Inversion of low to medium frequency velocities and densities from AVO data using invertible neural networks

Geophysics ◽  
2022 ◽  
pp. 1-44
Author(s):  
Yuhang Sun ◽  
Yang Liu ◽  
Mi Zhang ◽  
Haoran Zhang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Latent Variables ◽  
Low Frequency ◽  
Inversion Method ◽  
Elastic Parameters ◽  
Medium Frequency ◽  
Uniqueness Of Solutions ◽  
Avo Inversion ◽  
Training Samples

AVO (amplitude variation with offset) inversion and neural networks are widely used to invert elastic parameters. With more constraints from well log data, neural network-based inversion may estimate elastic parameters with greater precision and resolution than traditional AVO inversion, however, neural network approaches necessitate a massive number of reliable training samples. Furthermore, because the lack of low-frequency information in seismic gathers leads to multiple solutions of the inverse problem, both inversions rely heavily on proper low-frequency initial models. To mitigate the dependence of inversions on accurate training samples and initial models, we propose solving inverse problems with the recently developed invertible neural networks (INNs). Unlike conventional neural networks, which address the ambiguous inverse issues directly, INNs learn definite forward modeling and use additional latent variables to increase the uniqueness of solutions. Motivated by the newly developed neural networks, we propose an INN-based AVO inversion method, which can reliably invert low to medium frequency velocities and densities with randomly generated easy-to-access datasets rather than trustworthy training samples or well-prepared initial models. Tests on synthetic and field data show that our method is feasible, anti-noise capable, and practicable.

Application of Probabilistic Neural Network in Pattern Classification

2013 ◽  
Vol 441 ◽  
pp. 738-741 ◽  
Author(s):  
Shuo Ding ◽  
Xiao Heng Chang ◽  
Qing Hui Wu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Pattern Classification ◽  
Probabilistic Neural Network ◽  
Back Propagation ◽  
Back Propagation Neural Networks ◽  
Training Samples ◽  
The One ◽  
Speed Accuracy

The network model of probabilistic neural network and its method of pattern classification and discrimination are first introduced in this paper. Then probabilistic neural network and three usually used back propagation neural networks are established through MATLAB7.0. The pattern classification of dots on a two-dimensional plane is taken as an example. Probabilistic neural network and improved back propagation neural networks are used to classify these dots respectively. Their classification results are compared with each other. The simulation results show that compared with back propagation neural networks, probabilistic neural network has simpler learning rules, faster training speed and it needs fewer training samples; the pattern classification method based on probabilistic neural network is very effective, and it is superior to the one based on back propagation neural networks in classifying speed, accuracy as well as generalization ability.

Application of Hybrid Genetic Algorithm in Ground Stress Inversion

2011 ◽  
Vol 90-93 ◽  
pp. 337-341
Author(s):  
Ran Gang Yu ◽  
Yong Tian
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Neural Networks ◽  
Bp Neural Network ◽  
Local Minimum ◽  
Hybrid Genetic Algorithm ◽  
Inversion Method ◽  
Stress Inversion ◽  
Neural Network Inversion ◽  
Ground Stress

This paper propose genetic algorithm combined with neural networks, greatly improving the convergence rate of neural network aim at the disadvantage of the traditional BP neural network inversion method is easy to fall into local minimum and slow convergence.Finally, verified the feasibility and superiority of the above methods through the successful initial ground stress inversion of actual project.

scholarly journals Pattern Recognition of Spiking Neural Networks Based on Visual Mechanism and Supervised Synaptic Learning

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Xiumin Li ◽  
Hao Yi ◽  
Shengyuan Luo
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Visual Cortex ◽  
Image Classification ◽  
Learning Rule ◽  
Spiking Neural Networks ◽  
Layer By Layer ◽  
Intelligent Computing ◽  
Training Samples ◽  
Feed Forward Network

Electrophysiological studies have shown that mammalian primary visual cortex are selective for the orientations of visual stimuli. Inspired by this mechanism, we propose a hierarchical spiking neural network (SNN) for image classification. Grayscale input images are fed through a feed-forward network consisting of orientation-selective neurons, which then projected to a layer of downstream classifier neurons through the spiking-based supervised tempotron learning rule. Based on the orientation-selective mechanism of the visual cortex and tempotron learning rule, the network can effectively classify images of the extensively studied MNIST database of handwritten digits, which achieves 96 % classification accuracy based on only 2000 training samples (traditional training set is 60000 ). Compared with other classification methods, our model not only guarantees the biological plausibility and the accuracy of image classification but also significantly reduces the needed training samples. Considering the fact that the most commonly used deep learning neural networks need big data samples and high power consumption in image recognition, this brain-inspired computational neural network model based on the layer-by-layer hierarchical image processing mechanism of the visual cortex may provide a basis for the wide application of spiking neural networks in the field of intelligent computing.

Research on Expert System of Crop Disasters Based on Neural Networks

2012 ◽  
Vol 235 ◽  
pp. 34-38
Author(s):  
Jie Zhu ◽  
Wei Dong ◽  
Jing Zhang ◽  
Xu Ning Liu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Expert System ◽  
Bp Neural Network ◽  
Crop Production ◽  
Weight Optimization ◽  
Training Samples ◽  
Crop Diseases ◽  
Crop Diagnosis ◽  
Adjustment Of Parameters

In order to improve the efficiency of prediction and diagnose of crop diseases and pests, and solve the problems during the course of crop production and management, then an neural networks with weight adjustment of prediction model is proposed. The crop disasters are regarded as example, after the symptoms of disasters and features are classified, abstracted and coded, the adjustment of weight, optimization of network structure and reasonable adjustment of parameters of BP neural network are discussed, then a model is constructed to forecast the disasters of crop, the weight is used as knowledge to predict disasters of crop through studying training samples. Results have shown that the optimization expert system of crop disasters based on neural network has enhanced the ability of decision making of expert system, then greatly improved the accuracy and reliability of crop diagnosis.

Borehole electrical resistivity modeling using neural networks

Geophysics ◽  
2002 ◽  
Vol 67 (6) ◽  
pp. 1790-1797 ◽  
Author(s):  
Lin Zhang ◽  
Mary M. Poulton ◽  
Tsili Wang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Input Data ◽  
Window Length ◽  
Neural Network Approach ◽  
Earth Resistivity ◽  
Training Samples ◽  
Resistivity Model ◽  
Dual Laterolog ◽  
Hidden Nodes

A neural network approach has been applied to model downhole resistivity tools, i.e., to generate a synthetic tool response for a given earth resistivity model. The microlaterolog (MLL), shallow dual laterolog (DLLs), and deep dual laterolog (DLLd) tools are modeled using neural networks to demonstrate this approach. Efforts have been made to select various neural network parameters, including the type of neural network, the length of input data for training, the number of hidden nodes, and the number of training samples. A modular neural network (MNN) has been selected because it can facilitate the training and prediction of tool responses in formations with large resistivity variations. The input data for training are taken to be the model formation resistivity values sampled over a depth window. The window length is chosen based on the tool lengths. Three different window lengths are used for experiments: 6.1, 9.1, and 30.5 m. We found the longer window lengths generally have higher modeling accuracy for the three different types of logging tools. The number of hidden nodes needed to yield satisfactory training and prediction data varies from 8 to 25, depending on the type of tool and the window length. Up to 30 000 training samples have been collected to train the MNN. Our modeling examples show that the trained MNN can achieve about 90% accuracy for the MLL log response and about 83% accuracy for the DLLs and DLLd responses. The modeling errors can be described roughly with a Gaussian distribution.

scholarly journals Neural network technology to search for targets in remote sensing images of the Earth

2019 ◽  
pp. 180-186
Author(s):  
N S Abramov ◽  
А А Talalayev ◽  
V P Fralenko ◽  
O G Shishkin ◽  
V M Khachumov
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Neural Networks ◽  
High Performance ◽  
Remote Sensing Images ◽  
Single Class ◽  
The Earth ◽  
Training Samples ◽  
Performance Computing ◽  
Neural Network Technology

The paper introduces how multi-class and single-class problems of searching and classifying target objects in remote sensing images of the Earth are solved. To improve the recognition efficiency, the preparation tools for training samples, optimal configuration and use of deep learning neural networks using high-performance computing technologies have been developed. Two types of CNN were used to process ERS images: a convolutional neural network from the nnForge library and a network of the Darknet type. A comparative analysis of the results is obtained. The research showed that the capabilities of convolutional neural networks allow solving simultaneously the problems of searching (localizing) and recognizing objects in ERS images with high accuracy and completeness.

scholarly journals Of Neural Network Model Robustness Through Generating Invariant to Attributes Embeddings

2020 ◽  
Vol 23 (6) ◽  
pp. 1142-1154
Author(s):  
Marat Rushanovich Gazizov ◽  
Karen Albertovich Grigorian
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Model ◽  
Neural Network Model ◽  
Input Data ◽  
Domain Adaptation ◽  
High Accuracy ◽  
Important Criterion ◽  
Training Samples ◽  
Model Robustness

Model robustness to minor deviations in the distribution of input data is an important criterion in many tasks. Neural networks show high accuracy on training samples, but the quality on test samples can be dropped dramatically due to different data distributions, a situation that is exacerbated at the subgroup level within each category. In this article we show how the robustness of the model at the subgroup level can be significantly improved with the help of the domain adaptation approach to image embeddings. We have found that application of a competitive approach to embeddings limitation gives a significant increase of accuracy metrics in a complex subgroup in comparison with the previous models. The method was tested on two independent datasets, the accuracy in a complex subgroup on the Waterbirds dataset is 90.3 {y : waterbirds;a : landbackground}, on the CelebA dataset is 92.22 {y : blondhair;a : male}.

Complex-Valued Neural Network and Inverse Problems

2009 ◽  
pp. 27-55 ◽  
Author(s):  
Takehiko Ogawa
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Inverse Problems ◽  
Inversion Method ◽  
Complex Numbers ◽  
Original Network ◽  
Multilayer Neural Networks ◽  
Complex Valued ◽  
Inputs And Outputs

Network inversion solves inverse problems to estimate cause from result using a multilayer neural network. The original network inversion has been applied to usual multilayer neural networks with real-valued inputs and outputs. The solution by a neural network with complex-valued inputs and outputs is necessary for general inverse problems with complex numbers. In this chapter, we introduce the complex-valued network inversion method to solve inverse problems with complex numbers. In general, difficulties attributable to the ill-posedness of inverse problems appear. Regularization is used to solve this ill-posedness by adding some conditions to the solution. In this chapter, we also explain regularization for complex-valued network inversion.

An Efficiency Algorithm for SDCP Program

2014 ◽  
Vol 971-973 ◽  
pp. 1533-1536
Author(s):  
Ning Xiao
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Particle Swarm Optimization ◽  
Bp Neural Network ◽  
Intelligent Algorithm ◽  
Swarm Optimization ◽  
Hybrid Intelligent Algorithm ◽  
Random Simulation ◽  
Training Samples ◽  
Stochastic Particle

For more effectively solving SDCP,in the paper,using BP neural networks to approximate chance function,training samples are produced by random simulation,and a hybrid intelligent algorithm for SDCP combined stochastic particle swarm optimization and BP neural network is proposed.The experimental results show that the algorithm is more preferable.

Broadband seismic amplitude variation with offset inversion

Geophysics ◽  
2017 ◽  
Vol 82 (3) ◽  
pp. M43-M53 ◽  
Author(s):  
Zhaoyun Zong ◽  
Kun Li ◽  
Xingyao Yin ◽  
Ming Zhu ◽  
Jiayuan Du ◽  
...  
Keyword(s):  
Bayesian Inference ◽  
Frequency Domain ◽  
Seismic Data ◽  
Low Frequency ◽  
Well Log ◽  
Complex Frequency ◽  
Elastic Parameters ◽  
Log Data ◽  
Avo Inversion ◽  
Frequency Components

Seismic amplitude variation with offset (AVO) inversion is well-known as a popular and pragmatic tool used for the prediction of elastic parameters in the geosciences. Low frequencies missing from conventional seismic data are conventionally recovered from other geophysical information, such as well-log data, for estimating the absolute rock properties, which results in biased inversion results in cases of complex heterogeneous geologic targets or plays with sparse well-log data, such as marine or deep stratum. Broadband seismic data bring new opportunities to estimate the low-frequency components of the elastic parameters without well-log data. We have developed a novel AVO inversion approach with the Bayesian inference for broadband seismic data. The low-frequency components of the elastic parameters are initially estimated with the proposed broadband AVO inversion approach with the Bayesian inference in the complex frequency domain because seismic inversion in the complex frequency domain is helpful to recover the long-wavelength structures of the elastic models. Gaussian and Cauchy probability distribution density functions are used for the likelihood function and the prior information of model parameters, respectively. The maximum a posteriori probability solution is resolved to estimate the low-frequency components of the elastic parameters in the complex frequency domain. Furthermore, with those low-frequency components as initial models and constraints, the conventional AVO inversion method with the Bayesian inference in the time domain is further implemented to estimate the final absolute elastic parameters. Synthetic and field data examples demonstrate that the proposed AVO inversion in the complex frequency domain is able to predict the low-frequency components of elastic parameters well, and that those low-frequency components set a good foundation for the final estimation of the absolute elastic parameters.

Sign in / Sign up

Export Citation Format

Share Document