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.     

Plasticity in metamorphic traits of <Emphasis Type="Italic">Rana kukunoris</Emphasis> tadpoles: The interactive effects of food level and rearing temperature

Larval amphibians are particularly likely to encounter variation in rearing temperature and resource availability due to variation in aquatic breeding habitats. In this study, plasticity in growth rates, larval mass, larval period, and size at metamorphosis were examined in Rana kukunoris Nikolskii, 1918 under different combinations of temperature and food level. Larval period and larval body mass was sensitive to food level, and varied with temperature. Tadpoles metamorphosed at an older age at low temperature than those reared at warm temperature. Food level was a significant affect on larval period at low temperature, but not at warm temperature. Mass was heavier for tadpoles reared at low temperatures than those reared at warm temperatures. The effect of food level depended on temperature, because larvae reared at low temperature that were offered a high food level achieved a larger size than larvae offered a low food level, but this did not occur at warm temperature. Therefore, we suggest that high food availability at low temperature prolonged developmental periods, thus larvae are larger as metamorphs than those reared at warm temperatures.     

电化学氧化法处理垃圾渗滤液纳滤浓缩液

实验利用电化学氧化法处理垃圾渗滤液纳滤浓缩液,以提高废水的可生化性。研究考察了水力停留时间、进水流量、循环流量、电流强度和原水氯离子浓度对有机物去除的影响。研究结果表明,电化学氧化法的最佳运行条件如下:水力停留时间为3 h,进水流量为1 m3/h,循环流量为15 m3/h,电流强度为420 A。在上述条件下,原水COD浓度从3 100mg/L降到1 311.3 mg/L,去除率达到57.7%,BOD/COD值由0.03提升至0.31。氯离子对电解有促进作用,但原水氯离子浓度超过5 000 mg/L,不需要外加工业盐。     

MnO_2/Al_2O_3吸附草甘膦及微波紫外耦合降解再生工艺

以掺混煅烧法制备Mn O2/Al2O3,并对草甘膦进行吸附,将吸附态草甘膦置于微波紫外耦合系统中进行降解和再生。研究并给出了Mn O2/Al2O3的最佳制备条件、最佳吸附条件和微波紫外耦合降解再生的最佳工艺参数。Mn O2/Al2O3最佳制备条件为Mn O2质量分数15%,煅烧温度500℃,煅烧时间2 h。在常温下,Mn O2/Al2O3对草甘膦的最大吸附量为75 mg/g。微波紫外耦合系统最佳工艺参数为功率500 W,时间25 min,空气量0.06 m3/h。在此操作条件下,Mn O2/Al2O3的再生率达到85%,并且可以多次再生利用,草甘膦最终降解产物为二氧化碳、氮氧化物、磷酸和水,矿化率为65%。     

EGSB出水回流对EGSB—SBR工艺处理果汁废水的影响

采用EGSB—SBR工艺处理实际果汁废水(COD 2 608~6 500 mg/L,p H 5.0~7.0)。在EGSB反应器成功启动及驯化完成的情况下,连续运行49 d。实验结果表明:第25天起,控制EGSB回流比为3.00∶1,EGSB反应器可在无须添加Na HCO3的条件下稳定运行,从而降低了废水处理成本;第25天起,平均进水COD,BOD5,SS分别为5 968,2 130,1 020 mg/L,平均出水COD,BOD5,SS分别降至131,11,50 mg/L,平均COD,BOD5,SS去除率分别为98%,99%,95%;组合工艺对该实际果汁废水具有良好的处理效果。     

助剂作用下超声浸取电解锰渣

用8-羟基喹啉、黄原酸钾、十六烷基三甲基溴化铵、磷酸三丁酯、柠檬酸5种物质作浸取助剂,考察了助剂作用下超声辅助浸取法从电解锰渣中提取锰的工艺条件。实验结果表明：用1%（质量分数）柠檬酸作浸取助剂,在固液比（g/mL）为1∶4、酸矿比（mL/g）为0.3∶1、浸取温度为70℃的条件下,超声浸取15min,锰浸出率平均可达57.28%,是加热酸浸法锰浸出率的2.72倍,是无助剂超声辅助浸取法锰浸出率的1.52倍。     

复合式静电除尘器脱除电厂排放PM2.5研究

控制燃煤电厂的小颗粒PM2.5排放是控制大气可吸人颗粒物污染的重要途径之一.传统静电除尘器对亚微米级颗粒脱除效率较低,为提高脱除效率,建立了一种脉冲预荷电直流收尘的复合式除尘系统,采用较低能耗的高压窄脉冲放电对颗粒物预荷电,大大提高了亚微米级颗粒的荷电量.结合传统的直流静电除尘器可以大幅提高对亚微米级颗粒的脱除效率,对小于1μm的颗粒脱除效率可以达到90%以上.并分析了脉冲荷电的电源形式和电压等因素对脱除效率的影响,为改造传统静电除尘器提供了理论支持.     

环境影响后评价的最新进展与建议

结合《中华人民共和国环境影响评价法》的有关条款,探讨了环境影响后评价的概念、分类、适用对象、意义和内容,提出了环境影响后评价的管理和实施程序.结合多年的实践,分析了目前环境影响后评价工作在理论、方法和管理上存在的问题,提出了改进和完善的建议.案例实践表明,开展环境影响后评价有助于提高环境影响评价制度的有效性.