Carbon emissions index decomposition and carbon emissions prediction in Xinjiang from the perspective of population-related factors, based on the combination of STIRPAT model and neural network

Carbon emission prediction models: A review

Amidst growing concerns over the greenhouse effect, especially its consequential impacts, establishing effective Carbon Emission Prediction Models (CEPMs) to comprehend and predict CO2 emission trends is imperative for climate change mitigation. A review of 147 Carbon Emission Prediction Model (CEPM) studies revealed three predominant functions-prediction, optimization, and prediction factor selection. Statistical models, comprising 75 instances, were the most prevalent among prediction models, followed by neural network models at 21.8 %. The consistent rise in neural network model usage, particularly feedforward architectures, was observed from 2019 to 2022. A majority of CEPMs incorporated optimized approaches, with 94.4 % utilizing metaheuristic models. Parameter optimization was the primary focus, followed by structure optimization. Prediction factor selection models, employing Grey Relational Analysis (GRA) and Principal Component Analysis (PCA) for statistical and machine learning models, respectively, filtered factors effectively. Scrutinizing accuracy, pre-optimized CEPMs exhibited varied performance, Root Mean Square Error (RMSE) values spanned from 0.112 to 1635 Mt, while post-optimization led to a notable improvement, the minimum RMSE reached 0.0003 Mt, and the maximum was 95.14 Mt. Finally, we summarized the pros and cons of existing models, classified and counted the factors that influence carbon emissions, clarified the research objectives in CEPM and assessed the applied model evaluation methods and the spatial and temporal scales of existing research.

Spatial-temporal characteristics and influencing factors of carbon emission in Chengdu-Chongqing area: an urban transportation perspective

The Chengdu-Chongqing twin-city economic circle is a vital growth pole and a new power source for Chinese high-quality development. Studying the spatial-temporal characteristics of carbon emissions and the role of factors affecting them under the transportation perspective is of great significance for this region to realize the carbon peak and carbon neutrality and to formulate carbon emission reduction policies. We use the exploring spatial data analysis (ESDA) and spatial regression model combined with the STIRPAT model, and research finding: (1) The total carbon emissions in the research area gradually increased from 2014 to 2020, but the growth rate showed a significant decline in 2019. (2) There is significant spatial heterogeneity of carbon emissions in the study area; the hotspot areas of total carbon emissions are in Chongqing and Chengdu, forming a high-low aggregation of carbon emissions. Per capita carbon emissions show a high trend in the southwest and a low in the northeast. (3) From the factors of transportation perspective, highway density and private vehicles have a positive impact on carbon emissions, and urban road areas and public transportation have a very significant inhibition of carbon emissions and a spatial spillover effect. (4) Other factors, such as population size, national economic development, urbanization level, and industrial structure, all have a positive effect on carbon emissions, and disposable income has a negative effect on carbon emissions.

Multidrivers of energy-related carbon emissions and its decoupling with economic growth in Northwest China

Northwest China has great natural resource endowment to develop its economy, but factors such as geographic remoteness and technological backwardness result in lower economic levels and higher carbon emissions. This study calculated the energy-related carbon emissions of five provinces in this region, and the evolutionary characteristics of energy-related carbon emissions were analysed from the spatiotemporal perspective. The Kaya identity was applied to decompose the factors influencing energy-related carbon emissions, and the logarithmic mean divisia index (LMDI) and refined Laspeyres index were combined to calculate the role of each influencing factor on energy-related carbon emissions. Finally, the Tapio and LMDI models were used to analyse the evolution of the decoupling relationship between energy-related carbon emissions and economic growth and the role of various influencing factors. The energy-related carbon emissions in Northwest China showed an increasing trend. In terms of influencing factors, economic growth and urban expansion had the highest contributions to carbon emissions and decoupling inhibition, whereas population agglomeration had the opposite effect. Northwest China showed great decoupling trends between energy-related carbon emissions and economic growth.

The trajectory of carbon emissions and terrestrial carbon sinks at the provincial level in China

Global greenhouse gas emission, major factor driving climate change, has been increasing since nineteenth century. STIRPAT and CEVSA models were performed to estimate the carbon emission peaks and terrestrial ecosystem carbon sinks at the provincial level in China, respectively. Utilizing the growth characteristics and the peak time criteria for the period 1997-2019, the patterns of energy consumption and CO2 emissions from 30 Chinese provinces are categorized into four groups: (i) one-stage increase (5 provinces), (ii) two-stage increase (10 provinces), (iii) maximum around 2013 (13 provinces), and (iv) maximum around 2017 (2 provinces). According to the STIRPAT model, the anticipated time of peak CO2 emissions for Beijing from the third group is ~ 2025 in both business-as-usual and high-speed scenarios. For Xinjiang Uygur autonomous region from the first group and Zhejiang province from the second group, the expected peak time is 2025 to 2030. Shaanxi province from the fourth group is likely to reach carbon emission peak before 2030. The inventory-based estimate of China's terrestrial carbon sink is ~ 266.2 Tg C/a during the period 1982-2015, offsetting 18.3% of contemporary CO2 emissions. The province-level CO2 emissions, peak emissions and terrestrial carbon sinks estimates presented here are significant for those concerned with carbon neutrality.

Which model is more efficient in carbon emission prediction research? A comparative study of deep learning models, machine learning models, and econometric models

Accurately predicting future carbon emissions is of great significance for the government to scientifically promote carbon emission reduction policies. Among the current technologies for forecasting carbon emissions, the most prominent ones are econometric models and deep learning, but few works have systematically compared and analyzed the forecasting performance of the methods. Therefore, the paper makes a comparison for deep learning model, machine learning model, and the econometric model to demonstrate whether deep learning is an efficient method for carbon emission prediction research. In model mechanism, neural network for deep learning refers to an information processing model established by simulating biological neural system, and the model can be further extended through bionic characteristics. So the paper further optimizes the model from the perspective of bionics and proposes an innovative deep learning model based on the memory behavior mechanism of group creatures. Comparison results show that the prediction accuracy of the heuristic neural network is higher than that of the econometric model. Through in-depth analysis, the heuristic neural network is more suitable for predicting future carbon emissions, while the econometric model is more suitable for clarifying the impact of influencing factors on carbon emissions.

Industrial carbon emission efficiency prediction and carbon emission reduction strategies based on multi-objective particle swarm optimization-backpropagation: A perspective from regional clustering

Against the backdrop of global climate change, industrial carbon emission reduction has become an important pathway to for global low-carbon development. This study constructs a framework of geographic spatial constraints regionalization and multi-objective machine learning to predict future industrial carbon emission efficiency (ICEE) and explore strategies for carbon emission reduction. Firstly, the ICEE of 285 Chinese cities were calculated by the super-efficiency slacks-based measure. Secondly, the cities were classified into four ICEE level regions through the spatially constrained multivariate clustering. Next, the multi-objective particle swarm optimization-BP (MOPSO-BP) model was constructed to predict the future trends of ICEE in the four regions. Finally, the geographical detector and multi-scale geographically weighted regression were employed for exploring driving force and carbon emission reduction strategies in different regions. The results show that most cities had low or medium ICEE, while super efficiency cities were mainly distributed in the east coastal areas. The prediction performance of the MOPSO-BP model for the four regions was better than the ordinary particle swarm optimization-BP and traditional BP model. Except for the Agricultural Production Region, there is considerable room for improving the ICEE of other regions over the next decade. Macroeconomic and microeconomic development have a global effect in promoting regional ICEE improvement, urban construction shows a promoting or inhibiting effect in different regions, and information technology has significant spatial heterogeneity in its influence within each region. The analysis framework developed in the study is a reliable solution for managing and planning ICEE and provides constructive suggestions for future regional low-carbon development.

Research on carbon emission quota allocation scheme under "Double Carbon" target: a case study of industrial sector in Henan Province

To achieve China's "Double Carbon" target, overall carbon emissions should be effectively controlled, and carbon emission quota (CEQ) allocation is an important tool. This study develops carbon emission prediction, CEQ allocation, and scheme feasibility evaluation models based on the principles of fairness, efficiency, and economy. The purpose is to propose a suitable CEQ allocation scheme for the Industrial Sector in Henan Province (ISHP). The results show that (1) the allocation model combining the technique for order preference by similarity to ideal solution (TOPSIS) and the zero-sum gains DEA (ZSG-DEA) can trade off the fairness and efficiency principles. (2) The reallocation scheme has an environmental Gini coefficient of 0.393 (< 0.4), which maximizes efficiency while lowering the abatement costs by 126.268 billion yuan, making it an ideal scheme that considers multiple principles. (3) CEQ should be reduced in 7 subsectors of ISHP while increasing in 33 others. Carbon emissions from these 7 subsectors are high, and CEQ should be reduced in accordance with the fairness principle. Even if their abatement costs are high and CEQ rises according to the efficiency principle, the increase is much smaller than the decrease. The findings are useful for optimizing the CEQ allocation under the "Double Carbon" target.

Links among population aging, economic globalization, per capita CO2 emission, and economic growth, evidence from East Asian countries

Population aging, economic globalization, and economic growth simultaneously cause changes in environmental quality, but so far no studies have integrated these key factors into the same environmental policy framework. Thus, this study uses the more robust Westerlund cointegration test and the augmented mean group (AMG) estimator (robust to cross-sectional dependence (CD), heterogeneity, and endogeneity) to estimate the long-term relationship between population aging, economic globalization, economic growth, and per capita carbon emissions in East Asian countries during the period 1975-2018. The analysis results reflect that population aging significantly reduces the long-term per capita carbon emissions of specific East Asian countries. However, energy generation and economic globalization make significant contributions to long-run per capita carbon emissions. Moreover, the impact of economic growth on long-term per capita carbon emissions is significantly positive, while the impact of square of economic growth on long-run per capita carbon emissions is significantly negative, thus validating the inverted U-shaped environmental Kuznets curve (EKC) hypothesis for specific East Asian countries. The results of the causality test indicated a two-way causality between energy generation and per capita carbon dioxide emission, supporting the feedback hypothesis. There is also a two-way causal relationship between aging population and per capita carbon dioxide emission. Policy recommendations are discussed in response to the empirical findings of this study.

Forecasting the carbon emissions in Hubei Province under the background of carbon neutrality: a novel STIRPAT extended model with ridge regression and scenario analysis

The impact of global greenhouse gas emissions is increasingly serious, and the development of green low-carbon circular economy has become an inevitable trend for the development of all countries in the world. To achieve emission peak and carbon neutrality is the primary goal of energy conservation and emission reduction. As the core province in central China, Hubei Province is under prominent pressure of carbon emission reduction. In this paper, the future development trend of carbon emissions is analyzed, and the emission peak value and carbon peak time in Hubei Province is predicted. Firstly, the generalized Divisia index method (GDIM) model is proposed to determine the main influencing factors of carbon emissions in Hubei Province. Secondly, based on the main influencing factors identified, a novel STIRPAT (Stochastic Impacts by Regression on Population, Affluence, and Technology) extended model with ridge regression is established to predict carbon emissions. Thirdly, the scenario analysis method is used to set the variables of the STIRPAT extended model and to predict the emission peak value and carbon peak time in Hubei Province. The results show that Hubei Province's carbon emissions peaked first in 2025, with a peak value of 361.81 million tons. Finally, according to the prediction results, the corresponding suggestions on carbon emission reduction are provided in three aspects of industrial structure, energy structure, and urbanization, so as to help government establish a green, low-carbon, and circular development economic system and achieve the industry's cleaner production and sustainable development of society.

Analysis on the dynamic evolution of the equilibrium point of "carbon emission penetration" for energy-intensive industries in China: based on a factor-driven perspective

In order to achieve the carbon peaking and carbon neutrality goals, energy-intensive industries in China, as the main sectors of energy consumption and carbon emissions, had huge pressure to reduce emissions. In addition, the reduction of vegetation area led to a decline in carbon sink capacity, which further exacerbated the imbalance of mutual penetration between carbon source and carbon sink. Therefore, this article considered the role of carbon source and carbon sink and defined and calculated the "carbon emission penetration" (CEP) of the six energy-intensive industries from 2001 to 2020. The KAYA formula and the LMDI method were used to decompose the driving factors of CEP in the three aspects of scale, intensity, and structure. The combined model of STIRPAT and the environmental Kuznets curve (EKC) was used to simulate and analyze the equilibrium points of energy-intensive industries in China from the perspective of factor driving. The analysis results indicated that there were differences in the fluctuation trend of CEP in the six energy-intensive industries, which can be divided into three types: "two-stage growth," "steady growth," and "single peak." Secondly, the driving factors from the three aspects of scale, intensity, and structure-emission intensity (CE), energy consumption intensity (EI), industrial structure (IS), economic scale (GP), and carbon sequestration scale (PCA)-had differences in industry and time dimensions. And the realization time of the CEP equilibrium points of six industries showed a three-level gradient feature significantly. This can provide some reference for the low-carbon transformation of six energy-intensive industries and optimization of China's environmental management under the carbon peaking and carbon neutrality goals.

Carbon sinks and carbon emissions balance of land use transition in Xinjiang, China: differences and compensation

With the continuous enhancement of human activities, the contradiction between regional development and ecological protection is prominent in the ecologically fragile arid areas. It is of great significance for regional sustainable development to understand the ecological supply and demand problems caused by transformation of land using and formulate ecological compensation scheme scientifically. This study takes Xinjiang in China as the research area. It explores the land use transition characteristics and the changes in carbon supply and demand of Xinjiang using methods such as GIS spatial analysis and modified comparative ecological radiation forcing. Finally, the ecological compensation scheme is studied based on the theory of ecological radiation. The research shows that (I) in the study chronology, most of the areas produced only one change in land use. Land use is gradually developing towards the direction of ecological protection. After 2000, grassland recovered well, and 14,298 km² of other ecological land was transformed into grassland. (II) The change in the carbon sink of the Xinjiang ecosystem first decreased and then increased, and the ecological deficit area started to appear after 2010. The growth of grassland and cropland areas is essential to enhance the carbon sink capacity of arid zones. (III) The amount of ecological compensation in Xinjiang is 31.47 * 10⁸ yuan, and the proportion of the amount received by ecological compensation areas is related to the distance between the supply and demand areas, the amount of carbon sequestration, and the area of the region. This study provides a reference for achieving the healthy development of sustainable land use ecosystems in arid zones.

Spatial Pattern Analysis of Xinjiang Tourism Resources Based on Electronic Map Points of Interest

This study considers the Point of Interest data of tourism resources in Xinjiang and studies their spatial distribution by combining geospatial analysis methods, such as the average nearest neighbor index, standard deviation ellipse, kernel density analysis, and hotspot analysis, to explore their spatial distribution characteristics. Based on the analysis results, the following conclusions are made. Different categories of tourism resource sites have different spatial distributions, and all categories of tourism resources in Xinjiang are clustered in Urumqi city. The geological landscape resource sites are widely distributed and have a ring-shaped distribution in the desert area of southern Xinjiang. The biological landscape resources are distributed in a strip along the Tianshan Mountains. The water landscape resources are concentrated in the northern Xinjiang area. The site ruins are mostly distributed in the western region of Xinjiang. The distributions of the architectural landscape and entertainment and shopping resources are highly coupled with the distribution of cities. The distributions of the six categories of tourism resource points are in the northeast-southwest direction. The centripetal force and directional nature of the resource points of the water landscape are not obvious. The remaining five categories of resource points have their own characteristics. The distribution of resources in the site ruins is relatively even, and there are many hotspot areas in the geomantic and architectural landscapes, which are mainly concentrated in Bazhou and other places. The biological landscape has many cold-spot areas, distributed in areas such as Altai in northern Xinjiang and Hotan in southern Xinjiang. The remaining four categories have cold-spot and hotspot areas with different distributions. Tourism is an important thrust for economic development. The study of the distribution of tourism resources on the spatial distribution of tourism resources has clear guidance for later tourism development, can help the tourism industry optimize the layout of resources, and can promote tourism resources to achieve maximum benefits. The government can implement effective control and governance.

Carbon Emission Prediction Model and Analysis in the Yellow River Basin Based on a Machine Learning Method

Excessive carbon emissions seriously threaten the sustainable development of society and the environment and have attracted the attention of the international community. The Yellow River Basin is an important ecological barrier and economic development zone in China. Studying the influencing factors of carbon emissions in the Yellow River Basin is of great significance to help China achieve carbon peaking. In this study, quadratic assignment procedure regression analysis was used to analyze the factors influencing carbon emissions in the Yellow River Basin from the perspective of regional differences. Accurate carbon emission prediction models can guide the formulation of emission reduction policies. We propose a machine learning prediction model, namely, the long short-term memory network optimized by the sparrow search algorithm, and apply it to carbon emission prediction in the Yellow River Basin. The results show an increasing trend in carbon emissions in the Yellow River Basin, with significant inter-provincial differences. The carbon emission intensity of the Yellow River Basin decreased from 5.187 t/10,000 RMB in 2000 to 1.672 t/10,000 RMB in 2019, showing a gradually decreasing trend. The carbon emissions of Qinghai are less than one-tenth of those in Shandong, the highest carbon emitter. The main factor contributing to carbon emissions in the Yellow River Basin from 2000 to 2010 was GDP per capita; after 2010, the main factor was population. Compared to the single long short-term memory network, the mean absolute percentage error of the proposed model is reduced by 44.38%.