透射光谱的水体亚硝酸盐含量模拟估算

Simulated Estimation of Nitrite Content in Water Based on Transmission Spectrum

亚硝酸盐是水体中重要的必测指标之一,对于水体质量的评估有着重要意义。但传统的检测方法操作复杂、受干扰因素多、测定时间长、不能及时反映水质变化、无法及时有效地预警突发水污染事件。鉴于此,探索准确、实时、环保的环境水体和饮用水中的亚硝酸盐含量检测办法具有重要意义。采用优级纯试剂配制10种浓度的亚硝酸盐氮标准溶液(0.02,0.04,0.06,0.08,0.10,0.12,0.14,0.16,0.18和0.20 mg·L^(-1)),采用OCEAN-HDX-XR微型光纤光谱仪扫描10次各浓度亚硝酸盐溶液在181.1~1023.1 nm范围内的透射光谱,取平均值作为各浓度亚硝酸盐溶液原始透射光谱,之后以亚硝酸盐含量作为因变量,全波段原始透射光谱作为自变量,采用随机森林回归中特征变量重要性方法,筛选特征变量,再此基础上利用交叉验证法,挑选最为稳定的模型变量个数,建立亚硝酸盐优化随机森林反演模型。结果如下:(1)利用全波段建立的随机森林模变量解释率(var explained)=76.49%,均方残差(mean of squared residuals)=0.000688;(2)随机森林变量重要性方法筛选对亚硝酸盐反演的敏感波段,其中195.1 nm重要性值最高,并利用留一交叉法发现,当利用19个光谱特征变量时随机森林模型的均方根误差最低,以筛选光谱特征变量建立的优化随机森林变量解释率(var explained)=83.45%,均方残差(mean of squared residuals)=0.000552。变量筛选有效减少了光谱数据量,对优化模型的建立提供了基础;(3)对建立模型进行模型检验,其中全波段随机森林模型测试集R^(2)=0.8203,RMSE=0.03,检验集R^(2)=0.9793,RMSE=0.01,优化随机森林模型测试集R^(2)=0.8734,RMSE=0.022,检验集R^(2)=0.9798,RMSE=0.008,对比全波段随机森林模型与优化后随机森林模型后发现,优化随机森林模型测试集与检验集模型解释度、模型精度均要高于全波段随机森林模型,说明优化方法不仅可有效降低光谱维度,对于寻找亚硝酸盐光谱敏感波段,建立精度较高的亚硝酸盐反演模型有着积极意义。基于以上试验结果,提出了一种优化随机森林模型高光谱水质亚硝酸盐参数的反演方法,为水质亚硝酸盐参数动态检测提供了新方法。

NO_(2)-N is an important parameter in water bodies and can quickly detect organic pollution parameters.It is of great significance to the assessment of water quality.However,traditional methods are complicated in operation,subject to many interference factors,long measurement time,cannot reflect water quality changes in time,and cannot provide timely and effective early warning.For sudden water pollution incidents,because of the shortcomings of traditional methods,it is of great significance to explore accurate,real-time,and environmentally friendly detection methods for the NO_(2)-N content in environmental water bodies and drinking water.This experiment is to study the use of superior grade pure reagents to prepare 10 concentrations of NO_(2)-N nitrogen standard solutions(0.02,0.04,0.06,0.08,0.1,0.12,0.14,0.16,0.18 and 0.2 mg·L^(-1)),using the OCEAN-HDX-XR micro-fiber spectrometer to scan 10 times the transmission spectrum of the NO_(2)-N solution of each concentration in the range of 181.1~1023.1 nm.Take the average value as the original transmission spectrum of the NO_(2)-N solution of each concentration,and then take the NO_(2)-N content of the solution as the dependent variable and the original transmission spectrum as the independent variable.Use the method of variable feature importance in random forest regression to screen the feature variables.Based on the cross-validation method,the number of the most stable model variables is selected,and the NO_(2)-N optimization random forest inversion model is established.The results of the study are as follows:(1)The variable explained rate(Var Explained)of the random forest model established by the whole band(Var Explained)=76.49%,and the mean squared residuals(Mean of squared residuals)=0.000688;In the sensitive band of salt inversion,195.1 nm has the highest importance value,and the leave-one-out crossover method is used to find that the random forest model has the lowest root mean square error when 19 spectral characteristic variables are used to screen the optimized random forest established by spectral characteristic variables Variable Explained rate(Var Explained)=83.45%,Mean of squared residuals(Mean of squared residuals)=0.000552.Variable screening effectively reduces the amount of spectral data and provides a basis for the establishment of the optimization model;(3)Model verification of the established model,including the full-band random forest model test set R^(2)=0.8203,RMSE=0.03,test set R^(2)=0.9793,RMSE=0.01,optimized random forest model test set R^(2)=0.8734,RMSE=0.022,test set R^(2)=0.9798,RMSE=0.008,after comparing the full-band random forest model with the optimized random forest model,it is found that the optimized random forest model test set and test The interpretation and accuracy of the set model are higher than the full-band random forest model,indicating that the optimization method can not only effectively reduce the spectral dimension,but also has positive significance for finding the sensitive band of NO_(2)-N spectrum and establishing a high-precision NO_(2)-N inversion model..Based on the above test results,an inversion method for optimizing the hyperspectral water quality NO_(2)-N parameters of the random forest model is proposed,which provides a new method for the dynamic detection of water quality NO_(2)-N parameters.