检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:戴国忠 戴巍 吴宏武[2] DAI Guozhong;DAI Wei;WU Hongwu(Fujian Institute of Geotechnical Engineering Investingation and Surveying,Minhou 350108,Fujian,China;The Second Geological ExplorationInstitute of China Metallurgical Geology Bureau,Putian 351111,Fujian,China)
机构地区:[1]福建岩土工程勘察研究院有限公司,福建闽侯350108 [2]中国冶金地质总局第二地质勘查院,福建莆田351111
出 处:《化学研究》2023年第1期31-36,共6页Chemical Research
摘 要:为了提高地下水水化学成分分析精度,满足实际水质分析工作需要,研究多源光谱信息融合地下水水化学成分分析方法。采用荧光光谱仪与紫外光光谱仪,采集地下水水化学成分数据,并通过双重ICA操作分别提取紫外光谱与荧光光谱样本数据特征,采用Boosting集成的最小二乘支持向量机(LS-SVM)水样多源光谱融合建模方法,建立水化学成分分析模型,将提取到紫外与荧光光谱样本数据特征融合形成的特征数据集作为模型输入向量,将LS-SVM作为基础学习器,通过Boosting算法,以迭代停止判据为迭代终止条件,寻求水化学成分分析模型最优解,预测地下水水化学成分。实验结果表明,该方法利用多光谱信息融合进行地下水水化学成分分析的预测值与实际化学分析值更接近,分析效果显著高于应用单一光谱数据的水化学成分分析方法,能够满足实际地下水水化学成分分析需要。In order to improve the accuracy of groundwater chemical composition analysis and meet the needs of actual water quality analysis,the analysis method of groundwater chemical composition based on multi-source spectral information fusion is studied.The fluorescence spectrometer and ultraviolet spectrometer are used to collect the data of groundwater chemical composition,and the data characteristics of ultraviolet spectrum and fluorescence spectrum samples are extracted respectively through dual ICA operation.The water chemical composition analysis model is established by using the multi-source spectrum fusion modeling method of boosting integrated least squares support vector machine(LS-SVM).The feature data set formed by the feature fusion of the extracted UV and fluorescence spectrum sample data is used as the model input vector,and LS-SVM is used as the basic learner.Through the boosting algorithm and taking the iteration stop criterion as the iteration termination condition,the optimal solution of the hydrochemical composition analysis model is sought to predict the hydrochemical composition of groundwater.The experimental results show that the predicted value of groundwater hydrochemical composition analysis using multispectral information fusion is closer to the actual chemical analysis value,and the analysis effect is significantly higher than the hydrochemical composition analysis method using single spectral data,which can meet the needs of actual groundwater hydrochemical composition analysis.
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:18.224.200.110