Department of Earth and Environmental Sciences, Columbia University, New York, New York 10027, United States.
Lamont-Doherty Earth Observatory of Columbia University, Palisades, New York 10964, United States.
Environ Sci Technol. 2023 Jul 25;57(29):10708-10720. doi: 10.1021/acs.est.2c09264. Epub 2023 Jul 12.
Particulate matter air pollution is a leading cause of global mortality, particularly in Asia and Africa. Addressing the high and wide-ranging air pollution levels requires ambient monitoring, but many low- and middle-income countries (LMICs) remain scarcely monitored. To address these data gaps, recent studies have utilized low-cost sensors. These sensors have varied performance, and little literature exists about sensor intercomparison in Africa. By colocating 2 QuantAQ Modulair-PM, 2 PurpleAir PA-II SD, and 16 Clarity Node-S Generation II monitors with a reference-grade Teledyne monitor in Accra, Ghana, we present the first intercomparisons of different brands of low-cost sensors in Africa, demonstrating that each type of low-cost sensor PM is strongly correlated with reference PM, but biased high for ambient mixture of sources found in Accra. When compared to a reference monitor, the QuantAQ Modulair-PM has the lowest mean absolute error at 3.04 μg/m, followed by PurpleAir PA-II (4.54 μg/m) and Clarity Node-S (13.68 μg/m). We also compare the usage of 4 statistical or machine learning models (Multiple Linear Regression, Random Forest, Gaussian Mixture Regression, and XGBoost) to correct low-cost sensors data, and find that XGBoost performs the best in testing (: 0.97, 0.94, 0.96; mean absolute error: 0.56, 0.80, and 0.68 μg/m for PurpleAir PA-II, Clarity Node-S, and Modulair-PM, respectively), but tree-based models do not perform well when correcting data outside the range of the colocation training. Therefore, we used Gaussian Mixture Regression to correct data from the network of 17 Clarity Node-S monitors deployed around Accra, Ghana, from 2018 to 2021. We find that the network daily average PM concentration in Accra is 23.4 μg/m, which is 1.6 times the World Health Organization Daily PM guideline of 15 μg/m. While this level is lower than those seen in some larger African cities (such as Kinshasa, Democratic Republic of the Congo), mitigation strategies should be developed soon to prevent further impairment to air quality as Accra, and Ghana as a whole, rapidly grow.
颗粒物空气污染是导致全球死亡率的主要原因，尤其是在亚洲和非洲。解决高浓度和范围广泛的空气污染水平需要进行环境监测，但许多低收入和中等收入国家（LMICs）仍然监测不足。为了解决这些数据空白，最近的研究利用了低成本传感器。这些传感器的性能各不相同，关于非洲传感器相互比较的文献很少。我们在加纳阿克拉将 2 个 QuantAQ Modulair-PM、2 个 PurpleAir PA-II SD 和 16 个 Clarity Node-S Generation II 监测器与参考级 Teledyne 监测器进行了对比，首次在非洲进行了不同品牌的低成本传感器相互比较，证明了每种类型的低成本传感器 PM 与参考 PM 都有很强的相关性，但对于在阿克拉发现的环境混合物源存在偏高的偏差。与参考监测器相比，QuantAQ Modulair-PM 的平均绝对误差最低，为 3.04μg/m，其次是 PurpleAir PA-II（4.54μg/m）和 Clarity Node-S（13.68μg/m）。我们还比较了 4 种统计或机器学习模型（多元线性回归、随机森林、高斯混合回归和 XGBoost）对修正低成本传感器数据的作用，发现 XGBoost 在测试中表现最好（：0.97、0.94、0.96；平均绝对误差：0.56、0.80 和 0.68μg/m 分别为 PurpleAir PA-II、Clarity Node-S 和 Modulair-PM），但树基模型在纠正超出对比训练范围的数据时表现不佳。因此，我们使用高斯混合回归来修正 2018 年至 2021 年在加纳阿克拉周围部署的 17 个 Clarity Node-S 监测器网络的数据。我们发现，阿克拉的网络日平均 PM 浓度为 23.4μg/m，是世界卫生组织每日 PM 指导值 15μg/m 的 1.6 倍。虽然这一水平低于一些较大的非洲城市（如刚果民主共和国的金沙萨），但随着阿克拉和整个加纳的快速发展，应尽快制定缓解策略，防止空气质量进一步恶化。
