A comparative study of computational intelligence techniques applied to PM2.5 air pollution forecasting

Oprea, Mihaela; Mihalache, Sanda Florentina; Popescu, Marian

doi:10.1109/icccc.2016.7496746

Cited by 21 publications

(20 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper is an extension of [27] which proposed PM 2.5 air pollution forecasting models based on computational intelligence techniques. Starting from the study presented in [27], in this paper we extend the comparative study between artificial neural networks (ANNs) and adaptive neurofuzzy inference system (ANFIS) which are the most accurate computational intelligence models used for particulate matter (fraction PM 2.5 ) air pollution forecasting by increasing the number of neurons in the hidden layer of the ANN architecture.…”

Section: Discussionmentioning

confidence: 99%

“…Starting from the study presented in [27], in this paper we extend the comparative study between artificial neural networks (ANNs) and adaptive neurofuzzy inference system (ANFIS) which are the most accurate computational intelligence models used for particulate matter (fraction PM 2.5 ) air pollution forecasting by increasing the number of neurons in the hidden layer of the ANN architecture. We also present an extended overview of computational intelligence techniques based on neural networks approach with up to date solutions of air pollution forecasting.…”

Section: Discussionmentioning

confidence: 99%

“…This paper is an extension of [27] (doi: 10.1109/ICCCC.2016.7496746). A comprehensive comparative study is here presented.…”

Section: Introductionmentioning

confidence: 99%

“…Our research main goal is to identify the computational intelligence model that is more proper to real time PM 2.5 air pollutant forecasting in urban areas. Starting from the study presented in [27] a , in this paper we first perform a comparative study between the most accurate computational intelligence models that were used for particulate matter (fraction PM 2.5 ) air pollution forecasting: artificial neural networks (ANNs) and adaptive neuro-fuzzy inference system (ANFIS). Based on the obtained experimental results, we make a comprehensive analysis of best ANN architecture identification.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Computational Intelligence-based PM2.5 Air Pollution Forecasting

Oprea¹,

Mihalache²,

Popescu³

2017

INT J COMPUT COMMUN

Self Cite

View full text Add to dashboard Cite

Computational intelligence based forecasting approaches proved to be more efficient in real time air pollution forecasting systems than the deterministic ones that are currently applied. Our research main goal is to identify the computational intelligence model that is more proper to real time PM 2.5 air pollutant forecasting in urban areas. Starting from the study presented in [27] a , in this paper we first perform a comparative study between the most accurate computational intelligence models that were used for particulate matter (fraction PM 2.5 ) air pollution forecasting: artificial neural networks (ANNs) and adaptive neuro-fuzzy inference system (ANFIS). Based on the obtained experimental results, we make a comprehensive analysis of best ANN architecture identification. The experiments were realized on datasets from the AirBase databases with PM 2.5 concentration hourly measurements. The statistical parameters that were computed are mean absolute error, root mean square error, index of agreement and correlation coefficient.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

“…This paper is an extension of [27] (doi: 10.1109/ICCCC.2016.7496746). A comprehensive comparative study is here presented.…”

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Computational Intelligence-based PM2.5 Air Pollution Forecasting

Oprea¹,

Mihalache²,

Popescu³

2017

INT J COMPUT COMMUN

Self Cite

View full text Add to dashboard Cite

show abstract

“…PM 10 , PM 2.5 ), in particular (see e.g. [6], [10]). Moreover, artificial neural networks are universal approximators of nonlinear functions [11] that can be applied in various forecasting applications (see.…”

Section: Methodsmentioning

confidence: 99%

Applying Time Series Analysis for Artificial Intelligence Based Particulate Matter Prediction

Oprea¹,

Dragomir²,

Olteanu³

2017

Modelling, Identification and Control

Self Cite

View full text Add to dashboard Cite

Artificial intelligence based prediction models provide good air pollution forecasters, proper to real time forecasting systems. Among them, artificial neural networks are the most used ones, being universal approximators. Usually, the identification of the best neural model (i.e. most accurate one) is based on experiments and results of time series analysis. The paper focuses on time series analysis for particulate matter (PM) air pollutant prediction with artificial neural networks in the Ploiesti city. Two types of neural models were used: feed forward and radial basis function. For each model we have experimented several architectures in order to identify the most accurate one in terms of root mean square error and average square error. The experimental datasets include five time series with concentration measurements of five air pollutants, PM10, CO, NO 2 , NO x , and SO 2 in the period 2008-2012 at PH-6 air quality monitoring station from the Ploiesti city. KEY WORDSTime series analysis, artificial intelligence, air pollution, particulate matter prediction, artificial neural networks.

show abstract

A PM 2.5 Forecasting Model Based on Air Pollution and Meteorological Conditions in Neighboring Areas

Adrezo

Huang

Sandnes

2021

Communications in Computer and Information Science

View full text Add to dashboard Cite

Air pollution has received much attention in recent years, especially in the most densely populated areas. Sources of air pollution include factory emissions, vehicle emissions, building sites, wildfires, wood-burning devices, and coal power plants. Common and dangerous air pollutants include nitrogen dioxide (NO2), ozone (O3), carbon dioxide (CO2), particulate matter 10 (PM 10) and particulate matter 2.5 (PM 2.5). This study focused on PM 2.5 because it has an aerodynamic diameter less than or equal to 2.5 μm. The small size of this pollutant makes it easily inhaled by humans and may end up deep in the lungs or even the bloodstream. Such pollutants can trigger health problems such as asthma, respiratory inflammation, reduced lung function and lung cancer. The purpose of this work was to forecast the next hour of PM 2.5 based on air pollution concentrations and meteorological conditions. The approach also uses station location data to cluster the area and to determine the neighboring areas of each station. Forecasting is based on the Long Short-Term Memory (LSTM). The result shows that the proposed approach can effectively forecast the next hour of PM 2.5 pollution.

show abstract

A comparative study of computational intelligence techniques applied to PM2.5 air pollution forecasting

Cited by 21 publications

References 16 publications

Computational Intelligence-based PM2.5 Air Pollution Forecasting

Computational Intelligence-based PM2.5 Air Pollution Forecasting

Applying Time Series Analysis for Artificial Intelligence Based Particulate Matter Prediction

A PM 2.5 Forecasting Model Based on Air Pollution and Meteorological Conditions in Neighboring Areas

Contact Info

Product

Resources

About