Short-term prediction of carbon emissions based on the EEMD-PSOBP model

Carbon price prediction in China based on ensemble empirical mode decomposition and machine learning algorithms

The carbon emission trading market is crucial for reducing emissions, conserving energy, and enhancing the climate and environment. Studying carbon price forecasting can encourage China's involvement in international carbon financial instruments trading and promote the development of China's pilot carbon markets. This study employs ensemble empirical mode decomposition (EEDM) to convert the initial carbon price, which is a non-stationary signal, into several intrinsic mode functions and residual terms. Subsequently, hybrid machine learning methods are used to estimate the carbon price. For empirical analysis, the three main carbon markets with large trading volumes, Guangdong, Hubei, and Shenzhen, are selected from the eight pilot carbon markets. To achieve short-term carbon price prediction, a hybrid model combining a genetic algorithm (GA) and back propagation (BP) neural network is used. This model effectively addresses the issue of neural networks falling into local optimization. The results indicate that the hybrid algorithm is significantly superior to other algorithms for short-term prediction. Additionally, another hybrid model, combining the least squares support vector machine (LSSVM) and particle swarm optimization (PSO) algorithms, is employed to reduce forecast error while minimizing search parameters, which is not possible with traditional neural network models.

Leveraging the trend analysis for modeling of the greenhouse gas emissions associated with coal combustion

In this paper, it is aimed, for the first time, at deriving simple models, leveraging the trend analysis in order to estimate the future greenhouse gas emissions associated with coal combustion. Due to the expectations of becoming the center of global economic development in the future, BRICS-T (Brazil, the Russian Federation, India, China, South Africa, and Turkiye) countries are adopted as cases in the study. Following the models' derivation, their statistical validations and estimating accuracies are also tested through various metrics. In addition, the future greenhouse gas emissions associated with coal combustion are estimated by the derived models. The results demonstrate that the derived models can be successfully used as a tool for estimating the greenhouse gas emissions associated with coal combustions with accuracy ranges from at least 90% to almost 98%. Moreover, the estimating results show that the total amount of greenhouse gas emissions associated with coal combustions in the relevant countries and in the world will increase to 14 BtCO2eq and 19 BtCO2eq by 2035, with an annual growth of 2.39% and 1.71%, respectively. In summary, the current study's findings affirm the usefulness of trend analysis in deriving models to estimate greenhouse gas emissions associated with coal combustion.

A multi-factor combination prediction model of carbon emissions based on improved CEEMDAN

As the global greenhouse effect intensifies, carbon emissions are gradually becoming a hot topic of discussion. Accurate carbon emissions prediction is an important foundation to realize carbon neutrality and peak carbon dioxide emissions. To accurately predict carbon emissions, a multi-factor combination prediction model based on improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), bidirectional long short-term memory optimized by lemurs optimizer (LOBiLSTM) and least squares support vector machine optimized by lemurs optimizer (LOLSSVM), named ICEEMDAN-LOBiLSTM-LOLSSVM, is proposed. Firstly, the influencing factors of carbon emissions are selected by Spearman correlation coefficient, and carbon emissions are decomposed into intrinsic mode functions (IMFs) by ICEEMDAN. Secondly, the influencing factors and IMFs are input into LOBiLSTM and LOLSSVM respectively for prediction. Then, the point prediction results are obtained by weighting the prediction results of LOBiLSTM and LOLSSVM. Finally, probability density function of point prediction error is calculated by kernel density estimation, and the interval prediction results are calculated according to different confidence intervals. Carbon emissions of China and Germany are selected to verify the superiority of ICEEMDAN-LOBiLSTM-LOLSSVM. The experiment shows that RMSE, MAE, MAPE, and R2 of the proposed model are 0.4468, 0.3612, 0.0120, and 0.9839 respectively for China, which is the best among the nine models, as well as for Germany.

Prediction and balanced allocation of thermal power carbon emissions from a provincial perspective of China

Carbon control in the thermal power generation industry is crucial for achieving the overall carbon peak target. How to predict, evaluate, and balance the allocation of inter provincial carbon emissions has a significant impact on the decision-making of reasonable allocation of inter provincial carbon emissions in the target year. Therefore, this paper uses Monte Carlo-ARIMA-BP neural network and ZSG-DEA model to conduct temporal trend prediction and carbon emission quota allocation research. We propose the "intra provincial and inter provincial" framework for carbon emissions trading in thermal power plants, which aims to break through the barriers in carbon emission rights exchange among provinces. The conclusions are as follows: (1) the growth trend of carbon emissions from thermal power is gradually slowing down and is expected to peak before 2030. (2) Inner Mongolia, Jiangsu, and Shandong have high input-output efficiency, and are all the main output provinces for carbon emission quota allocation. After being adjusted using the ZSG-DEA model, they can still be at the forefront of efficiency. (3) The "intra provincial and inter provincial" framework for carbon emissions trading can effectively predict and allocate the carbon emission demand of each province from time and space dimensions, balance the carbon emission rights and interests of each province, and provide forward-looking planning suggestions for inter provincial carbon emission rights exchange.

Multi-step prediction of carbon emissions based on a secondary decomposition framework coupled with stacking ensemble strategy

Accurate prediction of carbon emissions is vital to achieving carbon neutrality, which is one of the major goals of the global effort to protect the ecological environment. However, due to the high complexity and volatility of carbon emission time series, it is hard to forecast carbon emissions effectively. This research offers a novel decomposition-ensemble framework for multi-step prediction of short-term carbon emissions. The proposed framework involves three main steps: (i) data decomposition. A secondary decomposition method, which is a combination of empirical wavelet transform (EWT) and variational modal decomposition (VMD), is used to process the original data. (ii) Prediction and selection: ten models are used to forecast the processed data. Then, neighborhood mutual information (NMI) is used to select suitable sub-models from candidate models. (iii) Stacking ensemble: the stacking ensemble learning method is innovatively introduced to integrate the selected sub-models and output the final prediction results. For illustration and verification, the carbon emissions of three representative EU countries are used as our sample data. The empirical results show that the proposed framework is superior to other benchmark models in predictions 1, 15, and 30 steps ahead, with the mean absolute percentage error (MAPE) of the proposed framework being as low as 5.4475% in Italy dataset, 7.3159% in France dataset, and 8.6821% in Germany dataset.

Simulation analysis of carbon peak path in China from a multi-scenario perspective: evidence from random forest and back propagation neural network models

China faces tough challenges in the process of low-carbon transformation. To determine whether China can achieve its new 2030 carbon peaking and carbon intensity reduction commitments, accurate prediction of China's CO₂ emissions is vital. In this paper, the random forest (RF) model was used to screen 26 carbon emission influencing factors, and seven indicators were selected as key variables for prediction. Subsequently, a three-layer back propagation (BP) neural network was constructed to forecast China's CO₂ emissions and intensity from 2020 to 2040 under the 13th Five-Year Plan, 14th Five-Year Plan, energy optimization, technology breakthrough, and dual control scenarios. The results showed that energy structure factors have the most significant impact on China's CO₂ emissions, followed by technology level, and economic development factors are no longer the main drivers. Under the 14th Five-Year Plan scenario, China can achieve its carbon peaking on time, reaching 10,434.082 Mt CO₂ emissions in 2030. Although the new commitment to intensity reduction (over 65%) under this scenario cannot be achieved, the 14th Five-Year Plan can bring about 73.359 and 539.710 Mt of CO₂ reduction in 2030 and 2040 respectively, compared to the 13th Five-Year Plan. Under the technology breakthrough and dual control scenarios, China will meet its new commitments ahead of schedule, with the dual control scenario being the optimal pathway for CO₂ emissions to peak at 9860.08 Mt in 2025. It is necessary for Chinese policy makers to adjust their current strategic planning, such as accelerating the transformation of energy structure and increasing investment in R&D to achieve breakthroughs in green technologies.

A daily carbon emission prediction model combining two-stage feature selection and optimized extreme learning machine

Global warming caused by increased carbon emissions is a common challenge for all mankind. Facing the unprecedented pressure of carbon emission reduction, it is particularly important to grasp the dynamics of carbon emission in time and accurately. This paper proposes a novel daily carbon emission forecasting model. Firstly, the daily carbon emission data is decomposed into a series of completely noise-free mode functions by improved complete ensemble empirical mode decomposition method with adaptive noise (ICEEMDAN). Then, a two-stage feature selection method composed of partial autocorrelation function (PACF) and ReliefF is applied to select appropriate input variables for the next prediction process. Finally, the extreme learning machine optimized by improved sparrow search algorithm (ISSA-ELM) is used to predict. The empirical results show that the proposed two-stage feature selection method can further improve the prediction accuracy. After two-stage feature selection, the values of R², MAPE, and RMSE were improved by 0.55%, 30.23%, and 28.46%, respectively. It can also be found that ISSA has good optimization performance. By combining with ISSA, R², MAPE, and RMSE improved by 7.60%, 31.97%, and 44.79%, respectively. Therefore, the proposed model can provide a valuable reference for the formulation of carbon emission reduction policies and future carbon emission prediction research.

A novel short-term carbon emission prediction model based on secondary decomposition method and long short-term memory network

Grasping the dynamics of carbon emission in time plays a key role in formulating carbon emission reduction policies. In order to provide more accurate carbon emission prediction results for planners, a novel short-term carbon emission prediction model is proposed. In this paper, the secondary decomposition technology combining ensemble empirical mode decomposition (EEMD) and variational mode decomposition (VMD) is used to process the original data, and the partial autocorrelation function (PACF) is applied to select the optimal model input. Then, the long short-term memory network (LSTM) is chosen for prediction. The secondary decomposition algorithm is innovatively introduced into the field of carbon emission prediction, and the empirical results illustrate that the secondary decomposition technology can further improve the prediction accuracy. Combined with the secondary decomposition, the R2, MAPE, and RMSE of the model are improved by 2.20%, 43.08%, and 36.92% on average. And the proposed model shows excellent prediction accuracy (R2 = 0.9983, MAPE = 0.0031, RMSE = 118.1610) compared with other 12 comparison models. Therefore, this model not only has potential value in the formulation of carbon emission reduction plans, but also provides a valuable reference for future carbon emission forecasting research.

Carbon Emissions in the Yellow River Basin: Analysis of Spatiotemporal Evolution Characteristics and Influencing Factors Based on a Logarithmic Mean Divisia Index (LMDI) Decomposition Method

The “14th Five-Year Plan” period is a critical period and a window to obtain emission peak and carbon neutrality in China. The Yellow River Basin, a vital location for population activities and economic growth, is significant to China’s emission peak by 2030. Analyzing carbon emissions patterns and decomposing the influencing factors can provide theoretical support for reducing carbon emissions. Based on the energy consumption data from 2000–2019, the method recommended by Intergovernmental Panel on Climate Change (IPCC) is used to calculate the carbon emissions in the Yellow River Basin. The Logarithmic Mean Divisia Index (LMDI) decomposition method decomposes the influence degree of each influencing factor. The conclusions are as follows: First, The Yellow River Basin has not yet reached the peak of carbon emissions. Regional carbon emissions trends are different. Second, Shandong, Shanxi, Henan and Inner Mongolia consistently ranked in the top four in total carbon emissions, with low carbon emission efficiency. Third, Economic development has the most significant contribution to carbon emissions; other factors have various effects on nine provinces.

Urban Sprawl and Carbon Emissions Effects in City Areas Based on System Dynamics: A Case Study of Changsha City

Climate change is a global problem facing mankind, and achieving peak CO2 emissions and carbon neutrality is an important task for China to respond to global climate change. The quantitative evaluation of the trends of urban energy consumption and carbon emissions is a premise for achieving this goal. Therefore, from the perspective of urban expansion, this paper analyzes the complex relationship between the mutual interactions and feedback between urban population, land expansion, economic growth, energy structure and carbon emissions. STELLA simulation software is used to establish a system dynamics model of urban-level carbon emissions effects, and Changsha city is used for the case study. The simulated outputs of energy consumption and carbon emissions cover the period from 1949 to 2016. From 1949 to 2016, Changsha’s total energy consumption and carbon emissions per capita have continuously grown. The total carbon emissions increased from 0.66 Mt-CO2 to 60.95 Mt-CO2, while the per capita carbon emissions increased from 1.73 t-CO2/10,000 people to 18.3 Mt-CO2/10,000 people. The analysis of the structure of carbon emissions shows that the industrial sector accounted for the largest proportion of emissions, but it had gradually dropped from between 60% and 70% to about 40%. The carbon emissions of residential and commercial services accounted for less than 25%, and the proportion of transportation carbon emissions fluctuated greatly in 2013 and 2016. From the perspective of carbon emissions effects, carbon emissions per unit of GDP had a clear downward trend, from 186.11 t-CO2/CNY104 to 1.33 t-CO2/CNY104, and carbon emissions per unit of land showed two inflection points: one in 1961 and the other in 1996. The general trend showed an increase first, followed by a decrease, then a stabilization. There is a certain linear correlation between the compactness of urban shape and the overall trend of carbon emissions intensity, while the urban shape index has no linear correlation with the growth rate of carbon emissions. The carbon emissions assessment model constructed in this paper can be used by other municipalities, and the assessment results can provide guidance for future energy planning and decision making.

Impact of uncertainty on regional carbon peak paths: an analysis based on carbon emissions accounting, modeling, and driving factors

Regional carbon emission paths have an important impact on the realization of China's carbon emission peak target. Due to the uncertainty of future development model, the change of carbon emissions will also face uncertainty, which will make achieving the peak target challenging. Taking Shandong, Henan, and Guangdong, three of China's most populous provinces, as examples, this study analyzed the impacts of uncertainties in carbon accounting principles, driving factors, and simulation mechanism on achieving the peak target. The results show that (1) under the baseline scenario, the accounting principles based on primary energy consumption and IPCC sector consumption will make the peaking time of Guangdong be evaluated as 2018 and 2030, respectively, and the simulation based on IPCC sector accounting will advance the peaking time of Shandong by at least 5 years, while Henan will be less affected. (2) When considering the impact of the energy structure, Guangdong and Henan are estimated to peak in 2011 and 2018, while without considering the impact of the energy structure, the peak in the two provinces may be after 2035. Energy structure has no effect on the estimation of peaking time for Shandong. In addition, the k value in the ridge regression method also has no effect on the peaking time for the three provinces; it only affects the simulations of annual carbon emissions. This study also presented the carbon emission trajectory under different scenarios; from the simulation results, environmental regulation measures such as accelerating industrial structure transformation and increasing energy consumption intensity may help to achieve the peak carbon emission target as soon as possible. It also suggests that uncertainty should be included in future carbon assessments to present a more complete carbon emission trajectory.