余长慧,刘良

• 1:武汉大学遥感信息工程学院

摘要(Abstract)：

目前PM_(2.5)浓度预测研究主要是对未来1 h的污染物浓度进行预测，不能满足污染物浓度较长时间细粒度预测的应用需求。构建了基于注意力机制的序列到序列（sequence to sequence,seq2seq）模型。模型主要由编码器、解码器和注意力模块3部分构成，其中，编码器用于提取时间特征，解码器使用注意力模块动态计算每个时刻的背景变量，从而预测未来时刻的PM_(2.5)浓度。使用2015—2018年北京市12个空气监测站点的小时级别的PM_(2.5)观测数据进行实验，并将结果与基准模型进行比较。结果表明，该模型预测结果较好。

关键词(KeyWords)： PM_(2.5);时空依赖;seq2seq模型;注意力机制

Abstract:

Keywords:

基金项目(Foundation): 国家重点研发计划（2016YFB0502301）

作者(Author): 余长慧,刘良

DOI: 10.14188/j.2095-6045.2020407

参考文献(References)：

• [1]李同文，孙越乔，杨晨雪，等.融合卫星遥感与地面测站的区域PM2. 5反演[J].测绘地理信息，2015, 40(3):6-9
• [2] Pope C A, Burnett R T, Thun M J, et al. Lung Cancer, Cardiopulmonary Mortality, and Long-Term Exposure to Fine Particulate Air Pollution[J]. JAMA,2002, 287(9):1 132-1 141
• [3] Li X, Peng L, Yao X J, et al. Long Short-Term Memory Neural Network for Air Pollutant Concentration Predictions:Method Development and Evaluation[J]. Environmental Pollution, 2017, 231:997-1 004
• [4] Chen J J, Lu J, Avise J C, et al. Seasonal Modeling of PM2. 5 in California’s San Joaquin Valley[J]. Atmospheric Environment, 2014, 92:182-190
• [5] Saide P E, Carmichael G R, Spak S N, et al. Forecasting Urban PM10 and PM2. 5 Pollution Episodes in very Stable Nocturnal Conditions and Complex Terrain Using WRF-Chem CO Tracer Model[J]. Atmospheric Environment, 2011, 45(16):2 769-2 780
• [6]王自发，谢付莹，王喜全，等.嵌套网格空气质量预报模式系统的发展与应用[J].大气科学，2006, 30(5):778-790
• [7] Li C, Hsu N C, Tsay S C. A Study on the Potential Applications of Satellite Data in Air Quality Monitoring and Forecasting[J]. Atmospheric Environment, 2011,45(22):3 663-3 675
• [8] Nieto P J G,Combarro E F,del Coz J J D,et al. A SVM-Based Regression Model to Study the Air Quality at Local Scale in Oviedo Urban Area(Northern Spain):A Case Study[J]. Applied Mathematics and Computation, 2013, 219(17):8 923-8 937
• [9] Box G E P, Jenkins G M. Time Series Analysis:Forecasting and Control[M]. San Francisco:HoldenDay, 1976
• [10] Hooyberghs J, Mensink C, Dumont G, et al. A Neural Network Forecast for Daily Average PM Concentrations in Belgium[J]. Atmospheric Environment, 2005,39(18):3 279-3 289
• [11] Yoon H, Jun S C, Hyun Y. A Comparative Study of Artificial Neural Networks and Support Vector Machines for Predicting Groundwater Levels in a Coastal Aquifer[J]. Journal of Hydrology, 2011, 396(1/2):128-138
• [12]黄婕，张丰，杜震洪，等.基于RNN-CNN集成深度学习模型的PM2. 5小时浓度预测[J].浙江大学学报（理学版），2019, 46(3):370-379
• [13] Hochreiter S, Schmidhuber J. Long Short-Term Memory[J]. Neural Computation, 1997, 9(8):1 735-1 780
• [14]郑洋洋，白艳萍，侯宇超.基于Keras的LSTM模型在空气质量指数预测的应用[J].数学的实践与认识，2019, 49(7):138-143
• [15]张鹏达.基于BP神经网络的城市环境空气质量预测模型[J].自动化技术与应用，2014, 33(1):9-11
• [16] Hwang S, Jeon G, Jeong J, et al. A Novel Time Series Based seq2Seq Model for Temperature Prediction in Firing Furnace Process[J]. Procedia Computer Science, 2019, 155:19-26
• [17] Karatzoglou A, Jablonski A, Beigl M. A seq2Seq Learning Approach for Modeling Semantic Trajectories and Predicting the Next Location[C]. Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, Seattle, USA, 2018
• [18]谢崇波.基于循环神经网络的城市空气质量预测研究[D].绵阳：西南科技大学，2019
• [19] Cho K, van Merrienboer B, Gulcehre C, et al. Learning Phrase Representations Using RNN Encoder-Decoder for Statistical Machine Translation[C]. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing(EMNLP), Doha, Qatar, 2014
• [20] Liang Yuxuan, Ke Songyu, Zhang Junbo, et al. GeoMAN:Multi-level Attention Networks for Geo-sensory Time Series Prediction[C]. Proceedings of the 27th International Joint Conference on Artificial Intelligence,Stockholm, Sweden, 2018