Lithology Identification of Volcanic Rocks Based on Extra-Trees Classifier: A Case Study of the Huoshiling Formation in the Chaganhua Subsag, Changling Fault Depression, Songliao Basin

doi:10.7657/XJPG20260211

Abstract

Abstract:

Volcanic rock reservoir is one of the key exploration targets in the Changling fault depression of the Songliao Basin in recent years. The logging responses of complex volcanic lithologies are crucial to clarifying the reservoir properties (lithology, physical property, electrical property, and oil-bearing property). Based on the microscopic analysis of complex volcanic lithology, the lithology of volcanic rocks in the Huoshiling formation of the Chaganhua subsag in the Changling fault depression was calibrated through thin-section examination, whole-rock X-ray diffraction (XRD) analysis, and quantitative analysis using the RoqScan mineral auto-identification system. The conventional logging data and elemental logging data of the calibrated interval were divided into training set and test set. The training set was used to fit the target lithology, and the test set was loaded into the model calculation for prediction. Moreover, the model was employed in blind well testing. The results show that the volcanic rocks in the Huoshiling formation of the Chaganhua subsag in the Changling fault depression can be categorized into 5 classes such as volcanic lava, pyroclastic lava, pyroclastic rock, sedimentary pyroclastic rock, and pyroclastic sedimentary rock, indicating complex and varying lithologies. Six algorithms, i.e. decision tree, LightGBM, random forest, neural network, K-nearest neighbor (KNN), and extra-trees classifier (ETC), were compared for distinguishing lithology, revealing the accuracy of above 77% for all algorithms. ETC exhibits the best performance, with an accuracy up to 90%. This model has a strong generalization ability and yields an accuracy of 89% in blind well testing while correcting the results of original cutting logging. It can accurately identify and predict the lithology of volcanic rocks in the study area and provide intelligent support for subsequent volcanic oil and gas exploration and development.

Key words: Songliao Basin, Changling fault depression, Huoshiling formation, volcanic rock, lithology, machine learning, extra-trees classifier

CLC Number:

TE122.1

WANG Yelei, CI Xinghua, DU Huanfu, HOU Wenhui, WANG Zhifeng, WANG Shunye, WANG Chunwei. Lithology Identification of Volcanic Rocks Based on Extra-Trees Classifier: A Case Study of the Huoshiling Formation in the Chaganhua Subsag, Changling Fault Depression, Songliao Basin[J]. Xinjiang Petroleum Geology, 2026, 47(2): 222-232.

Figures/Tables 12

Fig. 1.

Fig. 2.

Table 1.

Fig. 3.

Table 2.

Fig. 4.

Fig. 5.

Fig. 6.

Fig. 7.

Fig. 8.

Fig. 9.

Fig. 10.

References 30

[1]	THINESH K A, NARESH K S G, SRINIVASA R. Lithology prediction from well log data using machine learning techniques:A case study from Talcher coalfield,eastern India[J]. Journal of Applied Geophysics, 2022, 199:104605. doi: 10.1016/j.jappgeo.2022.104605
[2]	TIMUR M, DARKHAN K G, BAKHBERGEN B, et al. A comparison of machine learning algorithms in predicting lithofacies:Case studies from Norway and Kazakhstan[J]. Energies, 2021, 14(7):1896. doi: 10.3390/en14071896
[3]	WANG Pu, CHEN Xiaohong, WANG Benfeng, et al. An improved method for lithology identification based on a hidden Markov model and random forests[J]. Geophysics, 2020, 85(6):1-10. doi: 10.1190/geo2018-0881.1
[4]	GUO C, ZHANG T. Lithology prediction using machine learning and geophysical log data in tight sandstone gas reservoirs[J]. Journal of Natural Gas Science and Engineering, 2021, 86:103694.
[5]	潘少伟, 师少恒, 李宗强, 等. 群智能优化算法在石油工业中的研究进展与应用前景[J]. 世界石油工业, 2025, 32(5):83-95.
	PAN Shaowei, SHI Shaoheng, LI Zongqiang, et al. Research progress and prospects of swarm intelligence optimization algorithms in the petroleum industry[J]. World Petroleum Industry, 2025, 32(5):83-95.
[6]	陈秀娟, 冯镇涛, 曾芙蓉, 等. 页岩地层测井岩性识别技术发展现状[J]. 新疆石油地质, 2024, 45(6):742-752.
	CHEN Xiujuan, FENG Zhentao, ZENG Furong, et al. Development status of logging-based lithology identification technology for shale formations[J]. Xinjiang Petroleum Geology, 2024, 45(6):742-752.
[7]	秦志军, 操应长, 冯程. 基于改进型随机森林算法的页岩岩性识别:以准噶尔盆地芦草沟组为例[J]. 新疆石油地质, 2024, 45(5):595-603.
	QIN Zhijun, CAO Yingchang, FENG Cheng. Shale lithology identification based on improved random forest algorithm:A case of Lucaogou formation in Junggar Basin[J]. Xinjiang Petroleum Geology, 2024, 45(5):595-603.
[8]	赵然磊, 杨留栓, 徐晓, 等. 基于XGBoost算法的火山岩岩性识别方法与研究[J]. 地球物理学进展, 2025, 40(2):646-657. doi: 10.6038/pg2025II0019
	ZHAO Ranlei, YANG Liushuan, XU Xiao, et al. Lithology identification method and research of volcanic rock based on XGBoost algorithm[J]. Progress in Geophysics, 2025, 40(2):646-657. doi: 10.6038/pg2025II0019
[9]	单玄龙, 牟汉生, 刘玉虎, 等. 湖盆水下喷发火山岩相类型、特征与储集意义:以松辽盆地南部查干花地区白垩系为例[J]. 石油勘探与开发, 2023, 50(4):719-730. doi: 10.11698/PED.20220849
	SHAN Xuanlong, MU Hansheng, LIU Yuhu, et al. Subaqueous volcanic eruptive facies,facies model and its reservoir significance in a continental lacustrine basin:A case from the Cretaceous in Chaganhua area of southern Songliao Basin,NE China[J]. Petroleum Exploration and Development, 2023, 50(4):719-730.
[10]	刘双莲. 常规测井技术识别火山岩裂缝方法研究:以松南火山岩为例[J]. 非常规油气, 2022, 9(4):16-22.
	LIU Shuanglian. Study on method of identifying volcanic rock fractures by conventional logging technology:A case study on Songnan volcanic rock[J]. Unconventional Oil & Gas, 2022, 9(4):16-22.
[11]	牟丹, 张丽春, 徐长玲. 3种经典机器学习算法在火山岩测井岩性识别中的对比[J]. 吉林大学学报(地球科学版), 2021, 51(3):951-956.
	MOU Dan, ZHANG Lichun, XU Changling. Comparison of three classical machine learning algorithms for lithology identification of volcanic rocks using well logging data[J]. Journal of Jilin University(Earth Science Edition), 2021, 51(3):951-956.
[12]	许振浩, 马文, 李术才, 等. 岩性识别:方法、现状及智能化发展趋势[J]. 地质论评, 2022, 68(6):2290-2304.
	XU Zhenhao, MA Wen, LI Shucai, et al. Lithology identification:Method,research status and intelligent development trend[J]. Geological Review, 2022, 68(6):2290-2304.
[13]	黄金富, 王啊丽, 夏国朝, 等. 喷发相火山岩储层特征研究及地质意义[J]. 非常规油气, 2023, 10(6):27-34.
	HUANG Jinfu, WANG Ali, XIA Guochao, et al. Study on reservoir characteristics of eruptive facies volcanic rock and its geological significance[J]. Unconventional Oil & Gas, 2023, 10(6):27-34.
[14]	许方哲, 朱建峰, 刘玉虎, 等. 长岭断陷查干花次凹火石岭组火山岩喷发模式新认识[J]. 新疆石油地质, 2024, 45(5):533-540.
	XU Fangzhe, ZHU Jianfeng, LIU Yuhu, et al. New insights into eruption model of Huoshiling formation volcanic rocks in Chaganhua subsag of Changling fault depression[J]. Xinjiang Petroleum Geology, 2024, 45(5):533-540.
[15]	石云倩. 松辽盆地南部白垩系火石岭组火山岩特征与喷发就位环境及其储层发育模式[D]. 长春: 吉林大学, 2023.
	SHI Yunqian. Volcanic characteristics,eruptive environment and reservoir development model of the Cretaceous Huoshiling formation in the southern Songliao Basin[D]. Changchun: Jilin University, 2023.
[16]	李道伦, 查文舒, 刘旭亮, 等. 深度学习网络在非常规油气开发中的应用研究[J]. 非常规油气, 2024, 11(6):1-7.
	LI Daolun, ZHA Wenshu, LIU Xuliang, et al. Research on application of deep learning network in unconventional oil and gas development[J]. Unconventional Oil & Gas, 2024, 11(6):1-7.
[17]	王静, 束青林, 杜玉山, 等. 基于动态时间规整算法的页岩油裂缝预测方法研究及应用[J]. 特种油气藏, 2025, 32(1):61-70. doi: 10.3969/j.issn.1006-6535.2025.01.007
	WANG Jing, SHU Qinglin, DU Yushan, et al. Research and application of shale oil fracture prediction method based on dynamic time warping algorithm[J]. Special Oil & Gas Reservoirs, 2025, 32(1):61-70.
[18]	伍秋姿, 陈丽清, 陈玉龙, 等. 基于机器学习算法的深部页岩储层物性预测及有利勘探区优选[J]. 非常规油气, 2024, 11(5):95-105.
	WU Qiuzi, CHEN Liqing, CHEN Yulong, et al. Prediction of physical properties of deep shale reservoirs and optimization of favorable exploration areas based on machine learning algorithms[J]. Unconventional Oil & Gas, 2024, 11(5):95-105.
[19]	DUAN Yajun, XIE Jun, SU Yanchun, et al. Application of the decision tree method to lithology identification of volcanic rocks:Taking the Mesozoic in the Laizhouwan sag as an example[J]. Scientific Reports, 2020, 10(1):19209. doi: 10.1038/s41598-020-76303-y pmid: 33154548
[20]	罗水亮, 漆影强, 唐松, 等. 基于改进Stacking算法的碳酸盐岩储层测井岩性识别方法与应用[J]. 特种油气藏, 2025, 32(4):58-67. doi: 10.3969/j.issn.1006-6535.2025.04.007
	LUO Shuiliang, QI Yingqiang, TANG Song, et al. Lithology logging identification method and application to carbonate reservoirs based on improved Stacking algorithm[J]. Special Oil & Gas Reservoirs, 2025, 32(4):58-67.
[21]	王啟, 杨添微, 刘永震, 等. 基于随机森林算法的复杂碳酸盐岩岩性识别[J]. 工程地球物理学报, 2020, 17(5):550-558.
	WANG Qi, YANG Tianwei, LIU Yongzhen, et al. Identification of complex carbonate lithology based on random forest algorithm[J]. Chinese Journal of Engineering Geophysics, 2020, 17(5):550-558.
[22]	罗山贵, 赵玉龙, 肖红林, 等. 基于混合优化算法和深度神经网络模型结合的致密砂岩气藏裂缝参数优化[J]. 天然气工业, 2024, 44(9):140-151.
	LUO Shangui, ZHAO Yulong, XIAO Honglin, et al. Fracture parameter optimization of tight sandstone gas reservoirs based on the hybrid optimization algorithm and deep neural network model[J]. Natural Gas Industry, 2024, 44(9):140-151.
[23]	谷宇峰, 张道勇, 鲍志东, 等. 利用GS-LightGBM机器学习模型识别致密砂岩地层岩性[J]. 地质科技通报, 2021, 40(4):224-234.
	GU Yufeng, ZHANG Daoyong, BAO Zhidong, et al. Lithology prediction of tight sandstone formation using GS-LightGBM hybrid machine learning model[J]. Bulletin of Geological Science and Technology, 2021, 40(4):224-234.
[24]	LI Xinhai. Using “random forest”for classification and regression[J]. Chinese Journal of Applied Entomology, 2013, 50(4):1190-1197.
[25]	GHOSH S. Lithofacies classification from well logs using machine learning techniques:A case study from the Cambay Basin,India[J]. Journal of Petroleum Science and Engineering, 2016, 144:139-148.
[26]	ABHISHEK L. Optical character recognition using ensemble of SVM,MLP and extra trees classifier[R]. Belagavi,India: International Conference for Emerging Technology, 2020.
[27]	NANJO T, TANAKA S. Carbonate lithology identification with machine learning[R]. Abu,Dhabi: International Petroleum Exhibition & Conference, 2019.
[28]	YIRENKYI S, BOATENG C D, AHENE E, et al. Automatic lithology identification in meteorite impact craters using machine learning algorithms[J]. Scientific Reports, 2024, 14:14360. doi: 10.1038/s41598-024-62959-3 pmid: 38906899
[29]	熊峰, 廖一凡, 曹伟腾, 等. 基于卷积神经网络-深度迁移学习的岩性自动识别研究[J]. 安全与环境工程, 2023, 30(4):26-34.
	XIONG Feng, LIAO Yifan, CAO Weiteng, et al. Study on automatic recognition of rock lithology based on convolutional neural network and deep transfer learning[J]. Safety and Environmental Engineering, 2023, 30(4):26-34.
[30]	赵兴东, 王宏宇, 白夜. 基于卷积神经网络迁移学习模型的矿岩智能识别方法[J]. 矿床地质, 2023, 42(5):1003-1010.
	ZHAO Xingdong, WANG Hongyu, BAI Ye. Mineralized and barren rock intelligent identification method based on convolutional neural network transfer learning model[J]. Mineral Deposits, 2023, 42(5):1003-1010.

算法	训练速度	可解释性	抗噪声能力	高维数据处理	适用场景
决策树	快	★★★★	★★	★★	小样本快速原型开发
LightGBM	极快	★★	★★★	★★★★	中等规模测井数据解释
随机森林	中等	★★★	★★★★	★★★	中等样本稳健分类
神经网络	慢	★	★★	★★★★★	复杂特征建模
K近邻	无训练	★★	★	★	特征维度小于10
极度随机树	快	★★★	★★★★★	★★★	高噪声环境（老井）

岩性	自然伽马/ API	深侧向电阻率/ （Ω·m）	声波时差/ （μs·m^-1）	中子孔隙度/ %	密度/ （g·cm^-3）	Na含量/ %	K含量/ %	Si含量/ %	Al含量/ %	Ca含量/ %	Mg含量/ %	Fe含量/ %	Mn含量/ %
流纹质凝灰岩	126.27	144.95	208.24	8.30	2.60	1.49	3.15	29.84	6.36	1.28	0.69	2.95	0.09
安山质凝灰岩	108.80	985.54	192.20	4.82	2.59	1.90	3.08	29.73	5.88	1.24	0.68	2.92	0.09
沉凝灰岩	123.51	64.59	217.05	10.76	2.64	0.99	3.01	28.93	6.65	1.33	0.91	3.55	0.08
火山角砾岩	101.22	508.50	199.55	5.35	2.57	1.71	3.14	27.61	6.20	1.85	1.05	2.78	0.09
玄武质凝灰岩	107.78	348.93	195.10	7.53	2.49	1.33	3.89	25.32	6.29	3.10	1.39	3.16	0.13
泥岩	115.25	37.77	227.68	13.99	2.59	1.42	2.86	25.36	7.21	1.66	1.09	4.15	0.11
凝灰质砂岩	92.19	201.57	207.89	11.20	2.49	1.53	2.50	25.45	6.93	1.66	1.07	3.89	0.08
含砾细砂岩	87.34	185.74	200.79	9.54	2.58	1.61	2.52	25.95	7.19	1.49	1.09	4.14	0.11
细砂岩	79.74	107.27	199.87	7.63	2.55	1.47	2.33	24.93	6.26	1.54	0.81	3.22	0.08
角砾凝灰岩	91.22	455.33	200.37	6.28	2.65	1.48	2.57	26.65	6.31	1.02	0.87	2.95	0.08
粗面安山岩	80.82	1 092.69	183.06	6.62	2.61	3.61	2.55	25.67	6.28	1.97	1.36	3.47	0.07
玄武岩	82.64	2 629.63	178.92	7.57	2.60	1.98	2.35	21.37	6.50	1.97	1.45	3.62	0.07