameters is treated as a variable and estimated along with the elastic properties. We use the reversible jump Hamiltonian Monte Carlo (RJHMC) algorithm to sample models from a variable dimensional model space and obtain a globally optimum model and uncertainty estimates. We use a synthetic and good quality real data set from Columbus Basin in Trinidad, which has a proven gas reservoir, to demonstrate the algorithm. The RJHMC results calibrate well with the logs and show the areal extents of the density anomalies within the 3D volume.