基于贝叶斯推理的LS-SVM矿产资源定量预测

doi:10.12068/j.issn.1005-3026.2017.11.023

东北大学学报:自然科学版 ›› 2017, Vol. 38 ›› Issue (11): 1633-1636.DOI: 10.12068/j.issn.1005-3026.2017.11.023

基于贝叶斯推理的LS-SVM矿产资源定量预测

韩创益^1,2，王恩德¹，夏建明¹，崔顺哲²

(1. 东北大学资源与土木工程学院，辽宁沈阳110819; 2. 金策工业综合大学资源勘探工程学院，平壤999093)

收稿日期:2016-06-12 修回日期:2016-06-12 出版日期:2017-11-15 发布日期:2017-11-13
通讯作者: 韩创益
作者简介:韩创益(1980-)，男，朝鲜平壤人，东北大学博士研究生; 王恩德(1957-)，男，辽宁盖州人，东北大学教授，博士生导师.
基金资助:
国家重大基础研究发展计划项目(2012CB416800)；国家自然科学基金资助项目(41372098).

Mineral Resource Quantitative Prediction Based on LS-SVM Combining with Bayesian Inference

HAN Chang-ik^{1, 2}， WANG En-de¹， XIA Jian-ming¹， CHOE Sun-chol²

1. School of Resources & Civil Engineering， Northeastern University， Shenyang 110819， China; 2. College of Geoexploration Engineering， Kimchaek University of Technology， Pyongyang 999093， DPRK.

Received:2016-06-12 Revised:2016-06-12 Online:2017-11-15 Published:2017-11-13
Contact: HAN Chang-ik
About author:-
Supported by:
-

摘要/Abstract

摘要： 针对矿产资源定量预测过程中最小二乘支持向量机(LS-SVM)的参数选择具有主观性和随意性，提出了一种与贝叶斯推理相结合的LS-SVM资源定量预测方法，并将其与证据权法(WofE)进行了对比.在训练过程中采用贝叶斯推理方法对LS-SVM的参数选择进行优化，进而构建矿产资源定量预测优化模型.研究表明，该方法不但克服了参数选择的局限性，而且以后验概率形式输出预测结果，从而可提高预测精度.

关键词: 贝叶斯推理, LS-SVM, 矿产资源, 定量预测, 证据权法

Abstract: In the mineral resources quantitative prediction using the least squares support vector machine (LS-SVM)， precision of results are influenced by the selection of its parameters. The prediction method based on the LS-SVM combining with Bayesian inference is proposed and it is also compared with weights-of-evidence (WofE) method. During the training process， the optimized parameters of LS-SVM are chosen by Bayesian inference method， which can build the optimized model for the mineral resources quantitative prediction. The results show that the proposed method not only overcomes randomness and limitation of its optimal parameter selection， but also increases the accuracy of prediction by exporting the prediction result in the form of posterior probability.

Key words: Bayesian inference, LS-SVM, mineral resource, quantitative prediction, WofE(weights-of-evidence)

中图分类号:

P612

韩创益，王恩德，夏建明，崔顺哲. 基于贝叶斯推理的LS-SVM矿产资源定量预测[J]. 东北大学学报:自然科学版, 2017, 38(11): 1633-1636.

HAN Chang-ik ， WANG En-de， XIA Jian-ming， CHOE Sun-chol. Mineral Resource Quantitative Prediction Based on LS-SVM Combining with Bayesian Inference[J]. Journal of Northeastern University Natural Science, 2017, 38(11): 1633-1636.

参考文献

[1]张道军.逻辑回归空间加权技术及其在矿产资源信息综合中的应用［D］.武汉:中国地质大学，2015.(Zhang Dao-jun.Spatially weighted technology for logistic regression and its application in mineral prospectivity mapping ［D］.Wuhan:China University of Geosciences，2015.)
[2]刘文博.非线性矿产资源预测定量模型研究［D］.长春:吉林大学，2015.(Liu Wen-bo.Quantitative research of nonlinera mineral resources predictive model ［D］.Changchun:Jilin University，2015.)
[3]于萍萍.基于知识驱动的矿产资源定量预测评价关键技术研究［D］.北京:中国地质大学(北京)，2015.(Yu Ping-ping.Research on the key technologies of knowledge-driven quantitative prediction and evaluation of mineral resources ［D］.Beijing:China University of Geosciences，2015.)
[4]Porwal A，Carranza E J M.Introduction to the special issue:GIS-based mineral potential modeling and geological data analyses for mineral exploration ［J］.Ore Geology Reviews，2015，71:477-483.
[5]Zuo R G，Carranza E J M.Support vector machine:a tool for mapping mineral prospectivity ［J］.Computers & Geosciences，2011，37:1967-1975.
[6]Abedi M，Norouzi G H，Bahroudi A.Support vector machine for multi-classification of mineral prospectivity areas ［J］.Computers & Geosciences，2012，46:272-283.
[7]Suykens J A K，Vandewalle J.Least squares support vector machine classifiers ［J］.Neural Processing Letter，1999，9(3):293-300.
[8]Galiano V R，Castillo M S，Olmo M C，et al.Machine learning predictive models for minral prospectivity:an evaluation of neural networks，random forest，regression trees and support vector machines ［J］.Ore Geology Reviews，2015，71:804-848.
[9]Gestel T V，Suykens J A K，Lanckriet G，et al.Bayesian framework for least-squares support vector machine classifiers，Gaussian processes，and kernel fisher discriminant analysis ［J］.Neural Computation，2002，14:1115-1147.
[10]Cline J S，Hofstra A H，Muntean J L，et al.Carlin-type gold deposits in Nevada:critical geologic characteristics and viable models ［J］.Economic Geology，2005，100:451-484.

基于贝叶斯推理的LS-SVM矿产资源定量预测

Mineral Resource Quantitative Prediction Based on LS-SVM Combining with Bayesian Inference

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价

[1]	年海威;毛志忠;. 一种新型的硫容量智能预报方法[J]. 东北大学学报(自然科学版), 2011, 32(9): 1225-1228.
[2]	郑云虹;李凯;. 基于AHP的矿产资源型企业生态安全综合评价[J]. 东北大学学报(自然科学版), 2007, 28(3): 445-448.