Chen Yinsheng, Huang Lin, Xie Xiaodong, Liu Zhenxin, Hu Jianlin
Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution Control, Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science & Technology, Nanjing 210044, China.
Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution Control, Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science & Technology, Nanjing 210044, China.
Sci Total Environ. 2024 Feb 20;912:168672. doi: 10.1016/j.scitotenv.2023.168672. Epub 2023 Nov 26.
Accurate prediction of particulate matter with aerodynamic diameter ≤ 2.5 μm (PM) is important for environmental management and human health protection. In recent years, many efforts have been devoted to develop air quality predictions using the machine learning and deep learning techniques. In this study, we propose a deep learning model for short-term PM predictions. The salient feature of the proposed model is that the convolution in the model architecture is causal, where the output of a time step is only convolved with components of the same or earlier time step from the previous layer. The model also weighs the spatial correlation between multiple monitoring stations. Through temporal and spatial correlation analysis, relevant information is screened from the monitoring stations with a strong relationship with the target station. Information from the target and related sites is then taken as input and fed into the model. A case study is conducted in Nanjing, China from January 1, 2020 to December 31, 2020. Using historical air quality and meteorological data from nine monitoring stations, the model predicts PM concentrations for the next hour. The experimental results show that the predicted PM concentrations are consistent with observation, with correlation coefficient (R) and Root Mean Squared Error (RMSE) of our model are 0.92 and 6.75 μg/m. Additionally, to better understand the factors affecting PM levels in different seasons, a machine learning algorithm based on Principal Component Analysis (PCA) is used to analyze the correlations between PM and its influencing factors. By identifying the main factors affecting PM and optimizing the input of the predictive model, the application of PCA in the model further improves the prediction accuracy, with decrease of up to 17.2 % in RMSE and 38.6 % in mean absolute error (MAE). The deep learning model established in this study provide a valuable tool for air quality management and public health protection.
准确预测空气动力学直径≤2.5微米的颗粒物（PM）对于环境管理和人类健康保护至关重要。近年来，人们致力于运用机器学习和深度学习技术来开展空气质量预测。在本研究中，我们提出了一种用于短期PM预测的深度学习模型。该模型的显著特点是其模型架构中的卷积是因果性的，即一个时间步的输出仅与前一层中相同或更早时间步的分量进行卷积。该模型还权衡了多个监测站之间的空间相关性。通过时空相关性分析，从与目标站关系密切的监测站中筛选出相关信息。然后将来自目标站和相关站点的信息作为输入并馈入模型。在中国南京进行了一个案例研究，时间跨度为2020年1月1日至2020年12月31日。利用九个监测站的历史空气质量和气象数据，该模型预测下一小时的PM浓度。实验结果表明，预测的PM浓度与观测值一致，我们模型的相关系数（R）和均方根误差（RMSE）分别为0.92和6.75微克/立方米。此外，为了更好地理解不同季节影响PM水平的因素，使用基于主成分分析（PCA）的机器学习算法来分析PM与其影响因素之间的相关性。通过识别影响PM的主要因素并优化预测模型的输入，PCA在模型中的应用进一步提高了预测精度，RMSE降低了高达17.2%，平均绝对误差（MAE）降低了38.6%。本研究建立的深度学习模型为空气质量管理和公共卫生保护提供了一个有价值的工具。
