WANG Huaixiu，FENG Siyi，LIU Zuiliang. Geological structure recognition model based on improved random forest algorithm[J]. Coal Science and Technology，2023，51（4）：149−156
. DOI: 10.13199/j.cnki.cst.2021-0754| Citation: |
WANG Huaixiu，FENG Siyi，LIU Zuiliang. Geological structure recognition model based on improved random forest algorithm[J]. Coal Science and Technology，2023，51（4）：149−156 . DOI: 10.13199/j.cnki.cst.2021-0754
|
Seismic attributes are often used for structural interpretation and prediction. In order to overcome the problems of multiple solutions and uncertainty caused by single seismic attribute prediction, seismic multi-attribute fusion technology is used to interpret and predict geological structures. Based on the classical machine learning random forest algorithm model, an improved random forest algorithm is proposed to fuse and classify multiple seismic attributes. Combining the seismic multi-attribute fusion technology with the improved random forest algorithm, a geological structure recognition model based on the improved random forest algorithm is established. Taking the second mining area of the second belt of Shanxi Xinyuan Coal Co., Ltd. as the research area, based on the twelve seismic attributes extracted from the three-dimensional seismic exploration results, through the attribute correlation analysis and feature importance analysis of the twelve attributes, according to the results, all twelve attributes are retained for subsequent attribute fusion. Using the exposed and verified geological structure faults and collapse columns as sample labels, an improved grid search optimization algorithm is proposed. The number of classifiers and the maximum feature number of a single decision tree are combined to search the grid. The algorithm model is established based on Python language platform. The experimental results show that the prediction accuracy of the improved algorithm model reaches 97%, After subsequent model verification, it is proved that compared with several algorithms such as logistic regression, gradient lifting and decision tree, the improved random forest algorithm can more effectively identify abnormal bodies such as faults and collapse columns in geological structures, with higher recognition accuracy and wider applicability.
| [1] |
A. H. Balch. COLOR SONAGRAMS: A New Dimension In Seismic Data Interpretation[J]. A. H. Balch,2012,36(6):1043−1251.
|
| [2] |
乐友喜,王永刚. 非参数回归法在孔隙度参数预测中的应用[J]. 地质科学,2002(1):118−126. doi: 10.3321/j.issn:0563-5020.2002.01.015
LE Youxi,WANG Yonggang. Application of nonparametric regression method in porosity parameter prediction[J]. Geological Sciences,2002(1):118−126. doi: 10.3321/j.issn:0563-5020.2002.01.015
|
| [3] |
季玉新,欧 钦. 优选地震属性预测储层参数方法及应用研究[J]. 石油地球物理勘探,2003(S1):57−62,138. doi: 10.3321/j.issn:1000-7210.2003.z1.012
JI Yuxin,OU Qin. Method and application of optimizing seismic attributes to predict reservoir parameters[J]. Petroleum Geophysical Exploration,2003(S1):57−62,138. doi: 10.3321/j.issn:1000-7210.2003.z1.012
|
| [4] |
曹琳昱,朱仕军,周 强. 基于粒子群优化的BP网络在地震属性融合技术中的应用[J]. 石油与天然气地质,2010,31(05):685−688. doi: 10.11743/ogg20100519
CAO Linyu,ZHU Shijun,ZHOU Qiang. Application of BP network based on Particle Swarm Optimization in seismic attribute fusion technology[J]. Petroleum and Natural Gas Geology,2010,31(05):685−688. doi: 10.11743/ogg20100519
|
| [5] |
NISHINO KO, NAYAR SHREE K, JEBARA TONY. Clustered blockwise PCA for representing visual data. [J]. IEEE transactions on pattern analysis and machine intelligence, 2005, 27(10).
|
| [6] |
孙振宇,彭苏萍,邹冠贵. 基于SVM算法的地震小断层自动识别[J]. 煤炭学报,2017,42(11):2945−2952. doi: 10.13225/j.cnki.jccs.2017.0972
SUN Zhenyu,PENG Suping,ZOU guangui. Automatic recognition of small seismic faults based on SVM algorithm[J]. Acta coalae Sinica,2017,42(11):2945−2952. doi: 10.13225/j.cnki.jccs.2017.0972
|
| [7] |
施尚明,王 杰,段彦清. 基于RGB多地震属性融合的储层预测[J]. 黑龙江科技大学学报,2016,26(5):502−505. doi: 10.3969/j.issn.2095-7262.2016.05.007
SHI Shangming,WANG Jie,DUAN Yanqing. Reservoir prediction based on RGB multi seismic attribute fusion[J]. Journal of Heilongjiang University of Science and Technology,2016,26(5):502−505. doi: 10.3969/j.issn.2095-7262.2016.05.007
|
| [8] |
朱可丹,王雅春,衣启樊,等. 地震属性融合技术在海拉尔盆地乌东斜坡带南屯组储层预测中的应用[J]. 物探化探计算技术,2017,39(1):109−115. doi: 10.3969/j.issn.1001-1749.2017.01.16
ZHU Kedan,WANG Yachun,YI Qifan,et al. Application of seismic attribute fusion technology in reservoir prediction of Nantun Formation in Wudong slope belt of Hailar Basin[J]. Geophysical and Geochemical Exploration Calculation Technology,2017,39(1):109−115. doi: 10.3969/j.issn.1001-1749.2017.01.16
|
| [9] |
杨宏伟,吴海燕,魏国华,等. 基于概率核地震属性融合的砂体预测方法研究[J]. 地球物理学进展,2020,35(1):216−221. doi: 10.6038/pg2020CC0241
YANG Hongwei,WU Haiyan,WEI Guohua,et al. Study on sand body prediction method based on probabilistic nuclear seismic attribute fusion[J]. Progress in Geophysics,2020,35(1):216−221. doi: 10.6038/pg2020CC0241
|
| [10] |
邱 晗, 丛向元, 王 虹, 等. 地震属性融合技术在松辽盆地扶余油层砂岩预测中的应用[A]//中国石油学会石油物探专业委员会、中国地球物理学会勘探地球物理委员会. 中国石油学会2019年物探技术研讨会论文集[C]. 中国石油学会石油物探专业委员会、中国地球物理学会勘探地球物理委员会: 石油地球物理勘探编辑部, 2019: 4.
QIU Han, CONG Xiangyuan, WANG Hong, et al. Application of seismic attribute fusion technology in sandstone prediction of Fuyu reservoir in Songliao Basin [A]//Petroleum Geophysical Committee of Chinese Petroleum Society, Exploration Geophysical Committee of Chinese Geophysical Society. Proceedings of Geophysical Technology Symposium of Chinese Petroleum Society in 2019 [C]. Exploration geophysical Committee of Chinese Geophysical Society: Editorial Department of Petroleum Geophysical Exploration, 2019: 4.
|
| [11] |
BREIMAN L. Random Forests[J]. Machine Learning,2001,45:5−32.
|
| [12] |
李贞贵. 随机森林改进的若干研究[D]. 厦门: 厦门大学, 2013.
LI Zhengui. Some studies on random forest improvement [D]. Xiamen : Xiamen University, 2013
|
| [13] |
赵金超,李 仪,王 冬,等. 基于优化的随机森林心脏病预测算法[J]. 青岛科技大学学报(自然科学版),2021,42(2):112−118. doi: 10.16351/j.1672-6987.2021.02.016
Zhao Jinchao,Li Yi,Wang Dong,Zhang Junhu. Stochastic Forest heart disease prediction algorithm based on optimization[J]. Journal of Qingdao University of Science and Technology (NATURAL SCIENCE EDITION),2021,42(2):112−118. doi: 10.16351/j.1672-6987.2021.02.016
|
| [14] |
MD NASIM ADNAN, MD ZAHIDUL ISLAM. Optimizing the number of trees in a decision forest to discover a subforest with high ensemble accuracy using a genetic algorithm[J]. Knowledge-Based Systems, 2016, 110.
|
| [15] |
温博文,董文瀚,解武杰,等. 基于改进网格搜索算法的随机森林参数优化[J]. 计算机工程与应用,2018,54(10):154−157. doi: 10.3778/j.issn.1002-8331.1612-0328
WEN Bowen,DONG Wenhan,XIE WuJie,et al. optimization of random forest parameters based on improved grid search algorithm[J]. Computer Engineering and Application,2018,54(10):154−157. doi: 10.3778/j.issn.1002-8331.1612-0328
|
| [16] |
LIU Xiao, SONG Mingli, TAO Dacheng, et al. Random forest construction with robust semisupervised node splitting. [J]. IEEE Transactions on image Processing : A Publication of the IEEE Signal Processing Society, 2015, 24(1).
|
| [17] |
赵 东,臧雪柏,赵宏伟. 基于果蝇优化的随机森林预测方法[J]. 吉林大学学报(工学版),2017,47(2):609−614. doi: 10.13229/j.cnki.jdxbgxb201702036
ZHAO Dong,ZANG Xuebai,ZHAO Hongwei. Random forest prediction method based on Drosophila optimization[J]. Journal of Jilin University (Engineering Edition),2017,47(2):609−614. doi: 10.13229/j.cnki.jdxbgxb201702036
|
| [18] |
石文兵,苏树智. 基于优化随机森林算法的高校餐饮企业营业额预测模型[J]. 通化师范学院学报,2021,42(2):88−94. doi: 10.13877/j.cnki.cn22-1284.2021.02.015
SHI Wenbing,SU Shuzhi. Turnover prediction model of University catering enterprises based on optimized random forest algorithm[J]. Journal of Tonghua Normal University,2021,42(2):88−94. doi: 10.13877/j.cnki.cn22-1284.2021.02.015
|
| [19] |
邹冠贵,任 珂,吉 寅,等. 基于主成分分析和最近邻算法的断层识别研究[J]. 煤田地质与勘探,2021,49(4):15−23.
ZOU guangui,REN Ke,JI Yin,et al. Fault recognition based on principal component analysis and nearest neighbor algorithm[J]. Coal geology and Exploration,2021,49(4):15−23.
|
| [20] |
董守华,石亚丁,汪 洋. 地震多参数BP人工神经网络自动识别小断层[J]. 中国矿业大学学报,1997,4(3):16−20. doi: 10.3321/j.issn:1000-1964.1997.03.004
DONG Shouhua,SHI Yading,WANG Yang. Automatic identification of small faults by BP artificial neural network with multi parameters[J]. Journal of China University of Mining and Technology,1997,4(3):16−20. doi: 10.3321/j.issn:1000-1964.1997.03.004
|
| [21] |
刘冬花. 陷落柱对煤矿安全的影响[J]. 内蒙古煤炭经济,2014,4(11):148,165. doi: 10.3969/j.issn.1008-0155.2014.11.095
LIU Donghua. Influence of collapse column on coal mine safety[J]. Inner Mongolia Coal Economy,2014,4(11):148,165. doi: 10.3969/j.issn.1008-0155.2014.11.095
|
| [22] |
庄益明. 煤层小断层地震多属性精细解释方法研究[D]. 徐州: 中国矿业大学, 2018.
ZHUANG Yiming. Research on seismic multi-attribute fine interpretation method of small fault in coal seam [D]. Xuzhou: China University of Mining and Technology, 2018
|
| [1] | ZHANG Cun, JIA Sheng, HUA Ye, SONG Qi. Research progress of mine 3D geological modeling: Principle, method and application[J]. COAL SCIENCE AND TECHNOLOGY, 2025, 53(2): 222-238. DOI: 10.12438/cst.2024-1743 |
| [2] | LIAN Huiqing, YAN Tao, YIN Shangxian, XU Bin, KANG Jia, ZHOU Wang, YAN Guocheng. Research on early warning of roof water inrush in working faces based on a transparent hydrogeological model[J]. COAL SCIENCE AND TECHNOLOGY, 2025, 53(1): 259-271. DOI: 10.12438/cst.2024-0713 |
| [3] | LUO Yunxiu, MAO Shanjun, ZHANG Pengpeng, LI Zhen, MA Yuanping, WANG Yanbin, TENG Yan. Research and application of coal exploration data management method in working face based on GIS[J]. COAL SCIENCE AND TECHNOLOGY, 2022, 50(12): 254-261. DOI: 10.13199/j.cnki.cst.2021-0511 |
| [4] | SHI Xinxiao, WANG Jian, SUN Wenxiao. 3D reconstruction of geological body based on tetrahedron model[J]. COAL SCIENCE AND TECHNOLOGY, 2022, 50(11): 150-155. |
| [5] | CHENG Jianyuan, LIU Wenming, ZHU Mengbo, YU Beijian, WANG Yi, ZHANG Zeyu. Experimental study on cascade optimization of geological models in intelligent mining transparency working face[J]. COAL SCIENCE AND TECHNOLOGY, 2020, 48(7). |
| [6] | SUN Yuecheng, LI Yongfei, SUN Shouliang. Research on key technologies and new method of high precision 3D geological modeling[J]. COAL SCIENCE AND TECHNOLOGY, 2019, (9). |
| [7] | GAO Lijun, PANG Jiandong, XIE Yinggang, ZHOU Longgang. Analysis on potential geological mining model of deep coalbedmethane in Linxing Block[J]. COAL SCIENCE AND TECHNOLOGY, 2019, (9). |
| [8] | QIN Muguang, ZHAO Xusheng, ZHANG Qinghua, YUE Jun, ZOU Yunlong. Study on outburst early warning model based on gas geological features[J]. COAL SCIENCE AND TECHNOLOGY, 2018, (12). |
| [9] | LIU Guangwei SONG Jiachen BAI Runcai LI Peng, . Study on accuracy evaluation of 3D geological model based on C-F Method[J]. COAL SCIENCE AND TECHNOLOGY, 2017, (11). |
| [10] | Design and Practices on Geological-Measure Space Management Information System of Steep Inclined Seam[J]. COAL SCIENCE AND TECHNOLOGY, 2011, (11). |
| 1. |
刘晋云, 阚宝祥, 陈元恪, 邢雪良. 基于机器学习方法分析新安江地震台钻孔体应变观测影响因素. 地震地磁观测与研究. 2025(02)
| |
| 2. |
刘俊杰，马凯，黄泽华，田苗，邱芹军，陶留锋，谢忠. 基于迁移学习及通道先验注意力机制的地质构造识别. 广西师范大学学报(自然科学版). 2025(02): 107-120 .
| |
| 3. |
甘盟，刘攀峰，岳大斌，文美兰，高文，邓鹏，陈若，叶伟. 基于随机森林算法的川西木绒锂矿区及外围地电化学技术找矿预测. 地质与勘探. 2025(02): 359-370 .
| |
| 4. |
赵玉程，李英建，沈世民，韩玉喜，宋杰. 基于网格搜索和投票分类模型的喷油器故障诊断研究. 机床与液压. 2024(05): 213-220 .
| |
| 5. |
肖观红，鲁海峰. 基于PCA-GA-RF的矿井突水水源快速识别模型. 煤矿安全. 2024(06): 184-191 .
|
Supported by: Beijing Renhe Information Technology Co., Ltd. 
DownLoad: