Hashad Khaled, Gu Jiajun, Yang Bo, Rong Morena, Chen Edric, Ma Xiaoxin, Zhang K Max
Sibley School of Mechanical and Aerospace Engineering, Cornell University, Ithaca, NY 14853, USA.
Department of Computer Science, Cornell University, Ithaca, NY 14853, USA.
Sci Total Environ. 2021 Jun 15;773:144760. doi: 10.1016/j.scitotenv.2020.144760. Epub 2021 Feb 4.
Communities located in near-road environments are exposed to traffic-related air pollution (TRAP), causing adverse health effects. While roadside vegetation barriers can help mitigate TRAP, their effectiveness to reduce TRAP is influenced by site-specific conditions. To test vegetation designs using direct field measurements or high-fidelity numerical simulations is often infeasible since urban planners and local communities often lack the access and expertise to use those tools. There is a need for a fast, reliable, and easy-to-use method to evaluate vegetation barrier designs based on their capacity to mitigate TRAP. In this paper, we investigated five machine learning (ML) methods, including linear regression (LR), support vector machine (SVM), random forest (RF), XGBoost (XGB), and neural networks (NN), to predict size-resolved and locationally dependent particle concentrations downwind of various vegetation barrier designs. Data from 83 computational fluid dynamics (CFD) simulations was used to train and test the ML models. We developed downwind region-specific models to capture the complexity of this problem and enhance the overall accuracy. Our feature space was composed of variables that can be feasibly obtained such as vegetation width, height, leaf area index (LAI), particle size, leaf area density (LAD) and wind speed at different heights. RF, NN, and XGB performed well with a normalized root mean square error (NRMSE) of 6-7% and an average test R value >0.91, while SVM and LR had an NRMSE of approximately 13% and an average test R value of 0.56. Using feature selection, vegetation dimensions and particle size had the highest influence in predicting pollutant concentrations. The ML models developed can help create tools to aid local communities in developing mitigation strategies to address TRAP problems.
位于近道路环境中的社区暴露于与交通相关的空气污染（TRAP）中，会对健康产生不利影响。虽然路边植被屏障有助于减轻TRAP，但它们减少TRAP的效果受到特定地点条件的影响。由于城市规划者和当地社区通常缺乏使用直接实地测量或高保真数值模拟来测试植被设计的途径和专业知识，因此使用这些方法往往不可行。需要一种快速、可靠且易于使用的方法，基于植被屏障减轻TRAP的能力来评估其设计。在本文中，我们研究了五种机器学习（ML）方法，包括线性回归（LR）、支持向量机（SVM）、随机森林（RF）、XGBoost（XGB）和神经网络（NN），以预测各种植被屏障设计下风向按尺寸解析且位置相关的颗粒物浓度。来自83次计算流体动力学（CFD）模拟的数据用于训练和测试ML模型。我们开发了特定下风向区域的模型，以捕捉该问题的复杂性并提高整体准确性。我们的特征空间由诸如植被宽度、高度、叶面积指数（LAI）、粒径、叶面积密度（LAD）和不同高度处的风速等可切实获得的变量组成。RF、NN和XGB表现良好，归一化均方根误差（NRMSE）为6 - 7%，平均测试R值>0.91，而SVM和LR的NRMSE约为13%，平均测试R值为0.56。通过特征选择，植被尺寸和粒径对预测污染物浓度的影响最大。所开发的ML模型有助于创建工具，以协助当地社区制定缓解策略来解决TRAP问题。
