Global warming is a major environmental issue facing humanity, and the resulting climate change has severely affected the environment and daily lives of people. China attaches great importance to and actively responds to climate change issues. In order to achieve the “dual carbon” goal, it is necessary to clearly define the emission reduction path and scientifically predict future carbon emissions, which is the basis for setting emission reduction targets. To ensure the accuracy of data, this study applies the emission coefficient method to calculate the carbon emissions from the energy consumption in 30 provinces, regions, and cities in China from 1997 to 2021. Considering the spatial correlation between different regions in China, we propose a new machine learning prediction model that incorporates spatial weighting, namely, an LSTM-CNN combination model with spatial weighting. The spatial weighting explains the spatial correlation and the combined model is used to analyze the carbon emissions in the 30 provinces, regions, and cities of China from 2022 to 2035 under different scenarios. The results show that the LSTM-CNN combination model with four convolutional layers performs the best. Compared with other models, this model has the best predictive performance, with an MAE of 8.0169, an RMSE of 11.1505, and an $R^2$ of 0.9661 on the test set. Based on different scenario predictions, it is found that most cities can achieve carbon peaking before 2030. Some cities need to adjust their development rates based on their specific circumstances in order to achieve carbon peaking as early as possible. This study provides a research direction for deep learning time series forecasting and proposes a new predictive method for carbon emission forecasting.

This article conducts a computable general equilibrium (CGE) model to investigate the impacts of a carbon tax on economy at province levels in China since China features significantly differentiated development modes across regions. Three representative provinces including Henan, Fujian, and Chongqing are selected as the sample. The empirical results indicate that carbon tax is an efficient policy to reduce carbon emissions accompanied with negative impact on provincial economy. To cushion the negative impacts of carbon tax, a moderate carbon tax rate and carbon tax recycling policy are recommended according to the simulation results.

This paper investigates the development trends and variation characteristics of China’s economy, energy consumption and carbon emissions from 2007 to 2030, and the impacts on China’s economic growth, energy consumption, and carbon emissions under the carbon tax policy scenarios, based on the dynamic computable general equilibrium (CGE) model. The results show that during the simulation period, China’s economy will keep a relatively high growth rate, but the growth rate will slow down under the benchmark scenario. The energy consumption intensity and the carbon emissions intensity per unit of Gross Domestic Product (GDP) will continually decrease. The energy consumption structure and industrial structure will gradually optimize. With the economic growth, the total energy consumption will constantly increase, and the carbon dioxide emissions are still large, and the situation of energy-saving and emission-reduction is still serious. The carbon tax is very important for energy-saving and emission-reduction and energy consumption structure optimization, and the effect of the carbon tax on GDP is small. If the carbon tax could be levied and the enterprise income tax could be reduced at the same time, the dual goals of reducing energy consumption and carbon emissions and increasing the GDP growth can be achieved. Improving the technical progress level of clean power while implementing a carbon tax policy is very meaningful to optimize energy consumption structure and reduce the carbon emissions, but it has some offsetting effect to reduce energy consumption.

Improving urban ecological efficiency is an integral part of ecological protection and high-quality development of the Yellow River Basin. We used the super-efficiency slacks-based model with unexpected output to measure the ecological efficiency of 62 prefecture-level cities in the Yellow River Basin from 2005 to 2018. Its spatial distribution characteristics and convergence are discussed. The influencing factors and spatial spillovers of the ecological efficiency are assessed through the spatial Dubin model. The results show that: 1) The ecological efficiency is highest in cities in the lower reaches of the Yellow River Basin, mid-level in the upper reaches, and lowest in the middle reaches. 2) There is no σ convergence in the ecological efficiency of the Yellow River Basin, but there is absolute β convergence and conditional β convergence. 3) Economic development, financial development, and technological innovation significantly promote ecological efficiency, and the spatial spillover effects are significant. Increased connection with the outside world can significantly improve ecological efficiency, but there is no apparent spatial spillover effect for these connections. The industrial structure and urbanization rate reduced ecological efficiency and have a significant negative spillover effect. The energy consumption structure reduces the level of ecological efficiency, and the spillover effect is not significant.

This paper constructs an Economy-Energy-Emissions (3E) System Dynamics Model using the megacity of Beijing, China, as an example, to estimate the effects of different policy scenarios (including three single-policy scenarios and four combined-policy scenarios) on the core variables of Beijing's 3E system from 2021 to 2035. The results suggest two main points. (1) Following the current development trend, the proportion of the GDP represented by the added value of advanced high-precision industries (Gao Jing Jian in Chinese) will only be 43% in 2035, implying a limited role in promoting economic growth. Despite effective control of total energy consumption, fossil energy's share of total consumption will reach 57% by 2035, hindering the process of making the energy consumption structure cleaner and leading to failure to achieve the targeted inflection point in CO₂ emissions by 2025. PM_2.5 control shows some successful results and will decrease to 19 μ g/m³ in 2035. However, a gap compared to other world-class cities remains. (2) The implementation of a single policy for either industrial structure optimization, energy structure transformation, or emissions control cannot simultaneously meet the goal of high-quality coordinated development of Beijing's 3E system, whereas the comprehensive implementation of policies in all three dimensions is demonstrably effective.