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.     

Characteristics of roadside air pollution in Korean metropolitan city (Daegu) over last 5 to 6 years: temporal variations, standard exceedances, and dependence on meteorological conditions

The present study performed a roadside data analysis to provide baseline data for exploring associations between environmental exposure to four gaseous pollutants and health effects on residents living near roadways. The yearly roadside concentrations of CO and SO₂ showed a well-defined decreasing trend, whereas those of NO₂ and O₃ exhibited the reverse trend. In most cases, the diurnal trends of the roadside concentrations were well-defined for all seasons, plus the daytime concentrations were higher than the nighttime concentrations. In contrast to the other target pollutants, the daytime O₃ concentrations observed at the roadside sites were lower than those observed at the residential site, likely due to high-levels of fresh NO from traffic emissions that rapidly react with O₃, thereby reducing the O₃ roadside level. The Sunday roadside concentrations of CO, NO₂, and SO₂ were similar to or somewhat lower than the weekday concentrations. Conversely, for O_3, the Sunday roadside concentrations were similar to or somewhat higher than the weekday concentrations. The higher O₃ concentrations on Sunday may be due to the reduced titration from a decrease in NO_x emissions under VOC-limited conditions (low VOC/NO_x conditions). The monthly averages of O₃ concentrations exhibited the reverse seasonal variation to the other target compounds, with peak O₃ concentrations between April and June, and the second peak between August and October. It is also suggested that for O₃, the 8-h standard is more stringent than the 1-h standard, while for NO₂ and SO₂, the 1-h standard is more stringent than the 24-h standard. The multiple regression equations obtained from the relationship between the concentrations and five meteorological parameters indicated that the number and type of meteorological variables in the equations varied according to the pollutant, monitoring station, or season.     

Effects of hand weeding strip and nitrogen fertilizer on corn plants

The objective of the present research was to evaluate effects of different strip weed control associated with nitrogen fertilizer on corn applied after planting. The experiment was set and conducted in Botucatu, S?o Paulo State, Brazil, and the hybrid planted was Dekalb 333-B. A completely randomized block design with four replications was used. Experimental plots were disposed as a factorial scheme 2 x 2 x 4, constituted by two types of weeding on row (with or without manual hoeing), two types of weeding on inter-row (with or without manual hoeing), and four nitrogen levels applied after planting (00, 60, 90, and 120 kg ha(-1)). Plots were composed by six rows with 5 m length. Nitrogen fertilizer was applied at 35 days after emergence (d.a.e). For weed community it was evaluated: weed density, dominancy, frequency, and relative importance. The main weed species were: Brachiaria plantiginea, Amaranthus retroflexus, Bidens pilosa, Cyperus rotunds, Brachiaria decumbens, Euphorbia heterofila, Oxalis latifolia, Acanthospermum hispidum, Commelina benghalensis. It was evaluated corn height at 40 and 100 d.a.e., first ear insertion height at 100 d.a.e., and final grain yield at harvesting. Plants and first ear insertion height were affected when nitrogen fertilizer was not applied. Treatments without weed control showed that weed interfered negatively with plants height. There were no correlation between weeds and nitrogen fertilizer for all parameters evaluated. Parcels without weed showed the highest ear weights and final grain production. Treatments that received nitrogen fertilizer, independently of studied arrangement, provided higher yields.     

Urban wild meat consumption and trade in central Amazonia

The switch from hunting wild meat for home consumption to supplying more lucrative city markets in Amazonia can adversely affect some game species. Despite this, information on the amounts of wild meat eaten in Amazonian cities is still limited. We estimated wild meat consumption rates in 5 cities in the State of Amazonas in Brazil through 1046 door-to-door household interviews conducted from 2004 to 2012. With these data, we modeled the relationship between wild meat use and a selection of socioeconomic indices. We then scaled up our model to determine the amounts of wild meat likely to be consumed annually in the 62 urban centers in central Amazonia. A total of 80.3% of all interviewees reported consuming wild meat during an average of 29.3 (CI 11.6) days per year. Most wild meat was reported as bought in local markets (80.1%) or hunted by a family member (14.9%). Twenty-one taxa were cited as consumed, mostly mammals (71.6%), followed by reptiles (23.2%) and then birds (5.2%). The declared frequency of wild meat consumption was positively correlated with the proportion of rural population as well as with the per capita gross domestic product of the municipality (administrative divisions) where the cities were seated. We estimated that as much as 10,691 t of wild meat might be consumed annually in the 62 urban centers within central Amazonia, the equivalent of 6.49 kg per person per year. In monetary terms, this amounts to US$21.72 per person per year or US$35.1 million overall, the latter figure is comparable to fish and timber production in the region. Given this magnitude of wild meat trade in central Amazonia, it is fundamental to integrate this activity into the formal economy and actively develop policies that allow the trade of more resilient taxa and restrict trade in species sensitive to hunting.     

Genetic Diversity and Population Size in Four Rare Southern Appalachian Plant Species

Allozyme diversity was examined in four rare, high-montane plant species from the Appalachian Mountains of southeastern North America. These species may represent relictual members or descendants of an alpine community that was more widespread during the late Pleistocene. We sampled five populations of Geum radiatum (Rosaceae), Carex misera (Cyperaceae), Trichophorum cespitosum (Cyperaceae), and the four known populations of Calamagrostis cainii (Poaceae). Genetic diversity was low for all species but was typical of that found for plant species with limited ranges. Low genetic diversity may reflect historical events associated with changes in the species' biogeography. As the Pleistocene climate warmed, suitable habitat decreased in areal extent and became fragmented, probably resulting in smaller, more-isolated populations. In recent times these species, which co-occur in fragile rock outcrop habitats, have been adversely affected by human activities. Genetic analyses revealed reduced diversity in populations of decreasing size for three species. Estimates of gene flow were low ( Nm < 1.0) in all four species. Positive associations between genetic diversity and population size, evidence of recent population declines, and the low estimates of gene flow suggest that genetic drift may play a prominent role in shaping the present-day genetic composition of these species. Furthermore, these data suggest that the genetically depauperate populations are unlikely to regain genetic variation without human intervention.