TY - JOUR
T1 - Predicting hourly ozone concentrations using wavelets and ARIMA models
AU - Salazar, Ledys
AU - Nicolis, Orietta
AU - Ruggeri, Fabrizio
AU - Kisel’ák, Jozef
AU - Stehlík, Milan
N1 - Funding Information:
Open access funding provided by Johannes Kepler University Linz. We acknowledge LIT-2016-1-SEE-023 project ?Modeling complex dependencies: how to make strategic multicriterial decisions?/MODEC? and FONDECYT Regular N1151441. The authors are very grateful to the Editor, Associated Editor and the Reviewers for their valuable comments.
PY - 2018/1/19
Y1 - 2018/1/19
N2 - In recent years, air pollution has been a major concern for its implications on human health. Specifically, ozone ((Formula presented.)) pollution is causing common respiratory diseases. In this paper, we illustrate the process of modeling and prediction hourly (Formula presented.) pollution measurements using wavelet transforms. We split the time series of (Formula presented.) in daily intervals and estimate scale and wavelet coefficients for each interval by the discrete wavelet transform (DWT) with Haar filter. Subsequently we apply cumulated autoregressive integrated moving average (ARIMA) to estimate the coefficients and forecast their evolution in future intervals. Then the inverse discrete wavelet transform is implemented for the reconstruction of the time series and the forecast in the near future. In order to assess the performance of the proposed methodology, we compare the predictions obtained by the DWT–ARIMA with those obtained by the ARIMA model. Several theoretical results are shown through a simulation study.
AB - In recent years, air pollution has been a major concern for its implications on human health. Specifically, ozone ((Formula presented.)) pollution is causing common respiratory diseases. In this paper, we illustrate the process of modeling and prediction hourly (Formula presented.) pollution measurements using wavelet transforms. We split the time series of (Formula presented.) in daily intervals and estimate scale and wavelet coefficients for each interval by the discrete wavelet transform (DWT) with Haar filter. Subsequently we apply cumulated autoregressive integrated moving average (ARIMA) to estimate the coefficients and forecast their evolution in future intervals. Then the inverse discrete wavelet transform is implemented for the reconstruction of the time series and the forecast in the near future. In order to assess the performance of the proposed methodology, we compare the predictions obtained by the DWT–ARIMA with those obtained by the ARIMA model. Several theoretical results are shown through a simulation study.
KW - Autoregressive integrated moving average (ARIMA)
KW - Discrete wavelet transform (DWT)
KW - Haar wavelet
KW - Ozone ($$\mathrm{O}_{3}$$O3)
UR - http://www.scopus.com/inward/record.url?scp=85040661060&partnerID=8YFLogxK
U2 - 10.1007/s00521-018-3345-0
DO - 10.1007/s00521-018-3345-0
M3 - Article
AN - SCOPUS:85040661060
SN - 0941-0643
VL - 31
SP - 1
EP - 10
JO - Neural Computing and Applications
JF - Neural Computing and Applications
IS - 8
ER -
