Reservoir characterisation method with multi-component seismic data by unsupervised learning and colour feature blending

Zhang, Kai; Lin, Niantian; Fu, Chao; Zhang, Dong; Jin, Xing; Zhang, Chong

doi:10.1080/08123985.2019.1603078

Cited by 32 publications

(5 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning has been applied to a wide variety of energy-related problems. Montgomery et al [25] used supervised learning to build data-driven models to forecast shale gas production and Zhang et al [26] developed a multi-component method for reservoir characterization using unsupervised learning. Miftakhov et al [27] used reinforcement learning to maximize the Net Present Value (NPV) of waterflooding by training a reinforcement learning agent to control the water injection rate.…”

Section: Literature Reviewmentioning

confidence: 99%

Parallel Automatic History Matching Algorithm Using Reinforcement Learning

Alomar¹,

Williams²

2023

Energies

View full text Add to dashboard Cite

Reformulating the history matching problem from a least-square mathematical optimization problem into a Markov Decision Process introduces a method in which reinforcement learning can be utilized to solve the problem. This method provides a mechanism where an artificial deep neural network agent can interact with the reservoir simulator and find multiple different solutions to the problem. Such a formulation allows for solving the problem in parallel by launching multiple concurrent environments enabling the agent to learn simultaneously from all the environments at once, achieving significant speed up.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Parallel Automatic History Matching Algorithm Using Reinforcement Learning

Alomar¹,

Williams²

2023

Energies

View full text Add to dashboard Cite

show abstract

“…Various machine learning algorithms have been applied for lithofacies identification and characterization. A reservoir prediction method was developed based on unsupervised learning and color feature blending, where several seismic attributes were extracted using cluster analysis to highlight oil and gas anomalies [ 9 ]. Non-hierarchical cluster analysis was used for assisting permeability prediction with transforming the well logs into electrofacies in dolomite and sandstone intervals in the Ogallah Field, USA [ 10 ], specifying the facies for a well in sandstone formation in West Africa before predicting the formation permeability [ 11 ], and the identification of heterogeneous carbonate reservoirs in a Southern Iraqi oilfield [ 12 ].…”

Section: Introductionmentioning

confidence: 99%

Robust reservoir identification by multi-well cluster analysis of wireline logging data

Szabó

Kilik

Dobróka

2023

Heliyon

View full text Add to dashboard Cite

“…For instance, [18] proved the concept by using unsupervised ML and a colour feature blending technique to perform reservoir prediction from multiple seismic attributes. The results showed that the approach could help highlight interesting geological and hydrocarbon characteristics and improve traditional seismic interpretation techniques.…”

Section: Introductionmentioning

confidence: 99%

Ensemble Deep Learning-Based Porosity Inversion From Seismic Attributes

et al. 2023

View full text Add to dashboard Cite

Underground porosity is important in many earth sciences and engineering fields, including hydrocarbon reservoir characterization and geothermal energy production. Popular methods largely rely on the analysis of lithological core data, well logs, and seismic inversion methods. While these methods are reliable, they are also time-consuming, expensive, and difficult to implement. In addition, seismic inversion has nonlinearity, data dimensionality, and non-uniqueness issues. However, deep learning (DL) can provide a more flexible, efficient, and accurate capability by mapping directly from seismic attributes to underground porosity. Therefore, we trained several DL models with different optimization functions. In the training steps, we labelled every seismic attribute data point with its corresponding porosity derived from the welllogs. In contrast to popular ensemble techniques, we proposed a weighted prediction approach based on the strengths of each model. Testing results showed a coefficient of determination (R 2 ) of 0.94345 and a Pearson's correlation coefficient of 0.9725 between the actual model and the model of the proposed approach, versus 0.9681 and 0.9716 for the best single and popular ensemble models, respectively. Further, we tested the effectiveness of our method using real seismic data from the North Sea. With a Pearson's correlation value of 0.9743, the inverted model ranges from 27 to 35%, compared to the reference model, which has an overall range of 20 to 33%. These results provide insights into the potential of the proposed method and its applicability to any other seismic volume to determine spatially varying underground porosity from seismic attributes directly.INDEX TERMS Deep neural networks, ensemble methods, seismic inversion, reservoir properties.

show abstract

Reservoir characterisation method with multi-component seismic data by unsupervised learning and colour feature blending

Cited by 32 publications

References 29 publications

Parallel Automatic History Matching Algorithm Using Reinforcement Learning

Parallel Automatic History Matching Algorithm Using Reinforcement Learning

Robust reservoir identification by multi-well cluster analysis of wireline logging data

Ensemble Deep Learning-Based Porosity Inversion From Seismic Attributes

Contact Info

Product

Resources

About