Seismic Data Assimilation With An Imperfect Model

Oliver, Dean S.; Alfonzo, Miguel

doi:10.3997/2214-4609.201802283

Cited by 4 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Variational Auto-encoder (VAE) and Generative Adversarial Network (GAN) are generative models in the field of deep learning, which have strong generative ability. It performs well in processing complex high-dimensional data and has been successfully applied in the field of image processing [7][8].…”

Section: Introductionmentioning

confidence: 99%

Quality Control Method of Exploration and Development Data Based on Machine Learning

2020

View full text Add to dashboard Cite

Because of increased exploration depth and increasingly complex geological environment survey area, makes the actual acquired seismic exploration data contains a lot of noise, the noise composition is serious interference signal effectively, affect the signal to noise ratio and resolution of the seismic data, reduce the quality of the seismic exploration data, to the subsequent inversion and interpretation, and finally brought difficulties such as oil and gas exploration work. This paper mainly studies the quality control method of exploration and development data based on machine learning. In this paper, the classification and source of desert noise are analyzed first, and a convolutional neural network with branch structure (BCDNet) is proposed to enhance the ability of extracting effective signal features from desert seismic exploration data, so as to better recover the seismic in-phase axis polluted by desert seismic random noise.

show abstract

Section: Introductionmentioning

confidence: 99%

Quality Control Method of Exploration and Development Data Based on Machine Learning

2020

View full text Add to dashboard Cite

show abstract

Evaluating the impact of 4D seismic data artefacts in data assimilation

Rosa

Schiozer

Davólio

2023

View full text Add to dashboard Cite

Time-lapse or 4D Seismic data (4DS) are important constraints in reservoir studies because they enable monitoring of saturation and pressure changes that result from hydrocarbon production. 4DS have been quantitatively added, along with production data, in history matching or data assimilation (DA) procedures to reduce uncertainty and improve production forecasts. Before performing quantitative studies, it is important to ensure that the 4DS are reliable, with minimal artifacts such as side-lobe effects, that can disturb the identification of anomalies. In this work, we propose different ways of treating 4DS in DA for a real reservoir. Explicitly, we evaluated the impact on DA results when considering different amounts of 4D information and three treatments to the identified artifacts. The treatments were: ignoring them, excluding them from DA, or defining no seismic changes at their locations. The results show that well and seismic matches are improved when 4DS are assimilated, also improving the production predictions. Despite being a thin reservoir, assimilating two single-layer maps allowed us to predict relevant observed dynamic behaviour, such as the evolved gas trapped in the lower interval. Furthermore, when a treatment was applied to the artifacts, they produced better models than using a single two-layer map (with lower production errors and visually closer impedances to the observed data). Our recommendation is the assimilation of well and 4DS data, with the exclusion of unreliable information, for better life-cycle decisions.

show abstract

Efficient Assimilation of Crosswell Electromagnetic Data Using Ensemble-Based History-Matching Framework

Zhang

Hoteit

2019

Day 1 Wed, April 10, 2019

View full text Add to dashboard Cite

This template is provided to give authors a basic shell for preparing your manuscript for submittal to an SPE meeting or event. Styles have been included (Head1, Head2, Para, FigCaption, etc.) to give you an idea of how your finalized paper will look before it is published by SPE. All manuscripts submitted to SPE will be extracted from this template and tagged into an XML format; SPE's standardized styles and fonts will be used when laying out the final manuscript. Links will be added to your manuscript for references, tables, and equations. Figures and tables should be placed directly after the first paragraph they are mentioned in. The technical content of your paper WILL NOT be changed. Please start your manuscript below.

show abstract

Seismic Data Assimilation With An Imperfect Model

Cited by 4 publications

References 0 publications

Quality Control Method of Exploration and Development Data Based on Machine Learning

Quality Control Method of Exploration and Development Data Based on Machine Learning

Evaluating the impact of 4D seismic data artefacts in data assimilation

Efficient Assimilation of Crosswell Electromagnetic Data Using Ensemble-Based History-Matching Framework

Contact Info

Product

Resources

About