Yazar "Yildizhan, Hasan" seçeneğine göre listele
Listeleniyor 1 - 20 / 26
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe A Multi-Country Statistical Analysis Covering Turkey, Slovakia, and Romania in an Educational Framework(Mdpi, 2023) Pekdogan, Tugce; Udristioiu, Mihaela Tinca; Puiu, Silvia; Yildizhan, Hasan; Hruska, MartinThis paper uses hierarchical regression analysis, a statistically robust method, to explore the correlations between two meteorological parameters and three particulate matter concentrations. The dataset is provided by six sensors located in three cities from three countries, and the measurements were taken simultaneously for three months at each minute. Analyses and calculations were performed with the Statistical Package for the Social Sciences (SPSS). The results underscore that the complexity of air pollution dynamics is affected by the location even when the same type of sensors is used, and emphasize that a one-size-fits-all approach cannot effectively address air pollution. The findings are helpful from three perspectives: for education, to show how to handle and communicate a solution for local communities' issues about air pollution; for research, to understand how easy a university can generate and analyze open-source data; and for policymakers, to design targeted interventions addressing each country's challenges.Öğe Alternative work arrangements: Individual, organizational and environmental outcomes(Cell Press, 2023) Yildizhan, Hasan; Hosouli, Sahand; Yilmaz, Sidika Ece; Gomes, Joao; Pandey, Chandan; Alkharusi, TarikFlexible working models are widely used around the world. Furthermore, several countries are currently transitioning to a 4-day workweek. These working models have significant effects on organizational behavior and the environment. The study investigates the employees' attitudes and behaviors toward flexible working and 4-day workweek and the impact on the environment. The semi-structured interview method was used in the study to determine employee attitudes and behaviors; the carbon footprint calculation method was used to determine the environmental impact of a 4-day workweek. According to the study's findings, it has been discovered that there would be a positive impact on socialization, happiness, stress factor, motivation, personal time, mental health, comfort, work-life balance, time-saving, willingness, positive working environment, personal time, and physical health. Furthermore, a 4-day workweek reduced commuting emissions by 20%, resulting in a 6,07 kg tCO(2)e reduction per person. As a result, the study attempted to draw attention holistically to the positive effects of the flexible working model and 4-day workweek. The study is intended to serve as a tool for decision-makers and human resource managers.Öğe Application of machine learning for solar radiation modeling(Springer Wien, 2021) Taki, Morteza; Rohani, Abbas; Yildizhan, HasanSolar radiation is an important parameter that affects the atmosphere-earth thermal balance and many water and soil processes such as evapotranspiration and plant growth. The modeling of the daily and monthly solar radiation by Gaussian process regression (GPR) with K-fold cross-validation model has been discussed recently. This study evaluated different neural models such as artificial neural network (ANN), support vector machine (SVM), adaptive network-based fuzzy inference system (ANFIS), and multiple linear regression (MLR) for estimating the global solar radiation (daily and monthly) with K-fold cross-validation method. For the appropriate comparison of the models, the randomized complete block (RCB) design applied in the training and test phases. Also, different data sets were evaluated by K-fold cross-validation in each model. The results showed that radial basis function (RBF) model has the lowest error for estimating the monthly and daily solar radiation. In this study, the result of RBF was compared with the GPR models. The conclusion indicated that RBF methodology can predict solar radiation with higher accuracy relative to the GPR model. The results of yearly solar radiation estimation (2009-2014) showed that the RBF model can estimate solar radiation with the MAPE and RMSE of 5.1% and 0.29, respectively. Also, the coefficient of correlation (R-2) between actual and estimated values throughout the year is 98% and can be used by the engineers and other researchers for solar and thermal applications.Öğe Appraisal of energy loss reduction in green buildings using large-scale experiments compiled with swarm intelligent solutions(Elsevier, 2023) Moayedi, Hossein; Yildizhan, Hasan; Al-Bahrani, Mohammed; Le Van, BaoToday, the issue of energy efficiency is a major one in global politics. The external environment, particularly the wind speed and outside air temperature, determines the thermal burden the cold outside air places on a building's interior. The heat load of a building is influenced by several factors, including the wall's heat transfer coefficients (W/mK), the coating material (W/mK), the inside temperature (degrees C), and the outside temperature (degrees C), and the temperature of external surface (degrees C). In this investigation, we undertake a comprehensive assessment, evaluation, and comparing the performance of two unique artificial approaches (BSA and COA) utilized for anticipating heat loss in green buildings; the optimum way is then identified depending on the R-2 and RMSE criteria. The outcomes demonstrate that BSA and COA have R-2 values of (0.97038 and 0.90158) and (0.9919 and 0.94239) in the training and testing phases. Additionally, the RMSE values for BSA and COA in the training and testing stages are (0.02541 and 0.08616) and (0.01336 and 0.06662), correspondingly. Also, the estimated MAEs (0.019055 and 0.0097193) denote a low level of training error for both methods. Regarding R-2, RMSE and MAE values, the COA predicts energy loss more accurately.Öğe Approximating heat loss in smart buildings through large scale experimental and computational intelligence solutions(Taylor & Francis Ltd, 2023) Ben Khedher, Nidhal; Mukhtar, Azfarizal; Yasir, Ahmad Shah Hizam Md; Khalilpoor, Nima; Foong, Loke Kok; Le, Binh Nguyen; Yildizhan, HasanThe attainment of energy sustainability in the building sector can be realised by implementing a green building programme, which has grown significantly over the last thirty years. Green building is considered a technical and management strategy within the building and construction industries. Many different prediction methods, both complex and simple, have been put out in recent years and used to solve a wide variety of issues. Several case studies have highlighted factors that impede energy and resource usage in green buildings. The utilisation, trends, and consequences of wall and thermal insulation materials are examined. The main scope of this investigation is to predict buildings' heat loss by applying artificial neural networks according to the heat transfer coefficients of walls and coating materials, as well as indoor, outdoor, and external surface temperatures. The data has been normalised and presented to two selected neural networks (Harmony search (HS) and particle swarm optimisation are used and contrasted (PSO)). For evaluating the accuracy of models, two statistical indexes are used (R (2) and RMSE). Model performance of PSO-MLP is shown by R (2) amounts of 0.97055 and 0.87381, respectively, and RMSE amounts of 0.02534 and 0.09685. Similarly, HS-MLP model accuracy is also indicated by R (2) amounts of 0.93839 and 0.84176 and RMSE amounts of 0.03635 and 0.10753. The analysis in this paper shows that PSO-MLP predicts heat loss with higher accuracy and improved performance.Öğe Assessment of Whole Milk Powder Production by a Cumulative Exergy Consumption Approach(Mdpi, 2023) Ucal, Esmanur; Yildizhan, Hasan; Ameen, Arman; Erbay, ZaferThe production of food is a sector that consumes a significant amount of energy and encompasses both agricultural and industrial processes. In this study, the energy consumption of whole milk powder production, which is known to be particularly energy-intensive, was examined. The study used a cumulative exergy consumption approach to evaluate the overall production process of whole milk powder, including the dairy farm (raw milk production) and dairy factory (powder production) stages. The results showed that raw milk production dominated energy and exergy consumption and carbon dioxide emissions. An amount of 68.3% of the total net cumulative exergy consumption in the system was calculated for raw milk production. In the dairy factory process, the highest energy/exergy consumption occurred during spray drying, followed by evaporation and pasteurization. In these three processes, 98.3% of the total energy consumption, 94.6% of the total exergy consumption, and 95.7% of the total carbon dioxide emissions in powder production were realized. To investigate the improvement potentials in the system, replacing fossil fuels with renewable energy sources and using pasture feeding in animal husbandry were evaluated. While using alternative energy sources highly influenced powder production, pasture feeding had a high impact on consumption in raw milk production. By using renewable energy and pasture feeding, the exergy efficiency, cumulative degree of perfection, renewability index, and exergetic sustainability index values for the overall process increased from 40.5%, 0.282, -0.22, and 0.68 to 68.9%, 0.433, 0.65, and 2.21, respectively.Öğe Assessment of window renovation potential in an apartment with an energy performance approach(Oxford Univ Press, 2024) Pekdogan, Tugce; Yildizhan, Hasan; Ahmadi, Mohammad Hossein; Sharifpur, MohsenWindows are of great importance in improving the energy efficiency of buildings. It is possible to achieve this with the help of the regeneration of window design. The amount of energy used, the expense of heating and cooling, and the emissions of greenhouse gases that contribute to climate change can all be significantly reduced by improving the energy efficiency of windows. For this, computer modeling and BIM-based simulation programs provide significant timesaving in simultaneously evaluating design variations' visual and thermal results. This study selected a four-story residential building to analyze the energy load and thermal comfort of the windows redesign and examine the energy-saving potential for residential buildings. To analyze the renewed window design strategies, a four-story apartment building is selected as a case study in Izmir/Turkey (38 degrees 4 ', 27 degrees 2 '). This apartment is built on a 90 m2 gross floor area. The existing indoor environmental conditions of the flat are generally observed as cool and low illuminated by the occupants, so the window design options must be compared and renewed. As the first option, current conditions are simulated. The second option is to simulate different patterns for window-to-wall ratio (WWR). Moreover, the third option is to simulate different types of glass in each window. Currently, the WWR of the selected flat in the north, east and south directions is around 10%. But more is needed to provide daylight to the apartment. This article used Autodesk Revit and Green Building Studio simulations to investigate WWR and glass types and evaluate energy use intensity's (EUI) impact. As a result, this study shows that a 10% WWR on all building facades leads to an EUI of 993.9 MJ/m2/year. In contrast, increasing the WWR to 95% significantly increased EUI, reaching 2121 MJ/m2/year. In addition, it has been shown that the use of low U-value glasses, such as translucent wall panels and super-insulated three-pane clear Low-E, can provide energy savings of up to 5% per year, and especially the super-insulated three-pane Low-E glass type provides the highest efficiency on all facades.Öğe Consumer purchasing behavior and its organizational evaluation toward solar water heating system(Elsevier, 2023) Celik, Onur; Yilmaz, S. Ece; Yildizhan, Hasan; Ameen, ArmanRenewable energy sources are fundamental to a country's economic growth. Solar energy is one of these resources that has a favorable effect on economic growth. Turkey's solar energy industry is still in its early stages. Due to its location and degree of sunshine each year, the country has a great solar potential. Despite the huge potential, solar energy awareness and utilization are not widespread in all parts of Turkey. In order to identify the factors that affect consumers' decisions to utilize water heating systems, which is a sort of solar energy system, the purpose of this research is to examine these systems. In this study, all factors influencing consumers' decisions to acquire solar water heating systems were evaluated holistically for the first time. A questionnaire was used in the study, which is a quantitative research technique. The study identifies the variables that influence consumers' attitudes toward solar collector purchases and assesses the consequences from an organizational point of view. The study's results act as a guide for decision-makers. & COPY; 2023 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).Öğe Examining effects of air pollution on photovoltaic systems via interpretable random forest model(Pergamon-Elsevier Science Ltd, 2024) Dudas, Adam; Udristioiu, Mihaela Tinca; Alkharusi, Tarik; Yildizhan, Hasan; Sampath, Satheesh KumarRenewable energy plays a vital role in power generation and solar photovoltaic systems due to resource availability throughout the year. This work aims to investigate the impact of air pollutants and meteorological parameters on the performance of the photovoltaic systems locally, taking into consideration the advantages of the photovoltaic power potential of the SW part of Romania, where Craiova is located (average solar radiation intensity >1350 kWh/m(2)/year). This study is based on a one-year dataset provided by a sensor that monitors particulate matter concentrations, volatile organic compounds, dioxide of carbon, ozone, noise, formaldehyde and three climate parameters (temperature, pressure, and relative humidity). The research methodology applies an innovative interpretable random forest model emphasising the implications of air pollution for photovoltaic systems. The proposed machine learning model was trained to predict the particulate matter level in air based on the basic environmental variable measurements. The study presents six random forest models of varying complexity, which reach the accuracy of classification for the selected problem up to 99 %, and applies the Shapley Additive Explanations technique to interpret the decision-making model. The observation regarding the highest concentration of particulate matter occurring during cold months, which typically do not align with peak solar irradiance, underscores the importance of considering various environmental factors in solar energy planning. With its practical implications, this insight offers decision-makers valuable information about the feasibility of optimising solar energy generation despite seasonal variations in air pollution levels, directly addressing their needs and concerns.Öğe Exergoenvironmental damages assessment in a desert-based agricultural system: A case study of date production(Wiley, 2022) Hesampour, Reza; Hassani, Mehrdad; Yildizhan, Hasan; Failla, Sabina; Gorjian, ShivaDeveloping countries, especially those in hot and dry areas, need more attention to achieve sustainable development as they apply excessive inputs in production processes. The present study aims to quantify the amount of environmental emissions and determine the most appropriate pattern of energy use in the date (Phoenix dactylifera L.) production process using thermodynamic analysis. The information was gathered through questionnaires and face-to-face interviews. From the results, cumulative exergy and energy demand for one Mg of date fruit production were calculated as 697 and 1640 MJ, respectively. Carbon dioxide emission was also measured at 197 kg Mg-1. Moreover, cumulative exergy consumption illustrated that manure and diesel fuel consumption is high, though diesel fuel and N consumption are given the most cumulative energy demand. Renewability indicator, cumulative degree of perfection, and the recoverable exergy ratio value of the date fruit production process were calculated as 0.62, 2.68, and 4.32, respectively. The date's chemical exergy value was calculated to be 14.96 MJ kg(-1). Dates have a high chemical exergy value because of their high carbohydrate content and lowwater content. As a result, crop chemical combinations have a direct impact on the production process. The total direct greenhouse gas emissions induced by the inputs consumption were 310.02 kg Mg-1. Emissions to air, soil, and water were 308.76, 5.60 x 10(-1) and 6.96 x 10(-1) kg Mg-1. In general, date production in Khuzestan province is partially renewable.Öğe Experimental investigation of nonuniform PV soiling(Pergamon-Elsevier Science Ltd, 2024) Alkharusi, Tarik; Alzahrani, Mussad M.; Pandey, Chandan; Yildizhan, Hasan; Markides, Christos N.Photovoltaic (PV) module soiling, i.e., the accumulation of dust on PV module surfaces, poses several challenges to PV system performance. Among these challenges, the nonuniform deposition of soiling across the module surface has received scarce attention. Soiling is directly associated with an overall performance loss, but can also potentially give rise to localised hotspots that can lead to long-term PV module failure. Therefore, addressing the issues arising from this nonuniformity is not only important for optimising energy production, but also for enhancing system reliability, and ensuring the long-term operation of relevant power generation systems. In this study, the impact of nonuniform soiling on PV performance is investigated experimentally by examining soil deposition on the upper surfaces of low-iron glass samples. Samples positioned at four different tilt angles were collected on a monthly basis over a one-year study period. Since the horizontal samples were found to represent the worst-case conditions, the most soiled sample at horizontal tilt was divided into four zones, each housing a single monocrystalline solar cell and examined further. The findings reveal that the soiled sample experiences an average transmittance deterioration of 13% relative to a clean sample, and a maximum (relative) spatial variation of 4% between the four zones. These optical losses affect the amount of sunlight received by the cells, resulting in a power deterioration of similar to 6-7% per 5% drop in transmittance. The soiled sample experienced an average temperature rise of 2 degrees C, and an average power output (and efficiency) reduction of 30% relative to the clean sample, and a maximum (relative) spatial variation of 7% between the zones. The 30% average power loss measured in this nonuniform soiling case is more than double that which would be expected theoretically for a transmittance loss of 13% but from uniform soiling, so these results highlight the importance of addressing PV soiling for optimal PV performance, and of accounting for spatial soiling nonuniformity.Öğe Falling film hydrodynamics and heat transfer under vapor shearing from various orientations(Aip Publishing, 2024) Zhao, Chuang-Yao; Li, Qiong-Tao; Zhang, Fang-Fang; Qi, Di; Yildizhan, Hasan; Jiang, Jun-MinVapor shearing is a common issue encountered in the operations of falling film heat exchangers. The vapor stream effect depends on its orientation. This study investigates liquid film hydrodynamics and heat transfer performance under the influence of vapor streams from different orientations. The results indicate that both orientation and velocity of vapor determine the encountering time and position of the films on the tube's two sides. The liquid film thickness uniformity and the liquid column deflection vary significantly depending on the orientation and velocity of the vapor. Zones of accelerated liquid film, climbing liquid film, liquid stagnation, and transition of liquid film flow pattern are observed. The gradient of film thickness along the tube axis and the deflection in time-averaged peripheral film thickness increase as the vapor orientation varies from 0 degrees to 90 degrees and subsequently decrease as the vapor orientation varies from 90 degrees to 180 degrees. Vapor streams have more pronounced effects on time-averaged peripheral film thickness in regions close to the liquid inlet and outlet. Vapor streams result in changes in peripheral heat transfer coefficients toward the downstream side depending on the orientation and velocity of the vapor. The impact of vapor streams on the overall heat transfer coefficient does not directly correlate with the velocity of the vapor when maintaining the same orientation.Öğe Forecasting ground-level ozone and fine particulate matter concentrations at Craiova city using a meta-hybrid deep learning model(Elsevier, 2024) El Mghouchi, Youness; Udristioiu, Mihaela T.; Yildizhan, Hasan; Brancus, MihaelaAir quality forecasting is vital for managing and mitigating the adverse effects of air pollution on human health, crops, and the environment. This study aims to forecast daily time series of ozone and fine particulate matter (PM) concentrations using a meta-hybrid deep NARMAX (Nonlinear Auto-Regressive Moving Average with eXogenous inputs) model. Two datasets were utilised: (a) data on meteorological parameters (temperature, air pressure, relative humidity) and air pollutant concentrations (particulate matter, ozone, dioxide of carbon, volatile organic compounds, formaldehyde) provided by a sensor model A3 situated in the centre of Craiova city, and (b) data on wind direction, wind speed, and sunshine duration provided by the National Meteorological Administration. The data sets covered a time interval from December 10, 2020, to January 05, 2024. Initially, a statistical analysis was conducted to assess the correlation between variables. Results revealed that ozone concentration is primarily influenced by meteorological variables such as temperature (r = 0.79), sunshine duration (r = 0.55), and relative humidity (r = -0.48), and secondarily by air pollution indicators including VOC (r = -0.34), PM concentrations (r = -0.34), and CO2 (r = -0.3). In the subsequent stage, thirteen Machine Learning (ML) models were employed in conjunction with an integral feature selection (IFS) method to identify the best combinations of predictor variables for predicting ozone and PMs. Finally, a deep NARMAX model was developed to forecast the next periods of ozone and PMs based on the optimal combinations identified earlier. Results indicated the selection of sixty best models for ozone forecasting and four best models for PMs. The R-2 values surpassed 0.97 for ozone and exceeded 0.8 for PMs, demonstrating the efficacy of the forecasting approach.Öğe From Local Issues to Global Impacts: Evidence of Air Pollution for Romania and Turkey(Mdpi, 2024) Pekdogan, Tugce; Udristioiu, Mihaela Tinca; Yildizhan, Hasan; Ameen, ArmanAir pollution significantly threatens human health and natural ecosystems and requires urgent attention from decision makers. The fight against air pollution begins with the rigorous monitoring of its levels, followed by intelligent statistical analysis and the application of advanced machine learning algorithms. To effectively reduce air pollution, decision makers must focus on reducing primary sources such as industrial plants and obsolete vehicles, as well as policies that encourage the adoption of clean energy sources. In this study, data analysis was performed for the first time to evaluate air pollution based on the SPSS program. Correlation coefficients between meteorological parameters and particulate matter concentrations (PM1, PM2.5, PM10) were calculated in two urban regions of Romania (Craiova and Drobeta-Turnu Severin) and Turkey (Adana). This study establishes strong relationships between PM concentrations and meteorological parameters with correlation coefficients ranging from -0.617 (between temperature and relative humidity) to 0.998 (between PMs). It shows negative correlations between temperature and particulate matter (-0.241 in Romania and -0.173 in Turkey) and the effects of humidity ranging from moderately positive correlations with PMs (up to 0.360 in Turkey), highlighting the valuable insights offered by independent PM sensor networks in assessing and improving air quality.Öğe Green building?s heat loss reduction analysis through two novel hybrid approaches(Elsevier, 2023) Moayedi, Hossein; Yildizhan, Hasan; Aungkulanon, Pasura; Escorcia, Yulineth Cardenas; Al-Bahrani, Mohammed; Le, Binh NguyenOne of the key reasons for the performance discrepancy between a building's intended usage and the actual operation is Heat Loss, which describes a building's envelope efficiency during in-use circumstances. In this setting, the ANN models' use for energy analysis of green buildings has become more established. This research aims to anticipate the heat loss of green buildings utilizing two artificial neural network-based methodologies (ANN). In particular, TLBO and BBO are used and contrasted. Additionally, RMSE, MAE, and R2 are used to calculate an absolute error for predicting heat loss to gauge the accuracy of the findings. The suggested TLBO-MLP standard is a reliable method with a positive outcome (RMSE = 0.01012 and 0.05216, and R2 = 0.99536 and 0.9651). Also, according to the training error ranges of [-0.0006078, 0.01133] and [-0.00040708, 0.010181] and testing error ranges of [0.0004724, 0.068666] and [0.0021984, 0.057688] for BBO-MLP and TLBO-MLP, respectively, shows that the TLBO-MLP reaches the lower range of error and can predict the heat loss with higher accuracy and it could properly forecast the heat loss of building technologies. Even so, the BBO-MLP standard provides this research with satisfactory performance (R2 = 0.9943 and 0.95175, and RMSE = 0.01122 and 0.06112). To increase the precision of calculating the heat loss of buildings, specifically integrating them with optimization algorithms, further study is required.Öğe How May New Energy Investments Change the Sustainability of the Turkish Industrial Sector?(Mdpi, 2023) Yildizhan, Hasan; Yildirim, Cihan; Gorjian, Shiva; Ameen, ArmanUtilization of renewable energy in the Turkish industrial sector is becoming more important nowadays. The tendency toward renewable energy can be clearly seen with newly planned energy investments. The energy appearance of the Turkish industrial sector for past two decades and ongoing energy projects are discussed in this study with the help of sustainability indicators. The sustainability index is based on advanced exergy analysis and shows the environmental impact of production processes and measures the transformation of energy resources in the Turkish industrial sector. This index was approximately 2.03 in 2000 and it improved to 2.25 in 2008, and then remained constant with minor fluctuations until 2019. Depending on the fulfillment of the continuing fossil, nuclear, and recommended renewable energy investment scenarios, the sustainability index may change to between 1.96 and 2.17 by 2023. None of the ongoing investments will make a major improvement in the sustainability of the industrial sector; therefore, a major shift toward the use of more renewable energy is urgently needed. Establishing solar or wind energy microgrids plants may improve the sustainability indicators drastically, therefore, encouragement of their investments is very important.Öğe Hydrothermal Investigation of the Performance of Microchannel Heat Sink with Ribs Employed on Side Walls(Walter De Gruyter Gmbh, 2021) Ahmad, Faraz; Cheema, Taqi Ahmad; Khan, Amjid; Mohib-Ur-Rehman, Muhammad; Yildizhan, HasanIn the present study, conjugate heat transfer and fluid flow performance of microchannel heat sink has been investigated using dimensionless parameters. Novel ribs of four different types are introduced on the side walls of channel, which include trapezoidal ribs, rectangular ribs, hydrofoil ribs, and elliptical ribs. The performance evaluation has been conducted by comparing friction factor (f), Nusselt number (Nu), fluid bulk temperature (T-f), wall shear stress (tau), field synergy number (Fc), irreversible heat loss (Q(d)), and Bejan number (Be) in a Reynolds number, ranging from Re = 100 to Re = 1000. The results revealed that the addition of these novel ribs are helpful in improving the overall thermal and hydraulic performance of microchannel heat sink. From the results of Bejan number, it has been revealed that more than 96 % of losses are because of heat transfer. However, at low Reynolds number, the frictional losses can be neglected, because of very low fluid velocity. Moreover, it has been revealed that synergetic relation between velocity and temperature gradient becomes weaker at higher Reynolds number. Furthermore, it is clear from this study that elliptical ribs performed better in thermal aspects, whereas hydrofoil ribs performed better at hydrodynamic aspects.Öğe Multivariable Air-Quality Prediction and Modelling via Hybrid Machine Learning: A Case Study for Craiova, Romania(Mdpi, 2024) El Mghouchi, Youness; Udristioiu, Mihaela Tinca; Yildizhan, HasanInadequate air quality has adverse impacts on human well-being and contributes to the progression of climate change, leading to fluctuations in temperature. Therefore, gaining a localized comprehension of the interplay between climate variations and air pollution holds great significance in alleviating the health repercussions of air pollution. This study uses a holistic approach to make air quality predictions and multivariate modelling. It investigates the associations between meteorological factors, encompassing temperature, relative humidity, air pressure, and three particulate matter concentrations (PM10, PM2.5, and PM1), and the correlation between PM concentrations and noise levels, volatile organic compounds, and carbon dioxide emissions. Five hybrid machine learning models were employed to predict PM concentrations and then the Air Quality Index (AQI). Twelve PM sensors evenly distributed in Craiova City, Romania, provided the dataset for five months (22 September 2021-17 February 2022). The sensors transmitted data each minute. The prediction accuracy of the models was evaluated and the results revealed that, in general, the coefficient of determination (R2) values exceeded 0.96 (interval of confidence is 0.95) and, in most instances, approached 0.99. Relative humidity emerged as the least influential variable on PM concentrations, while the most accurate predictions were achieved by combining pressure with temperature. PM10 (less than 10 mu m in diameter) concentrations exhibited a notable correlation with PM2.5 (less than 2.5 mu m in diameter) concentrations and a moderate correlation with PM1 (less than 1 mu m in diameter). Nevertheless, other findings indicated that PM concentrations were not strongly related to NOISE, CO2, and VOC, and these last variables should be combined with another meteorological variable to enhance the prediction accuracy. Ultimately, this study established novel relationships for predicting PM concentrations and AQI based on the most effective combinations of predictor variables identified.Öğe Observational study of ground-level ozone and climatic factors in Craiova, Romania, based on one-year high-resolution data(Nature Portfolio, 2024) Yildizhan, Hasan; Udristioiu, Mihaela Tinca; Pekdogan, Tugce; Ameen, ArmanAir pollution is a multifaceted issue affecting people's health, environment, and biodiversity. Gaining comprehension of the interactions between natural and anthropocentric pollutant concentrations and local climate is challenging. This study aims to address the following two questions: (1) What is the influential mechanism of climatic and anthropogenic factors on the ground-level ozone (O3) concentrations in an urban environment during different seasons? (2) Can the ozone weekend effect be observed in a medium-sized city like Craiova, and under which conditions? In order to answer these questions, ozone interactions with meteorological parameters (temperature, pressure, relative humidity) and pollutant concentrations (particulate matter, carbon dioxide, volatile organic compounds, formaldehyde, nitrogen dioxide, nitric oxide and carbon monoxide) is evaluated based on a one-year dataset given by a low-cost sensor and one-year dataset provided by the National Environment Agency. Using two statistical analysis programs, Python and SPSS, a good understanding of the correlations between these variables and ozone concentration is obtained. The SPSS analysis underscores the significant impact of three meteorological factors and nine other pollutants on the ozone level. A positive correlation is noticed in the summer when sunlight is intense and photochemical reactions are elevated. The relationship between temperature and ozone concentration is strong and positive, as confirmed by Spearman's rho correlation coefficient (r = 0.880). A significant negative correlation is found between relative humidity and ozone (r = -0.590). Moreover, the analysis shows that particulate matter concentrations exhibit a significant negative correlation with ozone (r approximate to -0.542), indicating that higher particulate matter concentrations reduce ozone levels. Volatile organic compounds show a significant negative correlation with ozone (r = -0.156). A negative relationship between ozone and carbon dioxide (r = -0.343), indicates that elevated carbon dioxide levels might also suppress ozone concentrations. A significant positive correlation between nitrogen dioxide and ozone (r = 0.060), highlights the role of nitrogen dioxide in the production of ozone through photochemical reactions. However, nitric oxide shows a negative correlation with ozone (r = -0.055) due to its role in ozone formation. Carbon monoxide has no statistically significant effect on ozone concentration. To observe the differences between weekdays and weekends, T-Test was used. Even though significant differences were observed in temperature, humidity, carbon dioxide, volatile organic compounds, nitrogen dioxide, nitric oxide and carbon monoxide levels between weekdays and weekends, the T-Test did not highlight a significant weekend ozone effect in a mid-sized city as Craiova. Using Python, the daily values were calculated and compared with the limit values recommended by the World Health Organization (WHO) and European Environment Agency (EEA). The WHO O3 recommended levels were exceeded for 13 times in one year. This study offers a comprehensive understanding of ozone pollution in a mid-sized city as Craiova, serving as a valuable reference for local decision-makers. It provides critical insights into the seasonal dynamics of ozone levels, emphasizing the significant role of temperature in ozone formation and the complex interactions between various pollutants and meteorological factors.Öğe Prediction, modelling, and forecasting of PM and AQI using hybrid machine learning(Elsevier Sci Ltd, 2023) Udristioiu, Mihaela T.; EL Mghouchi, Youness; Yildizhan, HasanThis paper proposes a combination of hybrid models like Input Variable Selection (IVS), Machine Learning (ML), and regression method to predict, model, and forecast the daily concentrations of particulate matter (PM1, PM2.5, PM10) and Air Quality Index (AQI). A sensor placed in the centre of Craiova, Romania, provides a two-year dataset for training, testing, and validation phases. The analysis identifies the most important predictor variables for PM prediction and forecasting. The coefficient of determination (R2) values in this stage exceeded 0.95 (95%), indicating a strong correlation between PM concentrations. The performance of the proposed models is evaluated by objective measures, including root mean squared error (RMSE) and standard deviation (a). RMSE ranged between 0.65 and 1 & mu;g/m3, while a has values between 2.75 and 4.1 & mu;g/m3, reflecting a high level of precision and a successful performance of the proposed models. Furthermore, 13 multivariable-based PM models are developed in this study and adjusted using a hybrid Least Square -Decision Tree approach. The R2 values for these adjusted models range from 0.66 to 0.75, while the RMSE and a vary between 8 and 9.1 & mu;g/m3. Finally, a handled application for multistep-ahead time series forecasting is elaborated by combining the Nonlinear System Identification (NARMAX) approach with Decision Tree machine learning. This application allows for forecasting PM concentrations and AQI for the next periods. The R2 values obtained in this stage surpass 0.93, indicating almost a high level of accuracy. The RMSE ranged between 4.43 and 6.25 & mu;g/m3, while the a ranged between 4.44 and 6.26 & mu;g/m3, further validating the precision of our forecasting model.
