Growing wildfire smoke represents a substantial threat to air quality and human health. However, the impact of wildfire smoke on human health remains imprecisely understood due to uncertainties in both the measurement of exposure of population to wildfire smoke and dose–response functions linking exposure to health. Here, we compare daily wildfire smoke-related surface fine particulate matter (PM_2.5) concentrations estimated using three approaches, including two chemical transport models (CTMs): GEOS-Chem and the Community Multiscale Air Quality (CMAQ) and one machine learning (ML) model over the contiguous US in 2020, a historically active fire year. In the western US, compared against surface PM_2.5 measurements from the US Environmental Protection Agency (EPA) and PurpleAir sensors, we find that CTMs overestimate PM_2.5 concentrations during extreme smoke episodes by up to 3–5 fold, while ML estimates are largely consistent with surface measurements. However, in the eastern US, where smoke levels were much lower in 2020, CTMs show modestly better agreement with surface measurements. We develop a calibration framework that integrates CTM- and ML-based approaches to yield estimates of smoke PM_2.5 concentrations that outperform individual approach. When combining the estimated smoke PM_2.5 concentrations with county-level mortality rates, we find consistent effects of low-level smoke on mortality but large discrepancies in effects of high-level smoke exposure across different methods. Our research highlights the differences across estimation methods for understanding the health impacts of wildfire smoke and demonstrates the importance of bench-marking estimates with available surface measurements.

中文翻译：

---

评估野火烟雾 PM2.5 的化学运输和机器学习模型：对健康影响评估的影响


不断增长的野火烟雾对空气质量和人类健康构成了重大威胁。然而，由于人口暴露于野火烟雾的测量以及将暴露与健康联系起来的剂量反应函数的不确定性，野火烟雾对人类健康的影响仍不精确。在这里，我们比较了使用三种方法估计的每日野火烟雾相关表面细颗粒物 （PM_2.5） 浓度，包括两个化学传输模型 （CTM）：GEOS-Chem 和社区多尺度空气质量 （CMAQ） 和一个机器学习 （ML） 模型在 2020 年美国本土，这是历史上活跃的火灾年。在美国西部，与美国环境保护署 （EPA） 和 PurpleAir 传感器的表面 PM_2.5 测量值相比，我们发现 CTM 在极端烟雾事件期间高估了 PM_2.5 浓度高达 3-5 倍，而 ML 估计值与表面测量值基本一致。然而，在美国东部，2020 年的烟雾水平要低得多，CTM 与地表测量的一致性略高。我们开发了一个校准框架，该框架集成了基于 CTM 和 ML 的方法，以产生优于单独方法的烟雾 PM_2.5 浓度估计值。当将估计的烟雾 PM_2.5 浓度与县级死亡率相结合时，我们发现低水平烟雾对死亡率的影响一致，但不同方法的高水平烟雾暴露的影响存在很大差异。我们的研究强调了理解野火烟雾对健康影响的估计方法之间的差异，并证明了使用可用表面测量值进行基准估计的重要性。