Research on modeling method of continuous spectrum water quality online detection based on random forest

Abstract

It’s common to use the method of continuous spectroscopy in water quality testing. But there’re some problems with it. For example, the scanning results have a large number of nonlinear signals, and the covariance between variables is serious, which can lead to a decrease in the model prediction accuracy. In this paper, the standard solutions of nitrate nitrogen (NO₃-N) and nitrite nitrogen (NO₂-N) were used as the subject to be tested, and the data of the scanned waves and absorbance were obtained by use of spectral detector. The data were processed by noise reduction first and then the random forest (RF) algorithm was adopted to establish the regression relationship between concentration and absorbance. For comparison, partial least squares (PLS) and support vector machine (SVM) algorithm models were also established. For the same given data, the three reverse models can make the projection of the concentration respectively. The experimental results show that the RF algorithm predicts NO₂-N concentrations significantly better than the SVM algorithm and PLS algorithm. This proves that the RF algorithm has good prediction ability in spectral water quality detection because of its high model accuracy and better adaptability, which could be a reference for similar research on continuous spectral water quality online detection.

References

[1] WeiK L, ChenM, WenZ Y. Research on signal processing for water quality monitoring based on continuous spectral analysis[J]. Spectroscopy and spectral analysis, 2014, 34(12):3368-3373

[2] WangC L, WangB, JiT. Simulated estimation of nitrite content in water based on transmission spectrum[J]. Spectroscopy and spectral analysis, 2022, 42(07):2181-2186

[3] HeM X, LiJ, FanW Y. Correlation between floc morphology and water quality based on partial least squares[J]. The administration and technique of environmental monitoring, 2021, 33(06):48-51

[4] YanW L, RenS Y, YueX X. Rapid detection of cAMP content in red jujube using near-infrared spectroscopy[J]. Optoelectronics letters, 2018, 14(5):380-383

[5] WangY M, ChenH R, ChenJ Y. Comparation of rice yield estimation model combining spectral index screening method and statistical regression algorithm[J]. Transactions of the Chinese society of agricultural engineering, 2021, 37(21):208-216

[6] CASTRILLO M, GARCÍA L Á. Estimation of high frequency nutrient concentrations from water quality surrogates using machine learning methods[J]. Water research, 2020, 172(C).

[7] MuH Y. Multi-models combined water quality analyzing based on multi-spectra[D], 2011, Hangzhou, Zhejiang University

[8] LiR N, WangQ, LiuS M. Water quality warning method based on canonical correlation coefficient and random forest[J]. China environmental science, 2021, 41(09):4457-4464

[9] MahsaM, KhanmohammadiK M, HosseinG. Classification of nanofluids solutions based on viscosity values: a comparative study of random forest, logistic model tree, Bayesian network, and support vector machine models[J]. Infrared physics and technology, 2022, 125: 104273

[10] NafouantiB N, LiJ X, AbbaM N. Prediction on the fluoride contamination in groundwater at the Datong Basin, Northern China: comparison of random forest, logistic regression and artificial neural network[J]. Applied geochemistry, 2021, 132: 105054

[11] BreimanL. Random forests[J]. Machine learning, 2001, 45(1):5-32

[12] YuanZ X. Study on spectral classification model based on random forest[J]. Modern information technology, 2021, 5(07):81-84

[13] LiS F, JiaM Z, DongD M. Fast measurement of sugar in fruits using near infrared spectroscopy combined with random forest algorithm[J]. Spectroscopy and spectral analysis, 2018, 38(06):1766-1771

[14] WangK, WangJ X, XingZ N. Infrared spectrum modeling method based on RF algorithm of improved feature selection[J]. Application research of computers, 2018, 35(10):3000-3002

[15] VliW, LvB B, FuH. Study on denoising of continuous spectrum on-line monitoring signal of water quality with micro-reagents based on HHT[J]. Optoelectronics letters, 2022, 18(2):115-121

[16] FangT J, AmieA, ShaneelC. Electrochemical detection of nitrate, nitrite and ammonium for on-site water quality monitoring[J]. Current opinion in electrochemistry, 2022, 32: 100926

[17] MelissaT, AlanK. Assessing the accuracy of nitrate concentration data for water quality monitoring using visual and cell phone quantification methods[J]. Citizen science: theory and practice, 2021, 6(1):2

[18] DongC Y, LiW Z, WangZ H. An automated flow-batch analyzer based on spectrophotometry for the determination of nitrite[J]. Optoelectronics letters, 2019, 15(5): 339-342