Potential forecast models have been developed for air pollution of summertime (Apr.–Aug.) ozone and wintertime (Nov.–Feb.) PM_2.5 in Chengdu using the multiple linear regression (MLR), back-propagation (BP) neural network (NN) and random forest (RF) algorithms. The key predicting factors for each of the models are selected from various potential factors that may impact the spatiotemporal distribution of pollutions. The models are trained and established with 2016–2018 datasets and evaluated with a data-withheld method and further with independent 2019 dataset. The results show that the MLR, NN and RF models are all capable to accurately predict O₃ and PM_2.5 pollution potentials in short lead-time (1–3 days) in Chengdu. The models are also found having quite stable performances in medium- and long-term (7–15 days lead time) forecasts. Among the three models, the MLR model performs the best in prediction of O₃, while RF model performs the best for PM_2.5.

以成都市为例, 以多项可能影响污染物时空分布的变量为潜在预报因子, 筛选关键入模因子, 利用2016—2018年数据为训练集, 采用多元线性回归、BP神经网络和随机森林算法, 建立成都市夏季(4—8月)臭氧及冬季(11—2月) PM_2.5污染潜势模型, 并利用2019年数据对模型的中长期污染潜势浓度的预报性能进行评估。结果表明, 建立的多元线性回归、BP神经网络和随机森林模型对成都市臭氧及PM_2.5的短期(1~3天)污染潜势都具有良好的预报效果, 对7~15天的中长期潜势预报表现稳定。其中, 多元线性回归模型和随机森林模型分别对臭氧和PM_2.5表现出相对最佳的预报性能。