Modeling and forecasting daily maximum hourly ozone concentrations using the RegAR model with skewed and heavy-tailed innovations

Sarnaglia, Alessandro José Queiroz; Monroy, Nátaly Adriana Jiménez; Vitória, Arthur Gomes da

doi:10.1007/s10651-018-0413-7

Cited by 4 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…denotes the one-step-ahead point forecast of Z t . Deviations from normality could be addressed by forecast intervals calculated with the methods addressed in Sarnaglia et al (2018). Similar conclusions related to the impact of the outlier in the confidence intervals are expected.…”

Section: Analysis Of Air Pollution Datasupporting

confidence: 57%

M-regression spectral estimator for periodic ARMA models. An empirical investigation

Sarnaglia

Reisen

Bondon

et al. 2021

Stoch Environ Res Risk Assess

Self Cite

View full text Add to dashboard Cite

The M -regression estimator has recently been widely used to build spectral estimators in time series models. In this paper, we extend this approach when the data follow a periodic autoregressive moving average (PARMA) process. We introduce an estimator of the parameters based on the classical Whittle estimator. The finite sample size performances of the proposed estimator are analyzed under the scenarios of PARMA processes with and without additive outliers (AO). Under the non-contaminated scenario, our estimator and the maximum Gaussian and Whittle likelihood estimators have similar behaviors. However, in the contaminated case, the two last estimators are severely biased, while the proposed estimator is robust. As a real data application, carbon monoxide (CO) concentrations are analyzed. A PARMA model is fitted and the data are forecasted with the model.

show abstract

Section: Analysis Of Air Pollution Datasupporting

confidence: 57%

M-regression spectral estimator for periodic ARMA models. An empirical investigation

Sarnaglia

Reisen

Bondon

et al. 2021

Stoch Environ Res Risk Assess

Self Cite

View full text Add to dashboard Cite

show abstract

“…In many studies, linear and nonlinear regression and their improved modeling methods based on multivariate statistics and traditional machine learning have been proposed; the modeling methods include ridge regression [Li, Hu, Zhou et al (2018)], least absolute shrinkage and selection operator regression [Xu, Fang, Shen et al (2018); Osborne and Turlach (2011)], partial least squares regression [Lavoie, Muteki and Gosselin (2019); Biancolillo, Naes, Bro et al (2017)], support vector regression (SVR) [Zhang, Gao, Tian et al (2016); Wei, Yu and Long (2014)], and artificial neural network (ANN) [Du and Xu (2017); Martinez-Rego, Fontenla-Romero and Alonso-Betanzos (2012)]. These regression methods have been applied to building mathematical models for various real-life scenarios, such as time series [Safari, Chung and Price (2018); Sarnaglia, Monroy and da Vitoria (2018) ;Sahoo, Jha, Singh et al (2019)] and industry [Xue and Yan (2017); Rato and Reis (2018); Sedghi, Sadeghian and Huang (2017); Khazaee and Ghalehnovi (2018); Gonzaga, Meleiro, Kiang et al (2009)]. However, many problems, such as multiple operating conditions and high nonlinearities, interfere with the prediction quality of key variables given the complexity of object processes and high-precision requirement of models.…”

Section: Introductionmentioning

confidence: 99%

Novel Ensemble Modeling Method for Enhancing Subset Diversity Using Clustering Indicator Vector Based on Stacked Autoencoder

Wang¹,

Yan²

2019

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

A single model cannot satisfy the high-precision prediction requirements given the high nonlinearity between variables. By contrast, ensemble models can effectively solve this problem. Three key factors for improving the accuracy of ensemble models are namely the high accuracy of a submodel, the diversity between subsample sets and the optimal ensemble method. This study presents an improved ensemble modeling method to improve the prediction precision and generalization capability of the model. Our proposed method first uses a bagging algorithm to generate multiple subsample sets. Second, an indicator vector is defined to describe these subsample sets. Third, subsample sets are selected on the basis of the results of agglomerative nesting clustering on indicator vectors to maximize the diversity between subsets. Subsequently, these subsample sets are placed in a stacked autoencoder for training. Finally, XGBoost algorithm, rather than the traditional simple average ensemble method, is imported to ensemble the model during modeling. Three machine learning public datasets and atmospheric column dry point dataset from a practical industrial process show that our proposed method demonstrates high precision and improved prediction ability.

show abstract

Estimating critical level of $$\hbox {PM}_{{10}}$$ to affect hospital infant admissions in Vitória, Brazil

Sarnaglia

Rodrigues

2021

Stoch Environ Res Risk Assess

View full text Add to dashboard Cite

Modeling and forecasting daily maximum hourly ozone concentrations using the RegAR model with skewed and heavy-tailed innovations

Cited by 4 publications

References 26 publications

M-regression spectral estimator for periodic ARMA models. An empirical investigation

M-regression spectral estimator for periodic ARMA models. An empirical investigation

Novel Ensemble Modeling Method for Enhancing Subset Diversity Using Clustering Indicator Vector Based on Stacked Autoencoder

Estimating critical level of $$\hbox {PM}_{{10}}$$ to affect hospital infant admissions in Vitória, Brazil

Contact Info

Product

Resources

About