Dynamically pre-trained deep recurrent neural networks using environmental monitoring data for predicting PM2.5

Bun Theang Ong, Komei Sugiura, Koji Zettsu

Research output: Contribution to journalArticle

69 Citations (Scopus)

Abstract

Fine particulate matter (PM 2.5) has a considerable impact on human health, the environment and climate change. It is estimated that with better predictions, US$9 billion can be saved over a 10-year period in the USA (State of the science fact sheet air quality. http://www.noaa.gov/factsheets/new, 2012). Therefore, it is crucial to keep developing models and systems that can accurately predict the concentration of major air pollutants. In this paper, our target is to predict PM 2.5 concentration in Japan using environmental monitoring data obtained from physical sensors with improved accuracy over the currently employed prediction models. To do so, we propose a deep recurrent neural network (DRNN) that is enhanced with a novel pre-training method using auto-encoder especially designed for time series prediction. Additionally, sensors selection is performed within DRNN without harming the accuracy of the predictions by taking advantage of the sparsity found in the network. The numerical experiments show that DRNN with our proposed pre-training method is superior than when using a canonical and a state-of-the-art auto-encoder training method when applied to time series prediction. The experiments confirm that when compared against the PM 2.5 prediction system VENUS (National Institute for Environmental Studies. Visual Atmospheric Environment Utility System. http://envgis5.nies.go.jp/osenyosoku/, 2014), our technique improves the accuracy of PM 2.5 concentration level predictions that are being reported in Japan.

Original languageEnglish
Pages (from-to)1553-1566
Number of pages14
JournalNeural Computing and Applications
Volume27
Issue number6
DOIs
Publication statusPublished - 2016 Aug 1
Externally publishedYes

Keywords

  • Deep learning
  • Elastic net
  • Environmental sensor data
  • Fine particulate matter
  • Pre-training
  • Recurrent neural networks
  • Time series prediction

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Dynamically pre-trained deep recurrent neural networks using environmental monitoring data for predicting PM<sub>2.5</sub>'. Together they form a unique fingerprint.

  • Cite this