Distribution prediction of the sepiolite-containing succession in the Member 1 of Maokou Formation in Sichuan Basin based on multi-gradient boosting algorithm

doi:10.7605/gdlxb.2026.048

Journal of Palaeogeography（Chinese Edition） ›› 2026, Vol. 28 ›› Issue (1): 381-397. doi: 10.7605/gdlxb.2026.048

• NEW TECHNOLOGY AND NEW METHODS • Previous Articles Next Articles

Distribution prediction of the sepiolite-containing succession in the Member 1 of Maokou Formation in Sichuan Basin based on multi-gradient boosting algorithm

SONG Jinmin¹(), REN Shan¹, LIU Shugen¹^,², WEN Long³, LI Zhiwu¹, LUO Bing³, LI Keran¹, YANG Di¹, WANG Hua³, YE Yuehao¹, JIN Xin¹, ZHANG Zhaoyi¹, GUO Jiaxin¹, SHAO Xingpeng¹, ZHANG Zubing¹

1 State Key Laboratory of Oil and Gas Reservoir Geology and Exploitation,Chengdu University of Technology,Chengdu 610059,China
2 Xihua University,Chengdu 610039,China
3 PetroChina Southwest Oil & Gas Field Company,Chengdu 610051,China

Received:2025-08-29 Revised:2025-10-23 Online:2026-02-01 Published:2026-02-09
About author:
SONG Jinmin,born in 1983,Ph.D.,is a professor at Chengdu University of Technology. He is specialises in research and teaching within the field of petroleum reservoir geology. E-mail: songjinmin2012@cdut.edu.cn.
Supported by:
National Naturral Science Foundation of China(42572132); National Naturral Science Foundation of China(U24B6001); National Science and Technology Major Project(2025ZD1400403)

基于多梯度提升器算法的四川盆地茅口组一段含海泡石层系分布预测^*

宋金民¹(), 任杉¹, 刘树根¹^,², 文龙³, 李智武¹, 罗冰³, 李柯然¹, 杨迪¹, 汪华³, 叶玥豪¹, 金鑫¹, 张钊益¹, 郭嘉欣¹, 邵兴鹏¹, 张祖兵¹

1 成都理工大学油气藏地质及开发工程全国重点实验室,四川成都 610059
2 西华大学,四川成都 610039
3 中国石油西南油气田公司,四川成都 610051

作者简介:
宋金民,男,1983年生,博士,成都理工大学教授,主要从事油气储层地质的研究和教学工作。E-mail: songjinmin2012@cdut.edu.cn。
基金资助:
*国家自然科学基金项目(42572132); 国家自然科学基金项目(U24B6001); 国家科技重大专项(2025ZD1400403)

Abstract

Abstract:

The sepiolite-containing succession in the Member 1 of the Middle Permian Maokou Formation in the Sichuan Basin exhibit self-generation and self-accumulation characteristics,positioning them as a promising new frontier for the exploration of unconventional gas reservoirs. However,the identification and predictive distribution of these strata are still underdeveloped. This study utilizes core samples,thin sections,X-ray diffraction(XRD)analysis,well logging,and mud logging data,performing sensitivity analysis to select six key well log curves: CNL,DEN,GR,RT,RXO,and AC. The SMOTE algorithm is employed to address feature imbalance. The workflow for predicting sepiolite-containing succession based on multi-gradient boosting algorithms is as follows: (1)The CatBoost algorithm is used for binary classification to determine the presence of sepiolite;(2)CatBoost performs multi-class classification to categorize the morphology of sepiolite-containing succession;(3)XGBoost is applied for regression analysis to predict the talc content in the sepiolite-containing succession;(4)The effective thickness of sepiolite-containing succession is identified based on talc content. The sepiolite-containing succession in the Member 1 of Maokou Formation primarily exhibit three morphologies: spotty,lenticular,and layered. Prediction results indicate that spotty talc is mainly developed in the northern and central southern regions of Sichuan Basin,with thickness increasing toward the northeast;lenticular talc is predominantly distributed in the western Sichuan region;and layered talc is mainly found in north western,central and southern Sichuan Basin. Overall,the sepiolite-containing succession in the Member 1 of Maokou Formation show a distribution pattern of‘thicker in the northeast,thinner in the southwest.’The Tongjiang-Changshou intracratonic sag area and the Hechuan-Weiyuan-Luzhou region serve as the sedimentary centers for the effective thickness of sepiolite-containing succession,providing a basis for future exploration and deployment in these areas.

Key words: gradient boosting machines, machine-learning, sepiolite containing succession, Member 1 of Maokou Formation, Permian, Sichuan Basin

摘要：

四川盆地中二叠统茅口组一段含海泡石层系具有自生自储、源内成藏的特点,为碳酸盐岩非常规气藏勘探的新领域,目前对其的识别和分布预测较为薄弱。基于岩心、薄片、XRD、测井与录井资料,通过敏感性分析选取CNL、DEN、GR、RT、RXO和AC 6条测井曲线,利用SMOTE算法处理特征平衡性差异,提出含海泡石层系基于多梯度提升器算法的综合预测流程。具体如下: (1)CatBoost算法以滑石作为预测分析载体,对是否含海泡石作二分类判断; (2)CatBoost算法对含海泡石层系进行滑石产状的多分类判断; (3)XGBoost算法对含海泡石层系的滑石含量进行回归预测; (4)识别不同产状含海泡石层系的有效厚度。茅一段含海泡石层系(滑石)主要发育斑点状、透镜状和层状3种产状。预测结果显示,斑点状滑石发育在川北和川中—蜀南地区,厚呈向北东增大趋势; 透镜状滑石主要分布在川西地区; 层状滑石见于川西北、川中和蜀南地区。四川盆地茅一段含海泡石层系整体具有“北东厚、南西薄”的分布特征,通江—长寿凹陷地区为含海泡石层系的沉积中心,合川—威远—泸州地区为含海泡石层系优势发育区,这为下一步的勘探部署提供了依据。

关键词: 梯度提升器算法, 机器学习, 含海泡石层系, 茅一段, 二叠系, 四川盆地

CLC Number:

P588.245

SONG Jinmin, REN Shan, LIU Shugen, WEN Long, LI Zhiwu, LUO Bing, LI Keran, YANG Di, WANG Hua, YE Yuehao, JIN Xin, ZHANG Zhaoyi, GUO Jiaxin, SHAO Xingpeng, ZHANG Zubing. Distribution prediction of the sepiolite-containing succession in the Member 1 of Maokou Formation in Sichuan Basin based on multi-gradient boosting algorithm[J]. Journal of Palaeogeography（Chinese Edition）, 2026, 28(1): 381-397.

宋金民, 任杉, 刘树根, 文龙, 李智武, 罗冰, 李柯然, 杨迪, 汪华, 叶玥豪, 金鑫, 张钊益, 郭嘉欣, 邵兴鹏, 张祖兵. 基于多梯度提升器算法的四川盆地茅口组一段含海泡石层系分布预测^*[J]. 古地理学报, 2026, 28(1): 381-397.

/ / Recommend / Download Citations

URL: http://www.gdlxb.cn/EN/10.7605/gdlxb.2026.048

http://www.gdlxb.cn/EN/Y2026/V28/I1/381

Figures/Tables 14

Fig.1 Sedimentary facies map(A)and integrated stratigraphic column(B)of the Member 1 of Maokou Formation of Sichuan Basin(modified from Song et al., 2024b)

Fig.2 Macro-developmental characteristics of sepiolite (talc) containing formation in the Member 1 of Maokou Formation of Well XT1 in Sichuan Basin

Fig.3 Petrological characteristics of the sepiolite containing formation in the Member 1 of Maokou Formation of Sichuan Basin

Fig.4 Plot of logging features versus sepiolite (talc)containing formation

Table 1 Statistics on completeness of different logging curves of sample wells and wells to be predicted in the Member 1 of Maokou Formation of Sichuan Basin

类型	不同测井曲线完整度
类型	GR	AC	CNL	DEN	RT	RXO	SP	PE	MSFL	CAL
样本井	0.99	0.98	0.97	0.92	0.91	0.91	0.85	0.64	0.43	0.30
待预测井	0.99	0.97	0.96	0.93	0.90	0.90	0.82	0.70	0.38	0.28

Table 2 Statistics of scoring results of different logging curves by random forest scorer in the Member 1 of Maokou Formation of Sichuan Basin

测井类型	GR	AC	CAL	DEN	RT	RXO	SP	PE	MSFL	CNL
分数	0.54	0.21	-0.034	0.24	0.21	0.21	0.34	0.42	-0.17	0.28

Fig.5 Distribution of sample data before and after the introduction of SMOTE algorithm

Fig.6 Schematic diagram of the model structure

Table 3 Comparison of performance results of different machine learning methods

模型类型	二分类判定滑石存在性问题				滑石产状多分类问题				滑石含量回归问题
模型类型	训练误差	验证误差	训练准确度	验证准确度	训练误差	验证误差	训练准确度	验证准确度	训练误差	验证误差
CatBoost	0.01	0.03	0.98	0.97	0.01	0.02	0.96	0.92	0.25	0.24
XGBoost	0.01	0.03	0.98	0.97	0.07	0.11	0.92	0.91	0.07	0.05
LightGBM	0.01	0.02	0.98	0.98	0.45	0.48	0.74	0.68	0.29	0.27
随机森林	0.18	0.18	0.54	0.54	0.84	0.85	0.32	0.31	0.23	0.21
ANN	0.21	0.14	0.92	0.95	1.01	0.97	0.41	0.41	0.64	0.44
SVM	/	0.02	/	0.95	/	0.60	/	0.62	/	0.38
KNN	/	0.20	/	0.65	/	0.87	/	0.11	/	1.27
贝叶斯	/	0.73	/	0.25	/	0.92	/	0.08	/	/

Fig.7 Validation results with reserved test set data(the abscissa represents actual attributes,and the ordinate represents predicted attributes in the confusion matrix)

Fig.8 Comparison of generalization capabilities of various regression models in predicting talc content

Table 4 Verification well comparison accuracy

序号	井代号	岩石学分析验证/%		滑石含量 XRD结果验证/%	总准确率 /%
序号	井代号	滑石存在性二分类	滑石产状多分类	滑石含量 XRD结果验证/%	总准确率 /%
1	YB7	91.24	90.54	89.41	90.1
2	HB11	78.56	77.98	81.72	79.4
3	LX2	84.17	82.34	76.56	81.0
4	QL16	98.62	97.53	92.14	96.1
5	W118	79.43	78.21	84.99	80.9
6	JT1	87.91	85.67	80.37	84.7
7	CT1	92.08	91.56	93.65	92.4
8	LT1	76.34	75.64	77.89	76.3
9	NC1	93.77	91.12	88.23	91.0
10	LS1	81.56	80.43	79.12	80.0
11	W117	95.43	94.21	91.38	93.0
12	FS1	89.72	88.65	78.77	85.4

Fig.9 Single-well verification chart of sepiolite content prediction in the Member 1 of Maokou Formation of Well HB1

Fig.10 Isopach of sepiolite-containing strata with different occurrences of the Member 1 of Maokou Formation in Sichuan Basin

References 36

[1]	白烨, 曹乃文, 邱庆良. 2021. 极限学习机在黏土矿物分析中的应用. 地质与资源, 30(4): 505-511.
	[Bai Y, Cao N W, Qiu Q L. 2021. Application of extreme learning machine in analysis of clay minerals. Geology and Resources, 30(4): 505-511]
[2]	范建平, 宋金民, 江青春, 刘树根, 叶玥豪, 黄士鹏, 王佳蕊, 苏旺, 李立基, 金鑫, 冯宇翔. 2022. 川东地区中二叠统茅口组一段储层特征与形成模式. 石油与天然气地质, 43(6): 1413-1430.
	[Fan J P, Song J M, Jiang Q C, Liu S G, Ye Y H, Huang S P, Wang J R, Su W, Li L J, Jin X, Feng Y X. 2022. Reservoir characteristics and development model of the Middle Permian Mao-1 Member in eastern Sichuan Basin. Oil & Gas Geology, 43(6): 1413-1430]
[3]	范建平, 宋金民, 刘树根, 江青春, 李智武, 杨迪, 金鑫, 苏旺, 叶玥豪, 黄士鹏, 王佳蕊, 姜华, 罗平. 2023. 四川盆地中二叠统茅一段灰岩—泥质灰岩韵律层古温度演化及驱动机制. 石油实验地质, 45(4): 726-738.
	[Fan J P, Song J M, Liu S G, Jiang Q C, Li Z W, Yang D, Jin X, Su W, Ye Y H, Huang S P, Wang J R, Jiang H, Luo P. 2023. Paleotemperature evolution and its driving mechanism during the formation of limestone-marl alternations in the first Member of Middle Permian Maokou Formation in Sichuan Basin. Petroleum Geology & Experiment, 45(4): 726-738]
[4]	胡东风, 王良军, 张汉荣, 段金宝, 夏文谦, 刘珠江, 魏全超, 王昆, 潘磊. 2020. 碳酸盐岩烃源岩气藏的发现及其油气地质意义: 以四川盆地涪陵地区中二叠统茅口组一段气藏为例. 天然气工业, 40(7): 23-33.
	[Hu D F, Wang L J, Zhang H R, Duan J B, Xia W Q, Liu Z J, Wei Q C, Wang K, Pan L. 2020. Discovery of carbonate source rock gas reservoir and its petroleum geological implications: a case study of the gas reservoir in the first Member of Middle Permian Maokou Formation in the Fuling area,Sichuan Basin. Natural Gas Industry, 40(7): 23-33]
[5]	江青春, 汪泽成, 苏旺, 黄士鹏, 曾富英, 冯周, 毕赫, 鲁卫华. 2021. 四川盆地中二叠统茅口组一段泥灰岩源内非常规天然气成藏条件及有利勘探方向. 中国石油勘探, 26(6): 82-97.
	[Jiang Q C, Wang Z C, Su W, Huang S P, Zeng F Y, Feng Z, Bi H, Lu W H. 2021. Accumulation conditions and favorable exploration orientation of unconventional natural gas in the marl source rock of the first Member of the Middle Permian Maokou Formation,Sichuan Basin. China Petroleum Exploration, 26(6): 82-97]
[6]	蒋航, 张玺华, 陈聪, 高兆龙, 山述娇, 罗平, 陈延贵, 李天军, 胡罗嘉. 2023. 川北地区茅口中晚期斜坡相沉积特征及其油气地质意义. 海相油气地质, 28(4): 381-390.
	[Jiang H, Zhang X H, Chen C, Gao Z L, Shan S J, Luo P, Chen T J, Li T J, Hu L J. 2023. Sedimentary characteristics of slope facies in mid-late stage of Maokou Formation in northern Sichuan Basin and its petroleum geological significances. Marine Origin Petroleum Geology, 28(4): 381-390]
[7]	蒋文博, 丁晓军, 郭华黏, 许姗姗, 黄斌, 李信. 2018. 黏土矿物预测方程的建立及在东营油田的应用. 石油地质与工程, 32(3): 95-97,125.
	[Jiang W B, Ding X J, Guo H N, Xu S S, Huang B, Li X. 2018. Establishment of prediction equations for clay minerals and their application in the Dongying Oilfield. Petroleum Geology and Engineering, 32(3): 95-97,125 ]
[8]	梁兴, 徐政语, 栗维民, 马立桥, 计玉冰, 罗瑀峰, 丁邦春. 2023. 蜀南—渝西地区中二叠统茅一段灰质源岩气储层特征及主控因素: 以DB1井为例. 石油实验地质, 45(4): 714-725.
	[Liang X, Xu Z Y, Li W M, Ma L Q, Ji Y B, Luo Y F, Ding B C. 2023. Characteristics and main controlling factors of the limy source rock gas reservoir in the first Member of the Middle Permian Maokou Formation in the southern Sichuan and western Chongqing area: a case study of well DB 1. Petroleum Geology & Experiment, 45(4): 714-725]
[9]	梁兴, 张磊, 蒋立伟, 单长安, 潘峰, 罗瑀峰, 孟阳, 王高成, 舒红林, 朱斗星, 李博硕, 汪振东, 姚秋昌, 徐政语. 2024. 四川盆地渝西大安地区灰质源岩气勘探突破与资源潜力. 中国石油勘探, 29(2): 30-45. doi: 10.3969/j.issn.1672-7703.2024.02.003
	[Liang X, Zhang L, Jiang L W, Shan C A, Pan F, Luo Y F, Meng Y, Wang G C, Shu H L, Zhu D X, Li B S, Wang Z D, Yao Q C, Xu Z Y. 2024. Exploration breakthrough and resource potential of limy source rock gas in Da’an area in the western Chongqing,Sichuan Basin. China Petroleum Exploration, 29(2): 30-45] doi: 10.3969/j.issn.1672-7703.2024.02.003
[10]	刘昇, 范存辉, 张本健, 张亚, 王尉, 罗冰, 白晓亮. 2023. 四川盆地东部中二叠统茅口组孤峰段展布特征及其油气地质意义. 石油与天然气地质, 44(4): 993-1008.
	[Liu S, Fan C H, Zhang B J, Zhang Y, Wang W, Luo B, Bai X L. 2023. Distribution characteristics of Gufeng Member of the Middle Permian Maokou Formation,eastern Sichuan Basin and its petrogeological significance. Oil & Gas Geology, 44(4): 993-1008]
[11]	刘树根, 文龙, 宋金民, 孙玮, 汪华, 金鑫, 郭海洋, 邓宾, 江青春, 李智武, 丁一, 叶玥豪, 王瀚, 范建平, 杨迪, 李柯然, 田小彬, 罗平. 2022. 四川盆地中二叠统构造-沉积分异与油气勘探. 成都理工大学学报(自然科学版), 49(4): 385-413.
	[Liu S G, Wen L, Song J M, Sun W, Wang H, Jin X, Guo H Y, Deng B, Jiang Q C, Li Z W, Ding Y, Ye Y H, Wang H, Fan J P, Yang D, Li K R, Tian X B, Luo P. 2022. Sedimentary topography and tectonic differentiation on the Middle Permian platform and hydrocarbon exploration in Sichuan Basin,SW China. Journal of Chengdu University of Technology(Science & Technology Edition), 49(4): 385-413]
[12]	宋金民, 刘树根, 金鑫, 汪华, 范建平, 江青春, 田小彬, 叶玥豪, 李亚, 李智武, 杨迪, 王佳蕊, 罗平. 2022. 四川盆地中二叠统含海泡石层系源储组合新模式及其油气勘探新领域. 成都理工大学学报(自然科学版), 49(2): 129-149.
	[Song J M, Liu S G, Jin X, Wang H, Fan J P, Jiang Q C, Tian X B, Ye Y H, Li Y, Li Z W, Yang D, Wang J R, Luo P. 2022. A new model of source-reservoir association and new fields of oil and gas exploration in the Middle Permian sepiolite-bearing strata,Sichuan Basin,China. Journal of Chengdu University of Technology(Science & Technology Edition), 49(2): 129-149]
[13]	宋金民, 刘树根, 李智武, 张本健, 邓宾, 江青春, 金鑫, 孙玮, 汪华, 郭海洋, 陈骁, 王佳蕊, 田小彬, 张玺华, 叶玥豪, 杨迪, 范建平, 罗平. 2023. 四川盆地中二叠统油气成藏模式与有利勘探区分布. 天然气工业, 43(11): 54-71.
	[Song J M, Liu S G, Li Z W, Zhang B J, Deng B, Jiang Q C, Jin X, Sun W, Wang H, Guo H Y, Chen X, Wang J R, Tian X B, Zhang X H, Ye Y H, Yang D, Fan J P, Luo P. 2023. Accumulation model and favorable exploration area distribution of the Middle Permian oil and gas in the Sichuan Basin. Natural Gas Industry, 43(11): 54-71]
[14]	宋金民, 江青春, 刘树根, 金鑫, 范建平, 李智武, 黄士鹏, 苏旺, 杨迪, 姜华, 叶玥豪, 王佳蕊, 王俊轲, 任杉. 2024a. 四川盆地中二叠统茅口组一段含海泡石层系古环境与沉积格局指示意义. 石油学报, 45(6): 914-931.
	[Song J M, Jiang Q C, Liu S G, Jin X, Fan J P, Li Z W, Huang S P, Su W, Yang D, Jiang H, Ye Y H, Wang J L, Wang J K, Ren S. 2024a. Paleoenvironment and sedimentary significances of sepiolite-containing succession in the first Member of Middle Permian Maokou Formation,Sichuan Basin. Acta Petrolei Sinica, 45(6): 914-931]
[15]	宋金民, 王佳蕊, 刘树根, 李智武, 罗平, 江青春, 金鑫, 杨迪, 黄士鹏, 范建平, 叶玥豪, 王俊轲, 邓豪爽, 王斌, 郭嘉欣. 2024b. 含海泡石层系泥质灰岩中自生黏土矿物的类型、组成与成岩演化过程: 以川东地区中二叠统茅口组茅一段为例. 石油勘探与开发, 51(2): 311-322.
	[Song J M, Wang J R, Liu S G, Li Z W, Luo P, Jiang Q C, Jin X, Yang D, Huang S P, Fan J P, Ye Y H, Wang J K, Deng H S, Wang B, Guo J X. 2024b. Types,composition and diagenetic evolution of authigenic clay minerals in argillaceous limestone of sepiolite-bearing strata: a case study of Mao-1 Member of Middle Permian Maokou Formation,eastern Sichuan Basin,SW China. Petroleum Exploration and Development, 51(2): 311-322]
[16]	宋金民, 王俊轲, 刘树根, 文龙, 叶玥豪, 罗冰, 李智武, 张本健, 金鑫, 杨迪, 张玺华, 王佳蕊, 周刚, 郭嘉欣, 张钊益, 罗平. 2025. 含海泡石层系有机质赋存类型与富集模式: 以川东地区茅口组一段为例. 石油勘探与开发, 52(5): 1054-1067. doi: 10.11698/PED.20250088
	[Song J M, Wang J K, Liu S G, Wen L, Ye Y H, Luo B, Li Z W, Zhang B J, Jin X, Yang D, Zhang X H, Wang J R, Zhou G, Guo J X, Zhang Z Y, Luo P. 2025. Occurrence types and enrichment model of organic matter in the sepiolite-containing successions: a case study of the Mao-1 Member of Mid-Permian Maokou Formation,Eastern Sichuan Basin,SW China. Petroleum Exploration and Development, 52(5):1054-1067]
[17]	王斌, 宋金民, 刘树根, 金鑫, 李智武, 叶玥豪, 杨迪, 王佳蕊, 王俊轲, 邓豪爽, 郭嘉欣, 罗平. 2024. 川西地区中二叠统茅口组二段白云岩类型与成因模式. 石油学报, 45(12): 1743-1760. doi: 10.7623/syxb202412004
	[Wang B, Song J M, Liu S G, Jin X, Li Z W, Ye Y H, Yang D, Wang J R, Wang J K, Deng H S, Guo J X, Luo P. 2024. Types and genetic modes of dolomite in the Member 2 of Middle Permian Maokou Formation in western Sichuan Basin. Acta Petrolei Sinica, 45(12): 1743-1760] doi: 10.7623/syxb202412004
[18]	王心乾, 余文端, 马晓东, 周韬, 邰浩, 崔钦宇, 邓空, 陆永潮, 刘占红. 2024. 基于常规测井曲线的页岩岩相识别与应用: 以苏北盆地溱潼凹陷阜宁组二段为例. 油气藏评价与开发, 14(5): 699-706,713.
	[Wang X Q, Yu W D, Ma X D, Zhou T, Tai H, Cui Q Y, Deng K, Lu Y C, Liu Z H. 2024. Identification and application of shale lithofacies based on conventional logging curves: a case study of the second Member of Funing Formation in Qintong sag,Subei Basin. Petroleum Reservoir Evaluation and Development, 14(5): 699-706,713 ]
[19]	夏文谦, 刘瑾, 俞凌杰, 张汉荣, 汪建辉, 魏富彬, 章思遥. 2023. 川东南涪陵地区二叠系茅口组一段泥质灰岩储层特征及主控因素. 矿物岩石, 43(4): 100-108.
	[Xia W Q, Liu J, Yu L J, Zhang H R, Wang J H, Wei F B, Zhang S Y. 2023. Characteristics and main controlling factors of argillaceous limestone reservoir in the first Member of Permian Maokou Formation in Fuling area,southeast Sichuan Basin. Mineralogy and Petrology, 43(4): 100-108]
[20]	杨跃明, 杨雨, 文龙, 张玺华, 陈聪, 陈康, 张亚, 狄贵东, 汪华, 谢忱. 2020. 四川盆地中二叠统天然气勘探新进展与前景展望. 天然气工业, 40(7): 10-22.
	[Yang Y M, Yang Y, Wen L, Zhang X H, Chen C, Chen K, Zhang Y, Di G D, Wang H, Xie C. 2020. New exploration progress and prospect of Middle Permian natural gas in the Sichuan Basin. Natural Gas Industry, 40(7): 10-22]
[21]	殷树军, 文政, 金雪英, 闫伟林, 王春燕, 师江波, 夏文豪, 李金奉, 聂妮, 郑盛敦. 2023. 泥灰岩非常规储层特征及测井表征方法; 以四川盆地合川—潼南地区茅口组一段为例. 石油学报, 44(7): 1105-1117. doi: 10.7623/syxb202307007
	[Yin S J, Wen Z, Jin X Y, Yan W L, Wang C Y, Shi J B, Xia W H, Li J F, Nie N, Zheng S D. 2023. Characteristics and logging characterization method of unconventional marl reservoir: a case study of the Member 1 of Maokou Formation in Hechuan-Tongnan area,Sichuan Basin. Acta Petrolei Sinica, 44(7): 1105-1117]
[22]	翟常博, 林良彪, 尤东华, 刘冯斌, 刘思雨. 2024. 川西南地区中二叠统茅口组一段沉积微相特征及有机质富集模式. 石油与天然气地质, 45(2): 440-456.
	[Zhai C B, Lin L B, You D H, Liu F B, Liu S Y. 2024. Sedimentary microfacies characteristics and organic matter enrichment pattern of the first Member of the Middle Permian Maokou Formation,southwestern Sichuan Basin. Oil & Gas Geology, 45(2): 440-456]
[23]	张培先, 何希鹏, 高全芳, 高玉巧, 孙斌, 蔡潇, 何贵松, 张志萍, 刘娜娜. 2021. 四川盆地东南缘二叠系茅口组一段页岩气藏地质特征及富集模式. 石油与天然气地质, 42(1): 146-157.
	[Zhang P X, He X P, Gao Q F, Gao Y Q, Sun B, Cai X, He G S, Zhang Z P, Liu N N. 2021. Geological characteristics and enrichment pattern of Permian Mao-1 Member shale gas reservoirs at the southeastern margin of Sichuan Basin. Oil & Gas Geology, 42(1): 146-157]
[24]	张宇, 曹清古, 罗开平, 李龙龙, 刘金连. 2022. 四川盆地二叠系茅口组油气藏勘探发现与启示. 石油与天然气地质, 43(3): 610-620.
	[Zhang Y, Cao Q G, Luo K P, Li L L, Liu J L. 2022. Reservoir exploration of the Permian Maokou Formation in the Sichuan Basin and enlightenment obtained. Oil & Gas Geology, 43(3): 610-620]
[25]	Cao K, Wei C, Gaidon A, Arechiga N,Ma, T Y. 2019. Learning imbalanced datasets with label-distribution-aware margin loss. Advances in Neural Information Processing Systems, 32(NeurIPS 2019).
[26]	Chawla N V, Bowter K W, Hall L O, Kegelmeyer W P. 2002. SMOTE: synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16: 321-357. doi: 10.1613/jair.953 URL
[27]	Chen T, Guestrin C. 2016. Xgboost: a scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining: 785-794.
[28]	Dorogush A V, Ershov V, Gulin A. 2018. The CatBoost algorithm. Microsoft Research Technical Report.
[29]	Friedman J H. 1999. Greedy function approximation: a gradient boosting machine. Annals of Statistics, 29(5): 1189-1232.
[30]	Hastie T, Tibshirani R, Friedman J. 2009. The Elements of Statistical Learning(2nd ed). New York: Springer.
[31]	Hyndman R J, Koehler A B. 2006. Another look at measures of forecast accuracy. International Journal of Forecasting, 22(4): 679-688. doi: 10.1016/j.ijforecast.2006.03.001 URL
[32]	Jin H, Song Q, Hu X. 2019. Auto-Keras: an efficient neural architecture search system. 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining: 1946-1956.
[33]	Koray A-M, Bui D, Kubi E, Ampomah W, Amosu A. 2024. Machine learning based reservoir characterization and numerical modeling from integrated well log and core data. Geoenergy Science & Engineering, 243: 213296.
[34]	Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay Edouard. 2011. Scikit-learn: machine learning in Python. Journal of Machine Learning Research, 12: 2825-2830.
[35]	Prokhorenkova L, Gusev G, Vorobev A, Dorogush A V, Gulin A. 2018. CatBoost: unbiased boosting with categorical features. Advances in Neural Information Processing Systems,31.
[36]	Wang Z H, Cai Y D, Liu D M, Lu J, Qiu F, Sun F R, Hu J H, Li Z T. 2024. Characterization of natural fracture development in coal reservoirs using logging machine learning inversion,well test data and simulated geostress analyses. Engineering Geology: 107696.

Please choose a citation manager

Content to export