Langergraber’s group developed UV–Vis spectrometry to measure in situ water quality parameters in real time (Langergraber et al., 2003 van den Broeke et al., 2006). It is based on a regression model between a spectrum curve and parameters measured by chemical methods. Ultraviolet–visible (UV–Vis) spectrometry is a widely used physical method to detect or monitor water parameter quality (Avagyan et al., 2014 Hu et al., 2016). Chemical methods are stable and accurate but have some disadvantages, including long measuring periods and the generation of secondary pollution (Ma et al., 2020). At present, both chemical and physical methods are used to analyze water parameters. There is a need to monitor water quality continuously in the river confluences of agricultural catchments. One of the reasons for pollution events is world population growth, which has resulted in an increasing need for agricultural farming and urban activities. At the same time, the pollution of surface water with excessive nutrients and toxic substances is also occurring worldwide. Rivers carry large quantities of water from the land to the ocean, forming part of the water cycle (Chahine, 1992). In fact, studies have reported an increase in pollution derived from all kinds of production and operation activities, such as industrial, agricultural and sanitary sewage pursuits (Khalid et al., 2018). Because oceans hold approximately 96.5% of all Earth's water and fresh water accounts for only 1% of the Earth’s available water resources (Boberg, 2005), the conservation of water resources is critical to the sustainable development of all human beings (Falkenmark, 2020). Although 71 percent of the Earth's surface is covered by water, it remains a precious resource (Baker et al., 2016 El Habr, 1995). Water is a key natural resource for the maintenance of all ecosystems on the planet. CNN method may obtain a better linear correlation coefficient (R 2) even with small number of samples and can be used for online water quality monitoring combined with UV–Vis spectrometry in agricultural catchment. The experimental results of this study show that both PLS and CNN methods may obtain an accurate result: linear correlation coefficient (R 2) between predicted value and true values of TOC concentrations is 0.927 with PLS model and 0.953 with CNN model, R 2 between predicted value and true values of TSS concentrations is 0.827 with PLS model and 0.915 with CNN model. Convolutional neural network (CNN) and partial least squares (PLS) methods are used to calculate water parameters and obtain accurate results. The absorption spectra of the water sample were acquired within a wavelength range from 200 to 800 nm. Samples were collected and immediately taken back to a laboratory for analysis. In this study, we plan to simplify water quality monitoring with UV–Vis spectrometry and artificial neural networks. In recent years, artificial neural networks have been extensively studied and used in various areas. UV–Vis spectrometry is widely used in place of traditional analytical methods because it is cost effective and fast and there is no chemical waste. Water quality monitoring is very important in agricultural catchments.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |