Institute of Remote Sensing and Geographic Information System, Peking University, Beijing, 100871, China.
School of Civil and Surveying & Mapping Engineering, Jiangxi University of Science and Technology, Ganzhou, 341000, China.
Environ Sci Pollut Res Int. 2022 Aug;29(36):54150-54166. doi: 10.1007/s11356-022-19574-4. Epub 2022 Mar 16.
Exposure to fine particulate matter can easily lead to health issues. PM concentrations are associated with various spatiotemporal factors, which makes the prediction of PM concentrations still a challenging task. One of the reasons that makes the accurate prediction by statistical learning method difficult is severe fluctuations in input data. In addition, the abstraction method of space will also affect the prediction results. To address these important issues, a novel hybrid decomposing-ensemble and spatiotemporal attention (DESA) model is proposed to improve the prediction accuracy by decomposing the mode-mixed time series into single-mode series and automatically assign weights to the spatiotemporal factors. In our proposed framework, raw PM series are firstly decomposed into simple sub-series via the complete ensemble empirical mode decomposition (CEEMD) method. Then, to keep the results independent of the spatial abstraction method, a data-driven approach called multiscale spatiotemporal attention network is employed to extract spatiotemporal features from the sub-series. Finally, the predictions of each sub-series are processed separately and combined to obtain the final prediction results. The experimental results indicate that the proposed model achieved the better performance with RMSE of 11.15, 17.49, 24.84, and 26.93 for 6-, 12-, 24-, and 36-h forecasting, respectively. The proposed method is expected to be applied in fine prediction of air pollution and controlling programs and therefore provide decision support or useful guidance.
暴露在细颗粒物中很容易导致健康问题。PM 浓度与各种时空因素有关，这使得 PM 浓度的预测仍然是一项具有挑战性的任务。使得统计学习方法难以准确预测的原因之一是输入数据的剧烈波动。此外，空间抽象方法也会影响预测结果。为了解决这些重要问题，提出了一种新的混合分解-集成和时空注意（DESA）模型，通过将混合模式的时间序列分解为单模式序列，并自动为时空因素分配权重，从而提高预测精度。在我们提出的框架中，原始 PM 序列首先通过完全集成经验模态分解（CEEMD）方法分解为简单的子序列。然后，为了使结果不受空间抽象方法的影响，采用了一种称为多尺度时空注意网络的数据驱动方法，从子序列中提取时空特征。最后，分别处理每个子序列的预测结果，并将其组合以获得最终的预测结果。实验结果表明，该模型在 6 小时、12 小时、24 小时和 36 小时预测中分别取得了 RMSE 为 11.15、17.49、24.84 和 26.93 的较好性能。该方法有望应用于空气污染的精细预测和控制计划，从而为决策提供支持或有用的指导。
