82nd EAGE Annual Conference & Exhibition最新文献

Complex Near-surface Velocity Modeling via U-net 基于U-net的复杂近地表速度模拟

82nd EAGE Annual Conference & Exhibition Pub Date : 2021-10-18 DOI: 10.3997/2214-4609.202112724

G. Niu, S. Wang, C. Zhou

引用次数: 0

Integrated high-resolution model building: a case study from the Sultanate of Oman 综合高分辨率模型构建:来自阿曼苏丹国的案例研究

82nd EAGE Annual Conference & Exhibition Pub Date : 2021-10-18 DOI: 10.3997/2214-4609.202112701

M. Farooqui, D. Carotti, M. Al-Jahdhami

引用次数: 0

Machine learning based deep carbonate reservoir characterization with physical constraints 基于机器学习的深部碳酸盐岩储层物理约束表征

82nd EAGE Annual Conference & Exhibition Pub Date : 2021-10-18 DOI: 10.3997/2214-4609.202112771

Y. Chen, L. Zhao, J. Pan, C. Li, K. Li, F. Zhang, J. Geng

{"title":"Machine learning based deep carbonate reservoir characterization with physical constraints","authors":"Y. Chen, L. Zhao, J. Pan, C. Li, K. Li, F. Zhang, J. Geng","doi":"10.3997/2214-4609.202112771","DOIUrl":"https://doi.org/10.3997/2214-4609.202112771","url":null,"abstract":"Summary Seismic characterization of deep carbonate reservoir is challenging due to the heterogeneous reservoir properties caused by the complex diagenesis and deep buried physical conditions. We propose a variety of physical constraints (including spatial constraint, continuity constraint, gradient constraint and category constraint) to guide the machine learning (Random Forest method) for reservoir quality prediction using multi-seismic attributes. Taking the carbonate reservoirs in the Tarim Basin, Western China as an example, we demonstrate that, various physical constraints are effective in enhancing the prediction performance based on the well test. The combination of the four proposed physical constraints gives the best prediction performance in terms of identifying reservoir and non-reservoir as well as inferring reservoir quality. We also show that a two-step strategy gives higher F1 score for reservoir quality evaluation. Machine learning based seismic prediction of deep carbonate reservoir with physical constraints suggests that this approach can effectively delineate the heterogeneous reservoir distribution, laying the foundation for geological model building and sweet spot detection.","PeriodicalId":143998,"journal":{"name":"82nd EAGE Annual Conference & Exhibition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126414803","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Towards digital twinning for single sensor streamer platforms 面向单传感器拖缆平台的数字孪生

82nd EAGE Annual Conference & Exhibition Pub Date : 2021-10-18 DOI: 10.3997/2214-4609.202112768

S. Rentsch, M. Silverberg

引用次数: 0

Practical deep learning inversion using neural architecture search and a flexible training dataset generator 使用神经结构搜索和灵活的训练数据集生成器的实用深度学习反演

82nd EAGE Annual Conference & Exhibition Pub Date : 2021-10-18 DOI: 10.3997/2214-4609.202112777

T. Shibayama, N. Mizuno, H. Kusano, A. Kinoshita, M. Minegishi, R. Sakamoto, K. Hasegawa, F. Kachi

{"title":"Practical deep learning inversion using neural architecture search and a flexible training dataset generator","authors":"T. Shibayama, N. Mizuno, H. Kusano, A. Kinoshita, M. Minegishi, R. Sakamoto, K. Hasegawa, F. Kachi","doi":"10.3997/2214-4609.202112777","DOIUrl":"https://doi.org/10.3997/2214-4609.202112777","url":null,"abstract":"Summary Deep learning has the potential to estimate velocity models directly from shot gathers, which would reduce the turn-around time of seismic inversion. Our study addresses two challenges in implementing deep learning techniques for seismic inversion: the practical generation of a large amount of training data and the search for the best neural network architecture. First, we propose a flexible system which parametrically generates velocity models to create a large-scale, complex and fully synthetic training dataset, without using a target subsurface model. Using this system, we created 300,000 synthetic velocity models for our experiments. Second, we employ neural architecture search techniques to design a suitable neural network using Optuna, an automatic hyperparameter optimisation framework. We incorporated the residual network into an encoder–decoder model and optimised its architecture. Thus, we obtained an optimal neural network model consisting of more than 100 hidden layers. We evaluated our model using the Marmousi2 model and the 1994 Amoco statics test dataset. The model demonstrated comprehensible estimations of the benchmark velocity models.","PeriodicalId":143998,"journal":{"name":"82nd EAGE Annual Conference & Exhibition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129495586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Inverse Hessian estimation in least-squares migration using chains of operators 基于算子链的最小二乘迁移逆Hessian估计

82nd EAGE Annual Conference & Exhibition Pub Date : 2021-10-18 DOI: 10.3997/2214-4609.202112700

T. Tangkijwanichakul, Sergey Fomel

引用次数: 0

GOMCRUST - The crustal-scale extension of the 2004 BP velocity model for long-offset OBN acquisition setting GOMCRUST - 2004年BP速度模型在长偏移OBN采集背景下的地壳尺度扩展

82nd EAGE Annual Conference & Exhibition Pub Date : 2021-10-18 DOI: 10.3997/2214-4609.202112776

A. Górszczyk, S. Sambolian, S. Operto

{"title":"GOMCRUST - The crustal-scale extension of the 2004 BP velocity model for long-offset OBN acquisition setting","authors":"A. Górszczyk, S. Sambolian, S. Operto","doi":"10.3997/2214-4609.202112776","DOIUrl":"https://doi.org/10.3997/2214-4609.202112776","url":null,"abstract":"Summary We present an extension of the 2004 BP velocity model which is suitable for the assessment of cutting-edge seismic imaging methods as FWI applied to ultra long-offset ocean-bottom node (OBN) acquisitions. The 2004 BP model is routinely utilized to benchmark various velocity-model building approaches - in particular those developed to tackle the challenges encountered in geological settings comprising salt structures. Those challenges are typically related to the correct reconstruction of the subsalt structures or the sharp velocity contrasts between the salt bodies and the surrounding sediments. To make this model suitable for testing the emerging long-offset OBN acquisitions, we embed the original 2004 BP model within a crustal-scale velocity model inspired by the structural interpretation of the tomographic results from the GUMBO experiment (Gulf of Mexico). The resulting model allows for wavefield propagation within the rifted continental crust and the upper mantle and therefore for the undershooting of the salt and subsalt structures. Consequently, there is no need for extrapolation of the original BP model boundaries or resizing/resampling of its spatial dimensions. The GOMCRUST can therefore be seen as a geologically consistent evolution of the 2004 BP model, which allows to benchmark various seismic imaging workflow with long-offset OBN surveys.","PeriodicalId":143998,"journal":{"name":"82nd EAGE Annual Conference & Exhibition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114364658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Prestack data attenuation compensation based on inversion 基于反演的叠前数据衰减补偿

82nd EAGE Annual Conference & Exhibition Pub Date : 2021-10-18 DOI: 10.3997/2214-4609.202112741

W. Cheng, S. Wang, C. Zhou, G. Pang

引用次数: 0

Estimation of Thomsen VTI parameters for seismic imaging using vertical and deviated wells 直井和斜井地震成像Thomsen VTI参数估计

82nd EAGE Annual Conference & Exhibition Pub Date : 2021-10-18 DOI: 10.3997/2214-4609.202112728

H. Miyamoto, G. Cambois

{"title":"Estimation of Thomsen VTI parameters for seismic imaging using vertical and deviated wells","authors":"H. Miyamoto, G. Cambois","doi":"10.3997/2214-4609.202112728","DOIUrl":"https://doi.org/10.3997/2214-4609.202112728","url":null,"abstract":"Summary Seismic data processing by pre-stack depth migration (PrSDM) requires a reliable initial velocity model. An accurate velocity model secures pre-stack gather flatness by short offset spread; however, a vertical transverse isotropy (VTI) model, for characterizing horizontal layering, should be sufficiently considered to extend offset usage and maximize image quality. This study sought a robust workflow of Thomsen VTI parameters, e and δ, estimation to stabilize anisotropic tomography analysis. Vertical and deviated wells offered the opportunity to derive the target parameters in a rather simple and elegant way. Anisotropic Backus averaging combined intrinsic and apparent anisotropy at seismic scale. In our case study, the calculated anisotropic parameters profiles were validated by WAVSPs and by the surface seismic data, which could be flattened effectively all the way to the largest offsets. In particular, steps like refraction FWI need an accurate anisotropic starting model to converge effectively. Cross-spread 3D seismic surveys are particularly ill suited for deriving shallow anisotropic velocity models and the vertical and deviated wells method provides a welcome alternative.","PeriodicalId":143998,"journal":{"name":"82nd EAGE Annual Conference & Exhibition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128967917","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

A deterministic 4D processing flow to suppress acquisition-related noise at Dalia and Rosa fields 在Dalia和Rosa油田抑制获取相关噪声的确定性4D处理流程

82nd EAGE Annual Conference & Exhibition Pub Date : 2021-10-18 DOI: 10.3997/2214-4609.202112772

N. Salaun, M. Pouget, Z. Yu, C. Beigbeder, A. Rivet, S. Dega, M. Peiro, A. Lafram, A. Grandi, E. Jungo

{"title":"A deterministic 4D processing flow to suppress acquisition-related noise at Dalia and Rosa fields","authors":"N. Salaun, M. Pouget, Z. Yu, C. Beigbeder, A. Rivet, S. Dega, M. Peiro, A. Lafram, A. Grandi, E. Jungo","doi":"10.3997/2214-4609.202112772","DOIUrl":"https://doi.org/10.3997/2214-4609.202112772","url":null,"abstract":"Summary Time-lapse seismic is now being used more frequently to assist reservoir development, prevent infrastructure damage or monitor geological storage. To better reveal true 4D signals while suppressing acquisition-related noise as a result of, for example, water velocity changes, source positioning errors etc., a new processing flow which focusses on correcting each noise-contributing factor based on its physical characteristics, has been developed to replace the conventional non-deterministic correction approach based on cross-survey matching. Our proposed flow is based on using common water bottom and the water-bottom travel time to invert each factor and correct for it, which allows for processing of each monitor survey independently and the possible acceleration of standard 4D processing timelines. We applied this workflow on two fields offshore Angola, one with strong subsidence and one without, and showed the superiority of this new approach to reveal the true 4D information. The subsidence effect, observable from the reservoir up to the water bottom, now better matches with the model of pressure changes in the new 4D results compared to legacy results. Even for field experiencing no subsidence effect, the time shift and NRMS maps obtained at the reservoir level are cleaner and easier to interpret from new flow.","PeriodicalId":143998,"journal":{"name":"82nd EAGE Annual Conference & Exhibition","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130933436","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

82nd EAGE Annual Conference &amp; Exhibition最新文献

82nd EAGE Annual Conference & Exhibition最新文献