Lin Shaofu, Zhang Yuying, Fei Xingjia, Liu Xiliang, Mei Qiang
Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China.
Navigation College, Jimei University, Xiamen 361021, China.
Toxics. 2024 Jul 30;12(8):554. doi: 10.3390/toxics12080554.
Accurate long-term PM prediction is crucial for environmental management and public health. However, previous studies have mainly focused on short-term air quality point predictions, neglecting the importance of accurately predicting the long-term trends of PM and studying the uncertainty of PM concentration changes. The traditional approaches have limitations in capturing nonlinear relationships and complex dynamic patterns in time series, and they often overlook the credibility of prediction results in practical applications. Therefore, there is still much room for improvement in long-term prediction of PM. This study proposes a novel long-term point and interval prediction framework for urban air quality based on multi-source spatial and temporal data, which further quantifies the uncertainty and volatility of the prediction based on the accurate PM point prediction. In this model, firstly, multi-source datasets from multiple monitoring stations are preprocessed. Subsequently, spatial clustering of stations based on POI data is performed to filter out strongly correlated stations, and feature selection is performed to eliminate redundant features. In this paper, the ConvFormer-KDE model is presented, whereby local patterns and short-term dependencies among multivariate variables are mined through a convolutional neural network (CNN), long-term dependencies among time-series data are extracted using the Transformer model, and a direct multi-output strategy is employed to realize the long-term point prediction of PM concentration. KDE is utilized to derive prediction intervals for PM concentration at confidence levels of 85%, 90%, and 95%, respectively, reflecting the uncertainty inherent in long-term trends of PM. The performance of ConvFormer-KDE was compared with a list of advanced models. Experimental results showed that ConvFormer-KDE outperformed baseline models in long-term point- and interval-prediction tasks for PM. The ConvFormer-KDE can provide a valuable early warning basis for future PM changes from the aspects of point and interval prediction.
准确的长期细颗粒物（PM）预测对于环境管理和公众健康至关重要。然而，以往的研究主要集中在短期空气质量点预测上，忽视了准确预测PM长期趋势以及研究PM浓度变化不确定性的重要性。传统方法在捕捉时间序列中的非线性关系和复杂动态模式方面存在局限性，并且在实际应用中常常忽略预测结果的可信度。因此，PM的长期预测仍有很大的改进空间。本研究提出了一种基于多源时空数据的城市空气质量长期点预测和区间预测框架，该框架在准确的PM点预测基础上进一步量化了预测的不确定性和波动性。在该模型中，首先对来自多个监测站的多源数据集进行预处理。随后，基于兴趣点（POI）数据对监测站进行空间聚类，以筛选出强相关的监测站，并进行特征选择以消除冗余特征。本文提出了ConvFormer-KDE模型，通过卷积神经网络（CNN）挖掘多变量之间的局部模式和短期依赖性，使用Transformer模型提取时间序列数据中的长期依赖性，并采用直接多输出策略实现PM浓度的长期点预测。利用核密度估计（KDE）分别得出置信水平为85%、90%和95%的PM浓度预测区间，反映了PM长期趋势中固有的不确定性。将ConvFormer-KDE的性能与一系列先进模型进行了比较。实验结果表明，在PM的长期点预测和区间预测任务中，ConvFormer-KDE优于基线模型。ConvFormer-KDE可以从点预测和区间预测方面为未来PM变化提供有价值的预警依据。
