Air quality forecasting is vital for managing and mitigating the adverse effects of air pollution on human health, crops, and the environment. This study aims to forecast daily time series of ozone and fine particulate matter (PM) concentrations using a meta-hybrid deep NARMAX (Nonlinear Auto-Regressive Moving Average with eXogenous inputs) model. Two datasets were utilised: (a) data on meteorological parameters (temperature, air pressure, relative humidity) and air pollutant concentrations (particulate matter, ozone, dioxide of carbon, volatile organic compounds, formaldehyde) provided by a sensor model A3 situated in the centre of Craiova city, and (b) data on wind direction, wind speed, and sunshine duration provided by the National Meteorological Administration. The data sets covered a time interval from December 10, 2020, to January 05, 2024. Initially, a statistical analysis was conducted to assess the correlation between variables. Results revealed that ozone concentration is primarily influenced by meteorological variables such as temperature (r = 0.79), sunshine duration (r = 0.55), and relative humidity (r = −0.48), and secondarily by air pollution indicators including VOC (r = −0.34), PM concentrations (r = −0.34), and CO2 (r = −0.3). In the subsequent stage, thirteen Machine Learning (ML) models were employed in conjunction with an integral feature selection (IFS) method to identify the best combinations of predictor variables for predicting ozone and PMs. Finally, a deep NARMAX model was developed to forecast the next periods of ozone and PMs based on the optimal combinations identified earlier. Results indicated the selection of sixty best models for ozone forecasting and four best models for PMs. The R2 values surpassed 0.97 for ozone and exceeded 0.8 for PMs, demonstrating the efficacy of the forecasting approach.

中文翻译：

---

使用元混合深度学习模型预测克拉约瓦市的地面臭氧和细颗粒物浓度


空气质量预测对于管理和减轻空气污染对人类健康、农作物和环境的不利影响至关重要。本研究旨在使用元混合深度 NARMAX（具有外源输入的非线性自回归移动平均）模型来预测臭氧和细颗粒物 (PM) 浓度的每日时间序列。使用了两个数据集：(a) 由位于克拉约瓦市中心，以及（b）国家气象局提供的风向、风速和日照时数数据。数据集涵盖的时间间隔为2020年12月10日至2024年1月5日。最初，进行统计分析以评估变量之间的相关性。结果表明，臭氧浓度主要受温度（r = 0.79）、日照时数（r = 0.55）和相对湿度（r = -0.48）等气象变量的影响，其次受VOC等空气污染指标的影响（r = - 0.34)、PM 浓度 (r = -0.34) 和 CO2 (r = -0.3)。在后续阶段，采用了 13 个机器学习 (ML) 模型与积分特征选择 (IFS) 方法相结合，以确定用于预测臭氧和 PM 的预测变量的最佳组合。最后，开发了一个深度 NARMAX 模型，用于根据先前确定的最佳组合来预测下一周期的臭氧和 PM。结果表明，选出了 60 个臭氧预测最佳模型和 4 个 PM 预测最佳模型。臭氧的R2值超过0.97并超过0。8 对于 PM，证明了预测方法的有效性。