基于深度学习的钨钼找矿靶区预测方法研究
|
摘要
随着矿产勘查工作由浅部矿向深部隐伏矿、由易识别矿向难识别矿发展,找矿难度日益增大,地质专家越来越重视新理论、新方法、新技术的应用。深度学习作为人工智能的前沿领域/技术,对于实现矿产资源预测"智能化预测评价"具有得天独厚的优势。本文以陕西省镇安县西部钨钼矿集区单元素化探异常原始数据为基础,提出了基于深度学习的钨钼矿产评价方法。该方法以归一化地球化学数据作为模型训练数据,通过深度学习中深度自编码网络方法实现异常值提取进而识别重点成矿有利地段,实现矿产资源找矿远景区定性预测。研究结果表明,在对957条单元素化探异常原始数据分类且做好模型标签后,整个过程在计算机的"黑盒子"中自动完成学习和预测,相较于传统预测研究方法,本文方法具有自动化程度高和客观性强的特征。此外,本文利用已知矿点构建训练数据集,采用随机森林方法对预测区进行矿产资源找矿靶区预测圈定,为进一步缩小找矿靶区范围提供科学依据。
With the exploration of minerals from shallow mines to deep concealed mines, from easy-to-identify mines to difficult-to-identify mines, the difficulty of prospecting is increasing, and geological experts are paying more and more attention to the application of new theories, new methods, and new technologies. As a frontier field and technology of artificial intelligence, deep learning has a unique advantage in realizing the intelligent forecasting and evaluation of mineral resources. The method uses normalized geochemical data as the training data to extract outliers by a neural network called Autoencoder and identify the favorable mineralization areas,and then realizes the qualitative prediction of mineral resources prospecting prospect. The research results show that after classifying the original data of 957 single elements geochemical anomalies and labeling of the model,the whole process automatically completes the learning and prediction in the "black box" of the computer,compared with the traditional prediction research method, this method of research is highly automated and objective. In addition, this paper uses the known mine sites to construct the training dataset, and uses the random forest method to predict the mineral resources prospecting target area in the prediction area, which provides a scientific basis for further narrowing the scope of the prospecting target area.
With the exploration of minerals from shallow mines to deep concealed mines, from easy-to-identify mines to difficult-to-identify mines, the difficulty of prospecting is increasing, and geological experts are paying more and more attention to the application of new theories, new methods, and new technologies. As a frontier field and technology of artificial intelligence, deep learning has a unique advantage in realizing the intelligent forecasting and evaluation of mineral resources. The method uses normalized geochemical data as the training data to extract outliers by a neural network called Autoencoder and identify the favorable mineralization areas,and then realizes the qualitative prediction of mineral resources prospecting prospect. The research results show that after classifying the original data of 957 single elements geochemical anomalies and labeling of the model,the whole process automatically completes the learning and prediction in the "black box" of the computer,compared with the traditional prediction research method, this method of research is highly automated and objective. In addition, this paper uses the known mine sites to construct the training dataset, and uses the random forest method to predict the mineral resources prospecting target area in the prediction area, which provides a scientific basis for further narrowing the scope of the prospecting target area.
引文
[1]严光生,薛群威,肖克炎,等.地质调查大数据研究的主要问题分析[J].地质通报,2015,34(7):1273-1279.[Yan G S, Xue Q W, Xiao K Y, et al. An analysis of major problems in geological survey big data[J]. Geological Bulletin of China, 2015,34(7):1273-1279.]
[2]黄宜华.大数据机器学习系统研究进展[J].大数据,2015,1(1):35-54.[Huang Y H. Research progress on big data machine learning system[J]. Big Data Research, 2015,1(1):35-54.]
[3] John Zukowsi. Java2从入门到精通[M].北京:电子工业出版社,2000.[John Zukowsi. Java 2:From entry to mastery[M]. Beijing:Electronic Industry Press, 2000.]
[4]黄林军,张勇,郭冰榕.机器学习技术在数据挖掘中的商业应用[J].中山大学学报论丛,2005(6):145-148.[Huang L J, Zhang Y, Guo B R. Commercial application of machine learning technology in data mining[J]. Sun Yatsen University Forum, 2005(6):145-148.]
[5]阴江宁,肖克炎,何凯涛,等.铜矿数字矿床模型专家系统的原理与技术实现[J].地质论评,2009,55(3):449-456.[Yin J N, Xiao K Y, He K T, et al. Principle and technology realization of copper mine digital deposit model expert system[J]. Geological Review, 2009,55(3):449-456.]
[6]于萍萍,陈建平,柴福山,等.基于地质大数据理念的模型驱动矿产资源定量预测[J].地质通报,2015,34(7):1333-1343.[Yu P P, Chen J P, Chai F S, et al. Research on model-driven quantitative prediction and evaluation of mineral resources based on geological big data concept[J]. Geological Bulletin of China, 2015,34(7):1333-1343.]
[7]朱月琴,谭永杰,张建通,等.基于Hadoop的地质大数据融合与挖掘技术框架[J].测绘学报,2015,44(S1):152-159.[Zhu Y Q, Tan Y J, Zhang J T, et al. A framework of hadoop based geologhy big data fusion and mining technologies[J]. Acta Geodaetica et Cartographica Sinica,2015,44(S1):152-159.]
[8]王晓.大数据环境下机器学习算法趋势研究[J].哈尔滨师范大学:自然科学学报,2013,29(4):48-50.[Wang X. Research on trends of machine learning algorithms in big data environments[J]. Natural Sciences Journal of Harbin Normal University, 2013,29(4):48-50.]
[9] Oliver C, Bemhard S, Alexander Z. Semi-Supervised Learning[J]. The MIT Press, 2006,172(2):530-530.
[10] Zhu X J. Semi-Supervised Learning Literature Survey[D]. Madison:Univercity of Wiscomnsin, 2008.
[11] Zhou Z H. Ensemble Methods:Foundations and Algorithms Boca Raton[M]. Boca Raton:CRC Press, 2012.
[12]王惠英,孙中平,孙志伟,等.基于深度学习的河道提取与变化监测应用——以永定河为例[J].北京测绘,2019,33(2):173-178.[Wang H Y, Sun Z P, Sun Z W, et al. The Application for extraction of river channels and change detection based on deep learning:A case study from Yongding River[J]. Beijing Surveying and Mapping,2019.33(2):173-178.]
[13] Xu Y Y, Xie Z, Wu L, et al. Multilane roads extracted from the Openstreet Map urban road network using random forests,wiley[J].Translation in GIS, 2018. DOI:10.1111/12514.
[14]周龙,韦素媛,崔忠马,等.基于深度学习的复杂背景雷达图像多目标检测[J].系统工程与电子技术,2019,41(6):1258-1264.[Zhou L, Wei S Y, Cui Z M, et al. Multi-objective detection of complex background radar image based on deep learning[J]. Systems Engineering and Electronics, 2019,41(6):1258-1264.]
[15] Hu B, Xu Y Y, Wan B,et al. Hydrothermally altered mineral mapping using synthetic application of Sentinel-2A MSI, ASTER and Hyperion data in the Duolong area, Tibetan Plateau, China[J]. Ore Geology Reviews, 2018,101:384-397.
[16]王圆圆,李京.基于决策树的高管狗数据特征选择及其对分类结果的影响分析[J].遥感学报,2007,11(1)69-76.[Wang Y Y, Li J. Analysis of Feature Selection and Its Impact on Hyperspectral Data Classification Based on Decision Tree Algorithm[J]. Journal of Remote Sensing,2007,11(1):69-76.]
[17]陈永良,周斌,李学斌.基于Boltzmann机的矿产靶区预测[J].地球物理学进展,2012,27(1):179-185.[Chen Y L,Zhou B, Li X B. Mineral target prediction based on Boltzmann machines[J]. Progress in Geophysics, 2012,27(1):179-185.]
[18] Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006,313(5786):504-507.
[19] Xu Y, Chen Z, Xie Z, et al. Quality assessment of building footprint data using a deep autoencoder network[J].International Journal of Geographical Information Science, 2017,31(10):1929-1951.
[20] Fiore U, Palmieri F, Castiglione A, et al. Network anomaly detection with the restricted Boltzmann machine[J].Neurocomputing, 2013,122:13-23.
[21] Chen H, Murray A F. Continuous restricted Boltzmann machine with an implementable training algorithm[J]. Vision Image and Signal Processing, IEE Proceedings, 2013,150:153-158.
[22] Sun J, et al. Application of deep belief networks for precision mechanism quality inspection[M]. Berlin:Springer,2014.
[2]黄宜华.大数据机器学习系统研究进展[J].大数据,2015,1(1):35-54.[Huang Y H. Research progress on big data machine learning system[J]. Big Data Research, 2015,1(1):35-54.]
[3] John Zukowsi. Java2从入门到精通[M].北京:电子工业出版社,2000.[John Zukowsi. Java 2:From entry to mastery[M]. Beijing:Electronic Industry Press, 2000.]
[4]黄林军,张勇,郭冰榕.机器学习技术在数据挖掘中的商业应用[J].中山大学学报论丛,2005(6):145-148.[Huang L J, Zhang Y, Guo B R. Commercial application of machine learning technology in data mining[J]. Sun Yatsen University Forum, 2005(6):145-148.]
[5]阴江宁,肖克炎,何凯涛,等.铜矿数字矿床模型专家系统的原理与技术实现[J].地质论评,2009,55(3):449-456.[Yin J N, Xiao K Y, He K T, et al. Principle and technology realization of copper mine digital deposit model expert system[J]. Geological Review, 2009,55(3):449-456.]
[6]于萍萍,陈建平,柴福山,等.基于地质大数据理念的模型驱动矿产资源定量预测[J].地质通报,2015,34(7):1333-1343.[Yu P P, Chen J P, Chai F S, et al. Research on model-driven quantitative prediction and evaluation of mineral resources based on geological big data concept[J]. Geological Bulletin of China, 2015,34(7):1333-1343.]
[7]朱月琴,谭永杰,张建通,等.基于Hadoop的地质大数据融合与挖掘技术框架[J].测绘学报,2015,44(S1):152-159.[Zhu Y Q, Tan Y J, Zhang J T, et al. A framework of hadoop based geologhy big data fusion and mining technologies[J]. Acta Geodaetica et Cartographica Sinica,2015,44(S1):152-159.]
[8]王晓.大数据环境下机器学习算法趋势研究[J].哈尔滨师范大学:自然科学学报,2013,29(4):48-50.[Wang X. Research on trends of machine learning algorithms in big data environments[J]. Natural Sciences Journal of Harbin Normal University, 2013,29(4):48-50.]
[9] Oliver C, Bemhard S, Alexander Z. Semi-Supervised Learning[J]. The MIT Press, 2006,172(2):530-530.
[10] Zhu X J. Semi-Supervised Learning Literature Survey[D]. Madison:Univercity of Wiscomnsin, 2008.
[11] Zhou Z H. Ensemble Methods:Foundations and Algorithms Boca Raton[M]. Boca Raton:CRC Press, 2012.
[12]王惠英,孙中平,孙志伟,等.基于深度学习的河道提取与变化监测应用——以永定河为例[J].北京测绘,2019,33(2):173-178.[Wang H Y, Sun Z P, Sun Z W, et al. The Application for extraction of river channels and change detection based on deep learning:A case study from Yongding River[J]. Beijing Surveying and Mapping,2019.33(2):173-178.]
[13] Xu Y Y, Xie Z, Wu L, et al. Multilane roads extracted from the Openstreet Map urban road network using random forests,wiley[J].Translation in GIS, 2018. DOI:10.1111/12514.
[14]周龙,韦素媛,崔忠马,等.基于深度学习的复杂背景雷达图像多目标检测[J].系统工程与电子技术,2019,41(6):1258-1264.[Zhou L, Wei S Y, Cui Z M, et al. Multi-objective detection of complex background radar image based on deep learning[J]. Systems Engineering and Electronics, 2019,41(6):1258-1264.]
[15] Hu B, Xu Y Y, Wan B,et al. Hydrothermally altered mineral mapping using synthetic application of Sentinel-2A MSI, ASTER and Hyperion data in the Duolong area, Tibetan Plateau, China[J]. Ore Geology Reviews, 2018,101:384-397.
[16]王圆圆,李京.基于决策树的高管狗数据特征选择及其对分类结果的影响分析[J].遥感学报,2007,11(1)69-76.[Wang Y Y, Li J. Analysis of Feature Selection and Its Impact on Hyperspectral Data Classification Based on Decision Tree Algorithm[J]. Journal of Remote Sensing,2007,11(1):69-76.]
[17]陈永良,周斌,李学斌.基于Boltzmann机的矿产靶区预测[J].地球物理学进展,2012,27(1):179-185.[Chen Y L,Zhou B, Li X B. Mineral target prediction based on Boltzmann machines[J]. Progress in Geophysics, 2012,27(1):179-185.]
[18] Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006,313(5786):504-507.
[19] Xu Y, Chen Z, Xie Z, et al. Quality assessment of building footprint data using a deep autoencoder network[J].International Journal of Geographical Information Science, 2017,31(10):1929-1951.
[20] Fiore U, Palmieri F, Castiglione A, et al. Network anomaly detection with the restricted Boltzmann machine[J].Neurocomputing, 2013,122:13-23.
[21] Chen H, Murray A F. Continuous restricted Boltzmann machine with an implementable training algorithm[J]. Vision Image and Signal Processing, IEE Proceedings, 2013,150:153-158.
[22] Sun J, et al. Application of deep belief networks for precision mechanism quality inspection[M]. Berlin:Springer,2014.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |