Key Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province, College of Information Engineering, China Jiliang University, Hangzhou, 310018, China.
National University of Singapore, Singapore, 117566, Singapore.
Environ Sci Pollut Res Int. 2021 Aug;28(29):39409-39422. doi: 10.1007/s11356-021-12657-8. Epub 2021 Mar 23.
The concentration of PM is one of the main factors in evaluating the air quality in environmental science. The severe level of PM directly affects the public health, economics and social development. Due to the strong nonlinearity and instability of the air quality, it is difficult to predict the volatile changes of PM over time. In this paper, a hybrid deep learning model VMD-BiLSTM is constructed, which combines variational mode decomposition (VMD) and bidirectional long short-term memory network (BiLSTM), to predict PM changes in cities in China. VMD decomposes the original PM complex time series data into multiple sub-signal components according to the frequency domain. Then, BiLSTM is employed to predict each sub-signal component separately, which significantly improved forecasting accuracy. Through a comprehensive study with existing models, such as the EMD-based models and other VMD-based models, we justify the outperformance of the proposed VMD-BiLSTM model over all compared models. The results show that the prediction results are significantly improved with the proposed forecasting framework. And the prediction models integrating VMD are better than those integrating EMD. Among all the models integrating VMD, the proposed VMD-BiLSTM model is the most stable forecasting method.
PM 浓度是环境科学中评估空气质量的主要因素之一。PM 的严重程度直接影响公众健康、经济和社会发展。由于空气质量的强非线性和不稳定性，很难预测 PM 随时间的挥发性变化。在本文中，构建了一种混合深度学习模型 VMD-BiLSTM，它结合了变分模态分解（VMD）和双向长短期记忆网络（BiLSTM），以预测中国城市的 PM 变化。VMD 根据频域将原始 PM 复杂时间序列数据分解为多个子信号分量。然后，BiLSTM 用于分别预测每个子信号分量，这显著提高了预测精度。通过与现有模型（如基于 EMD 的模型和其他基于 VMD 的模型）进行全面研究，我们证明了所提出的 VMD-BiLSTM 模型优于所有比较模型。结果表明，所提出的预测框架显著提高了预测结果。并且，集成 VMD 的预测模型优于集成 EMD 的预测模型。在所有集成 VMD 的模型中，所提出的 VMD-BiLSTM 模型是最稳定的预测方法。
