Modeling total phosphorus removal in an aquatic environment restoring horizontal subsurface flow constructed wetland based on artificial neural networks

Li, Wei; Zhang, Manyin; Wang, Yifei

doi:10.1007/s11356-015-4527-2

Cited by 13 publications

(7 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, environmental indicators have a more significant impact on different denitrifying bacteria, which also changes the diversity of denitrifying bacteria community. Accordingly, these results, combined with prediction models of the effects of environmental factors on nitrogen and phosphorus 29 – 31 , could be used to predict changes in the denitrifying bacterial community structure.…”

Section: Resultsmentioning

confidence: 99%

Denitrifying bacterial communities in surface-flow constructed wetlands during different seasons: characteristics and relationships with environment factors

Wei

Ping

et al. 2021

Sci Rep

Self Cite

View full text Add to dashboard Cite

Denitrification is an important part of the nitrogen cycle and the key step to removal of nitrogen in surface-flow wetlands. In this study, we explored space–time analysis with high-throughput sequencing to elucidate the relationships between denitrifying bacteria community structures and environmental factors during different seasons. Our results showed that along the flow direction of different processing units, there were dynamic changes in physical and chemical indicators. The bacterial abundance indexes (ACEs) in May, August, and October were 686.8, 686.8, and 996.2, respectively, whereas the Shannon-Weiner indexes were 3.718, 4.303, and 4.432, respectively. Along the flow direction, the denitrifying bacterial abundance initially increased and then decreased subsequently during the same months, although diversity tended to increase. The abundance showed similar changes during the different months. Surface flow wetlands mainly contained the following denitrifying bacteria genus: unclassified Bacteria (37.12%), unclassified Proteobacteria (18.16%), Dechloromonas (16.21%), unranked environmental samples (12.51%), unclassified Betaproteobacteria (9.73%), unclassified Rhodocyclaceae (2.14%), and Rhodanobacter (1.51%). During different seasons, the same unit showed alternating changes, and during the same season, bacterial community structures were influenced by the second genus proportion in different processing units. ACEs were strongly correlated with temperature, dissolved oxygen, and pH. Bacterial diversity was strongly correlated with temperature, electrical conductivity, pH, and oxidation reduction potential. Denitrifying bacteria are greatly affected by environmental factors such as temperature and pH.

show abstract

Section: Resultsmentioning

confidence: 99%

Denitrifying bacterial communities in surface-flow constructed wetlands during different seasons: characteristics and relationships with environment factors

Wei

Ping

et al. 2021

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…The model was divided into training data and validation data [31]. The data were divided into 112 groups of training data and 56 sets of validation data using a randomly generated method.…”

Section: Building the Bp Artificial Neural Networkmentioning

confidence: 99%

Using a Backpropagation Artificial Neural Network to Predict Nutrient Removal in Tidal Flow Constructed Wetlands

Zhang

Cai

et al. 2018

Water

Self Cite

View full text Add to dashboard Cite

Nutrient removal in tidal flow constructed wetlands (TF-CW) is a complex series of nonlinear multi-parameter interactions. We simulated three tidal flow systems and a continuous vertical flow system filled with synthetic wastewater and compared the influent and effluent concentrations to examine (1) nutrient removal in artificial TF-CWs, and (2) the ability of a backpropagation (BP) artificial neural network to predict nutrient removal. The nutrient removal rates were higher under tidal flow when the idle/reaction time was two, and reached 90 ± 3%, 99 ± 1%, and 58 ± 13% for total nitrogen (TN), ammonium nitrogen (NH 4 + -N), and total phosphorus (TP), respectively. The main influences on nutrient removal for each scenario were identified by redundancy analysis and were input into the model to train and verify the pollutant effluent concentrations. Comparison of the actual and model-predicted effluent concentrations showed that the model predictions were good. The predicted and actual values were correlated and the margin of error was small. The BP neural network fitted best to TP, with an R 2 of 0.90. The R 2 values of TN, NH 4 + -N, and nitrate nitrogen (NO 3 − -N) were 0.67, 0.73, and 0.69, respectively.

show abstract

“…However, the effects of different denitrifying bacterial genera on various environmental indicators were more obvious, thereby altering denitrifying bacteria community diversity. Accordingly, these results, combined with prediction models of the effects of environmental factors on nitrogen and phosphorus (Li W et al,2014;Li W et al,2015;Cui L et al,2016), could be used to predict changes in the 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 denitrifying bacterial community structure.…”

Section: Relationships Between Denitrifying Bacteria and Environmentamentioning

confidence: 99%

Denitrifying bacterial communities in surface-flow constructed wetlands during different seasons : characteristics and relationships with environment factors

Wei

Cui

et al. 2017

Preprint

Self Cite

View full text Add to dashboard Cite

Denitrification is an important part of the nitrogen cycle and the key step to removal of nitrogen in surface-flow wetlands. Denitrifying bacteria also function in denitrification. In this study, we explored space-time analysis with high-throughput sequencing to elucidate the relationships between denitrifying bacteria community structures and environmental factors during different seasons. Our results showed that along the flow direction of different processing units, there were dynamic changes in physical and chemical indicators. The bacterial abundance indexes (ACEs) in May, August, and October were 686.8, 686.8, and 996.2, respectively, whereas the Shannon-Weiner indexes were3.718, 4.303, and 4.432, respectively. Along the flow direction, the denitrifying bacterial abundance initially increased and then decreased subsequently during the same months, although diversity tended to increase. The abundance showed similar changes during the different months. Surface flow wetlands mainly contained the following denitrifying bacteria genus: unclassified Bacteria (37.12%), unclassified Proteobacteria (18.16%), Dechloromonas (16.21%), unranked environmental samples (12.51%), unclassified Betaproteobacteria (9.73%), unclassified Rhodocyclaceae (2.14%), and Rhodanobacter (1.51%). During different seasons, the same species processing units showed alternating changes, and during the same season, bacterial community structures were influenced by the second genus proportion in different processing units. ACEs were strongly correlated with temperature, dissolved oxygen, and pH. Bacterial diversity was strongly correlated with temperature, electrical conductivity, pH, and oxidation reduction potential. All denitrifying bacterial species were greatly affected by environmental factors, including temperature and pH, and the effects of electrical conductivity and oxidation reduction potential were similar. Abstract: Denitrification is an important part of the nitrogen cycle and the key step to removal of nitrogen in surface-flow wetlands. Denitrifying bacteria also function in denitrification. In this study, we explored space-time analysis with high-throughput sequencing to elucidate the relationships between denitrifying bacteria community structures and environmental factors during different seasons. Our results showed that along the flow direction of different processing units, there were dynamic changes in physical and chemical indicators. The bacterial abundance indexes (ACEs) in May, August, and October were 686.8, 686.8, and 996.2, respectively, whereas the Shannon-Weiner indexes were 3.718, 4.303, and 4.432, respectively. Along the flow direction, the denitrifying bacterial abundance initially increased and then decreased subsequently during the same months, although diversity tended to increase. The abundance showed similar changes during the different months. Surface flow wetlands mainly contained the following denitrifying bacteria genus: unclassified Bacteria (37.12%), unclassified Proteobacteria (18.16%), Dechloromon...

show abstract

Modeling total phosphorus removal in an aquatic environment restoring horizontal subsurface flow constructed wetland based on artificial neural networks

Cited by 13 publications

References 26 publications

Denitrifying bacterial communities in surface-flow constructed wetlands during different seasons: characteristics and relationships with environment factors

Denitrifying bacterial communities in surface-flow constructed wetlands during different seasons: characteristics and relationships with environment factors

Using a Backpropagation Artificial Neural Network to Predict Nutrient Removal in Tidal Flow Constructed Wetlands

Denitrifying bacterial communities in surface-flow constructed wetlands during different seasons : characteristics and relationships with environment factors

Contact Info

Product

Resources

About