College of Environment and Resources, Shanxi University, Taiyuan, PR China.
J Air Waste Manag Assoc. 2013 Jul;63(7):755-63. doi: 10.1080/10962247.2012.755940.
Primary fine particulate matters with a diameter of less than 10 microm (PM10) are important air emissions causing human health damage. PM10 concentration forecast is important and necessary to perform in order to assess the impact of air on the health of living beings. To better understand the PM10 pollution health risk in Taiyuan City, China, this paper forecasted the temporal and spatial distribution of PM10 yearly average concentration, using Back Propagation Artificial Neural Network (BPANN) model with various air quality parameters. The predicted results of the models were consistent with the observations with a correlation coefficient of 0.72. The PM10 yearly average concentrations combined with the population data from 2002 to 2008 were given into the Intake Fraction (IF) model to calculate the IFs, which are defined as the integrated incremental intake of a pollutant released from a source category or a region over all exposed individuals. The results in this study are only for main stationary sources of the research area, and the traffic sources have not been included. The computed IFs results are therefore under-estimations. The IFs of PM10 from Taiyuan with a mean of 8.5 per million were relatively high compared with other IFs of the United States, Northern Europe and other cities in China. The results of this study indicate that the artificial neural network is an effective method for PM10 pollution modeling, and the Intake Fraction model provides a rapid population risk estimate for pollutant emission reduction strategies and policies.
The PM10 (particulate matter with an aerodynamic diameter < or = 10 microm) yearly average concentration of Taiyuan, with a mean of 0.176 mg/m3, was higher than the 65 microg/m3 recommended by the U.S. Environmental Protection Agency (EPA). The spatial distribution of PM10 yearly average concentrations showed that wind direction and wind speed played an important role, whereas temperature and humidity had a lower effect than expected. Intake fraction estimates of Taiyuan were relatively high compared with those observed in other cities. Population density was the major factor influencing PM10 spatial distribution. The results indicated that the artificial neural network was an effective method for PM10 pollution modeling.
直径小于 10 微米的初级细颗粒物（PM10）是造成人类健康损害的重要空气排放物。为了评估空气对生物健康的影响，对 PM10 浓度进行预测是非常重要和必要的。为了更好地了解中国太原市的 PM10 污染健康风险，本文使用带有各种空气质量参数的反向传播人工神经网络（BPANN）模型，预测了 PM10 年平均浓度的时空分布。模型的预测结果与观测结果具有高度的一致性，相关系数为 0.72。将 2002 年至 2008 年的 PM10 年平均浓度与人口数据结合起来，输入到摄入量分数（IF）模型中，计算出的 IFs 定义为从源类别或区域释放的污染物对所有暴露个体的综合增量摄入量。本研究的结果仅针对研究区域的主要固定污染源，未包括交通源。因此，计算得出的 IFs 结果是低估的。与美国、北欧和中国其他城市的其他 IFs 相比，太原市 PM10 的 IFs 平均值为 8.5 百万分之比较高。本研究结果表明，人工神经网络是 PM10 污染建模的有效方法，摄入量分数模型为污染物减排策略和政策提供了快速的人群风险评估。
太原市 PM10（空气动力学直径≤10 微米的颗粒物）年平均浓度为 0.176mg/m3，高于美国环境保护署（EPA）建议的 65μg/m3。PM10 年平均浓度的空间分布表明，风向和风速起着重要作用，而温度和湿度的影响低于预期。与其他城市相比，太原市的摄入量分数估计值相对较高。人口密度是影响 PM10 空间分布的主要因素。结果表明，人工神经网络是 PM10 污染建模的有效方法。
