Forecasting SO₂ pollution incidents by means of Elman artificial neural networks and ARIMA models

DOI10.1155/2013/238259MaRDI QIDQ2015248zbMATH OpenOpenAlexWikidataFDO

Authors Antonio Bernardo Sánchez, Celestino Ordóñez, Fernando Sánchez Lasheras, Francisco Javier De Cos Juez, Javier Roca-Pardiñas

Publication date 23 June 2014

Published in Abstract and Applied Analysis (Search for Journal in Brave)

Copyright license Creative Commons Attribution 3.0 Unported

Full work available at URL https://doi.org/10.1155/2013/238259

zbMATH Keywords

\(\text{SO}_{2}\) emissionARIMA modelElman artificial neural network

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Environmental economics (natural resource models, harvesting, pollution, etc.) (91B76) Economic time series analysis (91B84)

Review text

Summary: An \(\text{SO}_{2}\) emission episode at coal-fired power station occurs when the series of bihourly average of \(\text{SO}_{2}\) concentration, taken at 5-minute intervals, is greater than a specific value. Advance prediction of these episodes of pollution is very important for companies generating electricity by burning coal since it allows them to take appropriate preventive measures. In order to forecast \(\text{SO}_{2}\) pollution episodes, three different methods were tested: Elman neural networks, autoregressive integrated moving average (ARIMA) models, and a hybrid method combining both. The three methods were applied to a time series of \(\text{SO}_2\) concentrations registered in a control station in the vicinity of a coal-fired power station. The results obtained showed a better performance of the hybrid method over the Elman networks and the ARIMA models. The best prediction was obtained 115 minutes in advance by the hybrid model.

Recommendations

• Forecasting concentrations of air pollutants by logarithm support vector regression with immune algorithms
• Modelling air pollution time-series by using wavelet functions and genetic algorithms
• Prediction of China's sulfur dioxide emissions by discrete grey model with fractional order generation operators
• Short-term prediction of air pollution in Macau using support vector machines
• scientific article; zbMATH DE number 1928749

Cites work

• scientific article; zbMATH DE number 3565994 (Why is no real title available?)
• Model identification of ARIMA family using genetic algorithms
• On a measure of lack of fit in time series models
• Time series forecasting using a hybrid ARIMA and neural network model

Cited in

(6)

• Prediction of China's sulfur dioxide emissions by discrete grey model with fractional order generation operators
• Comparison of supervised learning techniques for atmospheric pollutant monitoring in a Kraft pulp mill
• Improved pollution forecasting hybrid algorithms based on the ensemble method
• Predicting air pollutant emissions from a medical incinerator using grey model and neural network
• The use of multilayer perceptrons for statistical modeling \(\text{SO}_2\) nonlinear time series in Salta Capital, Argentina
• Modelling air pollution time-series by using wavelet functions and genetic algorithms

Describes a project that uses

Uses Software

• forecast
• Forecast

This page was built for publication: Forecasting \(\text{SO}_{2}\) pollution incidents by means of Elman artificial neural networks and ARIMA models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2015248)