基于无监督学习技术的碎屑岩储集层成岩相测井识别与应用: 以沾化凹陷三台组为例
孟圆 , 贾光华 , 李传华 , 张立强 , 张曙光
古地理学报 ›› 2025, Vol. 27 ›› Issue (3) : 746 -762.
基于无监督学习技术的碎屑岩储集层成岩相测井识别与应用: 以沾化凹陷三台组为例
Logging identification and application of diagenetic facies of clastic reservoir by unsupervised learning technology: a case study of the Santai Formation in Zhanhua sag,Bohai Bay Basin
渤海湾盆地济阳坳陷沾化凹陷埕岛—桩海地区侏罗系三台组近年来成为油气勘探重点层系,但受构造演化复杂、沉积类型多样、岩性多变的影响,储集层非均质性极强,储集层质量预测难度大,而成岩相类型的精确识别与划分对储集层的评价起至关重要的作用。传统利用有监督学习识别全井成岩相的方法在学习样本数目较少的情况下实用性有限,本研究开展基于单因素约束的无监督全井成岩相测井识别方法研究。结合视压实率、胶结物含量、面孔率和裂缝率将研究区成岩相划分为致密压实相、碳酸盐胶结相、溶蚀与裂缝相和不稳定成分弱溶蚀相。确定了GR(自然伽马)、AC(声波时差)、DEN(密度)、RD(深侧向电阻率)4条对成岩作用敏感的测井曲线作为成岩相测井识别的依据。分别对4条曲线聚类范围进行约束,确保了无监督学习方法与成岩相良好的映射关系。基于无监督学习划分的测井相种类,利用铸体薄片等资料实现测井相与成岩相的标定,完成地区成岩相的识别与划分。划分结果表明,溶蚀与裂缝相、不稳定成分弱溶蚀相为研究区储集层有利成岩相,2类成岩相对应较高的孔渗度,溶蚀与裂缝主要分布在含砾砂岩等粗粒岩中,不稳定成分弱溶蚀相主要分布在粉砂岩等细粒岩中。通过盲井成岩相对比,验证学习方法的准确性,进而为缺乏取心井段的储集层成岩相识别提出新的预测方法,对有利储集层的评价及预测具有一定意义。
The intricate tectonic evolution,coupled with diverse sedimentary environments and highly variable lithologies,results in strongly heterogeneous reservoirs in the Santai Formation of the Zhanhua sag,making reservoir quality prediction particularly challenging. This highlights the critical importance of accurately identifying and classifying diagenetic facies for effective reservoir evaluation. Traditional supervised learning methods for whole-well diagenetic facies identification are limited by the availability of training samples and thus often impractical in data-scarce scenarios. To address this,an unsupervised learning approach constrained by single-factor analysis is proposed for the logging-based identification of diagenetic facies. By integrating parameters such as apparent compaction rate,cement content,porosity,and fracture density,four diagenetic facies were identified: dense compaction facies,carbonate-cemented facies,dissolution-fracture facies,and weakly dissolved facies with unstable components. Four diagenesis-sensitive logging curves—GR(natural gamma),AC(acoustic travel time),DEN(density),and RD(deep lateral resistivity)—were selected as inputs for the unsupervised clustering algorithm. The clustering ranges of these curves were individually constrained to establish a reliable correlation between logging responses and diagenetic facies. Calibration of logging facies with diagenetic facies was conducted using core data,including thin-section analysis of cast samples,allowing for regional-scale identification and classification of diagenetic facies. The results show that the dissolution-fracture facies and weakly dissolved facies with unstable components represent the most favorable diagenetic facies for reservoir development. These are associated with relatively high porosity and permeability and are mainly distributed in coarse-grained rocks such as conglomeratic sandstones and,while the weakly dissolved facies with unstable components are mainly distributed in fine-grained rocks like siltstone. The accuracy of the proposed method was validated through comparisons with blind wells,demonstrating its effectiveness in non-cored intervals. This approach provides a novel method for predicting reservoir diagenetic facies and offers practical implications for the evaluation and prediction of high-quality reservoir zones in data-limited settings.
| [1] |
白烨, 薛林福, 石玉江, 潘保芝, 张海涛, 王建强. 2013. 测井成岩相自动识别及其在鄂尔多斯盆地苏里格地区的应用. 中国石油大学学报(自然科学版), 37(1): 35-41. |
| [2] |
[ |
| [3] |
陈亮. 2017. 埕岛油田中生界潜山油气藏勘探潜力分析. 中国石油大学(华东)硕士学位论文. |
| [4] |
[ |
| [5] |
陈晓曼, 苏欢. 2023. 基于核KMeans和SOM神经网络算法的海况聚类分析. 陕西科技大学学报, 41(3): 208-214. |
| [6] |
[ |
| [7] |
高辉, 孙卫. 2010. 鄂尔多斯盆地合水地区长8储层成岩作用与有利成岩相带. 吉林大学学报(地球科学版), 40(3): 542-548. |
| [8] |
[ |
| [9] |
何庆斌, 张继红. 2022. 松辽盆地南部大安地区姚一段特低渗砂岩成岩作用与成岩相. 成都理工大学学报(自然科学版), 49(6): 674-686. |
| [10] |
[ |
| [11] |
侯旭波. 2010. 济阳坳陷构造反转特征及其与叠合盆地演化关系. 中国石油大学(华东)博士论文. |
| [12] |
[ |
| [13] |
黄莉莎, 闫建平, 刘明洁, 张庄, 叶素娟, 张帆, 钟光海, 王敏, 王军, 耿斌. 2022. 深层致密砂岩气储层成岩相测井识别及应用: 以川西坳陷大邑须家河组须三段为例. 中国矿业大学学报, 51(1): 107-123. |
| [14] |
[ |
| [15] |
赖锦, 王贵文, 信毅, 周磊, 肖承文, 韩闯, 郑新年, 吴庆宽. 2014. 库车坳陷巴什基奇克组致密砂岩气储层成岩相分析. 天然气地球科学, 25(7): 1019-1032. |
| [16] |
[ |
| [17] |
赖锦, 王贵文, 黄龙兴, 官斌, 蒋晨, 冉冶, 张晓涛, 李梅, 王迪. 2015. 致密砂岩储集层成岩相定量划分及其测井识别方法. 矿物岩石地球化学通报, 34(1): 128-138. |
| [18] |
[ |
| [19] |
赖锦, 韩能润, 贾云武, 季玉山, 王贵文, 庞小娇, 贺志博. 2018. 基于测井资料的辫状河三角洲沉积储层精细描述. 中国地质, 45(2): 304-318. |
| [20] |
[ |
| [21] |
李昌, 沈安江, 常少英, 梁正中, 李振林, 孟贺. 2021. 机器学习法在碳酸盐岩岩相测井识别中应用及对比: 以四川盆地MX地区龙王庙组地层为例. 油气藏评价与开发, 11(4): 586-596. |
| [22] |
[ |
| [23] |
李国欣, 赵太平, 石玉江, 胡琮, 陈阵, 凡雪纯, 李栋, 赖锦. 2018. 鄂尔多斯盆地马家沟组碳酸盐岩储层成岩相测井识别评价. 石油学报, 39(10): 1141-1154. |
| [24] |
[ |
| [25] |
李嘉奇, 鲜本忠, 王剑, 连丽霞, 陈思芮, 贺静. 2022. 四棵树凹陷清水河组测井成岩相识别与储层评价. 东北石油大学学报, 46(1): 1-14. |
| [26] |
[ |
| [27] |
李明强, 张立强, 李政宏, 张亮, 毛礼鑫, 徐小童. 2021. 塔里木盆地下侏罗统阿合组下砂砾岩段致密砂岩成岩相划分及测井识别: 以库车坳陷依奇克里克地区为例. 天然气地球科学, 32(10): 1559-1570. |
| [28] |
[ |
| [29] |
李宁, 徐彬森, 武宏亮, 冯周, 李雨生, 王克文, 刘鹏. 2021. 人工智能在测井地层评价中的应用现状及前景. 石油学报, 42(4): 508-522. |
| [30] |
[ |
| [31] |
李政宏. 2020. 库车坳陷东部下侏罗统阿合组致密砂岩成岩相测井识别. 中国石油大学(华东)硕士学位论文. |
| [32] |
[ |
| [33] |
冉冶, 王贵文, 赖锦, 周正龙, 崔玉峰, 代全齐, 陈晶, 王抒忱. 2016. 利用测井交会图法定量表征致密油储层成岩相: 以鄂尔多斯盆地华池地区长7致密油储层为例. 沉积学报, 34(4): 694-706. |
| [34] |
[ |
| [35] |
孙超. 2021. 济阳坳陷埕岛—桩海地区中生界潜山储层岩性与储层质量. 科学技术与工程, 21(36): 15411-15420. |
| [36] |
[ |
| [37] |
王科. 2020. 济阳坳陷中生界碎屑岩储层储集特征及储层发育模式. 中国石油大学(华东)硕士学位论文. |
| [38] |
[ |
| [39] |
萧高健. 2022. 鄂尔多斯盆地红河油田长8段致密裂缝砂岩储层表征及“甜点油层”综合评价研究. 中国地质大学(武汉)博士论文: 42-48. |
| [40] |
[ |
| [41] |
袁静, 吴兵, 王永诗, 马立驰, 杨贵丽. 2022. 胜利滩海地区馆上段—明化镇组底部河流类型及演变. 沉积学报, 40(3): 813-824. |
| [42] |
[ |
| [43] |
张东晓, 尉玉龙, 李三百, 陈云天, 徐加放. 2021. 基于无监督机器学习的多段射孔压裂的分段优化. 中国石油大学学报(自然科学版), 45(4): 59-66. |
| [44] |
[ |
| [45] |
张光亚, 马锋, 梁英波, 赵喆, 秦雁群, 刘小兵, 张可宝, 客伟利. 2015. 全球深层油气勘探领域及理论技术进展. 石油学报, 36(9): 1156-1166. |
| [46] |
[ |
| [47] |
张浩. 2023. 基于约束聚类算法的跳频信号分选与定位技术研究. 电子科技大学硕士学位论文. |
| [48] |
[ |
| [49] |
朱世发, 贾业, 马立驰, 崔殿, 景安语, 佟欢. 2022. 渤海湾盆地济阳坳陷中生界复杂岩性风化壳储层特征、质量控因与甜点模型. 石油与天然气地质, 43(3): 514-527. |
| [50] |
[ |
| [51] |
|
| [52] |
|
| [53] |
|
| [54] |
|
| [55] |
|
/
| 〈 |
|
〉 |