A dynamic prediction method for coal seam thickness based on the KPCA-PSO-SVR model

Authors

YANG Tun, CCTEG Xi’an Research Institute (Group) Co., Ltd., Xi’an 710077, ChinaFollow
YE Shugang, CCTEG Xi’an Research Institute (Group) Co., Ltd., Xi’an 710077, China
MA Ming, CCTEG Xi’an Research Institute (Group) Co., Ltd., Xi’an 710077, China
WANG Qianyao, CCTEG Xi’an Research Institute (Group) Co., Ltd., Xi’an 710077, China

Abstract

Objectives and Methods With the development of high-precision and intelligent seismic exploration techniques, it is necessary to accurately quantify and interpret coal seam thickness to provide reliable data for constructing high-precision three-dimensional geological models. This will help ensure safe and efficient coal mining in coal mines. In coal seam thickness prediction, the comprehensive multi-attribute analysis method faces challenges such as the cumbersome selection of optimal seismic attributes and the low predictive accuracy of regression models. To address these challenges, this study proposed a support vector regression (SVR) prediction model based on kernel principal component analysis (KPCA) and particle swarm optimization (PSO) (also referred to as the KPCA-PSO-SVR model). This model employed KPCA for dimensionality reduction to reduce redundant information in seismic attributes. By combining the PSO algorithm, this model automatically optimized the hyperparameters (penalty coefficient c and kernel function parameter γ) of the SVR model, thereby overcoming the limitations of empirical parameter adjustments and effectively improving the prediction accuracy and efficiency. Furthermore, the introduction of an incremental learning mechanism, integrated with the dynamic incorporation of actual data revealed by mining faces, enabled the model to achieve dynamic quantitative interpretation of the coal seam thickness. Results and Conclusions Numerical analysis of the wedge-shaped forward model demonstrated that the dimensionality reduction via KPCA optimized multi-attribute combinations, providing high-quality data for the regression analysis model. The quantitative comparison of the prediction results of different models indicates that the KPCA-PSO-SVR model yielded a coefficient of determination (R²) of 0.9667, outperforming traditional SVR, PSO-SVR, grey wolf optimizer (GWO)-SVR, and back propagation neural network (BP-Net) models. Both the KPCA-PSO-SVR and PSO-SVR models exhibited high prediction accuracy and computational efficiency under varying proportions of training datasets. Field application to a survey area demonstrates that the KPCA-PSO-SVR model displayed excellent robustness and generalization capability under a small sample size in the coal mining area. This model yielded an R² value of 0.9858, higher than the values of its counterparts. After incremental training was conducted by incorporating actual data revealed by roadways of the mining face into the model, the maximum absolute error of the predicted thickness decreased from 0.622 m to 0.178 m, further enhancing the model’s adaptability and predictive performance. The KPCA-PSO-SVR model provides an effective technical solution for coal seam thickness interpretation, holding great significance for engineering applications.

Keywords

prediction of coal seam thickness, seismic attribute, kernel principal component analysis (KPCA), particle swarm optimization (PSO), support vector regression (SVR), dynamic prediction model

DOI

10.12363/issn.1001-1986.25.04.0248

Recommended Citation

YANG Tun, YE Shugang, MA Ming, et al. (2026) "A dynamic prediction method for coal seam thickness based on the KPCA-PSO-SVR model," Coal Geology & Exploration: Vol. 54: Iss. 3, Article 22.
DOI: 10.12363/issn.1001-1986.25.04.0248
Available at: https://cge.researchcommons.org/journal/vol54/iss3/22

Reference

[1] 罗忠琴，刘鹏，唐建益，等. 煤矿隐蔽致灾因素地震勘探现状与发展方向[J]. 中国煤炭，2023，49(1)：16−29.

LUO Zhongqin，LIU Peng，TANG Jianyi，et al. Present situtation and development direction of seismic exploration technology for hidden disaster-causing factors in coal mine[J]. China Coal，2023，49(1)：16−29.

[2] 彭苏萍. 我国煤矿安全高效开采地质保障系统研究现状及展望[J]. 煤炭学报，2020，45(7)：2331−2345.

PENG Suping. Current status and prospects of research on geological assurance system for coal mine safe and high efficient mining[J]. Journal of China Coal Society，2020，45(7)：2331−2345.

[3] 李启成，郭雷，孙颍川，等. 地震属性融合技术在煤层厚度预测中的研究[J]. 地球物理学进展，2017，32(5)：2014−2020.

LI Qicheng，GUO Lei，SUN Yingchuan，et al. Seismic attributes fusion and its research in predicting thickness of coal[J]. Progress in Geophysics，2017，32(5)：2014−2020.

[4] 索重辉，常锁亮，彭仕宓，等. 地震属性在煤层厚度预测上的分析与应用[J]. 科学技术与工程，2011，11(34)：8429−8433.

SUO Chonghui，CHANG Suoliang，PENG Shimi，et al. Study and application of seismic attributes on coal seam thickness prediction[J]. Science Technology and Engineering，2011，11(34)：8429−8433.

[5] 单蕊. 地震多属性分析技术在煤层厚度预测中的应用分析[J]. 物探化探计算技术，2021，43(3)：304−310.

SHAN Rui. Application of seismic multi–attribute analysis technique in coal seam thickness prediction[J]. Computing Techniques for Geophysical and Geochemical Exploration，2021，43(3)：304−310.

[6] 张玉忠，杨永波. 运用地震属性技术预测煤层厚度[J]. 煤炭技术，2009，28(3)：126−129.

ZHANG Yuzhong，YANG Yongbo. Forecast coal seam thickness by seismic attributes technology[J]. Coal Technology，2009，28(3)：126−129.

[7] 赵加凡，陈小宏. 基于主成分分析与K–L变换的双重属性优化方法[J]. 物探与化探，2005，29(3)：253−256.

ZHAO Jiafan，CHEN Xiaohong. Dual optimization of seismic attributes based on principal component analysis and K–L transform[J]. Geophysical and Geochemical Exploration，2005，29(3)：253−256.

[8] 程建远. 三维地震资料微机解释性处理技术[M]. 北京：石油工业出版社，2002.

[9] 章聚翰. 基于PCA–RBF神经网络模型的煤层厚度预测[J]. 陕西煤炭，2023，42(4)：136−139.

ZHANG Juhan. Prediction of coal seam thickness based on PCA–RBF neural network[J]. Shaanxi Coal，2023，42(4)：136−139.

[10] 李海霞，吴苏怡. 基于主成分分析方法的海量地震数据属性降维优化[J]. 地震工程学报，2019，41(3)：757−762.

LI Haixia，WU Suyi. Attribute reduction and optimization for massive seismic data based on principal component analysis[J]. China Earthquake Engineering Journal，2019，41(3)：757−762.

[11] SCHÖLKOPF B，SMOLA A，MÜLLER K R. Nonlinear component analysis as a kernel eigenvalue problem[J]. Neural Computation，1998，10(5)：1299−1319.

[12] 郑静静，王延光，杜磊，等. 基于概率核主成分分析的属性优化方法及其应用[J]. 石油地球物理勘探，2014，49(3)：567−571.

ZHENG Jingjing，WANG Yanguang，DU Lei，et al. Attribute optimization based on the probability kernel principal component analysis[J]. Oil Geophysical Prospecting，2014，49(3)：567−571.

[13] 郭彦省，孟召平，杨瑞昭，等. 地震属性及其在煤层厚度预测中的应用[J]. 中国矿业大学学报，2004，33(5)：557−562.

GUO Yansheng，MENG Zhaoping，YANG Ruizhao，et al. Seismic attributions analysis and it’s application in predicting thickness of coal[J]. Journal of China University of Mining & Technology，2004，33(5)：557−562.

[14] 李刚. 基于BP算法的煤层厚度预测技术应用研究[J]. 中国煤炭地质，2011，23(5)：45−48.

LI Gang. An applied research on coal thickness prediction technology based on BP algorithm[J]. Coal Geology of China，2011，23(5)：45−48.

[15] 梁耍，王世博，谢洋，等. 基于LSTM的煤层厚度动态预测方法研究[J]. 煤炭科学技术，2021，49(增刊1)：150−157.

LIANG Shua，WANG Shibo，XIE Yang，et al. Dynamic prediction method of coal seam thickness based on LSTM[J]. Coal Science and Technology，2021，49(Sup.1)：150−157.

[16] 刘晓明，王新，徐慧. 基于多目标随机森林的煤层厚度同步预测方法[J]. 计算机工程与设计，2021，42(4)：1116−1121.

LIU Xiaoming，WANG Xin，XU Hui. Synchronous prediction method for coal thickness based on multi–objective random forest[J]. Computer Engineering and Design，2021，42(4)：1116−1121.

[17] 陈同俊，王新，管永伟. 基于SVR和地震属性的构造煤厚度定量预测[J]. 煤炭学报，2015，40(5)：1103−1108.

CHEN Tongjun，WANG Xin，GUAN Yongwei. Quantitative prediction of tectonic coal seam thickness using support vector regression and seismic attributes[J]. Journal of China Coal Society，2015，40(5)：1103−1108.

[18] 曾爱平，张嘉玮，任恩明，等. 基于VMD和SVM的煤厚预测方法研究[J]. 煤田地质与勘探，2021，49(6)：243−250.

ZENG Aiping，ZHANG Jiawei，REN Enming，et al. Research on the coal thickness prediction method based on VMD and SVM[J]. Coal Geology & Exploration，2021，49(6)：243−250.

[19] 尹海洋，陈同俊，宋雄，等. 基于地震属性优化和机器学习的煤层厚度预测方法[J]. 煤田地质与勘探，2023，51(5)：164−170.

YIN Haiyang，CHEN Tongjun，SONG Xiong，et al. Methods for predicting the thickness of coal seams based on seismic attribute optimization and machine learning[J]. Coal Geology & Exploration，2023，51(5)：164−170.

[20] CORTES C，VAPNIK V. Support–vector networks[J]. Machine Learning，1995，20(3)：273−297.

[21] 沈加刚，宋宗平，关晓巍. 基于地震属性的支持向量机河道砂体厚度预测[J]. 西南石油大学学报(自然科学版)，2014，36(3)：75−81.

SHEN Jiagang，SONG Zongping，GUAN Xiaowei. Application of support vector machine to the prediction of the thickness of channel sand based on seismic attributes[J]. Journal of Southwest Petroleum University (Science & Technology Edition)，2014，36(3)：75−81.

[22] 李文俊，岳大力，何贤科，等. 地质模式约束的SVR属性融合在浅水三角洲储层描述中的应用：以西湖凹陷X气田为例[J]. 地质科技通报，2021，40(6)：106−113.

LI Wenjun，YUE Dali，HE Xianke，et al. Application of SVR attribute fusion constrained by geological model in reservoir description of shallow water delta：A case study of X gas field in Xihu sag[J]. Bulletin of Geological Science and Technology，2021，40(6)：106−113.

[23] SMOLA A J，SCHÖLKOPF B. A tutorial on support vector regression[J]. Statistics and Computing，2004，14(3)：199−222.

[24] CHAPELLE O，VAPNIK V，BOUSQUET O，et al. Choosing multiple parameters for support vector machines[J]. Machine Learning，2002，46(1)：131−159.

[25] 李素，袁志高，王聪，等. 群智能算法优化支持向量机参数综述[J]. 智能系统学报，2018，13(1)：70−84.

LI Su，YUAN Zhigao，WANG Cong，et al. Optimization of support vector machine parameters based on group intelligence algorithm[J]. CAAI Transactions on Intelligent Systems，2018，13(1)：70−84.

[26] KENNEDY J，EBERHART R. Particle swarm optimization[C]// Proceedings of ICNN’95–International Conference on Neural Networks. Perth：IEEE，1995：1942–1948.

[27] 张宪旭. 基于模型驱动的煤层强反射能量衰减方法[J]. 煤田地质与勘探，2020，48(3)：188−194.

ZHANG Xianxu. Model–driven energy attenuation method for coal seam strong reflection[J]. Coal Geology & Exploration，2020，48(3)：188−194.

[28] 吴海波，张平松，董守华. 分叉煤层时间域分辨率的探讨[J]. 地球物理学进展，2018，33(4)：1603−1608.

WU Haibo，ZHANG Pingsong，DONG Shouhua. Discussion on resolution of bifurcate coal seam in time–domain[J]. Progress in Geophysics，2018，33(4)：1603−1608.

[29] 袁卫，庞皓，曾五一. 统计学[M]. 北京：高等教育出版社，2000.

[30] MIRJALILI S，MIRJALILI S M，LEWIS A. Grey wolf optimizer[J]. Advances in Engineering Software，2014，69：46−61.

[31] 张长开，姜秀娣，朱振宇，等. 基于支持向量机的属性优选和储层预测[J]. 石油地球物理勘探，2012，47(2)：282−285.

ZHANG Changkai，JIANG Xiudi，ZHU Zhenyu，et al. Attributes selection and reservoir prediction based on support vector machine[J]. Oil Geophysical Prospecting，2012，47(2)：282−285.