Accelerating seismic fault and stratigraphy interpretation with deep CNNs: A case study of the Taranaki Basin, New Zealand

2020 ◽  
Vol 39 (10) ◽  
pp. 727-733
Author(s):  
Haibin Di ◽  
Leigh Truelove ◽  
Cen Li ◽  
Aria Abubakar
Keyword(s):  
New Zealand ◽  
Seismic Data ◽  
Reservoir Characterization ◽  
Seismic Survey ◽  
Deep Convolutional Neural Networks ◽  
Seismic Attribute ◽  
Data Set ◽  
Seismic Fault ◽  
Attribute Analysis ◽  
Specific Implementation

Accurate mapping of structural faults and stratigraphic sequences is essential to the success of subsurface interpretation, geologic modeling, reservoir characterization, stress history analysis, and resource recovery estimation. In the past decades, manual interpretation assisted by computational tools — i.e., seismic attribute analysis — has been commonly used to deliver the most reliable seismic interpretation. Because of the dramatic increase in seismic data size, the efficiency of this process is challenged. The process has also become overly time-intensive and subject to bias from seismic interpreters. In this study, we implement deep convolutional neural networks (CNNs) for automating the interpretation of faults and stratigraphies on the Opunake-3D seismic data set over the Taranaki Basin of New Zealand. In general, both the fault and stratigraphy interpretation are formulated as problems of image segmentation, and each workflow integrates two deep CNNs. Their specific implementation varies in the following three aspects. First, the fault detection is binary, whereas the stratigraphy interpretation targets multiple classes depending on the sequences of interest to seismic interpreters. Second, while the fault CNN utilizes only the seismic amplitude for its learning, the stratigraphy CNN additionally utilizes the fault probability to serve as a structural constraint on the near-fault zones. Third and more innovatively, for enhancing the lateral consistency and reducing artifacts of machine prediction, the fault workflow incorporates a component of horizontal fault grouping, while the stratigraphy workflow incorporates a component of feature self-learning of a seismic data set. With seven of 765 inlines and 23 of 2233 crosslines manually annotated, which is only about 1% of the available seismic data, the fault and four sequences are well interpreted throughout the entire seismic survey. The results not only match the seismic images, but more importantly they support the graben structure as documented in the Taranaki Basin.

Exploring New Zealand's marine territory

2011 ◽  
Vol 51 (1) ◽  
pp. 549 ◽  
Author(s):  
Chris Uruski
Keyword(s):  
New Zealand ◽  
Deep Water ◽  
Seismic Data ◽  
East Coast ◽  
Sedimentary Basins ◽  
Petroleum Exploration ◽  
Seismic Survey ◽  
Data Set ◽  
Eastern Australia ◽  
Deep Water Part

Around the end of the twentieth century, awareness grew that, in addition to the Taranaki Basin, other unexplored basins in New Zealand’s large exclusive economic zone (EEZ) and extended continental shelf (ECS) may contain petroleum. GNS Science initiated a program to assess the prospectivity of more than 1 million square kilometres of sedimentary basins in New Zealand’s marine territories. The first project in 2001 acquired, with TGS-NOPEC, a 6,200 km reconnaissance 2D seismic survey in deep-water Taranaki. This showed a large Late Cretaceous delta built out into a northwest-trending basin above a thick succession of older rocks. Many deltas around the world are petroleum provinces and the new data showed that the deep-water part of Taranaki Basin may also be prospective. Since the 2001 survey a further 9,000 km of infill 2D seismic data has been acquired and exploration continues. The New Zealand government recognised the potential of its frontier basins and, in 2005 Crown Minerals acquired a 2D survey in the East Coast Basin, North Island. This was followed by surveys in the Great South, Raukumara and Reinga basins. Petroleum Exploration Permits were awarded in most of these and licence rounds in the Northland/Reinga Basin closed recently. New data have since been acquired from the Pegasus, Great South and Canterbury basins. The New Zealand government, through Crown Minerals, funds all or part of a survey. GNS Science interprets the new data set and the data along with reports are packaged for free dissemination prior to a licensing round. The strategy has worked well, as indicated by the entry of ExxonMobil, OMV and Petrobras into New Zealand. Anadarko, another new entry, farmed into the previously licensed Canterbury and deep-water Taranaki basins. One of the main results of the surveys has been to show that geology and prospectivity of New Zealand’s frontier basins may be similar to eastern Australia, as older apparently unmetamophosed successions are preserved. By extrapolating from the results in the Taranaki Basin, ultimate prospectivity is likely to be a resource of some tens of billions of barrels of oil equivalent. New Zealand’s largely submerged continent may yield continent-sized resources.

THE DIRKALA SOUTH OIL DISCOVERY: FOCUSSING ON COST-EFFICIENT RESERVOIR DELINEATION

1995 ◽  
Vol 35 (1) ◽  
pp. 65
Author(s):  
S.I. Mackie ◽  
C.M. Gumley
Keyword(s):  
Production Performance ◽  
Seismic Survey ◽  
3D Seismic ◽  
Seismic Attribute ◽  
Data Set ◽  
Seismic Surveys ◽  
Seismic Modelling ◽  
Attribute Analysis ◽  
Cost Efficient ◽  
The Cost

The Dirkala Field is located in the southern Murta Block of PEL's 5 and 6 in the southern Cooper and Eromanga Basins. Excellent oil produc­tion from a single reservoir sandstone in the Juras­sic Birkhead Formation in Dirkala-1 had indicated a potentially larger resource than could be mapped volumetrically. The hypothesis that the resource was stratigraphically trapped led to the need to define the fluvial sand reservoir seismically and thereby prepare for future development.A small (16 km2) 3D seismic survey was acquired over the area in December 1992. The project was designed not only to evaluate the limits of the Birkhead sand but also to evaluate the cost effi­ciency of recording such small 3D surveys in the basin.Interpretation of the data set integrated with seismic modelling and seismic attribute analysis delineated a thin Birkhead fluvial channel sand reservoir. Geological pay mapping matched volu­metric estimates from production performance data. Structural mapping showed Dirkala-1 to be opti­mally placed and that no further development drill­ing was justifiable.Seismic characteristics comparable with those of the Dirkala-1 Birkhead reservoir were noted in another area of the survey beyond field limits. This led to the proposal to drill an exploration well, Dirkala South-1, which discovered a new oil pool in the Birkhead Formation. A post-well audit of the pre-drill modelling confirmed that the seismic response could be used to determine the presence of the Birkhead channel sand reservoir.The acquisition of the Dirkala-3D seismic survey demonstrated the feasibility of conducting small 3D seismic surveys to identify subtle stratigraphically trapped Eromanga Basin accumulations at lower cost and risk than appraisal/development drilling based on 2D seismic data.

The use of geologic expression workflows for basin scale reconnaissance: A case study from the Exmouth Subbasin, North Carnarvon Basin, northwestern Australia

2014 ◽  
Vol 2 (1) ◽  
pp. SA163-SA177 ◽  
Author(s):  
N. J. McArdle ◽  
D. Iacopini ◽  
M. A. KunleDare ◽  
G. S. Paton
Keyword(s):  
Seismic Data ◽  
Regional Scale ◽  
Normal Fault ◽  
Seismic Attributes ◽  
Data Sets ◽  
Seismic Attribute ◽  
Data Set ◽  
Attribute Analysis ◽  
Basin Scale ◽  
Northwestern Australia

The focus of this study is to demonstrate how seismic attributes can be used in the interpretation workflow to rapidly obtain a high-resolution view of the geology that is imaged within a seismic data set. To demonstrate the efficacy of seismic attribute analysis to basin scale reconnaissance, we apply a workflow to seismic data sets from the Exmouth Subbasin, northwestern Australia, with the aim of determining the geologic expression of the subsurface. Of specific interest are Barrow Group Jurassic and Cretaceous fluvial and marine sediments, that were faulted during the Jurassic-Cretaceous rifting associated with the breakup of East Gondwana. Regional-scale interpretations are made to develop a tectonostratigraphic context to the investigation. Target-level analyses, focused on features of exploration interest identified using regional reconnaissance, are made to calibrate attribute response and demonstrate the effectiveness of seismic attributes for rapid evaluation of prospectivity in the initial stages of exploration. The main structural episodes are distinguished using dip and azimuth attributes, and faulting is expressed using a combination of edge attributes which are used to create fault trend lineations. We observe three main structural trends: the main northeast–southwest Jurassic-Cretaceous syn-rift primary fault orientation of 48°, a secondary trend of 108°, taken to represent secondary conjugate faulting and a third trend of 100° interpreted as the reactivation of these faults into the postrift sediments. Stratigraphic attributes that respond to amplitude and frequency are used to create reservoir scale geobodies of faulted Macedon turbidites, which in turn are used for detailed tuning sensitivity analysis. The final part of the investigation is of the syn-rift magmatic system responsible for sills and dikes that exploit the normal fault network. These intrusive and extrusive features are important as are potential drilling hazards and can act as baffles to hydrocarbon migration.

Predict Channel Sand Body Distribution Characteristics of South Eighth District Based on RMS Amplitude Attributes & Frequency Division

2013 ◽  
Vol 734-737 ◽  
pp. 404-407 ◽  
Author(s):  
Yu Shuang Hu ◽  
Si Miao Zhu
Keyword(s):  
Seismic Data ◽  
Physical Property ◽  
Sedimentary Facies ◽  
Distribution Area ◽  
Frequency Division ◽  
Root Mean Square Amplitude ◽  
Seismic Attribute ◽  
Body Distribution ◽  
Attribute Analysis ◽  
Sand Body

A big tendency in oil industry is underestimating the heterogeneity of the reservoir and overestimating the connectivity, which results in overly optimistic estimates of the capacity. With the development of seismic attributes, we could pick up hidden reservoir lithology and physical property information from the actual seismic data, strengthen seismic data application in actual work, to ensure the objectivity of the results. In this paper, the channel sand body distribution in south eighth district of oilfield Saertu is predicted through seismic data root-mean-square amplitude and frequency division to identify sand body boundaries, predict the distribution area channel sand body characteristics successfully, which consistent with the sedimentary facies distribution. The result proves that seismic attribute analysis has good practicability in channel sand body prediction and sedimentary facies description.

scholarly journals Time-Lapse Seismic Monitoring of Onshore Reservoirs in Niger Delta, Field ‘K’ as a Case Study

2017 ◽  
Vol 1 (1) ◽  
pp. 23-27 ◽  
Author(s):  
A. Ogbamikhumi ◽  
T. Tralagba ◽  
E. E. Osagiede
Keyword(s):  
Seismic Data ◽  
Acoustic Impedance ◽  
Niger Delta ◽  
Rock Physics ◽  
Time Lapse ◽  
Seismic Survey ◽  
Impedance Change ◽  
Data Set ◽  
Reservoir Fluid ◽  
4D Seismic

Field ‘K’ is a mature field in the coastal swamp onshore Niger delta, which has been producing since 1960. As a huge producing field with some potential for further sustainable production, field monitoring is therefore important in the identification of areas of unproduced hydrocarbon. This can be achieved by comparing production data with the corresponding changes in acoustic impedance observed in the maps generated from base survey (initial 3D seismic) and monitor seismic survey (4D seismic) across the field. This will enable the 4D seismic data set to be used for mapping reservoir details such as advancing water front and un-swept zones. The availability of good quality onshore time-lapse seismic data for Field ‘K’ acquired in 1987 and 2002 provided the opportunity to evaluate the effect of changes in reservoir fluid saturations on time-lapse amplitudes. Rock physics modelling and fluid substitution studies on well logs were carried out, and acoustic impedance change in the reservoir was estimated to be in the range of 0.25% to about 8%. Changes in reservoir fluid saturations were confirmed with time-lapse amplitudes within the crest area of the reservoir structure where reservoir porosity is 0.25%. In this paper, we demonstrated the use of repeat Seismic to delineate swept zones and areas hit with water override in a producing onshore reservoir.

A dictionary learning method with atom splitting for seismic footprint suppression

Geophysics ◽  
2021 ◽  
pp. 1-97
Author(s):  
Dawei Liu ◽  
Lei Gao ◽  
Xiaokai Wang ◽  
wenchao Chen
Keyword(s):  
Dictionary Learning ◽  
Seismic Data ◽  
Reservoir Characterization ◽  
Original Data ◽  
Morphological Features ◽  
Time Slice ◽  
Learning Method ◽  
Seismic Attribute ◽  
Morphological Component Analysis ◽  
Value Decomposition

Acquisition footprint causes serious interference with seismic attribute analysis, which severely hinders accurate reservoir characterization. Therefore, acquisition footprint suppression has become increasingly important in industry and academia. In this work, we assume that the time slice of 3D post-stack migration seismic data mainly comprises two components, i.e., useful signals and acquisition footprint. Useful signals describe the spatial distributions of geological structures with local piecewise smooth morphological features. However, acquisition footprint often behaves as periodic artifacts in the time-slice domain. In particular, the local morphological features of the acquisition footprint in the marine seismic acquisition appear as stripes. As useful signals and acquisition footprint have different morphological features, we can train an adaptive dictionary and divide the atoms of the dictionary into two sub-dictionaries to reconstruct these two components. We propose an adaptive dictionary learning method for acquisition footprint suppression in the time slice of 3D post-stack migration seismic data. To obtain an adaptive dictionary, we use the K-singular value decomposition algorithm to sparsely represent the patches in the time slice of 3D post-stack migration seismic data. Each atom of the trained dictionary represents certain local morphological features of the time slice. According to the difference in the variation level between the horizontal and vertical directions, the atoms of the trained dictionary are divided into two types. One type significantly represents the local morphological features of the acquisition footprint, whereas the other type represents the local morphological features of useful signals. Then, these two components are reconstructed using morphological component analysis based on different types of atoms, respectively. Synthetic and field data examples indicate that the proposed method can effectively suppress the acquisition footprint with fidelity to the original data.

Applications of Artificial Neural Networks for Seismic Facies Classification

2021 ◽  
Vol 73 (02) ◽  
pp. 68-69
Author(s):  
Chris Carpenter
Keyword(s):  
Neural Network ◽  
Seismic Data ◽  
Reservoir Characterization ◽  
Probabilistic Neural Network ◽  
Oil Field ◽  
Seismic Facies ◽  
Data Set ◽  
Full Field ◽  
Facies Classification

This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 200577, “Applications of Artificial Neural Networks for Seismic Facies Classification: A Case Study From the Mid-Cretaceous Reservoir in a Supergiant Oil Field,” by Ali Al-Ali, Karl Stephen, SPE, and Asghar Shams, Heriot-Watt University, prepared for the 2020 SPE Europec featured at the 82nd EAGE Conference and Exhibition, originally scheduled to be held in Amsterdam, 1-3 December. The paper has not been peer reviewed. Facies classification using data from sources such as wells and outcrops cannot capture all reservoir characterization in the interwell region. Therefore, as an alternative approach, seismic facies classification schemes are applied to reduce the uncertainties in the reservoir model. In this study, a machine-learning neural network was introduced to predict the lithology required for building a full-field Earth model for carbonate reservoirs in southern Iraq. The work and the methodology provide a significant improvement in facies classification and reveal the capability of a probabilistic neural network technique. Introduction The use of machine learning in seismic facies classification has increased gradually during the past decade in the interpretation of 3D and 4D seismic volumes and reservoir characterization work flows. The complete paper provides a literature review regarding this topic. Previously, seismic reservoir characterization has revealed the heterogeneity of the Mishrif reservoir and its distribution in terms of the pore system and the structural model. However, the main objective of this work is to classify and predict the heterogeneous facies of the carbonate Mishrif reservoir in a giant oil field using a multilayer feed-forward network (MLFN) and a probabilistic neural network (PNN) in nonlinear facies classification techniques. A related objective was to find any domain-specific causal relationships among input and output variables. These two methods have been applied to classify and predict the presence of different facies in Mishrif reservoir rock types. Case Study Reservoir and Data Set Description. The West Qurna field is a giant, multibillion-barrel oil field in the southern Mesopotamian Basin with multiple carbonate and clastic reservoirs. The overall structure of the field is a north/south trending anticline steep on the western flank and gentle on the eastern flank. Many producing reservoirs developed in this oil field; however, the Mid- Cretaceous Mishrif reservoir is the main producing reservoir. The reservoir consists of thick carbonate strata (roughly 250 m) deposited on a shallow water platform adjacent to more-distal, deeper-water nonreservoir carbonate facies developing into three stratigraphic sequence units in the second order. Mishrif facies are characterized by a porosity greater than 20% and large permeability contrast from grainstones to microporosity (10-1000 md). The first full-field 3D seismic data set was achieved over 500 km2 during 2012 and 2013 in order to plan the development of all field reservoirs. A de-tailed description of the reservoir has been determined from well logs and core and seismic data. This study is mainly based on facies log (22 wells) and high-resolution 3D seismic volume to generate seismic attributes as the input data for the training of the neural network model. The model is used to evaluate lithofacies in wells without core data but with appropriate facies logs. Also, testing was carried out in parallel with the core data to verify the results of facies classification.

THE INTEGRATION OF MODERN TECHNOLOGY IN GIPPSLAND'S CENTRAL FIELDS STUDY

1994 ◽  
Vol 34 (1) ◽  
pp. 513
Author(s):  
P.V.Hinton P.V.Hinton ◽  
M.G.Cousins ◽  
P.E.Symes
Keyword(s):  
Seismic Data ◽  
Field Performance ◽  
Simulation Models ◽  
Modern Technology ◽  
Depositional Environments ◽  
Seismic Attribute ◽  
Sequence Stratigraphic ◽  
Multidisciplinary Study ◽  
Attribute Analysis ◽  
Definition Of

The central fields area of the Gippsland Basin, Australia, includes the Halibut, Cobia, Fortescue, and Mackerel oil fields. These large fields are mature with about 80% of the reserves produced. During 1991 and 1992 a multidisciplinary study, integrating the latest technology, was completed to help optimise the depletion of the remaining significant reserves.A grid of 4500 km of high resolution 3D seismic data covering 191 square kilometres allowed the identification of subtle structural traps as well as better definition of sandstone truncation edges which represent the ultimate drainage points. In addition, the latest techniques in seismic attribute analysis provided insight into depositional environments, seal potential and facies distribution. Sequence stratigraphic concepts were used in combination with seismic data to build complex multi million cell 3D geological models. Reservoir simulation models were then constructed to history match past production and to predict future field performance. Facility studies were also undertaken to optimise depletion strategies.The Central Fields Depletion Study has resulted in recommendations to further develop the fields with about 80 work-overs, 50 infill wells, reduction in separator pressures, and gas lift and water handling facility upgrades. These activities are expected to increase ultimate reserves and production. Some of the recommendations have been implemented with initial results of additional drilling on Mackerel increasing platform production from 22,000 BOPD to over 50,000 BOPD. An ongoing program of additional drilling from the four platforms is expected to continue for several years.

Sign in / Sign up

Export Citation Format

Share Document