A hybrid model for predicting air quality combining Holt–Winters and Deep Learning Approaches: A novel method to identify ozone concentration peaks DOI Open Access

N. Marrakchi,

Amal Bergam,

Hussam N. Fakhouri

et al.

Mathematical Modeling and Computing, Journal Year: 2023, Volume and Issue: 10(4), P. 1154 - 1163

Published: Jan. 1, 2023

Ozone (O3) from the troposphere is one of substances that has a strong effect on air pollution in city Tanger. Prediction this pollutant can have positive improvements quality. This paper presents new approach combining deep-learning algorithms and Holt–Winters method order to detect peaks obtain more accurate forecasting model. Given LSTM an extremely powerful algorithm, we hybridized with enhance Making use multiple accuracy metrics, models' efficiency investigated. Empirical findings reveal superiority hybrid model by providing forecasts are index agreement equal 0.91.

Language: Английский

Examining rheological behavior of CeO2-GO-SA/10W40 ternary hybrid nanofluid based on experiments and COMBI/ANN/RSM modeling DOI Creative Commons
Mojtaba Sepehrnia, Hamid Maleki,

Mahsa Karimi

et al.

Scientific Reports, Journal Year: 2022, Volume and Issue: 12(1)

Published: Dec. 21, 2022

In this study, the rheological behavior and dynamic viscosity of 10W40 engine oil in presence ternary-hybrid nanomaterials cerium oxide (CeO2), graphene (GO), silica aerogel (SA) were investigated experimentally. Nanofluid was measured over a volume fraction range VF = 0.25-1.5%, temperature T 5-55 °C, shear rate SR 40-1000 rpm. The preparation nanofluids involved two-step process, dispersed SAE using magnetic stirrer ultrasonic device. addition, CeO2, GO, SA nanoadditives underwent X-ray diffraction-based structural analysis. non-Newtonian (pseudoplastic) nanofluid at all temperatures fractions is revealed by analyzing stress, viscosity, power-law model coefficients. However, tend to Newtonian low temperatures. For instance, declines with increasing between 4.51% (at 5 °C) 41.59% 55 for 1.5 vol% nanofluid. experimental results demonstrated that decreasing fraction. assuming constant 100 rpm increase from increases least 95.05% (base fluid) no more than 95.82% (1.5 nanofluid). Furthermore, 0 1.5%, minimum 14.74% maximum 35.94% °C). Moreover, different methods (COMBI algorithm, GMDH-type ANN, RSM) used develop models nanofluid's their accuracy complexity compared. COMBI algorithm R2 0.9995 had highest among developed models. Additionally, RSM able generate predictive complexity.

Language: Английский

Citations

40
Machine learning algorithms for high-resolution prediction of spatiotemporal distribution of air pollution from meteorological and soil parameters DOI Creative Commons
Tao Hai, Ali H. Jawad,

A.H. Shather

et al.

Environment International, Journal Year: 2023, Volume and Issue: 175, P. 107931 - 107931

Published: April 15, 2023

This study uses machine learning (ML) models for a high-resolution prediction (0.1°×0.1°) of air fine particular matter (PM2.5) concentration, the most harmful to human health, from meteorological and soil data. Iraq was considered area implement method. Different lags changing patterns four European Reanalysis (ERA5) variables, rainfall, mean temperature, wind speed relative humidity, one parameter, moisture, were used select suitable set predictors using non-greedy algorithm known as simulated annealing (SA). The selected simulate temporal spatial variability PM2.5 concentration over during early summer (May-July), polluted months, three advanced ML models, extremely randomized trees (ERT), stochastic gradient descent backpropagation (SGD-BP) long short-term memory (LSTM) integrated with Bayesian optimizer. distribution annual average revealed population whole is exposed pollution level above standard limit. changes in temperature moisture humidity month before can predict May-July. Results higher performance LSTM normalized root-mean-square error Kling-Gupta efficiency 13.4% 0.89, compared 16.02% 0.81 SDG-BP 17.9% 0.74 ERT. could also reconstruct observed MapCurve Cramer's V values 0.95 0.91, 0.9 0.86 SGD-BP 0.83 0.76 provided methodology forecasting at high resolution peak months freely available data, which be replicated other regions generating maps.

Language: Английский

Citations

30
Machine learning-based country-level annual air pollutants exploration using Sentinel-5P and Google Earth Engine DOI Creative Commons
Bijay Halder, Iman Ahmadianfar, Salim Heddam

et al.

Scientific Reports, Journal Year: 2023, Volume and Issue: 13(1)

Published: May 17, 2023

Climatic condition is triggering human health emergencies and earth's surface changes. Anthropogenic activities, such as built-up expansion, transportation development, industrial works, some extreme phases, are the main reason for climate change global warming. Air pollutants increased gradually due to anthropogenic activities health. Nitrogen Dioxide (NO2), Carbon Monoxide (CO), Aerosol Optical Depth (AOD) truthfully important air quality measurement because those more harmful environment human's Earth observational Sentinel-5P applied monitoring pollutant chemical conditions in atmosphere from 2018 2021. The cloud computing-based Google Engine (GEE) platform components atmosphere. NO2 variation indicates high during time of activities. (CO) also located between two 1-month different maps. 2020 2021 results indicate AQI where 2019 low throughout year. Kolkata have seven station nitrogen dioxide recorded 102 (2018), 48 (2019), 26 (2020) 98 (2021), Delhi stations 99 49 37 (2020), 107 (2021). Delhi, Kolkata, Mumbai, Pune, Chennai huge fluctuations study periods, ~ 50-60% was recent time. AOD noticed Uttar Pradesh 2020. These that investigation much necessary future planning management otherwise; our planet earth mostly affected by climatic maybe life does not exist.

Language: Английский

Citations

27
Forecasting of fine particulate matter based on LSTM and optimization algorithm DOI
Nur’atiah Zaini, Ali Najah Ahmed, Lee Woen Ean

et al.

Journal of Cleaner Production, Journal Year: 2023, Volume and Issue: 427, P. 139233 - 139233

Published: Oct. 10, 2023

Language: Английский

Citations

27
A comprehensive approach combining positive matrix factorization modeling, meteorology, and machine learning for source apportionment of surface ozone precursors: Underlying factors contributing to ozone formation in Houston, Texas DOI
Delaney Nelson, Yunsoo Choi, Bavand Sadeghi

et al.

Environmental Pollution, Journal Year: 2023, Volume and Issue: 334, P. 122223 - 122223

Published: July 20, 2023

Language: Английский

Citations

24
Daily scale air quality index forecasting using bidirectional recurrent neural networks: Case study of Delhi, India DOI

Chaitanya B. Pande,

Nand Lal Kushwaha, Omer A. Alawi

et al.

Environmental Pollution, Journal Year: 2024, Volume and Issue: 351, P. 124040 - 124040

Published: April 27, 2024

Language: Английский

Citations

10
Optimizing building energy performance predictions: A comparative study of artificial intelligence models DOI
Omer A. Alawi, Haslinda Mohamed Kamar, Zaher Mundher Yaseen‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬‬

et al.

Journal of Building Engineering, Journal Year: 2024, Volume and Issue: 88, P. 109247 - 109247

Published: April 4, 2024

Language: Английский

Citations

9
Review of Strategies to Mitigate Dust Deposition on Solar Photovoltaic Systems DOI Creative Commons
Gowtham Vedulla,

Anbazhagan Geetha,

Ramalingam Senthil

et al.

Energies, Journal Year: 2022, Volume and Issue: 16(1), P. 109 - 109

Published: Dec. 22, 2022

In recent years, there has been an increased focus on developing and utilizing renewable energy resources due to several factors, including environmental concerns, rising fuel costs, the limited supply of conventional fossil fuels. The most appealing green conversion technology is solar energy, its efficient application can help world achieve Sustainable Development Goal 7: Access affordable, clean energy. Irradiance, latitude, longitude, tilt angle, orientation are a few variables that affect functioning photovoltaic (PV) system. Additionally, factors like dust accumulation soiling panel surfaces impact cost maintaining producing electricity from PV Dust characteristics (kind, size, shape, meteorological elements), one largest affecting performance, need be investigated devise specific solutions for efficiently harnessing essential findings ongoing investigations deposition surface structures various mitigating measures tackle issues presented in this review study. This comprehensive assessment critically evaluates current research effect system performance improvement techniques determine academic community’s future priorities.

Language: Английский

Citations

31
Monthly sodium adsorption ratio forecasting in rivers using a dual interpretable glass-box complementary intelligent system: Hybridization of ensemble TVF-EMD-VMD, Boruta-SHAP, and eXplainable GPR DOI
Mehdi Jamei, Mumtaz Ali, Masoud Karbasi

et al.

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 237, P. 121512 - 121512

Published: Sept. 13, 2023

Language: Английский

Citations

22
Data driven insights for parabolic trough solar collectors: Artificial intelligence-based energy and exergy performance analysis DOI
Tao Hai, Omer A. Alawi, Raad Z. Homod

et al.

Journal of Cleaner Production, Journal Year: 2024, Volume and Issue: 443, P. 141069 - 141069

Published: Jan. 31, 2024

Language: Английский

Citations

8