Electricity production based forecasting of greenhouse gas emissions in Turkey with deep learning, support vector machine and artificial neural network algorithms

Bakay, Melahat Sevgül; Ağbulut, Ümit

doi:10.1016/j.jclepro.2020.125324

Cited by 179 publications

(71 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to Bakay and Agbulut, 77 several statistical metrics such as coefficient of determination (R 2 ), root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage of error (MAPE), Legate and Willmott index of agreement (IA) and relative root mean square error (rRMSE) are employed to evaluate the performance and accuracy of stochastic models. Performance measures used are as follows:…”

Section: Model Performance Measures and Their Interpretationmentioning

confidence: 99%

Comparison of the advanced machine learning methods for better prediction accuracy of solar radiation using only temperature data: A case study

Mirbolouki

Heddam

Parmar

et al. 2021

Intl J of Energy Research

View full text Add to dashboard Cite

Estimation of solar radiation (SR) carries importance for planning available renewable energy, and it is also beneficial for solving agricultural, meteorological, and engineering problems. This study compares the ability of hybrid adaptive neuro fuzzy (ANFIS) models and long short-term memory to search a suitable approach for SR prediction with minimum number of input parameters (temperature) in Mediterranean region of Turkey, which could be useful for the regions in which other effective parameters (eg, relative humidity, wind speed) are not available. The models considered were assessed by considering four data splitting scenarios, 50% train-50% test, 60% train-40% test, 70% train-30% test, and 80% train-20% test. Among the hybrid methods, the ANFIS with grey wolf optimization and genetic algorithm showed a superior accuracy. The study shows that applying different data splitting scenarios is necessary for better assessment of the data-driven methods since the accuracies of the implemented methods increase by about 30% to 60% when the splitting data scenario varies from 50-50% to 80-20%. Sensitivity analysis shows that the performance of the model increases by about 40% using extraterrestrial radiation for the best model. The ANFIS with grey wolf optimization and genetic algorithm is recommended to predict monthly solar radiation with limited input data.

show abstract

Section: Model Performance Measures and Their Interpretationmentioning

confidence: 99%

Comparison of the advanced machine learning methods for better prediction accuracy of solar radiation using only temperature data: A case study

Mirbolouki

Heddam

Parmar

et al. 2021

Intl J of Energy Research

View full text Add to dashboard Cite

show abstract

“…The Sun is known as the primary source of energy on Earth and it also has the potential in providing a big part of daily energy demand (Oztop et al , 2013). In the community of engineers and researchers solar thermal systems especially solar air heaters has aroused interest since the middle of the past century because of different reasons including being inexpensive, relatively simple and low maintenance cost (Ergün and Eyinç, 2019; Bakay and Ağbulut, 2021). In addition, there are some research studies and reports presented that greenhouse gas emissions have a prominent negative environmental influence and consequent pollutions are potentially caused to the growing adverse and harmful climate change (Dhar et al , 2019; Kaya et al , 2019).…”

Section: Introductionmentioning

confidence: 99%

Numerical and experimental analysis of parallel-pass forced convection solar air heating wall with different plenum and absorber configurations

Khanları

Sözen

Afshari

et al. 2021

HFF

Self Cite

View full text Add to dashboard Cite

Purpose Over the recent years, solar energy has received outstanding attention from researchers. Solar energy applications and related large-scale projects are increasing to meet growing global energy demand as an economical, non-polluting and renewable energy source. The purpose of this study is investigating different plenum and absorber configurations of solar air heating wall (SAHW) experimentally and numerically. Design/methodology/approach In this study, various configurations of SAHW have been numerically simulated to determine the most effective design. According to the simulation results, two SAHWs with various plenum thicknesses have been fabricated and tested at different conditions. Findings Numerical simulation results indicated that parallel-flow SAHWs exhibited better performance in comparison with other placements of absorber plate. Regarding to the experimentally attained results, the highest thermal efficiency was reached to 80.51%. Also, the average deviation between experimentally and numerically obtained outlet temperature is 5.5%. Originality/value Considering the obtained results in the present study, designed SAHW has admissible efficiency to be used in various industrial and residential applications such as; air preheating, space heating and drying.

show abstract

“…CO 2 emission is the highest share on the greenhouse gases all over the world, and its share on total greenhouse gases is gradually increasing [11][12][13][14]. For example, CO 2 emissions in Turkey is of 69% of total GHG emissions in the year 1990, and it reached by 80.5% in the year 2018 [15]. The similar increment trends on the share of CO 2 emission are also observed for other counties, too [16][17][18][19][20][21] For this reason, numerous governments have tried to take some concrete steps to mitigate the carbon emissions by dealing with different carboncontrol mechanisms such as carbon taxes, cap-and-trade systems, carbon offsets, carbon caps, and eco-friendly technology norms [15,22].…”

Section: Introductionmentioning

confidence: 99%

“…For example, CO 2 emissions in Turkey is of 69% of total GHG emissions in the year 1990, and it reached by 80.5% in the year 2018 [15]. The similar increment trends on the share of CO 2 emission are also observed for other counties, too [16][17][18][19][20][21] For this reason, numerous governments have tried to take some concrete steps to mitigate the carbon emissions by dealing with different carboncontrol mechanisms such as carbon taxes, cap-and-trade systems, carbon offsets, carbon caps, and eco-friendly technology norms [15,22]. Out of these five mechanisms, the carbon tax is always the most popular one that directly sets prices on carbon content or carbon emissions of fossil-based fuels.…”

Section: Introductionmentioning

confidence: 99%

“…There has been a rapid increase in the number of countries adopting the carbon tax in recent years. That is, 17 of the 26 countries have started to apply the carbon tax after the year 2008 [15,23]. On the other hand, ecofriendly technology norms have been, for example, implemented to the very limited fields in the technological industries such as carbon cap and carbon offsets, the automotive battery sectors.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Well to Wheel: A life-cycle based analysis of CI engine powered with diesel and various alcohol blends

Ağbulut

2021

International Journal of Automotive Science and Technology

Self Cite

View full text Add to dashboard Cite

The core objective of the present research is to investigate the life cycle-based en-vironmental analysis of a CI engine powered with diesel (DF), diesel (90%) and etha-nol (10%) (E10), and diesel (90%) and methanol (10%) (M10) blends. The data is gathered when the engine runs at a constant engine speed of 1800 rpm, and varying engine loads from 2.5 Nm to 10 Nm with gaps of 2.5 Nm. In the results, higher CO2 emissions are recorded when the engine is fed by E10 and M10 test fuels due to the worsening engine performance and high-oxygen content of relevant alcohols. Cumu-latively, the CO2 emission is higher 17.37% for E10 and 24.76% for M10 test fuel in comparison to that of DF. Given that the life cycle analysis, it is noticed that DF has respectable advantages. In comparison to that of conventional DF, life cycle based total environmental pollution cost of E10 and M10 test fuels is calculated to be high-er by 4.13% and 8.61%, respectively. The highest specific life cycle-based environ-mental values are calculated to be 0.1371 $/kWh, 0.1444 $/kWh, and 0.1607 $/kWh for DF, E10, and M10 test fuels at 2.5 Nm. The highest life cycle based environmen-tal payback pollution values are achieved to be 22.62 years for DF, 23.83 years for E10, and 26.52 years for M10 test fuels at 2.5 Nm. In the conclusion, it is well-noticed that biofuels cannot compete with conventional DF in terms of economical and CO2-based life cycle environmental pollution issues in today’s technology.

show abstract

Electricity production based forecasting of greenhouse gas emissions in Turkey with deep learning, support vector machine and artificial neural network algorithms

Cited by 179 publications

References 69 publications

Comparison of the advanced machine learning methods for better prediction accuracy of solar radiation using only temperature data: A case study

Comparison of the advanced machine learning methods for better prediction accuracy of solar radiation using only temperature data: A case study

Numerical and experimental analysis of parallel-pass forced convection solar air heating wall with different plenum and absorber configurations

Well to Wheel: A life-cycle based analysis of CI engine powered with diesel and various alcohol blends

Contact Info

Product

Resources

About