Multitask Air-Quality Prediction Based on LSTM-Autoencoder Model

With the development of the data-driven modeling techniques, using the neural network to simulate the transport process of atmospheric pollutants and constructing <inline-formula> <tex-math notation="LaTeX">${\textrm {PM}}_{2.5}$ </tex-math></inline-formula> time-series prediction model have become a hot topic. The existing data-driven approaches often ignore the dynamical relationships among multiple sites in urban areas, which results in nonideal prediction accuracy. In response to this problem, this article proposes a long short-term memory (LSTM) autoencoder multitask learning model to predict <inline-formula> <tex-math notation="LaTeX">${\textrm {PM}}_{2.5}$ </tex-math></inline-formula> time series in multiple locations city wide. The model could implicitly and automatically excavate the intrinsic relevance among the pollutants in different stations. And the meteorological information from the monitoring stations is fully utilized, which is beneficial for the performance of the proposed model. Specifically, multilayer LSTM networks can simulate the spatiotemporal characteristics of urban air pollution particles. And using the stacked autoencoder to encode the key evolution pattern of urban meteorological systems could provide important auxiliary information for <inline-formula> <tex-math notation="LaTeX">${\textrm {PM}}_{2.5}$ </tex-math></inline-formula> time-series prediction. In addition, multitask learning could automatically discover the dynamical relationship between multiple key pollution time series and solve the problem of insufficient use of multisite information in the modeling process of the traditional data-driven methods. The simulation results of <inline-formula> <tex-math notation="LaTeX">${\textrm {PM}}_{2.5}$ </tex-math></inline-formula> prediction in Beijing indicate the effectiveness of the proposed method.

[1]  Yuqi Bai,et al.  Development of nonlinear empirical models to forecast daily PM2.5 and ozone levels in three large Chinese cities , 2016 .

[2]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[3]  Jorge Reyes,et al.  Prediction of PM2.5 concentrations several hours in advance using neural networks in Santiago, Chile , 2000 .

[4]  Ming Li,et al.  Forecasting Fine-Grained Air Quality Based on Big Data , 2015, KDD.

[5]  Rich Caruana,et al.  Multitask Learning , 1998, Encyclopedia of Machine Learning and Data Mining.

[6]  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.

[7]  Viktor Pocajt,et al.  The significance of periodic parameters for ANN modeling of daily SO2 and NOx concentrations: A case study of Belgrade, Serbia , 2019, Atmospheric Pollution Research.

[8]  Xuelong Li,et al.  Semi-Supervised Multitask Learning for Scene Recognition , 2015, IEEE Transactions on Cybernetics.

[9]  Yu Zheng,et al.  U-Air: when urban air quality inference meets big data , 2013, KDD.

[10]  Yu Zheng,et al.  p-Causality: Identifying Spatiotemporal Causal Pathways for Air Pollutants with Urban Big Data , 2016, ArXiv.

[11]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[12]  R. Sarpong,et al.  Bio-inspired synthesis of xishacorenes A, B, and C, and a new congener from fuscol† †Electronic supplementary information (ESI) available. See DOI: 10.1039/c9sc02572c , 2019, Chemical science.

[13]  Itai Kloog,et al.  A review of AirQ Models and their applications for forecasting the air pollution health outcomes , 2017, Environmental Science and Pollution Research.

[14]  Xuelong Li,et al.  Two-Stage Learning to Predict Human Eye Fixations via SDAEs , 2016, IEEE Transactions on Cybernetics.

[15]  Miss A.O. Penney.  (b) , 1974, The New Yale Book of Quotations.

[16]  J. Schwartz,et al.  A hybrid prediction model for PM2.5 mass and components using a chemical transport model and land use regression , 2016 .

[17]  Ying Liu,et al.  Distributed Jointly Sparse Multitask Learning Over Networks , 2018, IEEE Transactions on Cybernetics.

[18]  W. Marsden.  I and J , 2012 .

[19]  Youchuan Wan,et al.  Ground-level PM2.5 estimation over urban agglomerations in China with high spatiotemporal resolution based on Himawari-8. , 2019, The Science of the total environment.

[20]  Jen-Wei Huang,et al.  Adaptive Deep Learning-Based Air Quality Prediction Model Using the Most Relevant Spatial-Temporal Relations , 2018, IEEE Access.

[21]  Korris Fu-Lai Chung,et al.  Multitask Coupled Logistic Regression and its Fast Implementation for Large Multitask Datasets , 2015, IEEE Transactions on Cybernetics.

[22]  Jürgen Schmidhuber,et al.  Framewise phoneme classification with bidirectional LSTM and other neural network architectures , 2005, Neural Networks.

[23]  Majid Salari,et al.  Statistical models for multi-step-ahead forecasting of fine particulate matter in urban areas , 2019, Atmospheric Pollution Research.

[24]  Li-Chiu Chang,et al.  Multi-output support vector machine for regional multi-step-ahead PM2.5 forecasting. , 2019, The Science of the total environment.

[25]  A. Osses,et al.  Forecasting urban PM10 and PM2.5 pollution episodes in very stable nocturnal conditions and complex terrain using WRF–Chem CO tracer model , 2011 .

[26]  W. Geoffrey Cobourn,et al.  An enhanced PM2.5 air quality forecast model based on nonlinear regression and back-trajectory concentrations , 2010 .

[27]  Jianjun He,et al.  Air pollution characteristics and their relation to meteorological conditions during 2014-2015 in major Chinese cities. , 2017, Environmental pollution.

[28]  Yao Hu,et al.  An Enhanced LSTM for Trend Following of Time Series , 2019, IEEE Access.

[29]  Yong Li,et al.  Hourly PM2.5 concentration forecast using stacked autoencoder model with emphasis on seasonality , 2019, Journal of Cleaner Production.

[30]  Kaisheng Yao,et al.  Depth-Gated Recurrent Neural Networks , 2015 .

[31]  Shou-De Lin,et al.  Inferring Air Quality for Station Location Recommendation Based on Urban Big Data , 2015, KDD.

[32]  Congcong Wen,et al.  A novel spatiotemporal convolutional long short-term neural network for air pollution prediction. , 2019, The Science of the total environment.

[33]  Victor O. K. Li,et al.  An Extended Spatio-Temporal Granger Causality Model for Air Quality Estimation with Heterogeneous Urban Big Data , 2017, IEEE Transactions on Big Data.

[34]  Yang Zhang,et al.  Real-time air quality forecasting, part I: History, techniques, and current status , 2012 .

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

[36]  Wei Xiong,et al.  Stacked Convolutional Denoising Auto-Encoders for Feature Representation , 2017, IEEE Transactions on Cybernetics.

[37]  Zhongfei Zhang,et al.  Deep Air Learning: Interpolation, Prediction, and Feature Analysis of Fine-Grained Air Quality , 2017, IEEE Transactions on Knowledge and Data Engineering.