Improved Fractured Reservoir Characterization Using Neural Networks, Geomechanics and 3-D Seismic

1995 ◽  
Author(s):  
A.M. Zellou ◽  
A. Ouenes ◽  
A.K. Banik
Keyword(s):  
Neural Networks ◽  
Reservoir Characterization ◽  
Fractured Reservoir

Uncertainty quantification in fault detection using convolutional neural networks

Geophysics ◽  
2021 ◽  
pp. 1-45
Author(s):  
Runhai Feng ◽  
Dario Grana ◽  
Niels Balling
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Reservoir Characterization ◽  
Epistemic Uncertainty ◽  
Confidence Regions ◽  
Training Data ◽  
Model Parameters ◽  
Sigmoid Function ◽  
Learning Tools

Segmentation of faults based on seismic images is an important step in reservoir characterization. With the recent developments of deep-learning methods and the availability of massive computing power, automatic interpretation of seismic faults has become possible. The likelihood of occurrence for a fault can be quantified using a sigmoid function. Our goal is to quantify the fault model uncertainty that is generally not captured by deep-learning tools. We propose to use the dropout approach, a regularization technique to prevent overfitting and co-adaptation in hidden units, to approximate the Bayesian inference and estimate the principled uncertainty over functions. Particularly, the variance of the learned model has been decomposed into aleatoric and epistemic parts. The proposed method is applied to a real dataset from the Netherlands F3 block with two different dropout ratios in convolutional neural networks. The aleatoric uncertainty is irreducible since it relates to the stochastic dependency within the input observations. As the number of Monte-Carlo realizations increases, the epistemic uncertainty asymptotically converges and the model standard deviation decreases, because the variability of model parameters is better simulated or explained with a larger sample size. This analysis can quantify the confidence to use fault predictions with less uncertainty. Additionally, the analysis suggests where more training data are needed to reduce the uncertainty in low confidence regions.

Towards an Improved Ensemble Learning Model of Artificial Neural Networks

2016 ◽  
pp. 762-793
Author(s):  
Fatai Anifowose ◽  
Jane Labadin ◽  
Abdulazeez Abdulraheem
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Reservoir Characterization ◽  
Evaluation Criteria ◽  
Search Space ◽  
Combination Rules ◽  
Search Spaces ◽  
Ensemble Machine Learning ◽  
Artificial Neural ◽  
Hidden Neurons

Artificial Neural Networks (ANN) have been widely applied in petroleum reservoir characterization. Despite their wide use, they are very unstable in terms of performance. Ensemble machine learning is capable of improving the performance of such unstable techniques. One of the challenges of using ANN is choosing the appropriate number of hidden neurons. Previous studies have proposed ANN ensemble models with a maximum of 50 hidden neurons in the search space thereby leaving rooms for further improvement. This chapter presents extended versions of those studies with increased search spaces using a linear search and randomized assignment of the number of hidden neurons. Using standard model evaluation criteria and novel ensemble combination rules, the results of this study suggest that having a large number of “unbiased” randomized guesses of the number of hidden neurons beyond 50 performs better than very few occurrences of those that were optimally determined.

Sign in / Sign up

Export Citation Format

Share Document