Deep learning architecture for air quality predictions

With the rapid development of urbanization and industrialization, many developing countries are suffering from heavy air pollution. Governments and citizens have expressed increasing concern regarding air pollution because it affects human health and sustainable development worldwide. Current air quality prediction methods mainly use shallow models; however, these methods produce unsatisfactory results, which inspired us to investigate methods of predicting air quality based on deep architecture models. In this paper, a novel spatiotemporal deep learning (STDL)-based air quality prediction method that inherently considers spatial and temporal correlations is proposed. A stacked autoencoder (SAE) model is used to extract inherent air quality features, and it is trained in a greedy layer-wise manner. Compared with traditional time series prediction models, our model can predict the air quality of all stations simultaneously and shows the temporal stability in all seasons. Moreover, a comparison with the spatiotemporal artificial neural network (STANN), auto regression moving average (ARMA), and support vector regression (SVR) models demonstrates that the proposed method of performing air quality predictions has a superior performance.     

The fractionation and geochemical characteristics of rare earth elements measured in ambient size-resolved PM in an integrated iron and steelmaking industry zone

Environmental Science and Pollution Research - Improved understanding of the fractionation and geochemical characteristic of rare earth elements (REEs) from steel plant emissions is important due...     

Trends and variations of pH and hardness in a typical semi-arid river in a monsoon climate region during 1985–2009

The rapid growth of urbanization and industrialization, along with dramatic climate change, has strongly influenced hydrochemical characteristics in recent decades in China and thus could cause the variation of pH and general total hardness of a river. To explore such variations and their potential influencing factors in a river of the monsoon climate region, we analyzed a long-term monitoring dataset of pH, SO₄ ^2?, NO_x, general total hardness (GH), Mg²⁺, Ca²⁺, and Cl^? in surface water and groundwater in the Luan River basin from 1985 to 2009. The nonparametric Seasonal Kendall trend test was used to test the long-term trends of pH and GH. Relationship between the affecting factors, pH and GH were discussed. Results showed that pH showed a decreasing trend and that GH had an increasing trend in the long-term. Seasonal variation of pH and GH was mainly due to the typical monsoon climate. Results of correlation analysis showed that the unit area usage amounts of chemical fertilizer, NO₃ ^?, and SO₄ ^2? were negatively correlated with pH in groundwater. In addition, mining activity affected GH spatial variation. Acid deposition, drought, and increasing the use of chemical fertilizers would contribute to the acidification trend, and mining activities would affect the spatial variation of GH. Variations of precipitation and runoff in semi-arid monsoon climate areas had significant influences on the pH and GH. Our findings implied that human activities played a critical role in river acidification in the semi-arid monsoon climate region of northern China.     

Vehicle emission implications of drivers’ smart advisory system for traffic operations in work zones

Wireless communication systems have been broadly applied in various complicated traffic operations to improve mobility and safety on roads, which may raise a concern about the implication of the new technology on vehicle emissions. This paper explores how the wireless communication systems improve drivers’ driving behaviors and its contributions to the emission reduction, in terms of Operating Mode (OpMode) IDs distribution used in emission estimation. A simulated work zone with completed traffic operation was selected as a test bed. Sixty subjects were recruited for the tests, whose demographic distribution was based on the Census data in Houston, Texas. A scene of a pedestrian’s crossing in the work zone was designed for the driving test. Meanwhile, a wireless communication system called Drivers Smart Advisory System (DSAS) was proposed and introduced in the driving simulation, which provided drivers with warning messages in the work zone. Two scenarios were designed for a leading vehicle as well as for a following vehicle driving through the work zone, which included a base test without any wireless communication systems, and a driving test with the trigger of the DSAS. Subjects’ driving behaviors in the simulation were recorded to evaluate safety and estimate the vehicle emission using the Environmental Protection Agency (EPA) released emission model MOVES. The correlation between drivers’ driving behavior and the distribution of the OpMode ID during each scenario was investigated. Results show that the DSAS was able to induce drivers to accelerate smoothly, keep longer headway distance and stop earlier for a hazardous situation in the work zone, which driving behaviors result in statistically significant reduction in vehicle emissions for almost all studied air pollutants (p-values range from 4.10E-51 to 2.18E-03). The emission reduction was achieved by the switching the distribution of the OpMode IDs from higher emission zones to lower emission zones.

Implications: Transportation section is a significant source of greenhouse gas emissions. Many studies demonstrate that the wireless communication system dedicated for safety and mobility issues may contribute to the induction in vehicle emissions through changing driving behaviors. An insight into the correlation between the driving behaviors and the distribution of Operating Mode (OpMode) IDs is essential to enhance the emission reduction. The result of this study shows that with a Drivers Smart Advisory System (DSAS) drivers accelerated smoothly and stopped earlier for a hazardous situation, which induce the switch of the OpMode IDs from high emission zones to lower emission zones.     

The influence of Chinese population policy change on resources and the environment

Universal two-child policy has been implemented since the end of 2015 in China. This policy is anticipated to bring a significant increase in the total population, with profound influences on the resources and environment in the future. This paper analyzes the changing dynamics of urban and rural population, and forecasts urban and rural population from 2016 to 2030 at national and provincial scale using a double log linear regression model. Drawing upon the results of these two predictions, the impact of the population policy change on Chinese resources consumption and environmental pollution are predicted quantitatively. Given the future total population maintains current levels on resources consumption and environmental emission, the additional demand of resources and environment demand for the new population is forecasted and compared against the capacity on supply side. The findings are as follows: after implementing the universal two-child policy, China’s grain, energy consumption, domestic water demand, and pollutant emissions are projected to increase at different rates across provinces. To meet the needs arising from future population growth, food and energy self-sufficiency rate will be significantly reduced in the future, while relying more on imports. Stability of the water supply needs to be improved, especially in Beijing, Henan, Jiangsu, Qinghai, and Sichuan where the gap in future domestic water demand is comparatively larger. Environmental protection and associated governing capability are in urgent need of upgrade not least due to the increasing pressure of pollution.     

丹江口水库表层沉积物不同形态氮的赋存特征及其生物有效性

为了揭示丹江口水库沉积物氮空间分布特征及其生物有效性,采用连续分级提取法研究了表层沉积物中可交换态氮(Exchangeable nitrogen,EN)、酸解态氮(Acid hydrolysable nitrogen,HN)及残渣态氮(Residue nitrogen,RN)的赋存特征,同时结合生物可利用态氮的含量,探讨了各形态氮对生物可利用态氮的贡献。结果表明,丹江口水库沉积物中总氮(Total nitrogen,TN)在425~5796 mg/kg之间,平均为1 319.32 mg/kg,其中EN、HN和RN的平均值相对比例为2.15∶1.95∶1,且各形态氮含量的空间分布呈入库河流大于库区开阔区域的特征,尤其在丹江、老灌河以及犟河-堵河入库口的含量较大。潜在矿化氮(Potential mineralized nitrogen,PMN)含量在40.20~1 468.95 mg/kg之间,平均为275.06 mg/kg,其中EN对丹江口水库沉积物PMN的贡献较大,比例在19.85%~90.80%之间,平均为63.47%。各形态氮在不同的水环境条件下发生迁移转化,保持着水-沉积物界面氮的动态平衡。     

Economic and environmental value stream map (E2VSM) simulation for multi-product manufacturing systems

Value stream mapping (VSM) is a well-accepted tool within lean manufacturing concept which is often used for analysing and designing the flow of materials and information required to manufacture a product. However, the analysis is static and single product oriented, which fails to cope with either the variation of production plan or a multi-product environment. In addition, the environmental impact of a manufacturing system is highly associated with the dynamic consumption of energy and resources. Despite the recent integration of VSM with simulation or environmental studies (in the domain of energy efficiency), still neglected is the dynamic assessment of all the resources involved in a multi-product production environment. This paper presents a methodology for modelling multi-product manufacturing systems with dynamic material, energy and information flows with the aim to generate economic and environmental value stream maps (E²VSM). The proposed methodology is validated with an industrial case.     

Toxicity of sediment cores from Yangtze River estuary to zebrafish (<Emphasis Type="Italic">Danio rerio</Emphasis>) embryos

Toxicity evaluation is an important segment in sediment quality monitoring in order to protect aquatic organisms and human health. The purpose of this study is to assess the toxicity of sediments from three sediment cores in Yangtze River Estuary, China, using the zebrafish (Danio rerio) embryo tests. Fertilized zebrafish eggs were exposed to both whole sediments and sediment organic extracts prepared from collected sediments, in order to provide a comprehensive and realistic insight into the bioavailable toxicity potential of the sediments. As end points, development parameters (mortality, hatching rate, and abnormality) in the developing embryos were recorded during the 96-h exposure. The results showed that some samples increased mortality, inhibited the hatching of embryos, and induced morphological abnormalities. The embryonic toxicities presented serrated changes and irregular distribution with depth, which may be related to hydrodynamic effect and unstable environmental input. However, lethal and sub-lethal effects were more significant at the sub-surface sediments (10～40 cm), which indicated that the pollution is more serious in recent decades.