PREDICTION OF OIL-GAS RESOURCES IN SONGNEN PLAIN BASED ON SOIL GEOCHEMICAL DATA AND BACK-PROPAGATION NEURAL NETWORK
-
摘要:
基于东北地区多目标区域地球化学调查获得的海量土壤地球化学数据, 利用BP神经网络模型, 在土壤地球化学性质与油气田空间位置之间建立模型, 构造最优的油气资源预测模型. 以土壤54项地球化学指标以及XY坐标值共同作为模型输入层, 以样本是否在油气田内(1代表油气田内, 0代表油气田外)作为模型输出层, 基于随机抽取的油气田内和油气田外各500个土壤样本数据进行模型训练. 结果显示, 多次训练后识别准确率保持在90%左右, 说明该模型分类效果较好, 可用于油气资源预测. 利用该模型获得了松嫩平原11 291个土壤样本的含油气概率, 并绘制了油气资源预测图. 研究表明, 神经网络对于解决复杂的非线性地质问题可以发挥重要作用.
Abstract:Based on the massive data obtained from the multi-target regional geochemical survey in Northeast China, the back-propagation(BP) neural network is used to establish the model between soil geochemical property and spatial location of oil-gas fields, and construct the optimal prediction model of oil-gas resources. Taking both the 54 soil geochemical indexes and XY coordinate values as input layer of the model and whether the samples are inside the oil-gas fields (1 for inside, 0 for outside) as output layer, the study carries out the model training based on the data of each 500 soil samples randomly selected from inside and outside the oil-gas fields. The results show that the recognition accuracy remains at about 90% after repeated training, indicating that the model has good classification effect and can be used for prediction of oil-gas resources. The hydrocarbon-bearing probability of 11 291 soil samples from Songnen Plain is obtained by using the model, and then the prediction map of oil-gas resources is drawn. The study shows that neural network can play an important role in solving complex nonlinear geological problems.
-
Key words:
- neural network /
- prediction model /
- soil geochemistry /
- oil-gas resources /
- big data /
- Songnen Plain
-
-
表 1 样本含油气概率预测结果统计表
Table 1. Prediction results for the hydrocarbon-bearing probability of samples
含油概率/% 样本数量/个 含油概率/% 样本数量/个 ＜0.1 7076 0.5~0.6 295 0.1~0.2 574 0.6~0.7 321 0.2~0.3 405 0.7~0.8 309 0.3~0.4 337 0.8~0.9 541 0.4~0.5 295 0.9~1 1138 
下载: 导出CSV
-
[1] 吴传璧. 中国油气化探50年[J]. 地质通报, 2009, 28(11): 1572-1604. doi: 10.3969/j.issn.1671-2552.2009.11.007
Wu C B. Fifty years history of Chinese oil and gas geochemical exploration[J]. Geological Bulletin of China, 2009, 28(11): 1572-1604. doi: 10.3969/j.issn.1671-2552.2009.11.007
[2] 李括, 彭敏, 赵传冬, 等. 全国土地质量地球化学调查二十年[J]. 地学前缘, 2019, 26(6): 128-158. https://www.cnki.com.cn/Article/CJFDTOTAL-DXQY201906020.htm
Li K, Peng M, Zhao C D, et al. Vicennial implementation of geochemical survey of land quality in China[J]. Earth Science Frontiers, 2019, 26(6): 128-158. https://www.cnki.com.cn/Article/CJFDTOTAL-DXQY201906020.htm
[3] 赵君, 汪月华, 张哲寰. 多目标地球化学调查数据在松嫩平原油气藏远景预测的应用[J]. 地质与资源, 2020, 29(6): 635-640, 626. http://manu25.magtech.com.cn/Jweb_dzyzy/CN/abstract/abstract10258.shtml
Zhao J, Wang Y H, Zhang Z H. Application of multi-target geochemical survey data in prospect prediction of the oil-gas reservoirs in Songnen Plain[J]. Geology and Resources, 2020, 29(6): 635-640, 626. http://manu25.magtech.com.cn/Jweb_dzyzy/CN/abstract/abstract10258.shtml
[4] 周亚龙, 孙忠军, 杨志斌, 等. 多目标化探数据与油气藏指标特征的相关性研究[J]. 物探与化探, 2015, 39(3): 466-472. https://www.cnki.com.cn/Article/CJFDTOTAL-WTYH201503005.htm
Zhou Y L, Sun Z J, Yang Z B, et al. The correlation study of multi-objective geochemical data and index characteristics of the oil and gas reservoir[J]. Geophysical and Geochemical Exploration, 2015, 39(3): 466-472. https://www.cnki.com.cn/Article/CJFDTOTAL-WTYH201503005.htm
[5] 刘艳鹏, 朱立新, 周永章. 卷积神经网络及其在矿床找矿预测中的应用——以安徽省兆吉口铅锌矿床为例[J]. 岩石学报, 2018, 34 (11): 3217-3224.
Liu Y P, Zhu L X, Zhou Y Z. Application of convolutional neural network in prospecting prediction of ore deposits: Taking the Zhaojikou Pb-Zn ore deposit in Anhui Province as a case[J]. Acta Petrologica Sinica, 34(11): 2018, 34(11): 3217-3224.
[6] 翟明国, 杨树锋, 陈宁华, 等. 大数据时代: 地质学的挑战与机遇[J]. 中国科学院院刊, 2018, 33(8): 825-831. https://www.cnki.com.cn/Article/CJFDTOTAL-KYYX201808012.htm
Zhai M G, Yang S F, Chen N H, et al. Big data epoch: Challenges and opportunities for geology[J]. Bulletin of Chinese Academy of Sciences, 2018, 33(8): 825-831. https://www.cnki.com.cn/Article/CJFDTOTAL-KYYX201808012.htm
[7] 陈坤, 张建新. 基于神经网络模型的金矿成矿远景预测——以白马山-龙山地区为例[J]. 地质与资源, 2015, 24(2): 160-163. doi: 10.3969/j.issn.1671-1947.2015.02.015 http://manu25.magtech.com.cn/Jweb_dzyzy/CN/abstract/abstract8722.shtml
Chen K, Zhang J X. Prediction of gold metallogenic prospect based on the neural network model: A case study of the Baimashan-Longshan area in Hunan Province[J]. Geology and Resources, 2015, 24(2): 160-163. doi: 10.3969/j.issn.1671-1947.2015.02.015 http://manu25.magtech.com.cn/Jweb_dzyzy/CN/abstract/abstract8722.shtml
[8] 赵健, 刘展, 樊彦国, 等. BP神经网络精度估计及其在海洋油气资源预测中的应用[J]. 海洋科学, 2018, 42(11): 59-63. https://www.cnki.com.cn/Article/CJFDTOTAL-HYKX201811008.htm
Zhao J, Liu Z, Fan Y G, et al. Precision estimation of BP neural network and its application in ocean oil and gas resources prediction [J]. Marine Sciences, 2018, 42(11): 59-63. https://www.cnki.com.cn/Article/CJFDTOTAL-HYKX201811008.htm
[9] 陈剑平. 基于MATLAB的神经网络模式识别技术在油气化探中的研究及应用[D]. 北京: 中国地质大学, 2008.
Chen J P. The research and application of neural network pattern recognition technique for oil and gas[D]. Beijing: China University of Geosciences, 2008.
[10] 郑春雷, 史忠科. 基于神经网络的油气预测方法[J]. 西北工业大学学报, 2003, 21(5): 574-577. https://www.cnki.com.cn/Article/CJFDTOTAL-XBGD200305016.htm
Zheng C L, Shi Z K. Neural network prediction method and its application to oil and gas forecast[J]. Journal of Northwestern Polytechnical University, 2003, 21(5): 574-577. https://www.cnki.com.cn/Article/CJFDTOTAL-XBGD200305016.htm
[11] 王焕弟, 李明, 赵一民. 有监督的人工神经网络油气预测[J]. 铀矿地质, 2001, 17(1): 33, 48-55. https://www.cnki.com.cn/Article/CJFDTOTAL-YKDZ200101006.htm
Li H D, Li M, Zhao Y M. Research on supervised artificial neural network oil and gas prediction[J]. Uranium Geology, 2001, 17(1): 33, 48-55. https://www.cnki.com.cn/Article/CJFDTOTAL-YKDZ200101006.htm
[12] 杨丽娜, 解国军. 油气资源丰度预测的人工神经网络方法——以济阳坳陷为例[J]. 石油天然气学报(江汉石油学院学报), 2007, 29(1): 4, 55-58. https://www.cnki.com.cn/Article/CJFDTOTAL-JHSX200701014.htm
Yang L N, Xie G J. Artificial neural network method for oil and gas resource prediction-a case study of Jiyang depression[J]. Journal of Oil and Gas Technology(Journal of Jianghan Petroleum Institute), 2007, 29(1): 4, 55-58. https://www.cnki.com.cn/Article/CJFDTOTAL-JHSX200701014.htm
[13] 奚小环. 大数据与地球系统科学——再论全面发展时期的勘查地球化学[J]. 物探与化探, 2019, 43(3): 449-460. https://www.cnki.com.cn/Article/CJFDTOTAL-WTYH201903001.htm
Xi X H. Natural resources period: Big data and systematic science of the earth-more on exploration geochemistry during the overall development period[J]. Geophysical and Geochemical Exploration, 2019, 43(3): 449-460. https://www.cnki.com.cn/Article/CJFDTOTAL-WTYH201903001.htm
[14] 郭昂青. 松辽盆地油田开发建设对地质环境的负面影响——以大庆油田为例[J]. 地质与资源, 2016, 25(2): 176-180. http://manu25.magtech.com.cn/Jweb_dzyzy/CN/abstract/abstract8625.shtml
Guo A Q. Negative effect of the development and construction in the oilfield in Songliao Basin on geological environment: A case study of Daqing Oilfield[J]. Geology and Resources, 2016, 25(2): 176-180. http://manu25.magtech.com.cn/Jweb_dzyzy/CN/abstract/abstract8625.shtml
[15] 中华人民共和国国土资源部. DZ/T 0258—2014多目标区域地球化学调查规范(1∶250 000)[S]. 北京: 中国标准出版社, 2014: 1-42.
Ministry of Land and Resources of the People's Republic of China. DZ/T 0258—2014 Specification of multi-purpose regional geochemical survey(1∶250 000)[S]. Beijing: Standard Press of China, 2014: 1-42.
[16] Lappmann R P. An introduction to computing with neural nets[J]. IEEE ASSP Magazine, 1987, 4(42): 4-22.
[17] 白静, 徐兴友, 陈珊, 等. 松辽盆地长岭凹陷乾安地区青山口组一段沉积相特征与古环境恢复——以吉页油1井为例[J]. 中国地质, 2020, 47(1): 220-235. https://www.cnki.com.cn/Article/CJFDTOTAL-DIZI202001019.htm
Bai J, Xu X Y, Chen S, et al. Sedimentary characteristics and paleo-environment restoration of the First Member of Qingshankou Formation in Qian'an area, Changling sag, Songliao Basin: A case study of Jiyeyou 1 Well[J]. Geology in China, 2020, 47(1): 220-235. https://www.cnki.com.cn/Article/CJFDTOTAL-DIZI202001019.htm
[18] 孙圆辉, 沈平平, 阮宝涛, 等. 松辽盆地长岭断陷长深1号气田火山岩岩性及储渗特征研究[J]. 天然气地球科学, 2008, 19(5): 630-633. https://www.cnki.com.cn/Article/CJFDTOTAL-TDKX200805011.htm
Sun Y H, Shen P P, Yuan B T, et al. Lithologic and storage-permeation characteristics of Changshen 1 volcanic gas reservoirs in Jilin[J]. Natural Gas Geoscience, 2008, 19(5): 630-633. https://www.cnki.com.cn/Article/CJFDTOTAL-TDKX200805011.htm
[19] 张庆国, 鲍志东, 郭雅君, 等. 扶余油田扶余油层的浅水三角洲沉积特征及模式[J]. 大庆石油学院学报, 2007, 31(3): 4-7, 14. https://www.cnki.com.cn/Article/CJFDTOTAL-DQSY200703002.htm
Zhang Q G, Bao Z D, Guo Y J, et al. Sedimentary characteristics and model of the Fuyu oil bearing reservoir in Fuyu Oil Field[J]. Journal of Daqing petroleum institute, 2007, 31(3): 4-7, 14. https://www.cnki.com.cn/Article/CJFDTOTAL-DQSY200703002.htm
[20] Li S, Chen J, Xiang J. Applications of deep convolutional neural networks in prospecting prediction based on two-dimensional geological big data[J]. Neural Computing and Applications, 2020, 32(7): 2037-2053.
[21] Chen J P, Xiang J, Hu Q, et al. Quantitative geoscience and geological big data development: a review[J]. Acta Geologica Sinica, 2016, 90(4): 1490-1515.
-
图(6)
表(1)
计量
- 文章访问数: 1183
- PDF下载数: 27
- 施引文献: 0