Ozone Concentration Prediction using Artificial Neural Networks

Gavrilă, Camelia

doi:10.37358/rc.17.10.5860

Cited by 7 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Forecasting is a decision-making approach in which future occasions are in basic historical information predictions (Al-Janabi et al, 2015). These prediction models use various mathematical or statistical approaches (Gavrila, 2017) and take into account different parameters like NOx and NO 2 (Chersan et al, 2018). The modernistic models are on the basis of neural network and Bayesian network models (Chersan et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

Hybrid deep learning model for ozone concentration prediction: comprehensive evaluation and comparison with various machine and deep learning algorithms

Yafouz

Ahmed

Zaini

et al. 2021

Engineering Applications of Computational Fluid Mechanics

View full text Add to dashboard Cite

To accurately predict tropospheric ozone concentration(O 3 ), it is needed to investigate the variety of artificial intelligence techniques' performance, such as machine learning, deep learning and hybrid models. This research aims to effectively predict the hourly ozone trend via fewer input variables. This ozone prediction attempt is performed on diversity data of air pollutants (NO 2 , NO x , CO, SO 2 ) and meteorological parameters (wind-speed and humidity). The historical datasets are collected from 3 sites in Malaysia. The study's methodology progressed in two paths: standalone and hybrid models where hourly-averaged datasets are applied based on 5-time horizon analysis scenario, with different inputs' combinations. For evaluation, all models are tested throughout 5-performance indicator and illustrated on Modified Taylor diagram. Sensitivity analysis of input variables is quantified. Additionally, uncertainty analysis is conducted to assess their confidence level associated with Willmott Index. Based on R 2 , results indicated that XGBoost has higher accuracy compared to MLP and SVR; meanwhile, LSTM and CNN outweighs XGBoost. In terms of robustness and accuracy, the proposed hybrid model possesses superlative performance compared to all above-mentioned techniques. The proposed model achieved exceptional results as the highest R 2 , the highest 95% confidence degree, and narrower confidence interval width, are 93.48%, 98.16%, and 0.0014195, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

Hybrid deep learning model for ozone concentration prediction: comprehensive evaluation and comparison with various machine and deep learning algorithms

Yafouz

Ahmed

Zaini

et al. 2021

Engineering Applications of Computational Fluid Mechanics

View full text Add to dashboard Cite

show abstract

“…In this paper it is studied the incorporation effect of silica-aerogel granules in own and commercial plasters compositions to obtain new insulation plasters for buildings with low thermal conductivity and good mechanical strengths, using statistical models 10,11,12 based on detection of some patterns. Then, these models are used to forecast the optimum aerogel concentrations for buildings insulation.…”

Section: Introductionmentioning

confidence: 99%

Statistical analysis of the compositions of insulating plasters with aerogel

Gavrilă

Melita²

2023

Advanced Topics in Optoelectronics, Microelectronics, and Nanotechnologies XI

Self Cite

View full text Add to dashboard Cite

The quality of insulating materials is a very important aspect of the design of buildings and the assessment of the influence of the external environment to ensure the lowest possible thermal conductivity and the highest possible compression and flexural strengths. The purpose of this article is to analyze two sets of aerogel compositions in two types of plasters (own composition and commercial composition) to obtain new plasters with aerogel, used for buildings insulations. For the laboratory experiments, to measure the thermal conductivities of obtained plasters it was used a Heat Transfer Service Unit for Building and Insulating Materials, type H111N, and for determination of the mechanical strengths it was used a Universal Testing Machine Hegewald & Peschke INSPECT SOLO. The Wilcoxon Signed-Rank Test was used to determine the most effective composition in terms of isolation.

show abstract