Using improved neural network model to analyze RSP,NOx and NO2 levels in urban air in Mong Kok,Hong Kong

As the health impact of air pollutants existing in ambient addresses much attention in recent years, forecasting of airpollutant parameters becomes an important and popular topic inenvironmental science. Airborne pollution is a serious, and willbe a major problem in Hong Kong within the next few years. InHong Kong, Respirable Suspended Particulate (RSP) and NitrogenOxides NO_x and NO₂ are major air pollutants due to thedominant diesel fuel usage by public transportation and heavyvehicles. Hence, the investigation and prediction of the influence and the tendency of these pollutants are ofsignificance to public and the city image. The multi-layerperceptron (MLP) neural network is regarded as a reliable andcost-effective method to achieve such tasks. The works presentedhere involve developing an improved neural network model, whichcombines the principal component analysis (PCA) technique and theradial basis function (RBF) network, and forecasting thepollutant levels and tendencies based in the recorded data. Inthe study, the PCA is firstly used to reduce and orthogonalizethe original input variables (data), these treated variables arethen used as new input vectors in RBF neural network modelestablished for forecasting the pollutant tendencies. Comparingwith the general neural network models, the proposed modelpossesses simpler network architecture, faster training speed,and more satisfactory predicting performance. This improvedmodel is evaluated by using hourly time series of RSP, NO_x and NO₂ concentrations collected at Mong Kok Roadside Gaseous Monitory Station in Hong Kong during the year 2000. By comparing the predicted RSP, NO_x and NO₂ concentrationswith the actual data of these pollutants recorded at the monitorystation, the effectiveness of the proposed model has been proven.Therefore, in authors' opinion, the model presented in the paper is a potential tool in forecasting air quality parameters and hasadvantages over the traditional neural network methods.     

Risk-Based Prioritization of Air Pollution Monitoring Using Fuzzy Synthetic Evaluation Technique

Air pollution monitoring programs aim to monitor pollutants and their probable adverse effects at various locations over concerned area. Either sensitivity of receptors/location or concentration of pollutants is used for prioritizing the monitoring locations. The exposure-based approach prioritizes the monitoring locations based on population density and/or location sensitivity. The hazard-based approach prioritizes the monitoring locations using intensity (concentrations) of air pollutants at various locations. Exposure and hazard-based approaches focus on frequency (probability of occurrence) and potential hazard (consequence of damage), respectively. Adverse effects should be measured only if receptors are exposed to these air pollutants. The existing methods of monitoring location prioritization do not consider both factors (hazard and exposure) at a time. Towards this, a risk-based approach has been proposed which combines both factors: exposure frequency (probability of occurrence/exposure) and potential hazard (consequence).This paper discusses the use of fuzzy synthetic evaluation technique in risk computation and prioritization of air pollution monitoring locations. To demonstrate the application, common air pollutants like CO, NO_x, PM₁₀ and SO_x are used as hazard parameters. Fuzzy evaluation matrices for hazard parameters are established for different locations in the area. Similarly, fuzzy evaluation matrices for exposure parameters: population density, location and population sensitivity are also developed. Subsequently, fuzzy risk is determined at these locations using fuzzy compositional rules. Finally, these locations are prioritized based on defuzzified risk (crisp value of risk, defined as risk score) and the five most important monitoring locations are identified (out of 35 potential locations). These locations differ from the existing monitoring locations.     

太湖水质氮素质量浓度时空差异特征及影响因素分析

通过对2014—2016年湖体水质中氮素质量浓度分析,结合出入湖总氮浓度、水量、湖体水生生态等影响因素,发现太湖水体中总氮浓度呈现逐年下降的趋势,各监测点位总氮为0.530 mg/L～5.51 mg/L,时空分布不均,差异明显。时间上,总氮浓度表现为春季最高,夏季和秋季最低,且月均值变化曲线呈现出规律的正弦函数波形。空间上,总氮浓度大致表现出由西部湖区向东部湖区递减的趋势,呈现西部湖区﹥北部湖区﹥南部湖区﹥湖心区﹥东部湖区。要改善湖体水质,不仅要切断污染源,而且要加强水生生态功能修复。     

Euclidean贴近度水质评价法及其应用

分析了模糊综合评判在水质评价中的缺陷,将模糊数学中的贴近度与经典的Euclidean距离结合,提出Euclidean贴近度水质评价法。结果表明,该评价方法具有科学性、合理性,并且精度高,简单实用。     

Quantitative structure - activity study on the reductivedehalogenation potency of the halogenated aromatics

Ｑｕａｎｔｉｔａｔｉｖｅｓｔｒｕｃｔｕｒｅ－ａｃｔｉｖｉｔｙｓｔｕｄｙｏｎｔｈｅｒｅｄｕｃｔｉｖｅｄｅｈａｌｏｇｅｎａｔｉｏｎｐｏｔｅｎｃｙｏｆｔｈｅｈａｌｏｇｅｎａｔｅｄａｒｏｍａｔｉｃｓＨｕａｎｇＱｉｎｇｇｕｏ；ＷａｎｇＬｉａｎｓｈｅｎｇ；Ｈａｎ...     

大顶子山航电枢纽工程建库后上游水质总量控制研究

松花江大顶子山枢纽工程建设后,库区内水体流线及扩散规律的变化将影响库区内水质,受沿江排污影响,其规划目标的水环境容量将发生改变,因此对建库后上游水质总量控制进行研究很有意义.     

江苏省盐城市环境空气质量综合评价及整治对策

随着经济发展的加速,盐城已逐步融入长三角经济体系中,城市现代化建设正在大踏步向前迈进,城市生态环境问题也日益受到关注,生态环境问题已成为社会关注的焦点,是衡量盐城社会经济发展的重要指标,实现环境、经济、社会的和谐发展已逐步成为人们的共识.文章针对盐城环境空气质量问题,运用SO2、NO2和PM10等指标表示空气环境质量,采用模糊综合评价方法对盐城空气环境质量等级进行了划分,并采用API指数评价方法对污染程度作出了评价,分析了盐城环境空气质量面临的挑战,提出了盐城市区污染的防控措施.     

模糊数学在室内空气质量评价中的应用

随着生活水平的提高和生活方式的改变,人们在室内生活的时间越来越长,室内空气质量的优劣直接影响到人们的工作和生活.尤其是近年来,出现了大规模的装修热,因此而引起的室内空气污染问题也日益突出.为了能够更客观直接准确的反映出室内空气质量好坏,本文依据国家标准GB/T18880-2002中的标准值,将空气质量分为五个等级.并根据模糊数学的基本原理,选取评价因子,建立室内环境质量模糊综合评价隶属函数,确定了模糊矩阵,把它应用于室内环境质量的综合评价中.     

污水处理厂自动控制系统综述

针对我国污水处理厂自动控制系统的现状 ,简述了污水处理控制系统的控制原理、特点、构成和功能分析了系统的故障原因、干扰因素、智能性及提高系统智能性的方法 ,介绍了模糊控制等新方法在污水处理控制系统中的应用以及系统的功能扩展 ,为建立我国自己完善的污水处理厂集散控制系统提供了一些思路     

生态系统服务的核算方法

生态系统服务是指对人类生存及生活质量有贡献的生态系统产品和生态系统功能 ,包括由自然生态过程产生并维持的环境和资源条件。目前已有的生态系统服务核算方法可以分为市场价值法、替代市场法和假想市场法。