删除或更新信息,请邮件至freekaoyan#163.com(#换成@)

基于神经网络模型的海水硝酸盐测量方法研究

本站小编 Free考研考试/2022-02-11

基于神经网络模型的海水硝酸盐测量方法研究
其他题名Nitrate Measurement in the Ocean Based on Neural Network Model
侯耀斌1,2; 冯巍巍1,2; 蔡宗岐1; 王焕卿1; 刘增东3
发表期刊光谱学与光谱分析
ISSN1000-0593
2020
卷号40期号:10页码:3211-3216
关键词紫外吸收光谱海水硝酸盐神经网络光谱分析原位传感器
研究领域Environmental Sciences & Ecology
英文摘要Nitrate concentration is an important indicator for the marine ecosystem.Compared with laboratory chemical methods such as Cadmium-Reduction method,in-situ nitrate optical sensor is much faster and reagent-free in a long time and continuous monitoring.Partial Least Squares(PLS)method is often used in ultraviolet absorption spectrum modeling,which is difficult to optimize and has low generalization ability.The neural network can compel any no-linear function by any precision,which has high generalization ability in the modeling.A neural network model is established in the in-situ nitrate sensor to measure the nitrate concentration in seawater in which the nitrate concentration range is 30~750mug·L~(-1).Double-hidden layer neural network model is determined to adopt by contrasting performance of single-hidden layer and double-hidden layer to measure nitrate concentration,the input layer is absorption spectrum from 200to 275nm,the output layer is nitrate concentration,and sigmoid function is used as the activation function.Gradient descent method is used to update weighting parameters for the neural network of each layer,after 55 000times iteration,network training is conducted based on the learning rate of 0.26. After validation for the blind test of the model through 8-group randomized validation data,the nitrate concentration using double-hidden layer neural network model is higher in linear correlation to its actual concentration(R~2=0.997)in which the Root Mean Squared Error is 10.864,average absolute error is 8.442mug·L~(-1),average the relative error is 2.8%.Compared with single-hidden layer neural network model,the double-hidden layer neural network model has higher accuracy in which the average relative error is reduced by 4.92%,the Root Mean Squared Error of PLS is 4.58%using the same spectral data,while the mean relative error is 11.470.The result shows that the neural network model is much better than the Partial Least Squares model under certain conditions.It verifies the superiority of the neural network model applied to the nitrate concentration measurement by ultraviolet absorption spectrometry.The application test was carried out on theEnvironmental Monitoring 01 monitoring vessel of the Ministry of Natural Resources,the measurement results are basically identical with the laboratory method in 11stations,which is further proved from the reliability and practicality.
中文摘要硝酸盐浓度是海洋生态系统研究的重要指标。光学法硝酸盐原位传感器具有测量速度快、无需化学试剂的优点,在长时间连续监测方面,优于镉柱还原法等实验室化学方法。在计算模型方面目前国内外硝酸盐光学传感器多使用偏最小二乘法(PLS)对紫外吸收光谱进行光谱分析建模,模型优化难度较大且泛化能力较低,而神经网络模型理论上能够以任意精度逼近任何非线性连续函数,样本充足的情况下精度较高,泛化能力强。利用自主研制的海水硝酸盐原位传感器,研究了硝酸盐浓度范围为30~750mug·L~(-1)的人工海水的紫外吸收光谱,建立神经网络模型,定量计算水中的硝酸盐浓度。对比研究了单隐藏层和双隐藏层神经网络模型对硝酸盐浓度测量的性能,确定采用双隐藏层结构,模型的输入层为200~275nm波段的吸收光谱数据,输出层为硝酸盐浓度测量值,使用sigmoid函数作为激活函数。采用梯度下降法更新每一层神经网络的权值参数,学习率为0.26,迭代55 000次进行网络训练。通过8组随机验证数据进行模型盲测验证,得到的双隐层神经网络模型的硝酸盐浓度预测值和实际值的线性相关度较高(R~2=0.997),均方根误差为10.864,平均绝对误差为8.442mug·L~(-1),平均相对误差为2.8%,模型的精度较高,比单隐层神经网络模型的平均相对误差降低了4.92%,而利用同样的光谱数据建立的偏最小二乘算法的均方根误差为11.470,平均相对误差为4.58%,说明神经网络模型在一定条件下优于PLS模型的精度,验证了神经网络模型应用于紫外吸收光谱法硝酸盐浓度测量的优越性。搭载自然资源部环监01监测船环渤海航次进行了实际应用测试,在11个站位与实验室方法进行了比对测试,两种方法测量结果基本一致,进一步证明了该方法的可靠性和实用性。
文章类型Article
资助机构国家重点研发计划项目; 中国科学院关键技术人才项目; 烟台市重点研发计划项目; 中国科学院STS项目
收录类别CSCD
语种中文
CSCD记录号CSCD:6838473
引用统计
文献类型期刊论文
条目标识符http://ir.yic.ac.cnhttp://ir.yic.ac.cn/handle/133337/30323
专题中科院海岸带环境过程与生态修复重点实验室_海岸带环境过程实验室

作者单位1.中国科学院海岸带环境过程与生态修复重点实验室(烟台海岸带研究所),山东烟台264003;
2.中国科学院大学,北京100049;
3.山东省烟台生态环境监测中心,山东烟台264000

推荐引用方式
GB/T 7714侯耀斌,冯巍巍,蔡宗岐,等. 基于神经网络模型的海水硝酸盐测量方法研究[J]. 光谱学与光谱分析,2020,40(10):3211-3216.
APA侯耀斌,冯巍巍,蔡宗岐,王焕卿,&刘增东.(2020).基于神经网络模型的海水硝酸盐测量方法研究.光谱学与光谱分析,40(10),3211-3216.
MLA侯耀斌,et al."基于神经网络模型的海水硝酸盐测量方法研究".光谱学与光谱分析 40.10(2020):3211-3216.


PDF全文下载地址:

点我下载PDF
相关话题/光谱 测量 传感器 中国科学院 过程