A Deep Spatial-Temporal Ensemble Model for Air Quality Prediction

Abstract Air quality has drawn much attention in the recent years because it seriously affects people’s health. Nowadays, monitoring stations in a city can provide real-time air quality, but people also strongly desire air quality prediction, which is a challenging problem as it depends on several complicated factors, such as weather patterns and spatial-temporal dependencies of air quality. In this paper, we design a data-driven approach that utilizes historical air quality and meteorological data to predict air quality in the future. We propose a deep spatial-temporal ensemble(STE) model which is comprised of three components. The first component is an ensemble method with a weather-pattern-based partitioning strategy. It trains multiple individual models and combines them dynamically. The second one is to discover spatial correlation by analyzing Granger causalities among stations and generating spatial data as relative stations and relative areas. The last one is a temporal predictor based on deep LSTM to learn both long-term and short-term dependencies of air quality. We evaluate our model with data from 35 monitoring stations in Beijing, China. The experiments show that each component of our model makes contribution to the improvement in prediction accuracy and the model is superior to baselines.

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

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

[3]  K. Pericleous,et al.  Modelling air quality in street canyons : a review , 2003 .

[4]  W. Pfender,et al.  Use of a complex air pollution model to estimate dispersal and deposition of grass stem rust urediniospores at landscape scale , 2006 .

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

[6]  J. Bezdek,et al.  FCM: The fuzzy c-means clustering algorithm , 1984 .

[7]  Bruce Misstear,et al.  Real time air quality forecasting using integrated parametric and non-parametric regression techniques , 2015 .

[8]  J. Hooyberghs,et al.  A neural network forecast for daily average PM10 concentrations in Belgium , 2005 .

[9]  Siegfried Hörmann,et al.  Quality and performance of a PM10 daily forecasting model , 2008 .

[10]  William R. Burrows,et al.  CART Decision-Tree Statistical Analysis and Prediction of Summer Season Maximum Surface Ozone for the Vancouver, Montreal, and Atlantic Regions of Canada , 1995 .

[11]  K. Wilson,et al.  Linear stochastic models for forecasting daily maxima and hourly concentrations of air pollutants , 1975 .

[12]  Duy Nguyen-Tuong,et al.  Local Gaussian Process Regression for Real Time Online Model Learning , 2008, NIPS.

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

[14]  Xiangxu Meng,et al.  An air quality forecast model based on the BP neural network of the samples self-organization clustering , 2010, 2010 Sixth International Conference on Natural Computation.

[15]  Eric Horvitz,et al.  A Deep Hybrid Model for Weather Forecasting , 2015, KDD.

[16]  Fabio Tozeto Ramos,et al.  A Nonparametric Online Model for Air Quality Prediction , 2015, AAAI.

[17]  Rohit Mathur,et al.  An evaluation of real‐time air quality forecasts and their urban emissions over eastern Texas during the summer of 2006 Second Texas Air Quality Study field study , 2009 .

[18]  C. Granger.  Investigating Causal Relations by Econometric Models and Cross-Spectral Methods , 1969 .

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