| 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 |
| |
| 引用本文： | 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. |
| |
| 作者姓名： | 刘艳鹏 朱立新 周永章 |
| |
| 作者单位： | 中山大学地球科学与工程学院, 广州 510275;广东省地质过程与矿产资源探查重点实验室, 广州 510275;中山大学地球环境与地球资源研究中心, 广州 510275,中国地质调查局, 北京 100037,中山大学地球科学与工程学院, 广州 510275;广东省地质过程与矿产资源探查重点实验室, 广州 510275;中山大学地球环境与地球资源研究中心, 广州 510275 |
| |
| 基金项目： | 本文受国家重点研发计划项目（2016YFC0600506）、国家自然科学基金项目（41273040）、中国地质调查局（12120113067600）和广东省地质过程与矿产资源探查重点实验室基金联合资助. |
| |
| 摘 要： | 大数据人工智能地质学刚刚起步,基于大数据智能算法的地质研究是非常有意义的探索性实验。利用大数据和机器学习解决矿产预测问题,有助于人们克服不能全面考虑地质变量的困难及评估当前模型在已有数据中的可靠性。元素地表分布特征量主要受原岩成分、成矿作用影响和地表过程的影响,它们携带某些指示矿体就位的信息,即矿体在地下空间就位时在地表的响应,且未在地表过程中消失。以往的地球化学勘查工作仅仅识别异常,但未能发现矿体在地表响应的成矿特征量。本文以安徽省兆吉口铅锌矿床为例,通过机器学习,利用卷积神经网络算法,不断挖掘元素Pb分布特征与矿体地下就位空间的耦合相关性。经过1000次训练后,可以得到准确率0. 93,损失率0. 28的卷积神经网络模型。这种神经网络模型就是矿体在地下就位时元素在地表分布的响应,可以用来进行矿产资源预测。应用该模型对未知区进行预测,结果显示第53号区域具有很大概率存在尚未发现的矿体。
|
| 关 键 词： | 大数据 成矿预测 卷积神经网络 机器学习 地球化学 兆吉口铅锌矿床 |
| 收稿时间： | 2018/5/30 0:00:00 |
| 修稿时间： | 2018/9/10 0:00:00 |
Application of Convolutional Neural Network in prospecting prediction of ore deposits: Taking the Zhaojikou Pb-Zn ore deposit in Anhui Province as a case |
| |
| LIU YanPeng,ZHU LiXin and ZHOU YongZhang.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,2018,34(11):3217-3224. |
| |
| Authors: | LIU YanPeng ZHU LiXin and ZHOU YongZhang |
| |
| Institution: | School of Earth Sciences and Engineering, Sun Yat-sen University, Guangzhou 510275, China;Guangdong Provincial Key Laboratory of Geological Processes and Mineral Resource Survey, Guangzhou 510275, China;Centre for Earth Environment and Resources, Sun Yat-sen University, Guangzhou 510275, China,China Geological Survey, Beijing 100037, China and School of Earth Sciences and Engineering, Sun Yat-sen University, Guangzhou 510275, China;Guangdong Provincial Key Laboratory of Geological Processes and Mineral Resource Survey, Guangzhou 510275, China;Centre for Earth Environment and Resources, Sun Yat-sen University, Guangzhou 510275, China |
| |
| Abstract: | The development of big data and artificial intelligent geology has just started since geological researches focusing on big data intelligent algorithm are still in a stage of exploratory experiment with significant meaning. Mineral resources prediction is one of the core tasks of artificial intelligent geology. By using big data and machine learning to solve mineral resources prediction problems, it will help us overcome the difficulties brought by the unablilties of the fully considerations upon geological variables, and assess the reliability of current models in existing data. This research takes the Zhaojikou Pb-Zn ore deposit in Anhui Province as a case to use the Convolutional Neural Network (CNN) and the logistic regression to reveal the relationships between the surface distributions of element Pb and the occurrences of the ore-bodies through machine learning. Then a CNN prediction of mineral resources model was constructed. Finally, the unknown areas were evaluated via this model. After 1000 trainings, the CNN model can reach an accuracy of 0.93 and a loss of 0.28. The prediction results of unknown areas showed that Area 53 has a large probability to find potential ore-bodies. |
| |
| Keywords: | Big data Metallogenic prediction Convolutional Neural Network Machine learning Geochemistry Zhaojikou Pb-Zn Ore Deposit |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《岩石学报》浏览原始摘要信息 |
| 点击此处可从《岩石学报》下载免费的PDF全文 |
|
