A Hybrid Neural Network Model for Marine Dissolved Oxygen Concentrations Time-Series Forecasting Based on Multi-Factor Analysis and a Multi-Model Ensemble

Dissolved oxygen(DO)is an important indicator of aquaculture,and its accurate forecasting can effectively improve the quality of aquatic products.In this paper,a new DO hybrid forecasting model is proposed that includes three stages:multi-factor analysis,adaptive decomposition,and an optimizationbased ensemble.First,considering the complex factors affecting DO,the grey relational(GR)degree method is used to screen out the environmental factors most closely related to DO.The consideration of multiple factors makes model fusion more effective.Second,the series of DO,water temperature,salinity,and oxygen saturation are decomposed adaptively into sub-series by means of the empirical wavelet transform(EWT)method.Then,five benchmark models are utilized to forecast the sub-series of EWT decomposition.The ensemble weights of these five sub-forecasting models are calculated by particle swarm optimization and gravitational search algorithm(PSOGSA).Finally,a multi-factor ensemble model for DO is obtained by weighted allocation.The performance of the proposed model is verified by timeseries data collected by the pacific islands ocean observing system(PacIOOS)from the WQB04 station at Hilo.The evaluation indicators involved in the experiment include the Nash–Sutcliffe efficiency(NSE),Kling–Gupta efficiency(KGE),mean absolute percent error(MAPE),standard deviation of error(SDE),and coefficient of determination(R^(2)).Example analysis demonstrates that:①The proposed model can obtain excellent DO forecasting results;②the proposed model is superior to other comparison models;and③the forecasting model can be used to analyze the trend of DO and enable managers to make better management decisions.

Dissolved oxygen concentration control in wastewater treatment process based on reinforcement learning

In this article, the dissolved oxygen(DO) concentration control problem in wastewater treatment process(WWTP) is studied.Unlike existing control strategies that control DO concentration at a fixed value, here we develop a different control framework.Under the proposed control framework, an intelligent control method of DO concentration based on reinforcement learning(RL)algorithm is presented to resolve the DO concentration control problem. By using the deep deterministic policy gradient(DDPG)algorithm, the DO concentration of the fifth tank in the activated sludge reactor can be adjusted dynamically. In addition, by designing two different reward functions and by analysing the relationships among effluent quality, energy consumption, and DO concentration, the target of energy-saving and emission-reducing is achieved. The simulation results indicate that the designed control method can reduce energy consumption while ensuring that the effluent quality meet the specified standards.

Relationship of Abundance of Oceanic Sea Skaters, Halobates in the Tropical Pacific Ocean to Surface Biomass and Chlorophyll/Oxygen Concentrations

Relationship of population density of oceanic sea skaters collected from tropical and subtropical zones in the Pacific Ocean was examined to chlorophyll concentration/Dissolved Oxygen concentration and biomass in surface sea water. The four parameters shown above were measured at the site of 12oN 135oN during the cruise, MR13-03 cruise, and at the site of 25oN 160oE during another cruise KH-14-02. Significant and positive correlation between all biomass (especially invertebrates) and population density of oceanic sea skaters collected with a Neuston-Net trailing during 15 min was shown in overall analysis on the data of the both samplings (p oN 160oE than that at 12oN 135oN with similar value of chlorophyll value (p oN 160oE than that at 12oN 135oN for keeping high density population of oceanic sea skaters.

Effects of COD/N ratio and DO concentration on simultaneous nitrification and denitrification in an airlift internal circulation membrane bioreactor

The effects of chemical oxygen demand and nitrogen(COD/N)ratio and dissolved oxygen concentration(DO)on simultaneous nitrification and denitrification(SND)were investigated using an airlift internal circulation membrane bioreactor(AIC-MBR)with synthetic wastewater.The results showed that the COD efficiencies were consistently greater than 90% regardless of changes in the COD/N ratio.At the COD/N ratio of 4.77 and 10.04,the system nitrogen removal efficiency became higher than 70%.However,the nitrogen remova...

Performance of Sequencing Biofilm Batch Reactor(SBBR) under Micro-aerobic Condition for Aniline-Contaminated Wastewater Treatment

The performance of sequencing biofilm batch reactor( SBBR) under micro-aerobic condition for aniline-contaminated wastewater treatment was investigated in this study. Dissolved oxygen( DO) and aniline concentrations were selected as the operating variables to analyze,model,and optimize the process. In order to analyze the process,5 dependent parameters,chemical oxygen demand( COD),aniline,ammonium,total nitrogen( TN),and total phosphorous( TP) removal as the process responses were studied. From the results, increase in DO concentration could promote the removal of COD,aniline,ammonium,and TN,while increase in aniline concentration has a slightly negative impact on the removal of pollutants. The optimum DO concentration was found to be 0. 4-0. 5 mg /L. The removal efficiencies for COD,aniline,ammonium,and TN at the optimum point( DO concentration0. 5 mg /L,aniline concentration 11 mg /L) were 95. 84%,100%,75. 72%,and 45. 39%,respectively. The oxidative deamination was the main degradation method for aniline under micro-aerobic condition. Simultaneously nitrification-denitrification( SND)process performed under micro-aerobic condition and about 20%-40% nitrogen was removed by SND.