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.     

NARX神经网络模型在昆明市环境空气质量预测中的应用

神经网络模型作为一种重要的手段被广泛应用于数学计算、物理建模、水文模拟、环境预测、人工智能等研究领域。为验证神经网络模型在高原山地城市环境空气质量预测中的作用,以昆明市环境空气自动监测站气象因子和污染物浓度数据为基础,构建NARX神经网络模型,对污染物浓度进行预测。结果表明,基于NARX神经网络建立的预测模型具有很强的非线性动态描述能力,能够对环境空气6参数做出较为准确的预测,其预测浓度相对误差显著低于CMAQ、NAQPMS空气质量数值模式以及LSTM统计模型预测结果。优化后的NARX神经网络对污染物浓度变化趋势的预测较其他几个模式更为敏感。     

基于OPAQ的城市空气质量预报系统研究

空气质量预测在国内的关注度日益提高,传统的空气质量预测系统通常运用数值化学传输模型,利用物理方程来计算污染物的扩散、沉降和化学反应。而化学传输模型的预测准确性很大程度上需要依赖详细的污染源排放信息和气象模型的输出结果。基于统计模型的OPAQ空气质量预报业务系统,采用人工神经网络算法,可预测各污染物的日均值或日最大值。并对北京空气质量预报的结果进行了评价,OPAQ空气质量预报业务系统对空气质量预测的准确性较高,能够利用较低的计算资源得到较为准确的预测结果。与数值预报相比,OPAQ空气质量预报业务系统不需要大量的基础数据作为输入,可弥补数值预报的不足,并成为数值预报的有力补充。     

基于AGNES算法优化BP神经网络和GIS系统的大气污染物浓度预测

建立了大气污染物浓度与影响因子之间的BP神经网络,对城市中各监测点位的次日大气污染物浓度进行预测,采用GIS的插值分析进行污染物空间分布预测,其中BP神经网络的输入向量采用AGNES算法进行处理。以太原市区SO2、PM10浓度预测为例,选择气温、湿度、降水量、大气压强、风速和前5天的污染物浓度等10个参数训练BP神经网络,结果表明,BP神经网络的训练效果较好,预测结果与实际浓度显著相关,R2分别为0.988、0.976;结合太原市8个监测点位的污染物浓度预测值,运用GIS空间差值法绘出SO2、PM10的浓度分布预测图,该图与实际情况大体符合,并且与国控大气污染企业的分布显著相关,Pearson相关系数分别为0.969、0.949。     

Input strategy analysis for an air quality data modelling procedure at a local scale based on neural network

In recent years, a significant part of the studies on air pollutants has been devoted to improve statistical techniques for forecasting the values of their concentrations in the atmosphere. Reliable predictions of pollutant trends are essential not only for setting up preventive measures able to avoid risks for human health but also for helping stakeholders to take decision about traffic limitations. In this paper, we present an operating procedure, including both pollutant concentration measurements (CO, SO₂, NO₂, O₃, PM10) and meteorological parameters (hourly data of atmospheric pressure, relative humidity, wind speed), which improves the simple use of neural network for the prediction of pollutant concentration trends by means of the integration of multivariate statistical analysis. In particular, we used principal component analysis in order to define an unconstrained mix of variables able to improve the performance of the model. The developed procedure is particularly suitable for characterizing the investigated phenomena at a local scale.     

Multipoint source method in air pollution modelling of cold start emission

The paper presents a new method of air pollution modelling on a micro scale. For estimation of concentration of car exhaust pollutants, each car is treated as an instantaneous moving emission source. This approach enables us to model time and spatial changes of emission, especially during cold and cool start of an engine. These stages of engine work are a source of significant pollution concentration in urban areas. In this work, two models are proposed: one for the estimation of emission after cold start of the engine and another for the prediction of pollutant concentration. The first model (defined for individual exhaust gas pollutants) enables us to calculate the emission as a function of time after the cold or cool start, ambient temperature and average speed of motion. This model uses the HBEFA database. The second mathematical model is developed in order to calculate the pollutant dispersion and concentrations. The finite volume method is applied to discretise the set of partial differential equations describing wind flow and pollutant dispersion in the domain considered. Models presented in this paper can be called short-term models on a small spatial scale. The results of numerical simulation of pollutant emission and dispersion are also presented.     

A Knowledge-Based Approach to Environmental Biomonitoring

This paper presents the design, development and implementation of an integrated GIS-controlled knowledge-based system for environmental monitoring applications, utilizing indigenous flora for assessing quality. The system gathers and combines geographical, ecological, and physicochemical data of organisms' response to pollution within an intelligent computer program that (a) recognises groups of indigenous species suitable for long-term monitoring of a specific pollutant or a combination of pollutants, (b) estimates the ambient concentration of pollutant(s) from the population of the species comprising the bioindicator group and (c) provides biomonitoring capacity indices at national and international/transboundary levels. Significantly, a novel system in the form of a rational framework at the conceptual design level has been developed, that actually contributes towards achieving a cost-effective long-term biomonitoring program, with the flexibility to counter on-course any (anticipated or not) variations/modifications of the surveillance environment: the scheme assumes a robust dynamic cooperation between instrumental and biomonitoring systems, with a view to minimise uncertainty and monitoring costs and increase reliability of pollution control and abatement, aiming eventually at the shifting, partially or totally, from instrumental to natural monitoring. The proposed approach is presently implemented at pilot-scale for establishing a biomonitoring network at a large industrial area in Greece. The results obtained indicate that a cost-effective program can be only attained and maintained under a suitable financial/organizational scheme at the macro level, whereas the micro level viability strongly depends upon careful management of human resources and fixed assets.     

Traffic Parameters Estimation to Predict Road Side Pollutant Concentrations using Neural Networks

The analysis aims to evaluate which is the most important among traffic parameters (flows, queues length, occupancy degree, and travel time) to forecast CO and C₆H₆ concentrations. The study area was identified by Notarbartolo Road and bounded by Libertà Street and Sciuti Street in the urban area of Palermo in Southern Italy. In this area, various loop detectors and one pollution-monitoring site were located. Traffic data related to the pollution-monitoring site immediately near the road link were estimated by Simulation of Urban MObility (SUMO) traffic microsimulator software using as input the flows measured by loop detectors on other links of road network. Traffic and weather data were used as input variables to predict pollutant concentrations by using neural networks. Finally, after a sensitivity analysis, it was showed that queues length were the mostly correlated traffic parameters to pollutant concentrations. An erratum to this article can be found at     

t分布受控遗传算法优化BP神经网络的PM2.5质量浓度预测

根据齐齐哈尔大学监测点2014年3—5月PM2?5质量浓度及其对应的每小时的气象因素、气体污染物浓度，建立基于t分布受控遗传算法的BP神经网络模型（ BPM?TCG），对PM2?5质量浓度进行模拟预测。并将其与BP神经网络模型、遗传算法优化BP神经网络模型（ BP?GA）进行对比分析。3种模型预测结果表明：BPM?TCG模型预测精度最高，泛化能力最好。 BPM?TCG模型对PM2?5质量浓度的准确预测为预防和控制PM2?5提供依据。     

Pollutant sources and flows in a municipal sewage system

The flow of heavy metals (Cu, Ni, Cr, Cd, Zn, Pb) and cyanide in the Kokomo, Indiana collection system and wastewater treatment plant is analyzed. The primary objective is to determine the relative contributions of domestic and non-domestic sources to the total pollutant load in the system, and to assess the levels of discharge control required for the disposal of municipal sludge by landfill or agricultural landspreading. Sampling was conducted at point source locations, in major sewer trunk-and feeder lines, and at the treatment plant. Production and waste treatment data are presented for point sources sampled for the purpose of characterizing metal and cyanide discharges as a function of these parameters. A heavy metal mass balance is attempted for the treatment plant. Metal removal factors are presented for various plant operations. A simple statistical approach is presented for the design of a cost-effective sampling program for correlating point source and trunkline pollutant sampling. The purpose is to minimize the amount of sampling required to account for pollutants seen in trunkline and treatment plant streams in terms of discharges from specific point sources.