Simultaneous Rapid Analysis of Multiple Nitrogen Compounds in Polluted River Treatment Using Near-Infrared Spectroscopy and a Support Vector Machine

被引:2
作者
Huang, Jian [1 ,2 ]
Zhang, Xiong [2 ]
Sun, Qingye [1 ]
Zhang, Hua [2 ]
Yu, Xiaokun [2 ]
Wu, Zhaoliang [2 ]
机构
[1] Anhui Univ, Sch Resources & Environm Engn, Hefei 230601, Anhui, Peoples R China
[2] Anhui Jianzhu Univ, Key Lab Anhui Prov Water Pollut Control & Wastewa, Hefei 230601, Anhui, Peoples R China
来源
POLISH JOURNAL OF ENVIRONMENTAL STUDIES | 2017年 / 26卷 / 05期
关键词
near infrared spectroscopy; support vector machine; principal component analysis; intermittent aeration; REGRESSION; SEDIMENTS; AERATION; CHINA;
D O I
10.15244/pjoes/70002
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
An intermittent aerobic process has been developed to effectively remove nitrogen from polluted rivers. In addition, a chemometric model was developed to achieve simultaneous rapid analysis of total nitrogen, ammonia nitrogen, and nitrite nitrogen based on near-infrared spectroscopy data combined with a support vector machine. An intermittent aeration process showed that total nitrogen decreased from 54.25 mg.L-1 to 0.64 mg.L-1. Ammonia nitrogen decreased significantly in the aeration stage, but increased in the non-aeration stage. Eventually, ammonia nitrogen decreased from 45.04 mg.L-1 to 0.57 mg.L-1. Nitrite nitrogen and nitrate nitrogen increased in the aeration stage, but decreased in the non-aeration stage. The concentration ranges of nitrite nitrogen and nitrate nitrogen were, respectively, 0.05 similar to 31.40 mg.L-1 and 0 similar to 0.38 mg.L-1. The 138 water samples were collected during the intermittent aeration process, of which 116 samples were used as the calibration set and the remaining 22 samples were used as a test set in modeling. The actual concentration values and the near-infrared spectroscopy data were used as input of the models. Then the corresponding calibration values and predication values were output by the models. All the samples were scanned with near-infrared spectroscopy from 4,000 similar to 12,500 cm(-1) and measured by chemical methods. Principal component analysis of raw near-infrared spectral data showed that the matrix dimension of spectral data was significantly reduced, which decreased from 2,203x106 to 6x106. Support vector machine models of total nitrogen, ammonia nitrogen, and nitrite nitrogen showed that the calibration correlation coefficient (R-2) of calibration values and actual values were, respectively, 0.9561, 0.9661, and 0.9702, with the root mean square error of cross validation (RMSECV) being 0.09372, 0.04749, and 0.03187. The test results of support vector machine models of total nitrogen, ammonia nitrogen, and nitrite nitrogen showed that the predication correlation coefficient (R-2) of prediction values and actual values were, respectively, 0.9616, 0.9410, and 0.9284, with the root mean square error of prediction (RMSEP) being 0.09420, 0.08227, and 0.06770. This study indicated that nitrogen in a polluted river can be removed through the intermittent aerobic process. Moreover, simultaneous rapid determination of total nitrogen, ammonia nitrogen, and nitrite nitrogen may be achieved with near-infrared spectroscopy and a support vector machine. The results showed that the proposed methods provided effective treatment and detection technology for a polluted river.
引用
收藏
页码:2013 / 2019
页数:7
相关论文
共 50 条
[41]   Application of Particle Swarm Optimization Based Least Square Support Vector Machine in Quantitative Analysis of Extraction Solution of Safflower Using Near-infrared Spectroscopy [J].
Jin Ye ;
Yang Kai ;
Wu Yong-Jiang ;
Liu Xue-Song ;
Chen Yong .
CHINESE JOURNAL OF ANALYTICAL CHEMISTRY, 2012, 40 (06) :925-931
[42]   Rapid detection of microplastics in feeds using near-infrared spectroscopy [J].
Masoero, Giorgio ;
Barbera, Salvatore ;
Kaihara, Hatsumi ;
Mabrouki, Sabah ;
Patrucco, Sara Glorio ;
Abid, Khalil ;
Tassone, Sonia .
ACTA IMEKO, 2024, 13 (02) :10-10
[43]   Near-infrared calibration transfer via support vector machine and transfer learning [J].
Yu Binfeng ;
Ji Haibo .
ANALYTICAL METHODS, 2015, 7 (06) :2714-2725
[44]   SIMULTANEOUS ANALYSIS OF TOTAL PHOSPHORUS AND NITRATE NITROGEN IN DENITRIFYING PHOSPHORUS REMOVAL USING NEAR INFRARED SPECTROSCOPY [J].
Huang, Jian ;
Yuan, Xinrui ;
Zhang, Hua ;
Liu, Jiu ;
Sun, Weiwei ;
Xu, Yiqi ;
Ma, Tao ;
Li, Ming .
FRESENIUS ENVIRONMENTAL BULLETIN, 2018, 27 (10) :6952-6959
[45]   Rapid identification of adulterated rice based on data fusion of near-infrared spectroscopy and machine vision [J].
Song, Chenxuan ;
Liu, Jinming ;
Wang, Chunqi ;
Li, Zhijiang ;
Zhang, Dongjie ;
Li, Pengfei .
JOURNAL OF FOOD MEASUREMENT AND CHARACTERIZATION, 2024, 18 (05) :3881-3892
[46]   Classification of Wheat Grains in Different Quality Categories by Near Infrared Spectroscopy and Support Vector Machine [J].
Tan, Wenyi ;
Sun, Laijun ;
Zhang, Dan ;
Ye, Dandan ;
Che, Wenkai .
PROCEEDINGS OF 2016 2ND INTERNATIONAL CONFERENCE ON CLOUD COMPUTING AND INTERNET OF THINGS (CCIOT), 2016, :124-128
[47]   Early Stage Diagnosis of Endometrial Cancer Based on Near Infrared Spectroscopy and Support Vector Machine [J].
Zhai Wei ;
Xiang Yu-hong ;
Dai Yin-mei ;
Zhang Jia-jin ;
Zhang Zhuo-yong .
SPECTROSCOPY AND SPECTRAL ANALYSIS, 2011, 31 (04) :932-936
[48]   Qualitative identification of tea categories by near infrared spectroscopy and support vector machine [J].
Zhao, Jiewen ;
Chen, Quansheng ;
Huang, Xingyi ;
Fang, C. H. .
JOURNAL OF PHARMACEUTICAL AND BIOMEDICAL ANALYSIS, 2006, 41 (04) :1198-1204
[49]   Non-Invasive Blood Glucose Measurement Based on Near-Infrared Spectroscopy Combined With Label Sensitivity Algorithm and Support Vector Machine [J].
Meng Qi ;
Zhao Peng ;
Huan Ke-wei ;
Li Ye ;
Jiang Zhi-xia ;
Zhang Han-wen ;
Zhou Lin-hua .
SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44 (03) :617-624
[50]   Rapid and simultaneous quality analysis of the three active components in Lonicerae Japonicae Flos by near-infrared spectroscopy [J].
Xue Jintao ;
Yang Quanwei ;
Li Chunyan ;
Liu Xiaolong ;
Niu Bingxuan .
FOOD CHEMISTRY, 2021, 342