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

Li, Wei; Zhang, Yaqiong; Cai, Zhang-Jie; Zhang, Manyin; Xu, Weigang; Zhao, Xinsheng; Lei, Yinru; Pan, Xu; Li, Jing; Dou, Zhiguo

doi:10.3390/w10010083

Cited by 12 publications

(11 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wetlands are useful for controlling pollution related to phosphorus (P) [1][2][3][4], as it may be taken up by vegetation before being washed into lakes or rivers. Much research is concerned with the effects of P removal by plants in wetlands [1,5,6], especially with the control of non-point source pollution [7].…”

Section: Introductionmentioning

confidence: 99%

Phosphorus Solubilizing and Releasing Bacteria Screening from the Rhizosphere in a Natural Wetland

Cao

Liu

et al. 2018

Water

View full text Add to dashboard Cite

Inorganic phosphorus (P)-solubilizing bacteria (IPSB) and organic P-mineralizing bacteria (OPMB) were isolated from bacteria that were first extracted from the rhizosphere soil of a natural wetland and then grown on either tricalcium phosphate or lecithin medium. The solubilizing of inorganic P was the major contribution to P availability, since the isolated bacteria released much more available P from inorganic tricalcium phosphate than lecithin. IPSB No. 5 had the highest P release rate, that is, 0.53 mg·L −1 ·h −1 in 96 h, and R10 s release rate was 0.52 mg·L −1 ·h −1 in 10 days. The bacteria were identified as Pseudomonas sp. and Pseudomonas knackmussii, respectively. R10 released as much as 125.88 mg·L −1 dissolved P from tricalcium phosphate medium, while R4 released the most dissolved P from organic P medium among the isolates, with a concentration of 1.88 mg·L −1 and a releasing rate of 0.0078 mg·L −1 ·h −1 in ten days. P releasing increased with a pH decrease only when it was from inorganic P, not organic lecithin, and there was no significant correlation between the culture pH and P solubilizing. High-throughput sequencing analysis revealed that the dominant phylum in the studied wetland rhizosphere consisted of Acidobacteria, Proteobacteria, Bacteroidetes and Chloroflexi, accounting for 34.9%, 34.2%, 8.8% and 4.8%, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

Phosphorus Solubilizing and Releasing Bacteria Screening from the Rhizosphere in a Natural Wetland

Cao

Liu

et al. 2018

Water

View full text Add to dashboard Cite

show abstract

“…Ramya J. et al [31] and Wei L. et al [32] have designed and gave a simulation system as illustrated in Figure 15 and Figure 16 respectively, which they shown that the best value of MSE equal to 4.3515e-14 and equal to 1.3205e-15 were reached at the epoch 24 and 36 respectively. Thus, from the other previous works, we conclude that our proposed BPNN gets the best results in the training testing performance value, where the best SME value was equal to 1.85e-32 at the 12 th epoch of training.…”

Section: Resultsmentioning

confidence: 99%

Application and evaluation of the neural network in gearbox

Al-Azzawi

2020

TELKOMNIKA

View full text Add to dashboard Cite

We developed old designed of a Back-Propagation neural network (BPNN), which it was designed by other researchers, and we made modification in their structure. The 1 st velocity ratio was discriminated by lowest speed, and highest twist. The 6 th velocity ratio was discriminated by highest speed, and lowest twist. The aim of this paper is to design neural structure get best performance to control an electrical automotive transportation six-speed gearbox of the vehicle. We focus on the evaluation of the BPNN to select the suitable number of layers and neurons. Experimentally, the structure of the proposed BPNN are constructed from four layers: eight input nodes in the first layer that received data in binary number, 45 neurons in 1 st hidden-layer, 25 neurons in 2 nd hidden-layer, and 6 neurons in the fourth layer. The MSE and number of Epochs are the main factors used for the evaluation of the proposed structure, and compared with the other structures which was designed by other researchers. Experimentally, we discovered that the best value of Epoch and MSE was chosen when the BPNN consisted of two hidden-layers, 45, and 25 neurons in the 1 st and 2 nd hidden-layer respectively. The implementation was applied using MATLAB software.

show abstract

“…The GA algorithm can improve the BPNN's slow convergence, which easily falls into the local optima and other issues [25][29]. The optimization goals were the optimization of network weights, the network structure, and learning rules [26][30]. In this paper, the weights and thresholds were optimized by a genetic algorithm.…”

Section: Methodsmentioning

confidence: 99%

Prediction model for the water jet falling point in fire extinguishing based on a GA-BP neural network

Zhang

Dai

et al. 2019

PLoS ONE

View full text Add to dashboard Cite

Past research on the process of extinguishing a fire typically used a traditional linear water jet falling point model and the results ignored external factors, such as environmental conditions and the status of the fire engine, even though the water jet falling point location prediction was often associated with these parameters and showed a nonlinear relationship. This paper constructed a BP (Back Propagation) neural network model. The fire gun nozzle characteristics were included as model inputs, and the water discharge point coordinates were the model outputs; thus, the model could precisely predict the water discharge point with small error and high precision to determine an accurate firing position and allow for the timely adjustment of the spray gun. To improve the slow convergence and local optimality problems of the BP neural network (BPNN), this paper further used a genetic algorithm to optimize the BPNN (GA-BPNN). The BPNN can be used to optimize the weights in the network to train them for global optimization. A genetic algorithm was introduced into the neural network approach, and the water jet landing prediction model was further improved. The simulation results showed that the prediction accuracy of the GA-BP model was better than that of the BPNN alone. The established model can accurately predict the location of the water jet, making the prediction results more useful for firefighters.

show abstract

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

Cited by 12 publications

References 25 publications

Phosphorus Solubilizing and Releasing Bacteria Screening from the Rhizosphere in a Natural Wetland

Phosphorus Solubilizing and Releasing Bacteria Screening from the Rhizosphere in a Natural Wetland

Application and evaluation of the neural network in gearbox

Prediction model for the water jet falling point in fire extinguishing based on a GA-BP neural network

Contact Info

Product

Resources

About