Februriyana Pirade, Kim Lompe, Javier Jimenez-Lamana, Sulalit Bandyopadhyay, Katharina Zürbes, Nesrine Bali, Dušan Materić, Jan Willem Foppen
Abstract Nanoplastics are detected in surface water, yet accurately quantifying their particle number concentrations remains a significant challenge. In this study, we tested the applicability of a gold-labelling method to quantify nanoplastics in natural organic matter (NOM) containing water matrices. Gelatin-coated gold nanoparticles (Au-gel NPs) form conjugates with nanoplastics via electrostatic interaction which produces peak signals which can be translated into particle number concentration using single-particle inductively coupled plasma–mass spectrometry (SP-ICP-MS). We used water samples with various NOM concentrations, with and without the addition of 1 × 107 particles L−1 nanoplastics. Our results indicate that nanoplastics in low NOM samples (<1 mg·C L−1) could be successfully quantified. However, in high NOM samples (>15 mg·C L−1), only 13–19% of added nanoplastics were successfully quantified. Further digestion to remove NOM yielded only 10% of spiked nanoplastics. This discrepancy in high NOM samples could likely be attributed to the competition between nanoplastics and NOM existing in the water sample to bind with Au-gel NPs. Our study highlights the suitability of the Au-gel labelling method for quantifying nanoplastics in low NOM water samples. Nevertheless, further optimization, including pre-digestion steps, is essential to apply this method for high NOM water samples effectively.
{"title":"How suitable is the gold-labelling method for the quantification of nanoplastics in natural water?","authors":"Februriyana Pirade, Kim Lompe, Javier Jimenez-Lamana, Sulalit Bandyopadhyay, Katharina Zürbes, Nesrine Bali, Dušan Materić, Jan Willem Foppen","doi":"10.2166/aqua.2023.278","DOIUrl":"https://doi.org/10.2166/aqua.2023.278","url":null,"abstract":"Abstract Nanoplastics are detected in surface water, yet accurately quantifying their particle number concentrations remains a significant challenge. In this study, we tested the applicability of a gold-labelling method to quantify nanoplastics in natural organic matter (NOM) containing water matrices. Gelatin-coated gold nanoparticles (Au-gel NPs) form conjugates with nanoplastics via electrostatic interaction which produces peak signals which can be translated into particle number concentration using single-particle inductively coupled plasma–mass spectrometry (SP-ICP-MS). We used water samples with various NOM concentrations, with and without the addition of 1 × 107 particles L−1 nanoplastics. Our results indicate that nanoplastics in low NOM samples (&lt;1 mg·C L−1) could be successfully quantified. However, in high NOM samples (&gt;15 mg·C L−1), only 13–19% of added nanoplastics were successfully quantified. Further digestion to remove NOM yielded only 10% of spiked nanoplastics. This discrepancy in high NOM samples could likely be attributed to the competition between nanoplastics and NOM existing in the water sample to bind with Au-gel NPs. Our study highlights the suitability of the Au-gel labelling method for quantifying nanoplastics in low NOM water samples. Nevertheless, further optimization, including pre-digestion steps, is essential to apply this method for high NOM water samples effectively.","PeriodicalId":34693,"journal":{"name":"AQUA-Water Infrastructure Ecosystems and Society","volume":"7 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136351916","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mohammad Aasif Khaja, Shagoofta Rasool Shah, Abas Ahmad, Asiya Khursheed, Shiv Malani
Abstract The potential of water lilies, food waste, and sludge as substrates for biogas production through anaerobic digestion was investigated. We thoroughly characterized these substrates and found that water lilies had a pH of 6.4, total solids (TS) of 18.42%, volatile solids (VS) of 81.46%, and a moisture content of 87%. Food waste exhibited a pH of 7.6, TS at 27.23%, VS at 90.6%, and a moisture content of 75%. Sludge had a pH of 6.5, TS of 6%, VS of 60%, and a moisture content of 95%. Biogas production exhibited variations among the reactors. Reactor 1 reached a cumulative production of 2,527 mL, while Reactor 4 achieved 3,404 mL, with different lag phases. Reactor 4 displayed the highest biogas yield at 262 mL/g VS. Post-digestion tests confirmed efficient digestion, with volatile fatty acids ranging from 140 to 300 mg/L acetic acid and alkalinity levels between 800 and 1,500 mg CaCO3/L. Our study estimated a significant methane content, with the potential to produce 94.32 L of methane from 1 kg of TS.
{"title":"Biogas production from water lilies, food waste, and sludge: substrate characterization and process performance","authors":"Mohammad Aasif Khaja, Shagoofta Rasool Shah, Abas Ahmad, Asiya Khursheed, Shiv Malani","doi":"10.2166/aqua.2023.242","DOIUrl":"https://doi.org/10.2166/aqua.2023.242","url":null,"abstract":"Abstract The potential of water lilies, food waste, and sludge as substrates for biogas production through anaerobic digestion was investigated. We thoroughly characterized these substrates and found that water lilies had a pH of 6.4, total solids (TS) of 18.42%, volatile solids (VS) of 81.46%, and a moisture content of 87%. Food waste exhibited a pH of 7.6, TS at 27.23%, VS at 90.6%, and a moisture content of 75%. Sludge had a pH of 6.5, TS of 6%, VS of 60%, and a moisture content of 95%. Biogas production exhibited variations among the reactors. Reactor 1 reached a cumulative production of 2,527 mL, while Reactor 4 achieved 3,404 mL, with different lag phases. Reactor 4 displayed the highest biogas yield at 262 mL/g VS. Post-digestion tests confirmed efficient digestion, with volatile fatty acids ranging from 140 to 300 mg/L acetic acid and alkalinity levels between 800 and 1,500 mg CaCO3/L. Our study estimated a significant methane content, with the potential to produce 94.32 L of methane from 1 kg of TS.","PeriodicalId":34693,"journal":{"name":"AQUA-Water Infrastructure Ecosystems and Society","volume":"83 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136346658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Corrigendum: <i>AQUA – Water Infrastructure, Ecosystems and Society</i> 72 (7), 1115–1129: Application of system dynamics model for reservoir performance under future climatic scenarios in Gelevard Dam, Iran, Ali Babolhakami, Mohammad Ali Gholami Sefidkouhi and Alireza Emadi, https://dx.doi.org/10.2166/aqua.2023.193","authors":"","doi":"10.2166/aqua.2023.206","DOIUrl":"https://doi.org/10.2166/aqua.2023.206","url":null,"abstract":"","PeriodicalId":34693,"journal":{"name":"AQUA-Water Infrastructure Ecosystems and Society","volume":"122 25","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135136553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Elham Derakhshani, Ali Naghizadeh, Sobhan Mortazavi-Derazkola
Abstract In this research, the magnetic NiFe2O4 nanocomposite was synthesized using Pulicaria gnaphalodes methanolic extract and applied to remove penicillin G from aqueous solutions. The results of field emission scanning electron microscopy, X-ray powder diffraction, Fourier transform infrared, VSM, and energy-dispersive spectroscopy-mapping analyses showed that this nanocomposite was well synthesized with a size of approximately 50–70 nm. The maximum adsorption capacity of the magnetic NiFe2O4 nanocomposite was 22.95 mg/g under optimal conditions. In addition, the experimental data of penicillin G adsorption by the magnetic NiFe2O4 nanocomposite showed that ΔH and ΔS values were positive and ΔG was negative and were following the Temkin isotherm model with R2 = 0.99 and follows the pseudo-second-order kinetic model.
{"title":"Phyto-assisted synthesis of magnetic NiFe2O4 nanocomposite using the <i>Pulicaria gnaphalodes</i> methanolic extract for the efficient removal of an antibiotic from the aqueous solution: a study of equilibrium, kinetics, isotherms, and thermodynamics","authors":"Elham Derakhshani, Ali Naghizadeh, Sobhan Mortazavi-Derazkola","doi":"10.2166/aqua.2023.117","DOIUrl":"https://doi.org/10.2166/aqua.2023.117","url":null,"abstract":"Abstract In this research, the magnetic NiFe2O4 nanocomposite was synthesized using Pulicaria gnaphalodes methanolic extract and applied to remove penicillin G from aqueous solutions. The results of field emission scanning electron microscopy, X-ray powder diffraction, Fourier transform infrared, VSM, and energy-dispersive spectroscopy-mapping analyses showed that this nanocomposite was well synthesized with a size of approximately 50–70 nm. The maximum adsorption capacity of the magnetic NiFe2O4 nanocomposite was 22.95 mg/g under optimal conditions. In addition, the experimental data of penicillin G adsorption by the magnetic NiFe2O4 nanocomposite showed that ΔH and ΔS values were positive and ΔG was negative and were following the Temkin isotherm model with R2 = 0.99 and follows the pseudo-second-order kinetic model.","PeriodicalId":34693,"journal":{"name":"AQUA-Water Infrastructure Ecosystems and Society","volume":" 22","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135291560","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Flow pattern identification (FPI) is crucial for evaluating air entrapment in water pipelines and ensuring the safety of pipeline operations. The presence of two-phase flow in water pipelines not only leads to pressure fluctuations but also induces pipeline vibration. However, current research has primarily focused on using pressure-related signals for FPI, and the analysis of vibration signals in FPI is rare. In this study, FPI in water pipelines is investigated based on convolutional neural networks (CNNs) using high-frequency vibration signals. The information fusion of vibration signals in FPI is newly proposed via the stacked generalization technique. The proposed method is compared with pressure signal-based FPI methods and the effect of signal sampling parameters on FPI accuracy is discussed. The results show that the performance of vibration signals (including axial or radial acceleration signals) outperforms pressure signals in both time and frequency domains. Moreover, the fusion of vibration signals shows the superior results compared to any univariate signals. The duration of sampling has a more significant impact on the results of FPI than the sampling frequency. This study provides a new way that FPI theory is applied to solve air entrapment evaluation in water pipelines.
{"title":"Unraveling air–water two-phase flow patterns in water pipelines based on multiple signals and convolutional neural networks","authors":"Peng Zhao, Ziyang Xu, Haixing Liu, Bing Yu","doi":"10.2166/aqua.2023.319","DOIUrl":"https://doi.org/10.2166/aqua.2023.319","url":null,"abstract":"Abstract Flow pattern identification (FPI) is crucial for evaluating air entrapment in water pipelines and ensuring the safety of pipeline operations. The presence of two-phase flow in water pipelines not only leads to pressure fluctuations but also induces pipeline vibration. However, current research has primarily focused on using pressure-related signals for FPI, and the analysis of vibration signals in FPI is rare. In this study, FPI in water pipelines is investigated based on convolutional neural networks (CNNs) using high-frequency vibration signals. The information fusion of vibration signals in FPI is newly proposed via the stacked generalization technique. The proposed method is compared with pressure signal-based FPI methods and the effect of signal sampling parameters on FPI accuracy is discussed. The results show that the performance of vibration signals (including axial or radial acceleration signals) outperforms pressure signals in both time and frequency domains. Moreover, the fusion of vibration signals shows the superior results compared to any univariate signals. The duration of sampling has a more significant impact on the results of FPI than the sampling frequency. This study provides a new way that FPI theory is applied to solve air entrapment evaluation in water pipelines.","PeriodicalId":34693,"journal":{"name":"AQUA-Water Infrastructure Ecosystems and Society","volume":" 34","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135291552","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Leak detection has significant implications for the long-term stable operation of water distribution networks (WDNs). This study presented a novel leak detection method by calculating the angular variance between a pressure vector and other vectors in the database, to evaluate the presence of an anomaly in a network. The top priority for this method was to establish a reliable dataset collected from the pressure sensors, which is generated by EPANET 2.2. Numerous node water demand data in normal conditions were generated by the Monte Carlo method, and leak conditions with various leak flows were simulated by creating leak holes in the pipes. Through learning the composite normal and abnormal data in a certain proportion, the angle-based outlier detection model was employed to identify abnormal events. This angle-based method was applied in an actual WDN and the identification performance for anomalies was compared with that of previous detection methods. The results indicated that the novel method proposed in this study could significantly improve the accuracy and efficiency of leak detection compared to the threshold-based and distance-based detection methods.
{"title":"An angle-based leak detection method using pressure sensors in water distribution networks","authors":"Huimin Yu, Hua Zhou, Xiaodan Weng, Zhihong Long, Yu Shao, Tingchao Yu","doi":"10.2166/aqua.2023.202","DOIUrl":"https://doi.org/10.2166/aqua.2023.202","url":null,"abstract":"Abstract Leak detection has significant implications for the long-term stable operation of water distribution networks (WDNs). This study presented a novel leak detection method by calculating the angular variance between a pressure vector and other vectors in the database, to evaluate the presence of an anomaly in a network. The top priority for this method was to establish a reliable dataset collected from the pressure sensors, which is generated by EPANET 2.2. Numerous node water demand data in normal conditions were generated by the Monte Carlo method, and leak conditions with various leak flows were simulated by creating leak holes in the pipes. Through learning the composite normal and abnormal data in a certain proportion, the angle-based outlier detection model was employed to identify abnormal events. This angle-based method was applied in an actual WDN and the identification performance for anomalies was compared with that of previous detection methods. The results indicated that the novel method proposed in this study could significantly improve the accuracy and efficiency of leak detection compared to the threshold-based and distance-based detection methods.","PeriodicalId":34693,"journal":{"name":"AQUA-Water Infrastructure Ecosystems and Society","volume":" 29","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135291964","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract A field study is done to analyze the effects of water reuse for irrigation with a focus on seed germination, crop morphology, crop yield, nutritional values of edible parts, fertilizer reduction, and benefit–cost ratio. For the study, three different crops, Lablab bean, tomato, and chilli, are considered and every crop type is irrigated with groundwater (GW), diluted treated wastewater (DTWW), and treated wastewater (TWW). The study reveals that the DTWW is optimal for seed germination. Crops irrigated with the TWW have the highest morphological characteristics. Crop yield is highest for the TWW-irrigated Lablab bean and DTWW-irrigated tomato. Chilli remains unproductive until the end due to thermal stress. Nutritional values of the edible parts of the DTWW- and TWW-irrigated crops are lower than the GW-irrigated crops. Crops irrigated with the DTWW and TWW are applied with the reduced quantities of N, P and K fertilizers. Indeed, even when the dosages are low those crops are able to produce higher yields than the GW-irrigated crops which are applied with full fertilization. As the crop yield is high and fertilizer cost is less, the benefit–cost ratio is higher for water reuse irrigation than the GW irrigation.
{"title":"Irrigation water quality from wastewater reuse or groundwater sources: bridging the water–nutrient–food nexus","authors":"B. Bharani Baanu, K. S. Jinesh Babu","doi":"10.2166/aqua.2023.390","DOIUrl":"https://doi.org/10.2166/aqua.2023.390","url":null,"abstract":"Abstract A field study is done to analyze the effects of water reuse for irrigation with a focus on seed germination, crop morphology, crop yield, nutritional values of edible parts, fertilizer reduction, and benefit–cost ratio. For the study, three different crops, Lablab bean, tomato, and chilli, are considered and every crop type is irrigated with groundwater (GW), diluted treated wastewater (DTWW), and treated wastewater (TWW). The study reveals that the DTWW is optimal for seed germination. Crops irrigated with the TWW have the highest morphological characteristics. Crop yield is highest for the TWW-irrigated Lablab bean and DTWW-irrigated tomato. Chilli remains unproductive until the end due to thermal stress. Nutritional values of the edible parts of the DTWW- and TWW-irrigated crops are lower than the GW-irrigated crops. Crops irrigated with the DTWW and TWW are applied with the reduced quantities of N, P and K fertilizers. Indeed, even when the dosages are low those crops are able to produce higher yields than the GW-irrigated crops which are applied with full fertilization. As the crop yield is high and fertilizer cost is less, the benefit–cost ratio is higher for water reuse irrigation than the GW irrigation.","PeriodicalId":34693,"journal":{"name":"AQUA-Water Infrastructure Ecosystems and Society","volume":"85 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135341841","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Valentina Marsili, Filippo Mazzoni, Stefano Alvisi, Filomena Maietta, Caterina Capponi, Silvia Meniconi, Bruno Brunone, Marco Franchini
Abstract Recent studies point out that water distribution networks can be affected by long- and short-term pressure oscillations due to the users' activity. However, these transients, generated at the household level, before reaching the water distribution network pass through, and thus affect, the water service line and can contribute to its deterioration. Despite the role of user-induced transients in stressing service lines, few studies in the literature explored the topic, exclusively by means of laboratory tests. The current study is aimed to explore the effects of user's activity on a real service line starting from the field monitoring of pressure data at 500-Hz temporal resolution. Pressure signals are collected both when activating single water devices of the user supplied by the service line and during the ordinary use of domestic devices. The analyses of the acquired data highlight that the domestic service line is subjected to significant pressure variations (which can reach extreme values of −15 and +65 m) based on the device type and distance between the device and the service line and that the use of these devices can continuously stress the water service line.
{"title":"Investigation of pressure transients induced on a real water service line by user's activity","authors":"Valentina Marsili, Filippo Mazzoni, Stefano Alvisi, Filomena Maietta, Caterina Capponi, Silvia Meniconi, Bruno Brunone, Marco Franchini","doi":"10.2166/aqua.2023.276","DOIUrl":"https://doi.org/10.2166/aqua.2023.276","url":null,"abstract":"Abstract Recent studies point out that water distribution networks can be affected by long- and short-term pressure oscillations due to the users' activity. However, these transients, generated at the household level, before reaching the water distribution network pass through, and thus affect, the water service line and can contribute to its deterioration. Despite the role of user-induced transients in stressing service lines, few studies in the literature explored the topic, exclusively by means of laboratory tests. The current study is aimed to explore the effects of user's activity on a real service line starting from the field monitoring of pressure data at 500-Hz temporal resolution. Pressure signals are collected both when activating single water devices of the user supplied by the service line and during the ordinary use of domestic devices. The analyses of the acquired data highlight that the domestic service line is subjected to significant pressure variations (which can reach extreme values of −15 and +65 m) based on the device type and distance between the device and the service line and that the use of these devices can continuously stress the water service line.","PeriodicalId":34693,"journal":{"name":"AQUA-Water Infrastructure Ecosystems and Society","volume":"83 s370","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135341678","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract Recently with the growing demand for water quality monitoring, soft measurement sensors have drawn public attention, which can overcome the drawbacks of high cost and long time needed in traditional measurement methods. In this study, a machine learning-based soft monitoring sensor was developed to simultaneously monitor four water quality indicators including COD, NH4+-N, NO3--N, PO43--P. Firstly, specialized experimental equipment and calibration methods were developed to generate a matching dataset that collected over 94,000 data points. Secondly, five models including Multiple Linear Regression, Ridge Regression, AdaBoost, Decision Tree Regression, and Bagging Regression were constructed and compared. The learning accuracy of the models ranged from 0.8860 to 0.9999, among which the predicted value of Bagging Regression is highly fit to the true value. Subsequently, the fuzzy grade method was adopted to reduce the prediction error and strike a balance between efficiency and accuracy. Finally, the designed soft sensor was used for real-time monitoring at three monitoring points in Changzhou, China from September to October 2020, and the results proved the feasibility of the soft sensor in practical application. This study provided a fast and accurate method for water quality measurement, which is of great significance for the management of rural sewage treatment facilities.
{"title":"Design and application of soft sensors in rural sewage treatment facilities","authors":"Bing Li, Siyuan Mao, Tuo Tian, Huaibin Bi, Yuxin Tian, Xueyan Ma, Yong Qiu","doi":"10.2166/aqua.2023.062","DOIUrl":"https://doi.org/10.2166/aqua.2023.062","url":null,"abstract":"Abstract Recently with the growing demand for water quality monitoring, soft measurement sensors have drawn public attention, which can overcome the drawbacks of high cost and long time needed in traditional measurement methods. In this study, a machine learning-based soft monitoring sensor was developed to simultaneously monitor four water quality indicators including COD, NH4+-N, NO3--N, PO43--P. Firstly, specialized experimental equipment and calibration methods were developed to generate a matching dataset that collected over 94,000 data points. Secondly, five models including Multiple Linear Regression, Ridge Regression, AdaBoost, Decision Tree Regression, and Bagging Regression were constructed and compared. The learning accuracy of the models ranged from 0.8860 to 0.9999, among which the predicted value of Bagging Regression is highly fit to the true value. Subsequently, the fuzzy grade method was adopted to reduce the prediction error and strike a balance between efficiency and accuracy. Finally, the designed soft sensor was used for real-time monitoring at three monitoring points in Changzhou, China from September to October 2020, and the results proved the feasibility of the soft sensor in practical application. This study provided a fast and accurate method for water quality measurement, which is of great significance for the management of rural sewage treatment facilities.","PeriodicalId":34693,"journal":{"name":"AQUA-Water Infrastructure Ecosystems and Society","volume":"44 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135433013","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：