Research Laboratory in Hydrodynamics, Energetics & Atmospheric Environment (LHEEA), École Centrale de Nantes, Nantes 44300, France; Department of Mechanical Engineering, Faculty of Mechanical & Production Engineering, Institute of Technology, Arba Minch University, Arba Minch 21, Ethiopia.
Research Laboratory in Hydrodynamics, Energetics & Atmospheric Environment (LHEEA), École Centrale de Nantes, Nantes 44300, France.
J Environ Sci (China). 2021 Mar;101:428-439. doi: 10.1016/j.jes.2020.08.018. Epub 2020 Sep 18.
Currently, vehicle-related particulate matter is the main determinant air pollution in the urban environment. This study was designed to investigate the level of fine (PM) and coarse particle (PM) concentration of roadside vehicles in Addis Ababa, the capital city of Ethiopia using artificial neural network model. To train, test and validate the model, the traffic volume, weather data and particulate matter concentrations were collected from 15 different sites in the city. The experimental results showed that the city average 24-hr PM concentration is 13%-144% and 58%-241% higher than air quality index (AQI) and world health organization (WHO) standards, respectively. The PM results also exceeded the AQI (54%-65%) and WHO (8%-395%) standards. The model runs using the Levenberg-Marquardt (Trainlm) and the Scaled Conjugate Gradient (Trainscg) and comparison were performed, to identify the minimum fractional error between the observed and the predicted value. The two models were determined using the correlation coefficient and other statistical parameters. The Trainscg model, the average concentration of PM and PM exhaust emission correlation coefficient were predicted to be (R = 0.775) and (R = 0.92), respectively. The Trainlm model has also well predicted the exhaust emission of PM (R = 0.943) and PM (R = 0.959). The overall results showed that a better correlation coefficient obtained in the Trainlm model, could be considered as optional methods to predict transport-related particulate matter concentration emission using traffic volume and weather data for Ethiopia cities and other countries that have similar geographical and development settings.
目前，与车辆相关的颗粒物是城市环境中空气污染的主要决定因素。本研究旨在使用人工神经网络模型调查埃塞俄比亚首都亚的斯亚贝巴路边车辆的细颗粒物（PM）和粗颗粒物（PM）浓度水平。为了训练、测试和验证模型，从该市的 15 个不同地点收集了交通量、天气数据和颗粒物浓度。实验结果表明，该市的 24 小时平均 PM 浓度分别比空气质量指数（AQI）和世界卫生组织（WHO）标准高 13%-144%和 58%-241%。PM 结果也超过了 AQI（54%-65%）和 WHO（8%-395%）标准。使用 Levenberg-Marquardt（Trainlm）和 Scaled Conjugate Gradient（Trainscg）运行模型，并进行比较，以确定观测值和预测值之间的最小分数误差。使用相关系数和其他统计参数确定了这两个模型。Trainscg 模型预测的 PM 和 PM 排气排放的平均浓度相关系数分别为（R=0.775）和（R=0.92）。Trainlm 模型也很好地预测了 PM（R=0.943）和 PM（R=0.959）的排气排放。总体结果表明，Trainlm 模型获得了更好的相关系数，可以考虑将其作为使用交通量和天气数据预测埃塞俄比亚城市和其他具有类似地理和发展背景的国家与交通相关的颗粒物浓度排放的可选方法。
