- Home
- A-Z Publications
- First Break
- Previous Issues
- Volume 37, Issue 9, 2019
First Break - Volume 37, Issue 9, 2019
Volume 37, Issue 9, 2019
-
-
Tutorial: tomographic Bayesian uncertainty estimation
Authors Ian F. Jones, Rodrigo Felicio, Angeliki Vlassopoulou and Claudia HagenAbstractWhether we build a subsurface parameter model or deliver a subsurface image, our industry has been sadly lacking in attempting to assign ‘error bars’ to any of the products created. It transpires that this is an extremely difficult task to undertake in a quantitative manner. Assuming that we have an acceptable migration algorithm that honours the physics of the problem, then there are certain minimum acceptance criteria, which tell us that at least the derived model explains the observed data to within some acceptance threshold. Namely: image gathers that are ‘flat’ following migration with the obtained model, and which also match available well data — but these criteria do not tell us how accurate or precise the model or image is. Bayesian analysis of tomographic model error offers one approach to quantifying image positioning uncertainty, and here we give an overview of the elements involved in this procedure.
-
-
-
Automatic QC of denoise processing using a machine learning classification
Authors Maïza Bekara and Anthony DayAbstractNoise attenuation is an important part of a typical seismic data processing sequence. The general purpose of noise attenuation is to improve the resolution of seismic images. It can also be used to pre-condition the data prior to the application of certain processes to avoid the generation of artefacts. For example, applying a de-bubbling filter to marine seismic data that contains moderate swell noise will create visible low-frequency artefacts in the output. Therefore, adequately removing the swell noise with techniques similar to the one proposed by Bekara and van der Baan (2010) is a prerequisite before applying such a process.
-
-
-
Drivers of imbalance in machine learning uptake across geology and geophysics
Authors Samuel R. Fielding and Lorin DaviesAbstractMachine learning (ML) is being used to process and understand data more and more throughout geology and geophysics in oil and gas exploration. However, its uptake has been slower than it has been for other industries and within exploration has been much stronger for some types of data and disciplines than it has for others. For instance, there has been significant ML focus on seismic data, while other data, such as those generated by geochemistry, have received relatively little. This imbalance in ML uptake leaves much opportunity for the growth of ML applications in these undersaturated fields.
-
-
-
Transfer learning and Auto-ML: A geoscience perspective
Authors Ehsan Zabihi Naeini and Joshua UwaifoAbstractDeep learning continues to receive increasing attention from researchers and has been successfully applied to many domains. This paper further extends the work from Zabihi Naeini and Prindle (2018) by adopting and examining two classes of Machine Learning techniques and their applications in geoscience with a pragmatic view. These are Transfer Learning and Automated Machine Learning or Auto-ML (Feurer and Klein, 2015). Although machine learning (ML) is known to be most efficient and accurate when trained on a large volume of data, there are cases in practice where ML methods are also implemented with limited available data. In such cases ML algorithms are less efficient in generalising to new data and it is where Transfer Learning can add value. This is shown in an automatic petrophysical interpretation task where Transfer Learning is compared with training from scratch given a new geological area of interest, i.e., a set of wells in a different area. We show the efficiency of Transfer Learning in obtaining a model that generalizes successfully for the new wells investigated.
-
-
-
Physics-guided neural networks for predicting unconventional well performance — using Unconventional Rate Transient Analysis for smarter production data analytics
More LessAbstractGeoscience modelling poses many challenges due to the limited sampling and the complexity of the phenomena that create the resulting rock and its properties. When adding to the geologic and geomechanical complexity the various possible fluid flow mechanisms that are often not fully understood, one realizes quickly how daunting geomodelling could be. As a result, oil and gas fields are often bought and sold using reserves computed with simple decline curve analysis tools. Unfortunately, these simplified production analysis tools contain no physics and do not help develop oil and gas assets which require the knowledge of 1) rock properties distribution and 2) the impact of the rock properties on the selected production mechanism. For example, if one has a naturally fractured reservoir, the presence or absence of the natural fractures and the way the wells are drilled to encounter or avoid these rock properties will determine the reserves and the future of the company developing such an asset. Very often the future of many companies is not very bright due to their lack of knowledge of the distribution of the rock properties such as natural fractures and the subsequent fluid flow resulting from drilling and fracking into these heterogeneous rock properties.
-
-
-
Net reservoir discrimination through multi-attribute analysis at single sample scale
Authors Jonathan Leal, Rafael Jerónimo, Fabian Rada, Reinaldo Viloria and Rocky RodenAbstractSelf-Organizing Map (SOM) is an unsupervised neural network — a form of machine learning — that has been used in multi-attribute seismic analysis to extract more information from the seismic response than would be practical using only single attributes. The most common use is in automated facies mapping. It is expected that every neuron or group of neurons can be associated with a single depositional environment, the reservoir’s lateral and vertical extension, porosity changes or fluid content (Marroquín et al., 2009). Of course, the SOM results must be calibrated with available well logs. In this paper, the authors generated petrophysical labels to apply statistical validation techniques between well logs and SOM results. Based on the application of PCA to a larger set of attributes, a smaller, distilled set of attributes were classified using the SOM process to identify lithological changes in the reservoir (Roden et al., 2015).
-
-
-
Spatial aliasing removal using deep learning super-resolution
Authors A. Garg, A. Vos, N. Bortych, D.K. Gupta and D.J. VerschuurAbstractSeismic data are often either irregularly or insufficiently sampled. Irregular sampling can be due to encountered obstacles in the acquisition, thus resulting in a seismic data gap, whereas insufficient sampling is the result of a coarse acquisition grid, thus leading to sparse sampling along the spatial direction of the data. This irregular or insufficient sampling can affect the accuracy and resolution of seismic data processing steps such as surface-related multiple elimination, migration and inversion. For example, in the simple case of sparse sampling, it leads not just to the loss of high-wavenumbers, but also causes spatial aliasing due to the overlap of aliasing energy artifacts with the signal energy. When we image this spatially aliased coarse data, we encounter the trade-off between the resolution of the image and the aliasing artifacts. Therefore, seismic data interpolation has always been an essential requirement in seismic data processing.
-
-
-
Detection of near-surface heterogeneities at archaeological sites using seismic diffractions
Authors Jianhuan Liu, Quentin Bourgeois, Ranajit Ghose and Deyan DraganovAbstractThe detection of shallow buried ancient structures or objects of cultural heritage is a primary challenge for seismic surveys at archaeological sites. The knowledge of the distribution of shallow objects can assist archaeologists’ study of the past without making excavations. Excavations lead to surface exposure of the buried objects and potential damages and preservation issues. The seismic response arising from localized archaeological targets is encoded in diffractions, which can be used to locate the objects. However, the energy of a diffracted wave is usually weak and masked behind the strong presence of other coherent signals or coherent noise in the data (e.g., surface waves, specular reflections). This makes it difficult to detect and interpret reliably.
-
Volumes & issues
-
Volume 42 (2024)
-
Volume 41 (2023)
-
Volume 40 (2022)
-
Volume 39 (2021)
-
Volume 38 (2020)
-
Volume 37 (2019)
-
Volume 36 (2018)
-
Volume 35 (2017)
-
Volume 34 (2016)
-
Volume 33 (2015)
-
Volume 32 (2014)
-
Volume 31 (2013)
-
Volume 30 (2012)
-
Volume 29 (2011)
-
Volume 28 (2010)
-
Volume 27 (2009)
-
Volume 26 (2008)
-
Volume 25 (2007)
-
Volume 24 (2006)
-
Volume 23 (2005)
-
Volume 22 (2004)
-
Volume 21 (2003)
-
Volume 20 (2002)
-
Volume 19 (2001)
-
Volume 18 (2000)
-
Volume 17 (1999)
-
Volume 16 (1998)
-
Volume 15 (1997)
-
Volume 14 (1996)
-
Volume 13 (1995)
-
Volume 12 (1994)
-
Volume 11 (1993)
-
Volume 10 (1992)
-
Volume 9 (1991)
-
Volume 8 (1990)
-
Volume 7 (1989)
-
Volume 6 (1988)
-
Volume 5 (1987)
-
Volume 4 (1986)
-
Volume 3 (1985)
-
Volume 2 (1984)
-
Volume 1 (1983)