Department of Civil and Environmental Engineering, University of Tennessee, Knoxville, TN, USA.
Department of Civil and Environmental Engineering, University of Tennessee, Knoxville, TN, USA; Department of Atmospheric Sciences, National Central University, Taoyuan, Taiwan.
Environ Int. 2023 Jun;176:107969. doi: 10.1016/j.envint.2023.107969. Epub 2023 May 12.
Current machine learning (ML) applications in atmospheric science focus on forecasting and bias correction for numerical modeling estimations, but few studies examined the nonlinear response of their predictions to precursor emissions. This study uses ground-level maximum daily 8-hour ozone average (MDA8 O) as an example to examine O responses to local anthropogenic NOx and VOC emissions in Taiwan by Response Surface Modeling (RSM). Three different datasets for RSM were examined, including the Community Multiscale Air Quality (CMAQ) model data, ML-measurement-model fusion (ML-MMF) data, and ML data, which respectively represent direct numerical model predictions, numerical predictions adjusted by observations and other auxiliary data, and ML predictions based on observations and other auxiliary data. The results show that both ML-MMF (r = 0.93-0.94) and ML predictions (r = 0.89-0.94) present significantly improved performance in the benchmark case compared with CMAQ predictions (r = 0.41-0.80). While ML-MMF isopleths exhibit O nonlinearity close to actual responses due to their numerical base and observation-based correction, ML isopleths present biased predictions concerning their different controlled ranges of O and distorted O responses to NOx and VOC emission ratios compared with ML-MMF isopleths, which implies that using data without support from CMAQ modeling to predict the air quality could mislead the controlled targets and future trends. Meanwhile, the observation-corrected ML-MMF isopleths also emphasize the impact of transboundary pollution from mainland China on the regional O sensitivity to local NOx and VOC emissions, which transboundary NOx would make all air quality regions in April more sensitive to local VOC emissions and limit the potential effort by reducing local emissions. Future ML applications in atmospheric science like forecasting or bias correction should provide interpretability and explainability, except for meeting statistical performance and providing variable importance. Assessment with interpretable physical and chemical mechanisms and constructing a statistically robust ML model should be equally important.
目前大气科学中的机器学习（ML）应用主要集中在数值模型估计的预测和偏差修正上，但很少有研究考察其预测对前体排放的非线性响应。本研究以地面最大日 8 小时臭氧平均值（MDA8 O）为例，通过响应面建模（RSM）考察台湾局地人为 NOx 和 VOC 排放对 O 的非线性响应。研究考察了 RSM 的三种不同数据集，包括社区多尺度空气质量模型（CMAQ）数据、ML-测量-模型融合（ML-MMF）数据和 ML 数据，分别代表直接数值模型预测、观测和其他辅助数据调整后的数值预测，以及基于观测和其他辅助数据的 ML 预测。结果表明，与 CMAQ 预测（r=0.41-0.80）相比，ML-MMF（r=0.93-0.94）和 ML 预测（r=0.89-0.94）在基准案例中表现出显著提高的性能。由于其数值基础和基于观测的校正，ML-MMF 等面值呈现出与实际响应接近的 O 非线性，而 ML 等面值则呈现出对 O 和 O 对 NOx 和 VOC 排放比的响应的有偏差预测，与 ML-MMF 等面值相比，这意味着使用没有 CMAQ 模型支持的数据来预测空气质量可能会误导控制目标和未来趋势。同时，经观测校正的 ML-MMF 等面值也强调了来自中国大陆的跨境污染对区域 O 对本地 NOx 和 VOC 排放的敏感性的影响，跨境 NOx 会使 4 月所有空气质量区域对本地 VOC 排放更加敏感，并限制通过减少本地排放来提高潜在效率。未来大气科学中的 ML 应用，如预测或偏差修正，除了满足统计性能和提供变量重要性外，还应该提供可解释性和解释性。用可解释的物理和化学机制进行评估和构建统计稳健的 ML 模型应该同样重要。
