Prediction of effluent concentration in a wastewater treatment plant using machine learning models

Of growing amount of food waste, the integrated food waste and waste water treatment was regarded as one of the efficient modeling method. However, the load of food waste to the conventional waste treatment process might lead to the high concentration of total nitrogen(T-N) impact on the effluent water quality. The objective of this study is to establish two machine learning models—artificial neural networks(ANNs) and support vector machines(SVMs), in order to predict 1-day interval T-N concentration of effluent from a wastewater treatment plant in Ulsan, Korea. Daily water quality data and meteorological data were used and the performance of both models was evaluated in terms of the coefficient of determination(R~2), Nash–Sutcliff efficiency(NSE), relative efficiency criteria(d rel). Additionally, Latin-Hypercube one-factor-at-a-time(LH-OAT) and a pattern search algorithm were applied to sensitivity analysis and model parameter optimization, respectively. Results showed that both models could be effectively applied to the 1-day interval prediction of T-N concentration of effluent. SVM model showed a higher prediction accuracy in the training stage and similar result in the validation stage.However, the sensitivity analysis demonstrated that the ANN model was a superior model for 1-day interval T-N concentration prediction in terms of the cause-and-effect relationship between T-N concentration and modeling input values to integrated food waste and waste water treatment. This study suggested the efficient and robust nonlinear time-series modeling method for an early prediction of the water quality of integrated food waste and waste water treatment process.     

Fuelwood assessment at the micro-watershed level:a case study in Garhwal Himalaya,India

Biomass,as fuelwood,is one of the major sources of energy in rural areas,especially in the mountainous regions of the world.As the increasing human population exerts more pressure on the forest thereby inducing an adverse effect on the sustainability of the ecosystem,which consequently causes fuelwood crisis at a local level,this crisis is spatio-temporal in nature.Thus,the major objective of this study is to assess the sustainability of fuelwood at different probable scenarios at a micro watershed level.The present study was conducted in the Phakot watershed,the Tehri Garhwal district of central Himalaya in India,during 2006-2008.Based on the vegetation composition in the study area,the net primary productivity(NPP)value of the Oak forest,and mixed oak and sal forests,was used for the quantification of fuelwood availability in evergreen and deciduous forests,respectively.The fuelwood demand was calculated on the basis of seasonal fuelwood consumption values.Nine probable permutations for availability-demand scenarios assuming the existence of high(H),low(L)and average(A)conditions were analyzed for evaluating the stress.The available annual harvestable fuelwood in the watershed is in the minimum and maximum ranges of 2283.28 to 4066.00 tons,respectively,per year whereas it has a demand of 110.76 tons as the minimum to 3659 tons as the maximum annually.This shows that in the current availabilitydemand scenario,the watershed does not have fuelwood crisis in the present situation but needs to maintain the sustainability of the system.Based on our study,it is concluded that,globally,more spatio-temporal study is required to understand the issues at the local level.     

Nanoparticles in wastewater from a science-based industrial park - coagulation using polyaluminum chloride

The Hsinchu Science-based Industrial Park (HSIP) is the hi-tech manufacturing hub of Taiwan. Wastewater from the HSIP contains numerous nano-sized silicate particles whose size distributions peak at 2 and 90 nm. A 3-5 mg l(-1) as Al dose of polyaluminum chloride (PACl) was used in the field to coagulate these particles, but the removal efficiency was low. Laboratory scale tests indicated that although PACl coagulation removed 52% of the turbidity and 48% of the chemical oxygen demand (COD) from water, its effect on nano-particle removal was minimal. About 58% of the soluble COD was associated with colloidal Si particles. A light scattering test and transmission electron microscopy (TEM) demonstrated that the nano-particles agglomerated in approximately linear aggregates of sizes 100-300 nm. Prolonged contact between residual PACl and the nano-particles generated large aggregates with sizes of up to 10 microm and a fractal dimension of 2.24-2.63. The results presented herein should be of interest in the processing of "high-tech" wastewater that contains nanosized silica particles.     

A Recourse‐Based Interval Fuzzy Programming Model for Point‐Nonpoint Source Effluent Trading under Uncertainty

In this study, a recourse‐based interval fuzzy programming (RIFP) model is developed for tackling uncertainties expressed as fuzzy, interval, and/or probabilistic forms in an effluent trading program. It can incorporate preregulated water‐pollution control policies directly into its optimization process, such that an effective linkage between environmental regulations and economic implications (i.e., penalties) caused by improper policies due to uncertainty existence can be provided. The RIFP model is applied to point‐nonpoint source effluent trading of the Xiangxi River in China. The efficiency of trading efforts between water quality improvement and net system benefit under different degrees of satisfying discharge limits is analyzed. The results are able to help support (1) formulation of water‐pollution control strategies under various economic objectives and system‐reliability constraints, (2) selection of the desired effluent trading pattern for point and nonpoint sources, and (3) generation of tradeoffs among system benefit, satisfaction degree, and pollutant mitigation under multiple uncertainties. Compared with the traditional regulatory approaches, the results demonstrate that the water‐pollution control program can be performed more cost‐effectively through trading than nontrading.     

Effect of external potassium (K) supply on the uptake of 137Cs by spring wheat (Triticum aestivum cv. Tonic): a large-scale hydroponic study.

A large-scale hydroponic experiment was carried out in a non-controlled greenhouse. Spring wheat plants were grown to maturity at four levels of external K concentration (2, 4, 20 and 40 mgl(-1)) and one concentration of radiocaesium (8 Bqml(-1)). Concentrations of K and radiocaesium in the growth solution were closely monitored, and replenishments were made upon depletion. K effectively competed with radiocaesium in terms of root uptake. Activity concentrations of radiocaesium in plants differed significantly between the four K treatments; the activity concentration at the lowest external K concentration being 100 times higher than that at the highest K level. The relationship between radiocaesium uptake and external K level could be described by a negative power function; this showed that when the K level reached around 12 mgl(-1), further increases in the external K level resulted only in slight changes in its inhibitory effect. As a result of this inhibitory effect of potassium supply, concentrations of radiocaesium in plant tissues, grains in particular, were greatly reduced at high external K concentration. Mechanisms involved in Cs-K interaction in root uptake are also discussed.     

Innovative process routes for a high-quality concrete recycling

This study presents alternative methods for the processing of concrete waste. The mechanical stresses needed for the embrittlement of the mortar matrix and further selective crushing of concrete were generated by either electric impulses or microwaves heating. Tests were carried out on lab-made concrete samples representative of concrete waste from concrete mixer trucks and on concrete waste collected on a French demolition site. The results obtained so far show that both techniques can be used to weaken concrete samples and to enhance aggregate selective liberation (that is the production of cement paste-free aggregates) during crushing and grinding. Electric pulses treatment seems to appear more efficient, more robust and less energy consuming (1–3 kW h t^?1) than microwave treatment (10–40 kW h t^?1) but it can only be applied on samples in water leading to a major drawback for recycling aggregates or cement paste in the cement production process.