Auto imputation enabled deep Temporal Convolutional Network (TCN) model for pm2.5 forecasting

K. Krishna Rani Samal

doi:10.4108/eetsis.5102

Authors

K. Krishna Rani Samal Vellore Institute of Technology University

DOI:

https://doi.org/10.4108/eetsis.5102

Keywords:

Deep learning, Pollution, Imputation, Forecasting, PM2.5, TCN

Abstract

Data imputation of missing values is one of the critical issues for data engineering, such as air quality modeling. It is challenging to handle missing pollutant values because they are collected at irregular and different times. Accurate estimation of those missing values is critical for the air pollution prediction task. Effective forecasting is a significant part of air quality modeling for a robust early warning system. This study developed a neural network model, a Temporal Convolutional Network (TCN) with an imputation block (TCN-I), to simultaneously perform data imputation and forecasting tasks. As pollution sensor data suffer from different types of missing values whose causes are varied, TCN is attempted to impute those missing values in this study and perform prediction tasks in a single model. The results prove that the TCN-I model outperforms the baseline models.

References

Ma, J., Ding, Y., Cheng, J.C., Jiang, F., Gan, V.J. and Xu, Z. (2020) A lag-flstm deep learning network based on bayesian optimization for multi-sequential-variant pm2.5 prediction. Sustainable Cities and Society 60: 102237.

Zíková, N., Wang, Y., Yang, F., Li, X., Tian, M. and Hopke, P.K. (2016) On the source contribution to beijing pm2. 5 concentrations. Atmospheric Environment 134: 84–95.

Samal, K.K.R., Panda, A.K., Babu, K.S. and Das, S.K. (2021) An improved pollution forecasting model with meteorological impact using multiple imputation and fine-tuning approach. Sustainable Cities and Society : 102923.

Samal, K.K.R., Babu, K.S. and Das, S.K. (2020) Ors: The optimal routing solution for smart city users. In Electronic Systems and Intelligent Computing (Springer), 177–186.

Yang, J., Shi, B., Shi, Y., Marvin, S., Zheng, Y. and Xia, G. (2020) Air pollution dispersal in high density urban areas: Research on the triadic relation of wind, air pollution, and urban form. Sustainable Cities and Society 54: 101941.

Reiminger, N., Jurado, X., Vazquez, J., Wemmert, C., Blond, N., Wertel, J. and Dufresne, M. (2020) Methodologies to assess mean annual air pollution concentration combining numerical results and wind roses. Sustainable Cities and Society : 102221.

Samal, K.K.R., Babu, K.S. and Das, S.K. (2021) Temporalconvolutional denoising autoencoder network for air pollution prediction with missing values. Urban Climate 38: 100872.

Zhang, R., Liu, C., Hsu, P.C., Zhang, C., Liu, N., Zhang, J., Lee, H.R. et al. (2016) Nanofiber air filters with hightemperature stability for efficient pm2. 5 removal from the pollution sources. Nano letters 16(6): 3642–3649.

Kalisa, E., Fadlallah, S., Amani, M., Nahayo, L. and Habiyaremye, G. (2018) Temperature and air pollution relationship during heatwaves in birmingham, uk. Sustainable cities and society 43: 111–120.

Askariyeh, M.H., Zietsman, J. and Autenrieth, R. (2020) Traffic contribution to pm2. 5 increment in the near-road environment. Atmospheric Environment 224: 117113.

Hien, P., Bac, V., Tham, H., Nhan, D. and Vinh, L. (2002) Influence of meteorological conditions on pm2. 5 and pm2. 5- 10 concentrations during the monsoon season in hanoi, vietnam. Atmospheric Environment 36(21): 3473–3484.

Cheng, Y., He, K.b., Du, Z.y., Zheng, M., Duan, F.k. and Ma, Y.l. (2015) Humidity plays an important role in the pm2. 5 pollution in beijing. Environmental pollution 197: 68–75.

Zalakeviciute, R., López-Villada, J. and Rybarczyk, Y. (2018) Contrasted effects of relative humidity and precipitation on urban pm2. 5 pollution in high elevation urban areas. Sustainability 10(6): 2064.

Amarpuri, L., Yadav, N., Kumar, G. and Agrawal, S. (2019) Prediction of co 2 emissions using deep learning hybrid approach: A case study in indian context. In 2019 Twelfth International Conference on Contemporary Computing (IC3) (IEEE): 1–6.

Xu, X. and Yoneda, M. (2019) Multitask air-quality prediction based on lstm-autoencoder model. IEEE transactions on cybernetics .

Samal, K.K.R., Babu, K.S. and Das, S.K. (2021) Multidirectional temporal convolutional artificial neural network for pm2. 5 forecasting with missing values: A deep learning approach. Urban Climate 36: 100800.

Samal, K.K.R., Babu, K.S., Das, S.K. and Acharaya, A. (2019) Time series based air pollution forecasting using sarima and prophet model. In Proceedings of the 2019 International Conference on Information Technology and Computer Communications: 80–85.

Lagesse, B., Wang, S., Larson, T.V. and Kim, A.A. (2020) Predicting pm2. 5 in well-mixed indoor air for a large office building using regression and artificial neural network models. Environmental Science & Technology 54(23): 15320–15328.

Freeman, B.S., Taylor, G., Gharabaghi, B. and Thé, J. (2018) Forecasting air quality time series using deep learning. Journal of the Air & Waste Management Association 68(8): 866–886.

Samal, K., Babu, K.S. and Das, S.K. (2021) Spatiotemporal prediction of air quality using distance based interpolation and deep learning techniques. EAI Endorsed Transactions on Smart Cities 5(14): e4.

Samal, K.K.R., Babu, K.S., Acharya, A. and Das, S.K. (2020) Long term forecasting of ambient air quality using deep learning approach. In 2020 IEEE 17th India Council International Conference (INDICON) (IEEE): 1–6.

Ge, L., Zhou, A., Li, H. and Liu, J. (2019) Spatially finegrained air quality prediction based on dbu-lstm. In Proceedings of the 16th ACM International Conference on Computing Frontiers (ACM): 202–205.

Yeo, I., Choi, Y., Lops, Y. and Sayeed, A. Efficient pm2.5 forecasting using geographical correlation based on integrated deep learning algorithms .

Chen, H., Guan, M. and Li, H. (2021) Air quality prediction based on integrated dual lstm model. IEEE Access 9: 93285–93297.

Xie, H., Ji, L., Wang, Q. and Jia, Z. (2019) Research of pm2. 5 prediction system based on cnns-gru in wuxi urban area. In IOP Conference Series: Earth and Environmental Science (IOP Publishing), 300: 032073.

Gilik, A., Ogrenci, A.S. and Ozmen, A. (2021) Air quality prediction using cnn+ lstm-based hybrid deep learning architecture. Environmental Science and Pollution Research : 1–19.

Samal, K.K.R.S., Babu, K.S. and Das, S.K. (2023) Spatialtemporal prediction of air quality by deep learning and kriging interpolation approach. EAI Endorsed Transactions on Scalable Information Systems 10(5).

Quinteros, M.E., Lu, S., Blazquez, C., Cárdenas-R, J.P., Ossa, X., Delgado-Saborit, J.M., Harrison, R.M. et al. (2019) Use of data imputation tools to reconstruct incomplete air quality datasets: A case-study in temuco, chile. Atmospheric environment 200: 40–49.

Peña, M., Ortega, P. and Orellana, M. (2019) A novel imputation method for missing values in air pollutant time series data. In 2019 IEEE Latin American Conference on Computational Intelligence (LA-CCI) (IEEE): 1–6.

Yen, N.Y., Chang, J.W., Liao, J.Y. and Yong, Y.M. (2019) Analysis of interpolation algorithms for the missing values in iot time series: a case of air quality in taiwan. The Journal of Supercomputing : 1–26.

Wijesekara, W. and Liyanage, L. (2020) Comparison of imputation methods for missing values in air pollution data: Case study on sydney air quality index. In Future of Information and Communication Conference (Springer): 257–269.

Libasin, Z., Ul-Saufie, A.Z., Ahmat, H. and Shaziayani, W.N. (2020) Single and multiple imputation method to replace missing values in air pollution datasets: A review. In IOP Conference Series: Earth and Environmental Science (IOP Publishing), 616: 012002.

Lelieveld, J., Evans, J.S., Fnais, M., Giannadaki, D. and Pozzer, A. (2015) The contribution of outdoor air pollution sources to premature mortality on a global scale. Nature 525(7569): 367–371.

Zhai, B. and Chen, J. (2018) Development of a stacked ensemble model for forecasting and analyzing daily average pm2. 5 concentrations in beijing, china. Science of The Total Environment 635: 644–658.

Zhang, S., Guo, B., Dong, A., He, J., Xu, Z. and Chen, S.X. (2017) Cautionary tales on air-quality improvement in beijing. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences 473(2205): 20170457.

Chen, S. (2017), Beijing multi-site air-quality data dataset.

Samal, K.K.R., Babu, K.S., Panda, A.K. and Das, S.K. (2020) Data driven multivariate air quality forecasting using dynamic fine tuning autoencoder layer. In 2020 IEEE 17th India Council International Conference (INDICON) (IEEE): 1–6.

Stekhoven, D.J. and Bühlmann, P. (2012) Missforest—non-parametric missing value imputation for mixed-type data. Bioinformatics 28(1): 112–118.

Malarvizhi, M.R. and Thanamani, A.S. (2012) K-nearest neighbor in missing data imputation. International Journal of Engineering Research and Development 5(1): 5–7.

Beretta, L. and Santaniello, A. (2016) Nearest neighbor imputation algorithms: a critical evaluation. BMC medical informatics and decision making 16(3): 74.

Mustafa, Y.T., Tolpekin, V.A. and Stein, A. (2011) Application of the expectation maximization algorithm to estimate missing values in gaussian bayesian network modeling for forest growth. IEEE transactions on geoscience and remote sensing 50(5): 1821–1831.

Che, Z., Purushotham, S., Cho, K., Sontag, D. and Liu, Y. (2018) Recurrent neural networks for multivariate time series with missing values. Scientific reports 8(1): 1–12.

Gondara, L. and Wang, K. (2018) Mida: Multiple imputation using denoising autoencoders. In Pacific-Asia Conference on Knowledge Discovery and Data Mining (Springer): 260–272.

Singh, D. and Singh, B. (2020) Investigating the impact of data normalization on classification performance. Applied Soft Computing 97: 105524.

Guo, G. and Yuan, W. (2020) Short-term traffic speed forecasting based on graph attention temporal convolutional networks. Neurocomputing 410: 387–393.

Pandey, A. and Wang, D. (2019) Tcnn: Temporal convolutional neural network for real-time speech enhancement in the time domain. In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (IEEE): 6875–6879.

Meng, C., Jiang, X.S., Wei, X.M. and Wei, T. (2020) A time convolutional network based outlier detection formultidimensional time series in cyber-physical-social systems. IEEE Access 8: 74933–74942.

Bai, S., Kolter, J.Z. and Koltun, V. (2018) An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271 .

Liu, H. and Chen, C. (2020) Spatial air quality index prediction model based on decomposition, adaptive boosting, and three-stage feature selection: A case study in china. Journal of Cleaner Production : 121777.

Qiao, W., Moayedi, H. and Foong, L.K. (2020) Natureinspired hybrid techniques of iwo, da, es, ga, and ica, validated through a k-fold validation process predicting monthly natural gas consumption. Energy and Buildings: 110023.

Ausati, S. and Amanollahi, J. (2016) Assessing the accuracy of anfis, eemd-grnn, pcr, and mlr models in predicting pm2. 5. Atmospheric environment 142: 465–474.

Du, S., Li, T., Yang, Y. and Horng, S.J. (2018) Deep air quality forecasting using hybrid deep learning framework. arXiv preprint arXiv:1812.04783 .

Ma, J., Ding, Y., Cheng, J.C., Jiang, F. andWan, Z. (2019) A temporal-spatial interpolation and extrapolation method based on geographic long short-term memory neural network for pm2. 5. Journal of Cleaner Production 237: 117729.

Zhang, B., Zhang, H., Zhao, G. and Lian, J. (2020) Constructing a pm2. 5 concentration prediction model by combining auto-encoder with bi-lstm neural networks. Environmental Modelling & Software 124: 104600.

Tao, Q., Liu, F., Li, Y. and Sidorov, D. (2019) Air pollution forecasting using a deep learning model based on 1d convnets and bidirectional gru. IEEE Access 7: 76690–76698.