Air Pollution Prediction Using Long Short-Term Memory (LSTM) and Deep Autoencoder (DAE) Models

Many countries worldwide have poor air quality due to the emission of particulate matter (i.e., PM 10 and PM 2.5 ), which has led to concerns about human health impacts in urban areas. In this study, we developed models to predict fine PM concentrations using long short-term memory (LSTM) and deep autoencoder (DAE) methods, and compared the model results in terms of root mean square error (RMSE). We applied the models to hourly air quality data from 25 stations in Seoul, South Korea, for the period from 1 January 2015, to 31 December 2018. Fine PM concentrations were predicted for the 10 days following this period, at an optimal learning rate of 0.01 for 100 epochs with batch sizes of 32 for LSTM model, and DAEs model performed best with batch size 64. The proposed models effectively predicted fine PM concentrations, with the LSTM model showing slightly better performance. With our forecasting model, it is possible to give reliable fine dust prediction information for the area where the user is located.

[1]  William L. Crosson,et al.  Estimating Ground-Level PM(sub 2.5) Concentrations in the Southeastern United States Using MAIAC AOD Retrievals and a Two-Stage Model , 2014 .

[2]  Sameer Sharma,et al.  Neural Network Models for Air Quality Prediction: A Comparative Study , 2007 .

[3]  Sayan Mukhopadhyay,et al.  Deep Learning and Neural Networks , 2018 .

[4]  P. Fu,et al.  Airborne particulate matter pollution in urban China: a chemical mixture perspective from sources to impacts , 2017 .

[5]  Pericles A. Mitkas,et al.  Applying Machine Learning Techniques on Air Quality Data for Real-Time Decision Support , 2003 .

[6]  Dipankar Das,et al.  MTIL2017: Machine Translation Using Recurrent Neural Network on Statistical Machine Translation , 2019, J. Intell. Syst..

[7]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[8]  Y. Xing,et al.  The impact of PM2.5 on the human respiratory system. , 2016, Journal of thoracic disease.

[9]  Konrad Schindler,et al.  Online Multi-Target Tracking Using Recurrent Neural Networks , 2016, AAAI.

[10]  Gianluca Pollastri,et al.  Deep learning methods in protein structure prediction , 2020, Computational and structural biotechnology journal.

[11]  Yun Zeng,et al.  Progress in developing an ANN model for air pollution index forecast , 2004 .

[12]  Yuxia Li,et al.  Prediction of particulate matter concentration in Chengdu based on improved differential evolution algorithm and BP neural network model , 2018, 2018 IEEE 3rd International Conference on Cloud Computing and Big Data Analysis (ICCCBDA).

[13]  Qi Li,et al.  A hybrid model for spatiotemporal forecasting of PM2.5 based on graph convolutional neural network and long short-term memory. , 2019, The Science of the total environment.

[14]  Joaquín B. Ordieres Meré,et al.  Neural network prediction model for fine particulate matter (PM2.5) on the US-Mexico border in El Paso (Texas) and Ciudad Juárez (Chihuahua) , 2005, Environ. Model. Softw..

[15]  Shrestha Mohanty,et al.  Deep Air : Forecasting Air Pollution in Beijing , China , 2017 .

[16]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[17]  Jiachen Zhao,et al.  Long short-term memory - Fully connected (LSTM-FC) neural network for PM2.5 concentration prediction. , 2019, Chemosphere.

[18]  Qi Wang,et al.  Salient Band Selection for Hyperspectral Image Classification via Manifold Ranking , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[19]  Giorgio Corani,et al.  Air quality prediction in Milan: feed-forward neural networks, pruned neural networks and lazy learning , 2005 .

[20]  Hui Wang,et al.  An improved model for PM2.5 inference based on support vector machine , 2016, 2016 17th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD).

[21]  Qi Li,et al.  A Spatiotemporal Prediction Framework for Air Pollution Based on Deep RNN , 2017 .

[22]  Takeo Kanade,et al.  Computational Intelligence in Security for Information Systems , 2011, Lecture Notes in Computer Science.

[23]  Fei-Yue Wang,et al.  Traffic Flow Prediction With Big Data: A Deep Learning Approach , 2015, IEEE Transactions on Intelligent Transportation Systems.

[24]  Wenhao Huang,et al.  Deep Architecture for Traffic Flow Prediction: Deep Belief Networks With Multitask Learning , 2014, IEEE Transactions on Intelligent Transportation Systems.

[25]  Bo Zhang,et al.  A Novel Combined Prediction Scheme Based on CNN and LSTM for Urban PM2.5 Concentration , 2019, IEEE Access.

[26]  Jianzhou Wang,et al.  A hybrid model for PM₂.₅ forecasting based on ensemble empirical mode decomposition and a general regression neural network. , 2014, The Science of the total environment.

[27]  S. Samarasinghe,et al.  Complex time series analysis of PM10 and PM2.5 for a coastal site using artificial neural network modelling and k-means clustering , 2014 .

[28]  Weiwei Fang,et al.  Shape retrieval using deep autoencoder learning representation , 2016, 2016 13th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP).

[29]  Nikolaos M. Avouris,et al.  Short-term air quality prediction using a case-based classifier , 2001, Environ. Model. Softw..

[30]  SchmidhuberJürgen.  Deep learning in neural networks , 2015 .

[31]  Dong Yu,et al.  Deep Learning: Methods and Applications , 2014, Found. Trends Signal Process..

[32]  Jeffrey S. Wilson,et al.  Measurement and Modeling of Ground-Level Ozone Concentration in Catania, Italy using Biophysical Remote Sensing and GIS , 2017 .

[33]  Bert Brunekreef,et al.  Land use regression models for estimating individual NOx and NO₂ exposures in a metropolis with a high density of traffic roads and population. , 2014, The Science of the total environment.

[34]  Brian Nutter,et al.  Content Based Image Retrieval system using Wavelet Transformation and multiple input multiple task Deep Autoencoder , 2016, 2016 IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI).

[35]  Minglei Fu,et al.  Prediction of particular matter concentrations by developed feed-forward neural network with rolling mechanism and gray model , 2015, Neural Computing and Applications.

[36]  Xiang Li,et al.  Deep learning architecture for air quality predictions , 2016, Environmental Science and Pollution Research.

[37]  Sookyung Kim,et al.  Deep-dust: Predicting concentrations of fine dust in Seoul using LSTM , 2019, ArXiv.

[38]  Shikha Gupta,et al.  Identifying pollution sources and predicting urban air quality using ensemble learning methods , 2013 .

[39]  J. Gulliver,et al.  A review of land-use regression models to assess spatial variation of outdoor air pollution , 2008 .

[40]  Mengyin Fu,et al.  Recurrent Neural Networks based on LSTM for Predicting Geomagnetic Field , 2018, 2018 IEEE International Conference on Aerospace Electronics and Remote Sensing Technology (ICARES).

[41]  Yue-Shan Chang,et al.  Big data platform for air quality analysis and prediction , 2018, 2018 27th Wireless and Optical Communication Conference (WOCC).

[42]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[43]  Pedro G. Lind,et al.  Air quality prediction using optimal neural networks with stochastic variables , 2013, 1307.3134.