Space-time trends of PM2.5 constituents in the conterminous United States estimated by a machine learning approach, 2005-2015
Space-time trends of PM2.5 constituents in the conterminous United States estimated by a machine learning approach, 2005-2015
复制标题
DOI：
10.1016/j.envint.2018.10.029
复制
发表时间：
2018-12-01
影响因子：
11.8
通讯作者：
Liu, Yang
中科院分区：
文献类型：
--
作者：
Meng, Xia;Hand, Jenny L.;Liu, Yang
空气动力学直径小于2.5 μ m的颗粒物（PM2.5）是由各种排放源或通过二次反应/过程排放的化学成分的复杂混合物;然而，PM2.5主要基于其总质量浓度进行监管。由于对PM2.5成分的地面测量有限，确定不同PM2.5成分对气候变化、能见度下降和公共健康影响的研究受到阻碍。在这项研究中，基于随机森林算法开发了国家模型，这是一种具有高预测能力并能够提供可解释结果的机器学习方法，用于预测2005年至2015年美国周边PM2.5硫酸盐，硝酸盐，有机碳（OC）和元素碳（EC）的浓度。随机森林模型在每日水平上实现了高的袋外（OOB）R-2值，2005-2015年硫酸盐、硝酸盐、OC和EC的平均OOB R-2值分别为0.86、0.82、0.71和0.75。PM2.5硫酸盐、硝酸盐、OC和EC的长期时间趋势预测与相应的地面测量结果吻合良好。从2005年到2015年，美国全境PM2.5硫酸盐和EC水平的预测年平均值大幅下降;而PM2.5硝酸盐和OC的预测浓度在研究期间下降并波动。年度预测图捕捉了PM2.5成分的特征空间模式。硫酸盐和硝酸盐的年平均浓度分布具有明显的区域性，在加州，硫酸盐浓度由东向西逐渐降低，硝酸盐浓度在中西部、纽约市区和加州较高。OC和EC在东南部和西北部具有区域性高浓度，在城市中心附近具有局部高浓度。PM2.5各组分的空间分布特征与其排放源、二次过程和输送的分布特征相一致。因此，在这项研究中开发的国家模式可以提供的PM2.5成分的时空分布的完整的时空覆盖在美国的补充评估，这可能是有益的，以评估PM2.5成分对辐射收支和能见度退化的影响，并支持县或市一级的区域至国家健康研究的暴露评估，以了解PM2.5成分的急性和慢性毒性以及健康影响，从而为制定针对性强、效果好的PM2.5污染治理措施提供科学依据。
Particulate matter with aerodynamic diameter less than 2.5 mu m (PM2.5) is a complex mixture of chemical constituents emitted from various emission sources or through secondary reactions/processes; however, PM2.5 is regulated mostly based on its total mass concentration. Studies to identify the impacts on climate change, visibility degradation and public health of different PM2.5 constituents are hindered by limited ground measurements of PM2.5 constituents. In this study, national models were developed based on random forest algorithm, one of machine learning methods that is of high predictive capacity and able to provide interpretable results, to predict concentrations of PM2.5 sulfate, nitrate, organic carbon (OC) and elemental carbon (EC) across the conterminous United States from 2005 to 2015 at the daily level. The random forest models achieved high out-of-bag (OOB) R-2 values at the daily level, and the mean OOB R-2 values were 0.86, 0.82, 0.71 and 0.75 for sulfate, nitrate, OC and EC, respectively, over 2005-2015. The long-term temporal trends of PM2.5 sulfate, nitrate, OC and EC predictions agreed well with their corresponding ground measurements. The annual mean of predicted PM2.5 sulfate and EC levels across the conterminous United States decreased substantially from 2005 to 2015; while concentrations of predicted PM2.5 nitrate and OC decreased and fluctuated during the study period. The annual prediction maps captured the characterized spatial patterns of the PM2.5 constituents. The distributions of annual mean concentrations of sulfate and nitrate were generally regional in the extent that sulfate decreased from east to west smoothly with enhancement in California and nitrate had higher concentration in Midwest, Metro New York area, and California. OC and EC had regional high concentrations in the Southeast and Northwest as well as localized high levels around urban centers. The spatial patterns of PM2.5 constituents were consistent with the distributions of their emission sources and secondary processes and transportation. Hence, the national models developed in this study could provide supplementary evaluations of spatio-temporal distributions of PM2.5 constituents with full time-space coverages in the conterminous United States, which could be beneficial to assess the impacts of PM2.5 constituents on radiation budgets and visibility degradation, and support exposure assessment for regional to national health studies at county or city levels to understand the acute and chronic toxicity and health impacts of PM2.5 constituents, and consequently provide scientific evidence for making targeted and effective regulations of PM2.5 pollution.