Forecasting CO2 emissions in Hebei, China, through moth-flame optimization based on the random forest and extreme learning machine.

Prediction of GDP growth rate based on carbon dioxide (CO2) emissions

Application of extreme learning machine (ELM) forecasting model on CO2 emission dataset of a natural gas-fired power plant in Dhaka, Bangladesh

Factor analysis and forecasting of CO2 emissions in Hebei, using extreme learning machine based on particle swarm optimization

Carbon dioxide (CO2) emissions continue to rise globally despite efforts to combat climate change. Energy industry emissions are a pressing global issue, causing devastating impacts. Hence, it is vital to accurately and efficiently forecast CO2 emissions. Thus, this study comprehensively analyzes forecasting CO2 emissions by comparing various hybrid combinations of regression and time series methods to explore the CO2 emissions in Pakistan. First, divide the yearly time series of CO2 emissions into the long-run curve trend series and the residual subseries. The long-run curve trend subseries is modeled using parametric and nonparametric regression methods, while various standard time series models are used to forecast the residual subseries. However, the forecasts of each subseries will be combined to obtain the final forecast of CO2 emissions. This work used four different accuracy mean errors, a statistical test, and a graphical analysis as performance measures to evaluate the proposed hybrid forecasting technique. The findings confirmed that the proposed hybrid combination forecasting technique is highly accurate and efficient in forecasting CO2 emissions. Likewise, according to the proposed final optimal hybrid combination forecasting model, Pakistan's per capita CO2 emissions will be 1.130215 metric tons in 2030. Pakistan's escalating emission trend signals that creative solutions must be implemented to curb it. Thus, the government must price carbon footprints, regulate electricity from zero-carbon sources, reduce population, encourage afforestation in densely populated areas, adopt clean technology, and fund research.

Paraffin odor intensity is an important quality indicator when a paraffin inspection is performed. Currently, paraffin odor level assessment is mainly dependent on an artificial sensory evaluation. In this paper, we developed a paraffin odor analysis system to classify and grade four kinds of paraffin samples. The original feature set was optimized using Principal Component Analysis (PCA) and Partial Least Squares (PLS). Support Vector Machine (SVM), Random Forest (RF), and Extreme Learning Machine (ELM) were applied to three different feature data sets for classification and level assessment of paraffin. For classification, the model based on SVM, with an accuracy rate of 100%, was superior to that based on RF, with an accuracy rate of 98.33–100%, and ELM, with an accuracy rate of 98.01–100%. For level assessment, the R2 related to the training set was above 0.97 and the R2 related to the test set was above 0.87. Through comprehensive comparison, the generalization of the model based on ELM was superior to those based on SVM and RF. The scoring errors for the three models were 0.0016–0.3494, lower than the error of 0.5–1.0 measured by industry standard experts, meaning these methods have a higher prediction accuracy for scoring paraffin level.

Floating photovoltaic systems provide better land use and higher energy output through water cooling effects, but accurate power forecasting remains challenging due to complex environmental factors and measurement errors. This study presents an improved ieaching-learning-based optimization algorithm with extreme learning machine for floating photovoltaic power forecasting. The method uses an adaptive teaching factor that adjusts the balance between exploration and exploitation during optimization, replacing fixed teaching factors with continuous, iteration-based adjustment. The research evaluated the approach using comprehensive real data from a floating photovoltaic installation at Universiti Malaysia Pahang Al-Sultan Abdullah, Malaysia. The proposed method achieved superior forecasting accuracy compared to benchmark algorithms including standard teaching-learning-based optimization with extreme learning machine, manta rays foraging optimization with extreme learning machine, moth flame optimization with extreme learning machine, ant colony optimization with extreme learning machine and salp swarm algorithm with extreme learning machine. The improved teaching-learning-based optimization approach demonstrated a root mean squared error of 7.81 kW and coefficient of determination of 0.9386, outperforming all comparison methods with statistically significant improvements. The algorithm showed faster convergence, enhanced stability, and superior computational efficiency while maintaining accuracy suitable for real-time grid integration applications. Phase current measurements were identified as the most important predictors for floating photovoltaic power forecasting. The system achieved high prediction accuracy with most forecasts falling within acceptable error tolerance, making the proposed approach a reliable solution for floating photovoltaic power forecasting that supports grid integration and renewable energy deployment. The methodology addresses unique characteristics of aquatic solar installations while providing practical implementation viability for operational floating photovoltaic systems.

Supported by the coordinated development strategy, the Beijing–Tianjin–Hebei (BTH) region has achieved rapid development but also faces severe energy consumption and environmental pollution problems. As the main responsibility of emission reduction, the coordinated and orderly implementation of carbon emission reduction in Beijing, Tianjin, and Hebei is of great significance to the realization of the carbon neutrality target. Based on this, this study comprehensively uses the expanded STIRPAT model, optimized extreme learning machine (ELM) network, entropy method, and zero-sum gains DEA (ZSG-DEA) model to explore the carbon emission drivers, long-term emission reduction pathway, and carbon quota allocation in the BTH region. The results of the driving factor analysis indicate that the proportion of non-fossil energy consumption is a significant driving factor for Beijing’s carbon emissions, and the improvement of the electrification level can inhibit the carbon emissions. The total energy consumption has the greatest impact on the carbon emissions of Tianjin and Hebei. The simulation results reveal that under the constraint of the carbon neutrality target, Beijing, Tianjin, and Hebei should formulate more stringent emission reduction measures to ensure that the overall carbon emission will reach its peak in 2030. The cumulative emission reduction rate should exceed 60% in 2060, and negative carbon technology should be used to offset carbon emissions of not less than 360 million tons (Mt) per year by 2060. Furthermore, the allocation results show that Beijing will receive a greater carbon quota than Hebei. The final allocation scheme will greatly promote and encourage carbon emission reduction in Hebei Province, which is conducive to achieving the goal of carbon neutrality.

Comparison of ELM, RF, and SVM on E-nose and E-tongue to trace the quality status of mandarin (Citrus unshiu Marc.)

Purpose. Development and verification of a method for calculating and forecasting CO2 emissions from coal combustion at thermal power plants based on proximate analysis data. Calculation of gross and specific CO2 emissions per unit of output energy and mass of coal consumed at Ukrainian thermal power plants (TPPs). Methodology. Methods of mathematical statistics were used for processing the data of ultimate and proximate analysis of 170samples of A, L, G, and LFG coal ranks with low heat value on operating state in the range of 17.2 to 31.0 MJ/kg and ash content on dry state (Ad) in the range of 3.8 to 38.0% to determine relationships between carbon emission factors (kc), calorific value, and ash content. Findings. The values of emission factors and gross CO2 emissions for mixtures of coals of grades A and L, G and LFG at Ukrainian TPPs in 20172021 were calculated. For 2021, the average value of for coals of grades G and LFG was 94,128 g/GJ, and for coals of grades A and L it was 104,987 g/GJ. Gross CO2 emissions at Ukrainian TPPs have been in the range of 3849million tons in recent years, and their annual reduction is due to a decrease in energy production and fuel consumption at TPPs, primarily of grades A and L. Originality. Empirical dependencies kc for steam coal of different ranks are determined in the form of The coefficients a, b, and c are determined for grades A, L, G, and LFG and their mixtures. The relationship between the carbon content in coal and the low heat value for coal is linear: where K is a coefficient depending on the coal grade. The values of K are determined for coal of grades A, L, G, and LFG. Practical value. Verification of the created method shows that the calculation error is less than 1.0%. This is in line with the requirements of the Monitoring Procedure and Directive 2003/87/EC. In 2021, the specific CO2 emission per unit of output energy at TPPs in Ukraine was 1,084 g/kWh for all ranks of steam coal. The values of specific CO2 emissions per unit mass of consumed coal were 1.94 t/t for coals of all grades, 1.91 t/t for grades G and LFG, and 2.21 t/t for grades A and L. The official annual reports of the Ministry of Energy of Ukraine contain information on the amount of produced electricity, consumed coal, and forecast balances of electricity production at TPPs, therefore, the values of specific emissions established by us are convenient to use for estimating and forecasting carbon dioxide emissions.

The variety of Chinese cabbage seeds were recognized using hyperspectral imaging with 256 bands from 874 to 1,734 nm in the present paper. A total of 239 Chinese cabbage seed samples including 8 varieties were acquired by hyperspectral image system, 158 for calibration and the rest 81 for validation. A region of 15 pixel x 15 pixel was selected as region of interest (ROI) and the average spectral information of ROI was obtained as sample spectral information. Multiplicative scatter correction was selected as pretreatment method to reduce the noise of spectrum. The performance of four classification algorithms including Ada-boost algorithm, extreme learning machine (ELM), random forest (RF) and support vector machine (SVM) were examined in this study. In order to simplify the input variables, 10 effective wavelengths (EMS) including 1,002, 1,005, 1,015, 1,019, 1,022, 1,103, 1,106, 1,167, 1,237 and 1,409 nm were selected by analysis of variable load distribution in PLS model. The reflectance of effective wavelengths was taken as the input variables to build effective wavelengths based models. The results indicated that the classification accuracy of the four models based on full-spectral were over 90%, the optimal models were extreme learning machine and random forest, and the classification accuracy achieved 100%. The classification accuracy of effective wavelengths based models declined slightly but the input variables compressed greatly, the efficiency of data processing was improved, and the classification accuracy of EW-ELM model achieved 100%. ELM performed well both in full-spectral model and in effective wavelength based model in this study, it was proven to be a useful tool for spectral analysis. So rapid and nondestructive recognition of Chinese cabbage seeds by hyperspectral imaging combined with machine learning is feasible, and it provides a new method for on line batch variety recognition of Chinese cabbage seeds.

Due to frequent drought events, increased water demand for agricultural production and limited, accurate estimation of reference evapotranspiration (ETo) is necessary for developing crop irrigation schemes and rational allocation of regional water resources. The extreme learning machine (ELM) was optimized using four biological heuristic algorithms, namely, Grey Wolf Optimizer (GWO-ELM), Moth-Flame Optimization (MFO-ELM), Particle Swarm Optimization (PSO-ELM), Whale Optimization Algorithm (WOA-ELM), and besides three types of empirical models (temperature-, radiation-, and mass transfer-based), and Penman model (P-M) were also applied to estimate the daily ETo in the Hetao irrigation district (HID). The results demonstrated that GWO-ELM obtained the highest estimation accuracy (R2 = 0.945–0.955; RRMSE = 14.52–15.29%; MAE = 0.124–0.141 mm d−1, and NSE = 0.942–0.952) at all stations when using mass transfer combination (Tmax, Tmin, RH, u2) as models input, and the GWO-ELM hybrid model outperformed other models. Herein, the biogenic heuristic algorithm can effectively enhance the ELM performance in ETo estimation, it was strongly recommended for estimating daily ETo in the HID using the hybrid GWO-ELM model and mass transfer combination as input. The optimized hybrid algorithms, especially GWO-ELM, can accurately estimate daily ETo with limited meteorological data, which can provide scientific guidance for the development of precision agriculture in the HID. Abbreviations: ANN: artificial neural network; BP: back propagation neural network; CMA: China Meteorological Administration; D-T: Dalton; EL: elevation; ELM: extreme learning machine; ETo: reference evapotranspiration; GEP: gene expression programming; GP: genetic programming; GWO: gray wolf optimization; H-S: Hargreaves-Samani; MFO: moth flame optimization; ML: machine learning; P-M model: FAO-56 Penman-Monteith (P-M) model; P-T: Priestley-Taylor; PSO: particle swarm optimization; RF: random forest; R-O: Rohwer; SVM: support vector machine; SVR: support vector regression; WOA: whale optimization algorithm

Day ahead carbon emission forecasting of the regional National Electricity Market using machine learning methods

The vegetation index (VI) has been successfully used to monitor the growth and to predict the yield of agricultural crops. In this paper, a long-term observation was conducted for the yield prediction of maize using an unmanned aerial vehicle (UAV) and estimations of chlorophyll contents using SPAD-502. A new vegetation index termed as modified red blue VI (MRBVI) was developed to monitor the growth and to predict the yields of maize by establishing relationships between MRBVI- and SPAD-502-based chlorophyll contents. The coefficients of determination (R2s) were 0.462 and 0.570 in chlorophyll contents’ estimations and yield predictions using MRBVI, and the results were relatively better than the results from the seven other commonly used VI approaches. All VIs during the different growth stages of maize were calculated and compared with the measured values of chlorophyll contents directly, and the relative error (RE) of MRBVI is the lowest at 0.355. Further, machine learning (ML) methods such as the backpropagation neural network model (BP), support vector machine (SVM), random forest (RF), and extreme learning machine (ELM) were adopted for predicting the yields of maize. All VIs calculated for each image captured during important phenological stages of maize were set as independent variables and the corresponding yields of each plot were defined as dependent variables. The ML models used the leave one out method (LOO), where the root mean square errors (RMSEs) were 2.157, 1.099, 1.146, and 1.698 (g/hundred grain weight) for BP, SVM, RF, and ELM. The mean absolute errors (MAEs) were 1.739, 0.886, 0.925, and 1.356 (g/hundred grain weight) for BP, SVM, RF, and ELM, respectively. Thus, the SVM method performed better in predicting the yields of maize than the other ML methods. Therefore, it is strongly suggested that the MRBVI calculated from images acquired at different growth stages integrated with advanced ML methods should be used for agricultural- and ecological-related chlorophyll estimation and yield predictions.

The standard of living has significantly risen along with ongoing economic progress, but CO2 emissions have also been rising. The reduction in CO2 resulting from the daily activities of residents has become a crucial priority for every province. A relevant study on the carbon emissions of Hebei Province residents was conducted for this publication, aiming to provide a theoretical basis for the sustainable development of Hebei Province. The first part of the article calculates the carbon emissions of Hebei Province people from 2005 to 2020 using the emission factor method and the Consumer Lifestyle Approach (CLA). Secondly, the Logarithmic Mean Divisia Index (LMDI) decomposition approach is used to assess the components that influence both direct and indirect carbon emissions. Finally, the scenario analysis approach is employed in conjunction with the LEAP model to establish baseline, low-carbon, and ultra-low-carbon scenarios to predict the trend of residents’ carbon emissions in Hebei Province from 2021 to 2040. The results show that the total carbon emissions of residents in Hebei Province from 2005 to 2020 rose, from 77.45 million tons to 153.35 million tons. Income level, energy consumption intensity, and population scale are factors that contribute to the increase in direct carbon emissions, while consumption tendency factors have a mitigating effect on direct carbon emissions. Economic level, consumption structure, and population scale factors are factors that contribute to the increase in indirect carbon emissions, while energy consumption intensity and energy structure factors have a mitigating effect on indirect carbon emissions. The prediction results show that under the baseline scenario, the cumulative residents’ carbon emissions in Hebei Province will not reach a zenith from 2021 to 2040. However, under the low-carbon situation, the carbon emissions of residents in Hebei Province will peak in 2029, with a peak of 174.69 million tons, whereas under the ultra-low-carbon scenario, it will peak in 2028, with a peak of 173.27 million tons.

China's transportation industry is entering a stage of high-quality development. Carbon emissions and environmental protection issues have put pressure on the construction of a green and low-carbon transportation system, and the transportation industry has become one of the industries with the fastest growth in carbon emissions. Therefore, it is of great significance to study the influencing factors of carbon dioxide emissions in the transportation industry and predict its carbon emissions. This article first thoroughly analyzes the main sources of carbon emissions in the transportation industry, including nine major energy consumption sources such as coal, gasoline, and diesel, and obtains the carbon emission values ​​from 2000 to 2017. Secondly, a linear regression analysis was performed on 13 pre-selected influencing factors and CO2 emissions in the transportation industry. In order to obtain the potential similarities between the factors, factor 13 is divided into four categories: economic scale, population size, transportation structure, and energy consumption. Each category and factor analysis is divided into four potential factors. Third, a training model was established based on the data from 2000 to 2012. Four algorithms, neural network (BP), extreme learning machine (ELM), genetic algorithm optimized neural network (GA-BP), and genetic algorithm optimized extreme learning machine (GA-ELM) are used to predict 2013 to 2017 and compare the predicted value of its respective algorithm with the actual value. Finally, the results show that the genetic algorithm optimized extreme learning machine (GA-ELM) hybrid heuristic algorithm has the highest degree of fit between the predicted value and the true value, which further illustrates the carbon emissions of the hybrid heuristic algorithm in the transportation industry. For the superiority of the prediction, the study also shows that the four influencing factors seriously affect the carbon emissions of the transportation industry. Therefore, accelerating the upgrading of the transportation structure and changing the proportion of energy consumption will be important measures for the transportation sector to control carbon emissions in the next step, so as to promote the sustainable development of the transportation system.