阿什卡国际油气软件

 找回密码
 立即注册
搜索
热搜: 建模数模 裂缝描述 盆地模拟 数值试井 非常规 微地震 RMS软件 三维地质建模软件 开发地震 石油天然气 中石油 中石化 中海油 中化集团 蒋洁敏 王宜林 傅成玉 盆地模拟软件 沉积演化软件 油气资源远景评价 沉积层序模拟 非常规地震解释 微地震 地震反演 地震AVO分析 非常规油气勘探开发 四维地震 甜点预测 井间地震 页岩气开发技术 煤层气开发技术 三维地质建模 裂缝建模 油藏数值模拟 油藏动态分析 辅助历史拟合 试井解释 生产测井解释 生产动态分析 小井组快速数值模拟 建模数模成果规范化存储与应用 井筒节点分心 随钻数据实时传输 石油软件公司招聘 招聘信息 客户经理 项目服务 勘探开发 叠前同时反演 OpenFlow TemisFlow Dionisos PumaFlow interwell headwave transform IFP 法国石油研究院 KAPPA公司 ROXAR公司 Ecrin saphir topaze rubis emeraude tempest CougarFlow Amethyste restudio 斯伦贝谢 schlumberger 兰德马克 landmark Geoframe eclipse ofm peoffice neable ess ecs ees 中国石油 中国石化 中国海油 CNPC petrochina sinopec cnooc sinochem 测井解释 地震资料解释 地震资料处理 建模数模一体化 勘探开发一体化 地震地质油藏一体化 阿什卡公司招聘 油田工程服务 油田项目研究 软件代理 独家代理 阿什卡航空 最好的石油软件公司 最大的石油软件公司 阿什卡论坛 阿什卡年会 阿什卡公司官方微博 阿什卡公司官方网站 阿什卡公司地址 阿什卡公司电话 周晓舟 裘怿南 王家华 王佳华 SPE石油工程师协会 SEG地球物理协会 中国石油学会 大庆油田 新疆油田 克拉玛依油田 吐哈油田 吉林油田 辽河油田 冀东油田 玉门油田 华北油田 塔里木油田 大港油田 青海油田 BGP石油物探局 勘探开发研究院 采油厂 中海油湛江分公司 中海油上海分公司 中海油天津分公司 中海油广州分公司 中海油研究总院 待遇最好的石油软件公司 待遇最好的油田项目研究公司 最有实力的石油软件公司 业绩最好的石油软件公司 中国石油大学 大庆石油学院 东北石油大学 华东石油学院 西安石油学院 成都地质大学 西北石油学院 成都理工 油藏工程师 最好的地质建模软件 地质建模软件对比 导演李安 李双江 中国好声音 我是歌手 李天一 蓝可儿 西游·降魔篇 少年派的奇幻漂流
查看: 57|回复: 1

URTeC会议论文:地质分层自动解释和储层物性预测-在加拿...

[复制链接]
发表于 2022-7-25 14:31:29 | 显示全部楼层 |阅读模式
本帖最后由 Jijun.liu 于 2022-7-25 14:36 编辑

品质源于技术 服务源于态度

-------------------------------------------------------小贴士-------------------------------------------------------
图片1.png
URTeC非常规资源技术会议由SPE、AAPG、SEG等世界领先的专业协会联合主办。
----------------------------------------------------------------------------------------------------------------------
640.jpeg
WechatIMG2.png

论文简介




标题:

地质分层自动解释和储层物性预测-在加拿大西部沉积盆地十万口井大数据工区中的应用

作者:

张宝森,叶天睿,肖倚天,姚同云等

内容:

精确的地质分层自动解释和储层物性预测对油气勘探开发具有非常重要的意义,这项工作传统上是由地质工程师手工对比完成,耗时且低效,由于个人认识的差异,可能导致出现多个不同的地质分层方案,整个地层对比工作难以标准化和流程化,尤其对于拥有数万口井的成熟开发区块,构建精确的地质模型成为一项艰巨的任务。目前机器学习作为一项新兴技术,在石油行业得到了广泛的应用。

Transform软件基于机器学习的地质分层自动解释技术,它可以提供自动化、精确的地质分层自动拾取,本文以加拿大西部沉积盆地的Belly River组为例,探讨了在十万口井的大数据工区地质分层自动解释和储层物性快速评价的可行性。在海量数据清理的基础上,利用Subsequen Dynamic Time Warping 动态时间规整的机器学习算法,充分考虑了相邻测井曲线拉伸、挤压和移位组合等多种情况,来捕捉地层之间的横向变化。本文为国内外地质学家将大数据-机器学习技术应用于实际工区的地质分层自动解释给出了一个成功的示范案例。

WechatIMG3.png

论文全文

Automated Well Top Picking and Reservoir Property Analysis of the Belly River Formation of the Western Canada Sedimentary Basin

Baosen Zhang*1, Tianrui Ye1, Yitian Xiao1, Dongmei Li2, Guoping Wang2, Cong Su2, Tongyun Yao3, 1. Petroleum Exploration and Production Research Institute, SINOPEC, 2. International Petroleum Exploration and Production Corporation, SINOPEC, 3. ESSCA Group

Copyright 2022, Unconventional Resources Technology Conference (URTeC) DOI 10.15530/urtec-2022-3719133

This paper was prepared for presentation at the Unconventional Resources Technology Conference held in Houston, Texas, USA, 20-22 June 2022.

The URTeC Technical Program Committee accepted this presentation on the basis of information contained in an abstract submitted by the author(s). The contents of this paper have not been reviewed by URTeC and URTeC does not warrant the accuracy, reliability, or timeliness of any information herein. All information is the responsibility of, and, is subject to corrections by the author(s). Any person or entity that relies on any information obtained from this paper does so at their own risk. The information herein does not necessarily reflect any position of URTeC. Any reproduction, distribution, or storage of any part of this paper by anyone other than the author without the written consent of URTeC is prohibited.

Abstract

Accurate well top picking and reservoir property prediction plays crucial role for petroleum exploration and production. The task is traditionally done manually by geologists, and can be inconsistent and time-consuming. In addition, the work is difficult to normalize and standardize due to human bias. For unconventional resource plays with tens of thousands of wells, constructing geological models and algorithms can be a daunting task. Machine learning is an emerging technology that has been increasingly adopted in the energy industry. It can provide automated and accurate well top picking and reservoir property analysis.

This paper utilizes a case study in the Belly River Formation (BRF) of Western Canada Sedimentary Basin (WCSB) to discuss capabilities EnABLEd by automated well top picking and reservoir property analysis. First, 70993 wells with GR curve covering ~100000 km2of WCSB were filtered. Among them, 32510 coring wells help to determine boundaries of BRF. Second, several tops were manually picked as seeds for automated picking using Subsequent Dynamic Time Warping approach. After quality control and log normalization, automatic picks were promoted into new seeds for subsequent picking until all pickings were done. Finally, the distribution of the BRF were defined, and combining with logging curves, the variation law of reservoir properties (porosity, permeability, saturation, etc.) was analyzed.

Automated well top picking algorithm natively handles log normalization issues and picks. It completed ~70000s wells top picks in about 100 hours on cross section and map view, which may take over 1000 hours using traditional manual picking methods. Moreover, after automated well top picking, reservoir properties can be predicted as a “one-mouse-click” exercise. What need to do is to ascertain the acquired reservoir properties according to the production practice and to determine the algorithms and formulas according to the regional geological features. This workflow greatly improves efficiencies of the comprehensive reservoir evaluation and reservoir geological modeling of the WCSB by orders of magnitude.

Subsequently, combining automated well top picking and reservoir property analysis results and real-time data of oilfield production, the exploration and production sweet spot prediction of the BRF of the WCSB can be done. In conclusion, this efficient approach based on machine learning has been successfully applied to the potential assessment of petroleum resources in the BRF. The assessment results were used for petroleum reservoir exploration and production, oilfield development plan design, and portfolio management and optimization. Application of the method requires cooperation across different disciplines—data science and earth science. The interdisciplinary nature provides accurate prediction and design optimization for unconventional resources exploration and production.

Introduction

Since the 21st century, large-scale computing, big data and deep learning have triggered the Third AI Boom (Brynjolfsson and Mitchell, 2017). Recently, AI has also been widely used in petroleum exploration and production. Operators cooperate with academic institutes, IT companies and vendors to carry out AI application research, which is developing rapidly in the direction of digitalization, integration, visualization and artificial intelligence application (Li et al., 2020).

Accurate well top picking and reservoir property prediction plays crucial role for petroleum exploration and production. The task is traditionally done manually by geologists and can be inconsistent and time-consuming. In addition, the work is difficult to normalize and standardize due to human bias. For unconventional resource plays with tens of thousands of wells, constructing geological models and algorithms can be a daunting task. Machine learning is an emerging technology that has been increasingly adopted in the energy industry. It can provide automated and accurate well top picking and reservoir property analysis.

Previous attempts have been made to pick geologic well tops automatically using expert systems (Olea, 2003), neural networks (Luthi, 2001), and dynamic programming (Lineman et al., 1987; Inazaki, 1994; Steven et al., 2004; Fang, 2009). Although these previous efforts have been helpful in defining the problems and establishing the building blocks to solve well-log correlation automatically, owing to the nature of seismic data, they have clearly been observed to be much less successful than seismic picking algorithms. Comparing to seismic traces, well logs are more widely spaced (on the order of hundreds to thousands of meters), have inconsistent depth ranges with possible gaps, and may be from highly non-vertical well bores. As a variant of the Dynamic Time Warping (DTW) algorithm, Subsequence Dynamic Time Warping (SDTW) was introduced by Grant et al. (2018) to perform the relevant curve alignments. This technology and workflow uses the power of the modern computer and novel machine learning techniques to capture and model well-log patterns for correlating geologic events across thousands of wells. Using one or more well logs as source wells, a signature ‘thumbprint’ segment is correlated over many target wells to find the optimal stratigraphic intervals for well pick estimation.

This paper utilizes a case study in the BRF of the WCSB to discuss the capabilities enabled by automated well top picking and reservoir property analysis. This study is implemented to support the project of “Western Canada Sedimentary Basin– Edmonton/Belly River Potential Analysis” from SINOPEC International Petroleum Exploration and Production Corporation. First, an overview of the geological setting of the BRF of the WCSB was provided. Second, the methodology of the automated well top picking, including the theoretical basis and workflow, was explained in detail. Third, reservoir property analysis is applied to the BRF of the WCSB based on the automated well top picking results, empirical formulas or machine learning algorithms for property inference, and evaluations by geologists and engineers of petroleum exploration and production. Finally, to further deepen this research results, in the future the production sweet spot prediction model will be established based on production data and reservoir property analysis results, and the intelligent prediction of petroleum favorable areas in the BRF of the WCSB will be completed (Figure 1).

图片2.png

Figure 1. Flowchart summarizing the workflow of automated well top picking and reservoir property analysis of the BRF of the WCSB in this paper. It begins with automated target well top picking, followed by reservoir property analysis. Then the production sweet spot prediction is a future plan based on the above two works. Finally, a scientific and efficient data analysis and machine learning workflow will be developed.

Geological setting

The main deformation events recorded in the WCSB took place during two orogenic periods (Figure 2): Nevadan Orogeny (Late Jurassic to Early Cretaceous) and Laramide Orogeny (Late Cretaceous to Paleocene). Before the Nevadan Orogeny, the WCSB was a stable Craton basin deposited in the passive continental margin. As its provenance were mainly the Craton interior from the east, it is dominated by the shallow sea facies. After the Nevadan Orogeny, the WCSB was converted to a foreland basin deposited in the active continental margin. The input source of the littoral and fluvial facies has changed to the fold and thrust belt, which was formed by the compressive deformation fromJurassic to Paleocene, resulting in eastward transportation of the sedimentary units towards the WCSB.

图片3.png

Figure 2. Geological evolution diagram of the WCSB from Paleozoic to Cenozoic. The stratigraphic column is modified from the SINOPEC International Petroleum Exploration and Production Corporation.

Refining to the target layer, the BRF is a Late Cretaceous Campanian stage about 72-84 ma continental sandstone deposits. As the early Cretaceous was dominated by the marine deposits, the late Cretaceous BRF was sometimes affected by seaway intrusion and developed a small amount of mud shale deposits. The BRF is mainly composed of three sandstone-shale sub-cycles. The bottom boundary of the BRF, overlying the Lea Park Formation, is marked by the end of continuous marine shale deposition and the emergence of marine-continental transitional sandstone deposition. It remains extremely consistent in the whole WCSB scale, and the characteristics of its well logging curves are very distinctive (Figure 3). The top boundary of the BRF, underlying the Edmonton Formation, marks the emergence of large-scale transgression, the weakening of sandstone deposition, and the increasing of shale deposition. However, its consistency at the basin scale is poor, and its well logging curves’ characteristics are not obvious (Figure 3). Since the bottom boundary is easy to judge, most of effort were put into developing criteria for ascertaining the location of the top boundary. Finally, the top boundary was defined as the position where the maximum flood surface first appears, signed by the high natural gamma (GR) appearing and the amplitude of the resistivity (RD) decreasing (Figure 3).

图片4.png

Figure 3. The well logging curves characteristics of the BRF and its underlying and overlying strata, and its comprehensive judgment position of top and bottom boundaries. Blue and red triangles represent the sub-cycles of transgression and regression.

Methods

Using Accumap for data collection, 171814 well heads, 75301 wells with curves and 36818 wells with core data were combed out (Figure 4). Then,70993 wells drilled into the BRF with GR curves covering ~100000 km2 of WCSB were filtered. Among the filtered wells, 32510 coring wells help to determine the boundaries of BRF.

After data collection, SDTW algorithm was used for the automated well top picking. Figure 5 below shows two different hypothetical data series that might represent two well logs from adjacent wells. The DTW algorithm considers all possible stretch, squeeze, and shift combinations to optimally align the corresponding peaks and troughs along a minimal cost path (Grant et al., 2018). This approach is needed to capture laterally varying geologic changes from well to well as stratigraphic thinning and thickening occurs. However, the DTW does not handle situations where the start and end points represent different times or, in well logging curves, depths. To handle this limitation, Müller (2007) adjusted the DTW algorithm by, instead of aligning the sequences globally, finding a subsequence within the longer sequence that optimally fits the shorter sequence. The variation of the DTW algorithm is called Subsequence Dynamic Time Warping (SDTW), which has many applications in database querying.Database querying, intrinsically similar to well logging curves correlation, entails identifying the fragment in the dataset that is most likely the query by matching a smaller pattern representing the query into a much larger data sequences in the database (Grant et al., 2018).

图片5.png

Figure 4. Well data compilation and their tectonic locations of the WCSB.




图片7.png
 楼主| 发表于 2022-7-25 14:43:53 | 显示全部楼层
本帖最后由 Jijun.liu 于 2022-7-25 15:07 编辑






图片7.png

Figure 5. The difference between Euclidian Distance Matching and DTW Matching of series data, the computation of the DTW algorithm and various stencils used to accumulate gamma values and backtrack gamma matrix to obtain minimal cost paths, and the simplified diagram for querying the most optimal subsequence of SDTW (Chu et al., 2002; Müller, 2007; Grant et al., 2018).

Automated well top picking

First, in order to achieve efficient and accurate automated well top picking result, all wells of the WCSB were filtered to remove horizontal wells, wells with no GR curve, and wells not drilled into the BRF (Figure 6). Then, based on the horizontal distribution of all target wells and tectonic direction of the WCSB, the length and retrieval range of the horizontal transects were ascertained to ensure the efficiency and accuracy of the automated well top picking (Figure 6). Referring to tectonic geological principle and several rounds of repeated testing, the transect that is orthogonal to the WCSB strike with a search area of 400 to 500 wells was the sweet spot of the general PCs.

图片8.png

Figure 6. The workflow of well data filtering and the subsequent horizontal transects establishing. The color bar represents the KBs of all wells.

Second, several tops were manually picked as seeds for SDTW automated picking according to the established stratification criteria and their uniform distribution in the transect (Figure 7). Before conducting automated well top picking, the querying parameters, which directly affect the quality of automated well top picking, must be adjusted to the optimal values separately for both top and bottom boundaries (Figure 7). In this case study, we found that for the bottom boundary the “pick half width” of 40 m and the “maximum shift” of 120 m were the most optimal parameters; for the top boundary the two parameters were changed to 10 m and 40 m respectively.

图片9.png

Figure 7. The workflow of manually seed picking and curves and parameters selection. The three pictures in the lower left are the enlarged GR curves showing the specific locations of the seeds.

Third, based on the upper and lower top constraints and the seeds that are either manually picked or promoted from the automatic picks (Figure 8A), the top position were propagated to all curves with the predefined SDTW algorithm and parameters for the automated well top picking (Figure 8B). About 85-95% of the well tops can be picked by this automatic approach, while the remaining 5-15% together with the obvious misidentified ones can be amended manually (Figure 8B-C). Then the log normalization by flattening the target well top was used for the terminal check (Figure 8D). With the small shift of the transect, the same workflow showed from Figure 8A to 8D would be repeated until all the top and bottom boundaries of the BRF have been picked.

图片10.png

Figure 8. The core workflow of automated well top picking. A, promote automatic picks to manual seed picks; B, propagate automated picking to all wells; C, conduct quality control to the outliers manually; D, use log normalization for terminal check. The two red boxes B and C shows the same wells before and after manually quality control.

After all pickings were done, the distribution of the BRF were defined. The plane and 3D distributions of the BRF top and bottom boundaries of the key areas, as well as its thickness, is shown in Figure 9.

图片11.png

Figure 9. The plane and 3D distributions of the BRF top and bottom boundaries and its thickness of the key areas. The pink lines are the well surveys. The depth axis of the 3D image is distorted to reflect changes in thickness and depth.

Reservoir property analysis

After determining the distribution of the BRF and combining with well logging curves, the variation law of reservoir properties (shale content, porosity, permeability, saturation, etc.) was analyzed. The classical empirical formulas of the WCSB were introduced to calculate the reservoir physical properties. Referring to Figure 10, the shale content, effective porosity and water saturation in the plane distribution are shown, within which the water saturation was corrected using the machine learning approach listed in the right lower corner.Using the cut offs of the reservoir assessment criteria provided by the SINOPEC International Petroleum Exploration and Production Corporation, the “sand”, “reservoir” and “pay” evaluation result are shown in Figure 11.

图片12.png

Figure 10. The shale content, effective porosity and water saturation in the plane distribution of the key areas. Vsh, shale content; PHIE, effective porosity; Sw, water saturation.

图片13.png

Figure 11.The “sand”, “reservoir” and “pay” evaluation result in the plane distribution of the key areas.

Besides the reservoir properties analysis, the calculated reservoir physical properties from logging curves are also fitted with the coring data to improve the accuracy using data-driven method (Figure 12). Based on the 3D distribution of the reservoir physical properties and the relationship between them and well logging curves, the missing logging curves of the BRF are automatically generated (Figure 12).

图片14.png

Figure 12.The schematic diagram of the reservoir property correction and the missing curve automatically generated.

Discussion and Conclusion

Automated well top picking algorithm natively handles log normalization issues and picks. It completed ~70000s wells top picks in about 100 hours on cross section and map views, which may take over 1000 hours using traditional manual picking methods. Moreover, after automated well top picking, reservoir properties can be predicted as a “one-mouse-click” exercise. We only need to ascertain the acquired reservoir properties according to the production practice and to determine the algorithms and formulas according to the regional geological features. This workflow greatly improves efficiencies of the comprehensive reservoir evaluation and reservoir geological modeling of the WCSB by several orders of magnitude.

Subsequently, combining automated well top picking, reservoir property analysis results and real-time data of oilfield production, the exploration and production sweet spot prediction of the BRF of the WCSB can be completed. In conclusion, this efficient approach based on machine learning has been successfully applied to the potential assessment of petroleum resources in the BRF. The assessment results were used for petroleum reservoir exploration and production, oilfield development plan design, and portfolio management and optimization. Application of the method requires cooperation across different disciplines—data science and earth science. The interdisciplinary nature provides accurate prediction and design optimization for unconventional resources exploration and production.

Acknowledgement

We heartily thank Meng Han, Jin Meng, Yejie Zhou, Xianming Tang, Dongwei Zhang, Mingcai Hou and Hanting Zhong for numerous discussions. This study was financially supported by grants from the National Natural Science Foundation of China (42050104) to Mingcai Hou.

References


Brynjolfsson, E., and Mitchell, T., 2017, What can machine learning do? Workforce implications: Science, v. 358, p. 1530-1534.

Chu, S., Keogh, E., Hart, D., and Pazzani, M., 2002, Iterative Deepening Dynamic Time Warping for Time Series: Proceedings of the Second SIAM International Conference on Data Mining, Arlington, VA, USA, April 11-13, 2002.

Fang, C., 2009, From Dynamic Time Warping (DTW) to Hidden Markov Model (HMM), Final project report for ECE742 Stochastic Decision, University of Cincinnati.

Grant, C. W., Bashore, W. M., and Compton, S., 2018, Rapid Reservoir Modeling with Automated Tops Correlation: Unconventional Resources Technology Conference, Houston, Texas, USA, 23-25 July, 2018.

Inazaki, T., 1994, Automated borehole data correlation using dynamic depth warping techniques and an expert system, 7th Int. Cong. International Association of Engineering Geology, Lisboa, Rotterdam: Balkema, p. 4457-4466.

Li, H., Yu, H., Cao, N., Tian, H., and Cheng, S., 2020, Applications of Artificial Intelligence in Oil and Gas Development: Archives of Computational Methods in Engineering.

Lineman, D. J., Mendelson, J. D. and Toksoz, M. N., 1987, Well-to-Well Log Correlation Using Knowledge-Based Systems and Dynamic Depth Warping, SPWLA Twenty-Eight Annual Logging Symposium.

Luthi, S. M., 2001, Geological Well Logs: Their Use in Reservoir Modeling, Springer-Verlag.

Müller, M., 2007, Information Retrieval for Music and Motion, Information Retrieval for Music and Motion.

Olea, R. A., 2003, New Lithostratigraphic Applications of the CORRELATOR System, Meeting 77 of the 54th Session of the International Statistical Institute (ISI), Berlin.

Steven, Z., Ramoj, P., and Steve, D., 2004, Curve Alignment for Well-to-Well Log Correlation: SPE Annual Technical Conference and Exhibition.


-END-

推荐链接:

更多精彩
<微知识库>
-油气软件-
KAPPAOpenFlowMOVE问答
-油气论坛-
论文交流一体化建模数模


(关注微信号 每期早看到↘)




--------------版权声明--------------

阿什卡原创文章
转发请注明出处

--------------版权声明--------------


       石油  软件  服务  项目   ESSCA    咖啡  公益  文化  资讯      



您需要登录后才可以回帖 登录 | 立即注册

本版积分规则

加入阿什卡微公益e基金,共助贫困学生。
扫描图中二维码,加入阿什卡微信即时服务平台!

手机版|阿什卡公司:最具影响力的国际油气软件增值服务商! ( 京ICP备05022395号

GMT+8, 2022-9-25 20:17 , Processed in 1.447978 second(s), 23 queries .

Powered by Discuz! X3.4

Copyright © 2001-2021, Tencent Cloud.

快速回复 返回顶部 返回列表