Prediction Of Emissions Research Articles

Prediction of greenhouse gas emissions in Türkiye with long short-term memory (LSTM) and 1-dimensional convolutional neural network (1-DCNN) algorithms

ABSTRACT The sector with the largest share (32%) of total GHG emissions is now electricity and heat production. This means that more fossil fuels have to be burned to meet the ever-increasing demand for electricity and heat. This study aims to estimate the pollutants such as CO2, CH4, N2O, F-gases, and total GHGs produced during electricity generation in Türkiye using LSTM and 1-DCNN. In the training and prediction processes of these algorithms, the 1990-2020 values from the TURKSTAT were used as the data set. Seven of the data were used in the prediction process, while the remaining data were used in the training process of the algorithms. In 1990, a total of 57,543 GWh of electricity was produced in Türkiye, compared to 306,703 GWh in 2020. In 2020, 34.5% of the electricity was produced from coal, 0.1% from liquid fuels, 23.1% from natural gas, 25.5% from hydropower, and 16.8% from renewables and waste. While CO2 emissions comprised 69.05% of Türkiye’s total GHG emissions in 1990, this percentage rose to 78.92% in 2020. It was concluded that the algorithms preferred in this study gave satisfactory results separately for the estimation of GHG emissions released to the atmosphere during electricity production in Türkiye.

A comparative analysis and prediction of carbon emission in India using Machine learning models

<p style="line-height:150%;text-align:justify;text-indent:36.0pt;"><span style="background-color:yellow;font-family:"Times New Roman","serif";font-size:12.0pt;line-height:150%;">Among the most significant issues that will impact and pose a major threat to our future are global warming and climate change. This study focuses on forecasting India's carbon emissions, specifically examining the role of agriculture and agri-related industries, using time-series data from 1990 to 2020. </span><span style="background-color:lime;font-family:"Times New Roman","serif";font-size:12.0pt;line-height:150%;">To achieve this, a machine learning-based approach was proposed, utilizing five advanced models AdaBoost, XGB, Gradient Boosting, Random Forest, and Linear Regression. These models were selected for their ability to process large datasets, identify complex patterns, and provide precise predictions, offering a comprehensive framework for estimating carbon emissions. The approach aims to identify the most accurate predictive model for estimating carbon emissions, facilitating informed policy interventions and strategic planning. </span><span style="background-color:aqua;font-family:"Times New Roman","serif";font-size:12.0pt;line-height:150%;">The Carbon Budget 2023 research highlights that India's carbon emissions increased by 8.2% in 2023, raising significant concerns for environmental sustainability. Using the proposed machine learning models, the study facilitates robust data prediction. Among the five models, XGB demonstrates superior performance with evaluation metrics such as a Mean Absolute Error (MAE) of 19843, Root Mean Square Error (RMSE) of 24022, Mean Squared Error (MSE) of 5770998, R² value of 0.9, and test accuracy of 99%. These findings establish XGB as the most reliable model for forecasting carbon emissions. Consequently, XGB emerges as a powerful tool for accurately estimating emissions and addressing the challenges posed by climate change.</span></p>

Predictions of Dust Continuum Emission from a Potential Circumplanetary Disk: A Case Study of the Planet Candidate AB Aurigae b

Abstract Gas-accreting planets embedded in protoplanetary disks are expected to show dust thermal emission from their circumplanetary disks (CPDs). However, a recently reported gas-accreting planet candidate, AB Aurigae b, has not been detected in (sub)millimeter continuum observations. We calculate the evolution of dust in the potential CPD of AB Aurigae b and predict its thermal emission at 1.3 mm wavelength as a case study, where the obtained features may also be applied to other gas-accreting planets. We find that the expected flux density from the CPD is lower than the 3σ level of the previous continuum observation by the Atacama Large Millimeter/submillimeter Array with broad ranges of parameters, consistent with a nondetection. However, the expected planet mass and gas accretion rate are higher if the reduction of the observed near-infrared continuum and Hα line emission due to the extinction by small grains is considered, resulting in higher flux density of the dust emission from the CPD at (sub)millimeter wavelengths. We find that the corrected predictions of the dust emission are stronger than the 3σ level of the previous observation with the typical dust-to-gas mass ratio of the inflow to the CPD. This result suggests that the dust supply to the vicinity of AB Aurigae b is small if the planet candidate is not the scattered light of the star but is a planet and has a CPD. Future continuum observations at shorter wavelengths are required to obtain more robust clues to the question of whether the candidate is a planet or not.

A Comprehensive Approach to CO2 Emissions Analysis in High-Human-Development-Index Countries Using Statistical and Time Series Approaches

Reducing carbon dioxide (CO2) emissions is vital at both global and national levels, given their significant role in exacerbating climate change. CO2 emissions, stemming from a variety of industrial and economic activities, are major contributors to the greenhouse effect and global warming, posing substantial obstacles in addressing climate issues. It is imperative to forecast CO2 emissions trends and classify countries based on their emission patterns to effectively mitigate worldwide carbon emissions. This paper presents an in-depth comparative study on the determinants of CO2 emissions in twenty countries with high Human Development Index (HDI), exploring factors related to economy, environment, energy use, and renewable resources over a span of 25 years. The study unfolds in two distinct phases: initially, statistical techniques such as Ordinary Least Squares (OLS), fixed effects, and random effects models are applied to pinpoint significant determinants of CO2 emissions. Following this, the study leverages supervised and unsupervised time series approaches to further scrutinize and understand the factors influencing CO2 emissions. Seasonal AutoRegressive Integrated Moving Average with eXogenous variables (SARIMAX), a statistical time series forecasting model, is first used to predict emission trends from historical data, offering practical insights for policy formulation. Subsequently, Dynamic Time Warping (DTW), an unsupervised time series clustering approach, is used to group countries by similar emission patterns. The dual-phase approach utilized in this study significantly improves the accuracy of CO2 emissions predictions while also providing a deeper insight into global emission trends. By adopting this thorough analytical framework, nations can develop more focused and effective carbon reduction policies, playing a vital role in the global initiative to combat climate change.

An examination of daily CO2 emissions prediction through a comparative analysis of machine learning, deep learning, and statistical models.

Human-induced global warming, primarily attributed to the rise in atmospheric CO2, poses a substantial risk to the survival of humanity. While most research focuses on predicting annual CO2 emissions, which are crucial for setting long-term emission mitigation targets, the precise prediction of daily CO2 emissions is equally vital for setting short-term targets. This study examines the performance of 14 models in predicting daily CO2 emissions data from 1/1/2022 to 30/9/2023 across the top four polluting regions (China, India, the USA, and the EU27&UK). The 14 models used in the study include four statistical models (ARMA, ARIMA, SARMA, and SARIMA), three machine learning models (support vector machine (SVM), random forest (RF), and gradient boosting (GB)), and seven deep learning models (artificial neural network (ANN), recurrent neural network variations such as gated recurrent unit (GRU), long short-term memory (LSTM), bidirectional-LSTM (BILSTM), and three hybrid combinations of CNN-RNN). Performance evaluation employs four metrics (R2, MAE, RMSE, and MAPE). The results show that the machine learning (ML) and deep learning (DL) models, with higher R2 (0.714-0.932) and lower RMSE (0.480-0.247) values, respectively, outperformed the statistical model, which had R2 (- 0.060-0.719) and RMSE (1.695-0.537) values, in predicting daily CO2 emissions across all four regions. The performance of the ML and DL models was further enhanced by differencing, a technique that improves accuracy by ensuring stationarity and creating additional features and patterns from which the model can learn. Additionally, applying ensemble techniques such as bagging and voting improved the performance of the ML models by approximately 9.6%, whereas hybrid combinations of CNN-RNN enhanced the performance of the RNN models. In summary, the performance of both the ML and DL models was relatively similar. However, due to the high computational requirements associated with DL models, the recommended models for daily CO2 emission prediction are ML models using the ensemble technique of voting and bagging. This model can assist in accurately forecasting daily emissions, aiding authorities in setting targets for CO2 emission reduction.

Influencing Factors Analysis and Prediction of Gas Emission in Mining Face

Mine gas emission is one of the main causes of gas disasters. In order to achieve the accurate prediction of gas emission, a gas emission prediction model based on the random forest (RF) method was proposed in combination with the analysis of its influencing factors. The prediction results were compared with the support vector regression (SVR) and BP neural network (BPNN) methods, and then they were verified and analyzed through the Dongqu coal mine. The results show that the gas emission prediction model based on random forest has strong generalization and robustness, and RF has a wide range of parameter adaptation during the modeling process. When the number of trees (ntree) exceeds 100, its training error tends to stabilize, and changes in ntree have no substantial impact on the prediction performance. The SVR prediction model has significant bias in both the training and testing stages. Meanwhile, the BPNN model has excellent prediction results in the training phase, but there is a large error in the testing stage, which indicates that there is an “overfitting” phenomenon in the training stage, resulting in weak generalization. The evaluation of variable importance shows that the extraction rate, coal seam depth, daily production, gas content in adjacent layers, and coal seam thickness have a significant impact on gas emission. Meanwhile, through application analysis, it is further demonstrated that the random forest method has high accuracy, strong stability, and universality, and it can achieve good predictive performance without the need for complex parameter settings and optimization, making it is very suitable for predicting gas emission.

MLP Enhanced CO2 Emission Prediction Model with LWSSA Nature Inspired Optimization

Environmental degradation due to the rapid increase in CO₂ emissions is a pressing global challenge, necessitating innovative solutions for accurate prediction and policy development. Machine learning (ML) techniques offer a robust approach to modeling complex relationships between various factors influencing emissions. Furthermore, ML models can learn and interpret the significance of each factor’s contribution to the rise of CO2. This study proposes a novel hybrid framework combining a Multi-Layer Perceptron (MLP) with an enhanced Locally Weighted Salp Swarm Algorithm (LWSSA) to address the limitations of traditional optimization techniques, such as premature convergence and stagnation in locally optimal solutions. The LWSSA improves the standard Salp Swarm Algorithm (SSA) by incorporating a Locally Weighted Mechanism (LWM) and a Mutation Mechanism (MM) for greater exploration and exploitation. The LWSSA-MLP framework achieved a prediction accuracy of 97% and outperformed traditional optimizer-based MLP models across several evaluation metrics. A permutation feature significance analysis identified global trade, coal energy, export levels, urbanization, and natural resources as the most influential factors in CO₂ emissions, offering valuable insights for targeted interventions. The study provides a reliable and scalable framework for CO₂ emission prediction, contributing to actionable strategies for sustainable development and environmental resilience.

Spatial-temporal evolution and multi-scenario prediction of carbon emissions from land use in the adjacent areas of nature reserves

Spatial-temporal evolution and multi-scenario prediction of carbon emissions from land use in the adjacent areas of nature reserves

Carbon emission prediction and carbon emission reduction potential analysis of cement enterprises based on electricity data

Carbon emission prediction and carbon emission reduction potential analysis of cement enterprises based on electricity data

A peak carbon emission prediction method for enterprises based on IoT blockchain and grey neural network

A peak carbon emission prediction method for enterprises based on IoT blockchain and grey neural network

A Building Carbon Emission Prediction Model Based on Optimized Machine Learning Model

To improve the performance of traditional machine learning model, this study employs the chaotic particle swarm optimization (CPSO) and the fuzzy cuckoo search (FCS) algorithm to enhance the BP neural network and support vector machine (SVM), leading to CPSO-BP and FCS-SVM model, respectively. Simulation results indicate that both optimization algorithms significantly enhance the predictive accuracy of their respective models. The relative error of the FCS-SVM decreases by 2.68%, while the CPSO-BP model reduces by 9.75% compared to their pre-benchmark model. Although the CPSO-BP model demonstrates a more substantial improvement in the simulation, the performance of FCS-SVM remains superior to that of CPSO-BP model. Subsequently, the FCS-SVM model was selected to forecast carbon dioxide emissions in China's construction industry from 2022 to 2025, and the results were thoroughly analyzed. The findings indicate that total carbon emissions are expected to rise over the next four years; however, the growth rate is projected to slow significantly. Additionally, carbon emission intensity is anticipated to continue declining until 2023, although the rate of decline will be minimal.

Improve carbon dioxide emission prediction in the Asia and Oceania (OECD): nature-inspired optimisation algorithms versus conventional machine learning

This paper investigates the application of three nature-inspired optimisation algorithms – SHO, MFO, and GOA – combined with four machine learning methods – Gaussian Processes, Linear Regression, MLP, and Random Forest – to enhance carbon dioxide emission prediction in the OECD – Asia and Oceania region. The study uses historical carbon dioxide emissions data, socioeconomic indicators such as GDP, population density, energy consumption, and urbanisation rates, and environmental indicators such as temperature, precipitation, and forest cover. Through comprehensive experimentation, the study evaluates the performance of each combination, revealing varying effectiveness levels. The MFO-MLP combination achieved the highest accuracy with R2 values of 0.9996 and 0.9995 and RMSE values of 11.7065 and 12.8890 for the training and testing datasets, respectively. The GOA-MLP configuration achieved R2 values of 0.9994 and 0.99934 and RMSE values of 15.01306 and 14.59333. The SHO-MLP combination, while effective, showed lower performance with R2 values of 0.9915 and 0.9946 and RMSE values of 55.4516 and 41.575. The findings suggest hybrid techniques can significantly enhance prediction accuracy compared to conventional methods. This research provides valuable insights for policymakers and stakeholders, indicating that optimised machine learning models can support more informed and effective environmental policy-making and sustainability efforts in the OECD – Asia and Oceania region. Future research should explore additional optimisation algorithms and ensemble techniques to improve prediction robustness and accuracy. These findings offer a robust tool for policymakers to forecast emissions more accurately, aiding in developing targeted strategies to reduce carbon footprints and achieve climate goals.

Enhancement of Aeroengine Combustion Chamber Air Cooling Holes Design for Emission Reduction and Pattern Factor Control

The results of a comprehensive numerical analysis of temperature uniformity and NOx and CO emission predictions in an aeroengine annular combustor liner, conducted by geometrical modifications through design changes in primary cooling air, including effusion cooling holes, are shown in the paper. A total of five geometric configurations were studied using computational fluid dynamics (CFD) simulations in ANSYS CFX. The adopted combustion model was sort of a combination of the finite-rate (i.e., chemistry, chemical processes) and eddy dissipation model (FRC/EDM). Further, the combustion of liquid kerosene (C10H22) with air, subsequent to the evaporation of fuel droplets, was simulated, and the Rosin-Rammler droplet size distribution was used in spray modeling for accurate depiction of fuel atomization. Both thermal and prompt formation mechanisms of NOx were considered, while k-ε model for turbulence was adapted to capture the nature of emission. An annular combustion chamber of realistic dimensions with a double radial air swirler was modelled in 3D CAD to undertake this study for good, tangible results. Built contour plots allowed to analyze the temperature distribution and NOx concentration along the axis from the center of the injector. Charts on the pattern factor, temperature, and NOx and CO concentrations at the outlet of the combustor served as performance metrics. The simulation was implemented with a two-step chemical kinetics scheme for kerosene combustion with the P1 radiation model, which would give an accurate thermal radiation prediction. One of the major objectives of this research is to compare the CFD results at the combustor outlet with gas dynamic and thermodynamic calculations that have been carried out using AxStream software at the Department of Aeroengine Design, Kharkiv Aviation Institute. It is important to emphasize that the mean deviation of gas dynamic results obtained from AxStream and CFD simulation results was found to be insignificant, hence the CFD approach has been validated. The results testify that redesigning the combustor liner, especially in the design related to primary and effusion cooling holes, drastically reduced NOx and CO emissions. Also, these design modifications have helped in reducing or improving temperature uniformity at the combustor outlet, either way enhancing combustion efficiency and performance.

Predicting transient performance of a heavy-duty gaseous-fuelled engine using combined phenomenological and machine learning models

Decarbonizing long-haul goods transportation poses a substantial challenge. High-efficiency natural gas (NG) engines, which retain the efficiency of a diesel engine but reduce the carbon content of the fuel, offer substantial potential for near-term greenhouse gas (GHG) reductions. A fast-running model that can predict engine performance, GHG and air pollutant emissions is critical to assessing this approach for different applications and vehicle drivetrain configurations. This paper presents the development, validation and application of an engine system model that adapts GT-SUITE™’s phenomenological DI-Pulse predictive model to predict the performance and emissions of a 6-cylinder NG engine using a high pressure direct-injection combustion process. The model includes the engine air exchange system, enabling the prediction of the engine and in-cylinder conditions and overall performance over transient drive cycles. The engine model with a fixed set of calibration parameters captures the complex high-pressure direct injection combustion process and generates time-resolved parameters that are fed into a coupled machine learning model to predict emissions, including nitrogen oxide (NOx) and methane (CH4) emissions. While the 1-D model’s predictions for CH4 were not accurate, coupling the 1-D engine model with a machine learning model has been shown to substantially improve the estimation of CH4 emissions and allow accurate prediction of engine total GHG emissions over different duty cycles. The model has been validated using transient engine dynamometer data and is then applied to assess performance and emissions over several regulatory and real-world long-haul drive cycles. The model showed an average error of less than 5% in steady operation. Cumulative errors of NOx and CH4 emissions in studied cycles were also less than 10%. The results showed that CH4 share in total GHG emissions ranges from 0.2% to 1.4% over various drive cycles. By predicting engine performance and emissions, the developed combined model has considerable potential for use in engine evaluation studies, especially when combined with new technologies across different duty cycles.

Classification of NOx Emission in Marine Engines Utilizing kNN-Based Machine Learning Algorithms

Marine diesel engines are crucial for powering large vessels in the maritime sector and are known for their efficiency across various industries. However, increasing environmental concerns and stringent regulations targeting air pollutants such as nitrogen oxides (NOx) and particulate matter (PM) have heightened the need for advanced emission control technologies. Addressing this challenge, the study focuses on developing a reliable method to predict NOx emission levels in marine engines, reducing reliance on resource-intensive experimental testing. Leveraging machine learning techniques, particularly k-nearest neighbors (kNN)-based algorithms, the research classifies NOx emissions in marine engines operating under the Reactivity-Controlled Compression Ignition (RCCI) strategy. Comparative performance analysis reveals that the FPFS-kNN algorithm achieves the highest accuracy (90.00%) alongside strong precision (84.23%), recall (82.37%), and F1 score (82.47%). These findings underscore the potential of machine learning in emission prediction and highlight directions for future exploration in this domain.

Experimental and Numerical Study on NOx Emissions Characteristics in a Coaxial Staged Combustor

Abstract A deep understanding of NOx formation characteristics and correlations can significantly enhance the operational adjustment efficiency of gas turbine combustors. To reduce pollutants emissions, this study proposed a coaxial staged combustion technology, experimental and numerical work was further conducted to investigate the impact of fuel stage ratio on NOx formation in an industrial gas turbine combustor operating at different loads. The dome equivalence ratio was ranging from 0.455 to 0.635, the fuel stage ratio was ranging from 0.27 to 3.23. Experimental results show that NOx emissions can be controlled within 25 ppm at 15% O2 with the combustor outlet temperature up to 1673 K. There exists an optimal fuel stage ratio that leads to the lowest NOx emissions. Moreover, as the dome equivalence ratio increases, the optimal fuel stage ratio decreases. Numerical results indicate that NOx generation through the prompt mechanism is negligible. At low-power conditions, NOx is primarily generated at the flame front through the N2O intermediate pathway. In contrast, at high-power conditions, NOx is mainly produced in the burnout and recirculation zones through the thermal pathway. Thermal NOx is highly sensitive to fuel stage ratios, unlike the relatively stable NOx production via the N2O intermediate mechanism. Based on the experimental data, it was found that the inner stage flame temperature has a more significant impact on NOx emissions. Furthermore, a new NOx emissions prediction model within an error of 20% that considers the impact of two-stage swirl flames was proposed.

CO2 Emission Prediction for Coal-Fired Power Plants by Random Forest-Recursive Feature Elimination-Deep Forest-Optuna Framework

As the greenhouse effect intensifies, China faces pressure to manage CO2 emissions. Coal-fired power plants are a major source of CO2 in China. Traditional CO2 emission accounting methods of power plants are deficient in computational efficiency and accuracy. To solve these problems, this study proposes a novel RF-RFE-DF-Optuna (random forest–recursive feature elimination–deep forest–Optuna) framework, enabling accurate CO2 emission prediction for coal-fired power plants. The framework begins with RF-RFE for feature selection, identifying and extracting the most important features for CO2 emissions from the power plant, reducing dimensionality from 46 to just 5 crucial features. Secondly, the study used the DF model to predict CO2 emissions, combined with the Optuna framework, to enhance prediction accuracy further. The results illustrated the enhancements in model performance and showed a significant improvement with a 0.12706 increase in R2 and reductions in MSE and MAE by 81.70% and 36.88%, respectively, compared to the best performance of the traditional model. This framework improves predictive accuracy and offers a computationally efficient real-time CO2 emission monitoring solution in coal-fired power plants.

Modeling the emitted carbon dioxide and monoxide gases in the gasification process using optimized hybrid machine learning models

Abstract The machine learning methods are hereby proposed to predict the amount of Carbon Monoxide (CO) and Carbon Dioxide (CO₂) emissions in a gasification process, which is one of the most important enabling technologies for carbon-containing materials, such as coal, biomass, and waste toward producing end products of worth, such as syngas, hydrogen, and synthetic fuels. In an attempt to support efforts for improving the emission prediction-a key criterion for enhancing efficiency and further, the environmental performance of gasification-two new advanced algorithms are being applied for the optimization of the model of a random forest: the Jellyfish Search Optimizer (JSO) and Sooty Tern Optimization Algorithm (STOA). The tuned RFJS (RF+JSO) was the best of these configurations, providing the least RMSE of 0.593 on test data and the highest R 2 on validation of 0.983, proving to be most effective for the prediction of emissions. This goes to attest that the model RFJS would be a strong tool in real-time-based carbon emissions reduction due to its effectiveness in dealing with major implications from environmental monitoring to regulation and further into sustainable energy production.

Prediction of Performance and Emission of Gasoline Engine Fueled with a Gasoline-Ethanol-Methanol Mixture Using One Dimensional Engine Modelling Based on Engine Test Results

The depletion of petroleum reserves as the basic raw material for gasoline production has driven studies into alternative fuels. One of the alternative fuels is alcohol, both ethanol and methanol. Due to their liquid form and physical-chemical properties similar to gasoline, small modifications to the engine are required. This paper will explain the effect of using a mixture of gasoline (in this case, RON 98 gasoline with methanol or methanol on engine performance and emissions. The fuel mixtures are as follows: G100, E10, E20, E30, M10, M20, M30. AVL Boost simulation software was used as a tool for 1-dimensional engine modelling, where the modeling is based on engine testing with G100 fuel. The results show that with increasing ethanol-methanol composition, torque and power decrease, and SFC increases. On the emission side, CO, CO2, and HC were decreased and NOx increased.

A Component-Design-Based Carbon Emission Calculation Method in the Life Cycle of a Prefabricated Building Structural Member System

Carbon emissions from buildings account for a large proportion of total social carbon emissions. Prefabricated buildings can effectively reduce carbon emissions in the construction materialization phase. The existing building carbon emission calculation method for prefabricated buildings seems too complicated due to the large amounts of data that need to be consulted in the production, transportation, construction, and demolition phases of each building. Meanwhile, the traditional building carbon emission calculation method must be carried out after the completion of construction drawings, because the consumption of labor, materials, and machinery must be calculated according to these drawings. This paper proposes a building carbon emission calculation method for prefabricated buildings based on the component design method. A case study proved that our method can calculate carbon emissions in the materialization phase of construction more quickly than the traditional quota carbon emission calculation method, and the results of the two methods differ by less than 10%. This method significantly improves the prediction of carbon emissions in the building materialization phase.