在这项研究中,在2017-2022年旱季(11月至4月),曼谷机场使用了六个单独的机器学习(ML)模型和一个堆叠集成模型(SEM)进行白天能见度估算。单个ML模型是随机森林,自适应提升,梯度增强,极端梯度增强,轻型梯度增压机,和猫提升。SEM是通过组合来自各个模型的输出而开发的。此外,影响能见度的因素的影响是使用Shapley加法膨胀(SHAP)方法检查的,一种受基于博弈论的方法启发的可解释ML技术。预测变量包括不同的空气污染物,气象变量,和时间相关的变量。光梯度增强机器模型被确定为最有效的单个ML模型。在每小时的时间尺度上,它在四个指标中的三个指标中表现最佳,ρ=0.86,MB=0,ME=0.48km(第二低),RMSE=0.8公里。在每天的时间尺度上,模型在所有评估指标中表现最好,ρ=0.92,MB=0.0km,ME=0.3公里,RMSE=0.43公里。在每小时时间尺度上,SEM在四个指标中的三个指标上优于所有单个模型,ρ=0.88,MB=0.0km,(第二低),RMSE=0.75公里。在每日尺度上,它表现最好,ρ=0.93,MB=0.02km,ME=0.27公里,RMSE=0.4公里。从2017年到2021年,季节性平均原始能见度(VISorig)和气象归一化能见度(VISnorm)下降,但在2022年上升。VISorig的下降速度是VISnorm的下降速度的两倍,这表明气象能见度下降的影响。SHAP分析确定相对湿度(RH),PM2.5,PM10,季节年份的一天(即,朱利安戴)(JD),和O3是影响能见度的最重要变量。在低RH时,能见度对RH的变化不敏感。然而,超过一个门槛,RH和能见度之间的负相关可能是由于气溶胶的吸湿性增长。PM2.5和PM10的Shapley值对RH的依赖性以及不同RH间隔下平均能见度的变化也表明了气溶胶吸湿性生长对能见度的影响。能见度与PM2.5和PM10之间存在负相关关系。能见度在低至中等浓度下与O3呈正相关,在非常高的浓度下影响减弱。JD在冬季与能见度呈强烈负相关,而在夏季后期与能见度呈微弱正相关。这项研究的结果表明,采用机器学习技术来预测可见性和理解影响其波动的因素是可行的。
In this study, six individual machine learning (ML) models and a stacked ensemble model (SEM) were used for daytime
visibility estimation at Bangkok airport during the dry season (November-April) for 2017-2022. The individual ML models are random forest, adaptive boosting, gradient boosting, extreme gradient boosting, light gradient boosting machine, and cat boosting. The SEM was developed by the combination of outputs from the individual models. Furthermore, the impact of factors affecting
visibility was examined using the Shapley Additive exPlanation (SHAP) method, an interpretable ML technique inspired by the game theory-based approach. The predictor variables include different air pollutants, meteorological variables, and time-related variables. The light gradient boosting machine model is identified as the most effective individual ML model. On an hourly time scale, it showed the best performance across three out of four metrics with the ρ = 0.86, MB = 0, ME = 0.48 km (second lowest), and RMSE = 0.8 km. On a daily time scale, the model performed the best for all evaluation metrics with ρ = 0.92, MB = 0.0 km, ME = 0.3 km, and RMSE = 0.43 km. The SEM outperformed all the individual models across three out of four metrics on an hourly time scale with ρ = 0.88, MB = 0.0 km, (second lowest), and RMSE = 0.75 km. On the daily scale, it performed the best with ρ = 0.93, MB = 0.02 km, ME = 0.27 km, and RMSE = 0.4 km. The seasonal average original (VISorig) and meteorologically normalized
visibility (VISnorm) decrease from 2017 to 2021 but increase in 2022. The rate of decrease in VISorig is double than rate of decrease in VISnorm which suggests the effect of meteorology visibility degradation. The SHAP analysis identified relative humidity (RH), PM2.5, PM10, day of the season year (i.e., Julian day) (JD), and O3 as the most important variables affecting visibility. At low RH,
visibility is not sensitive to changes in RH. However, beyond a threshold, a negative correlation between RH and visibility is found potentially due to the hygroscopic growth of aerosols. The dependence of the Shapley values of PM2.5 and PM10 on RH and the change in average visibilities under different RH intervals also suggest the effect of hygroscopic growth of aerosol on visibility. A negative relationship has been identified between
visibility and both PM2.5 and PM10. Visibility is positively correlated with O3 at lower to moderate concentrations, with diminishing impact at very high concentrations. The JD is strongly negatively related to visibility during winter while weakly associated positively later in summer. Findings from this research suggest the feasibility of employing machine learning techniques for predicting visibility and understanding the factors influencing its fluctuations.