Extended STIRPAT Model Research Articles

Does county urban shrinkage in China affect the concentration of lung-accessible particulate matter? An analysis from spatial effects and EKC perspectives.

The environmental effects of urban shrinkage have gradually attracted academic attention. Based on spatial effects and EKC perspectives, this study constructs an environmental impact assessment framework and examines the impact of urban shrinkage on the concentration of lung-accessible particulate matter at the county level in China from 2013 to 2020. The results show that, from a two-dimensional perspective in space and time, lung-accessible particulate matter concentrations show a decreasing trend in the time series and an obvious autocorrelation feature in space. Urban shrinkage can affect lung-accessible particulate matter concentrations through spatial effects. Through direct effects, urban shrinkage promotes the increase of lung-accessible particulate matter concentrations. Through spillover effects, urban shrinkage suppresses the growth of lung-accessible particulate matter concentrations. The effect of urban shrinkage on lung-accessible particulate matter concentration is nonlinear (EKC). This may be the result of the "siphon effect." Furthermore, in the extended STIRPAT model, it was found that population and economic and technological factors differentially affect lung-accessible particulate matter concentrations in shrinking cities. This study gives a new idea and insight into the changes in environmental pollution in shrinking cities.

CNN-GRU-Attention Neural Networks for Carbon Emission Prediction of Transportation in Jiangsu Province

With the increasing energy use and carbon emissions in the transportation industry, its impact on the greenhouse effect is gradually being recognized. Therefore, this study aims to explore the achievement of carbon emission peak and carbon neutrality in transportation through prediction. The research employs a deep learning model, the CNN-GRU-Attention model, to predict carbon emissions in the transportation industry in Jiangsu, China. We select influencing factors through an extended STIRPAT model coupled with Lasso regression, and construct the CNN-GRU-Attention traffic carbon emission prediction model according to data indicators from 1995 to 2021. The model predicts carbon emissions from the transportation industry in Jiangsu Province between 2022 and 2035 under six distinct scenarios and proposes corresponding emission reduction strategies. The results show that the model in this study has higher prediction accuracy compared with other models, with a mean absolute error (MAE) of 0.061582, root mean square error (RMSE) of 0.085025, and R2 of 0.91609 on the test set. Scenario-based predictions reveal that emission peak in the transportation industry in Jiangsu Province can be achieved under the clean development and comprehensive low-carbon scenarios, with technological innovation being the primary driver of low-carbon emission reductions. This study provides a novel approach for forecasting carbon emissions from the transportation industry and explores the implementation path of emission peak through this method.

Carbon Emission Analysis of Low-Carbon Technology Coupled with a Regional Integrated Energy System Considering Carbon-Peaking Targets

Analyzing the carbon emission behavior of a regional integrated energy system (RIES) is crucial for aligning with carbon-peaking development strategies and ensuring compliance with carbon-peaking implementation pathways. This study focuses on a building cluster area in Shanghai, China, aiming to provide a comprehensive analysis from both macro and micro perspectives. From a macro viewpoint, an extended STIRPAT model, incorporating the environmental Kuznets curve, is proposed to predict the carbon-peaking trajectory in Shanghai. This approach yields carbon-peaking implementation pathways for three scenarios: rapid development, stable development, and green development, spanning the period of 2020–2040. At a micro scale, three distinct RIES system configurations—fossil, hybrid, and clean—are formulated based on the renewable energy penetration level. Utilizing a multi-objective optimization model, this study explores the carbon emission behavior of a RIES while adhering to carbon-peaking constraints. Four scenarios of carbon emission reduction policies are implemented, leveraging green certificates and carbon-trading mechanisms. Performance indicators, including carbon emissions, carbon intensity, and marginal emission reduction cost, are employed to scrutinize the carbon emission behavior of the cross-regional integrated energy system within the confines of carbon peaking.

An Empirical Analysis of the Impact of Urbanization and Consumption Structure Upgrading on Carbon Emissions in Fujian Province

This paper analyzes the theoretical mechanism by which urbanization and consumption structure upgrading exert an impact on carbon emissions in the context of promoting higher quality and efficiency in urbanization, advancing the transition and upgrading of consumption structure, and achieving carbon peaking and carbon neutrality (“dual carbon”) goals. By establishing an extended STIRPAT model and an intermediary model, this paper takes nine prefecture-level cities in Fujian Province from 2011 to 2021 as samples to investigate the effects of urbanization and consumption structure upgrading on carbon emission reduction in Fujian Province, revealing the interrelationship and transmission mechanism among the three. The results of this study show that: (i) The relationship between urbanization and carbon emissions in Fujian Province from 2011 to 2021 shows an inverted U-shaped curve, i.e. urbanization accelerated carbon emissions in the early stage and inhibited carbon emissions in the later stage; (ii) the regional heterogeneity analysis shows that under the current urbanization background, the upgrading of consumption structure in western and southern Fujian can significantly reduce carbon emissions, while the relationship between consumption structure upgrading and carbon emission reduction in eastern Fujian is not significant; (iii) the upgrading of consumption structure can help achieve and promote carbon emission reduction through increasing the proportions of the tertiary industry and immaterial consumption and enhancing the level of culture and education, while exerting little effect on carbon emission reduction through consumption in transportation, communication and health care.

Analysis of the Measurement of Transportation Carbon Emissions and the Emission Reduction Path in the Yangtze River Economic Belt under the Background of “Dual Carbon” Goals

Carbon emissions from the Yangtze River Economic Belt are an important element of China’s carbon emission endeavor, and a study of its emission reduction pathway can provide a reference for the country’s overall management of carbon emission reduction. From the perspective of energy consumption, this paper uses the carbon emission factor method to estimate the carbon emissions of the transportation industry in the Yangtze River Economic Belt during 2006–2020, based on the extended STIRPAT model, considering the influence of seven factors, i.e., population size, urbanization rate, GDP per capita, transportation added value, energy structure, energy intensity, and transportation intensity, on carbon emissions. Based on these factors, a scenario analysis, combined with a forecasting model, is used to predict the peak carbon performance of the transportation industry under different development scenarios. The results show that the overall carbon emissions of transportation in the YEB from 2006 to 2020 show a fluctuating upward trend, and the downstream carbon emissions are significantly higher than those in other regions. The main factors influencing carbon emissions from transportation in different upstream, midstream, and downstream regions vary, with both population and economic factors contributing to carbon emissions, while technical factors affect them differently. There are significant differences in the peak carbon performance of transportation under different development scenarios, and the government should take effective measures to work towards achieving the goals of the low-carbon or enhanced low-carbon scenarios.

Decoupling state of urban development and carbon emissions and its driving factors and predictions: A case study of Chengdu metropolitan area

Prioritizing the reduction of carbon emissions in key developing urban centers is a significant step toward achieving China's carbon peaking and neutrality goals. We examined the Chengdu metropolitan area as a case study. We proposed a coupled method for inversely estimating nighttime light and carbon emissions from energy consumption, enhancing the accuracy of fitting at the county scale and addressing the issue of missing energy consumption data. We integrated the Tapio decoupling model and the Logarithmic Mean Divisia Index (LMDI) model for comprehensive analysis, mitigating the limitations arising from the use of a singular model. Furthermore, we employed a multi-scenario analysis with an extended STIRPAT model to forecast the carbon emission trajectory of the Chengdu urban agglomeration and elucidate potential pathways for achieving carbon peaking and carbon neutrality goals. The findings indicated the following:(1)carbon emissions are predominantly concentrated in regions characterized by high levels of urban development. Forested land serves as the primary carbon sink; however, its capacity in the Chengdu metropolitan area fails to offset carbon emissions from energy consumption;(2)factor decomposition analysis revealed that economic development was the principal driver of carbon emissions, leading to an increase of 23.7964 million tons. Conversely, energy intensity emerged as the primary mitigation factor, reducing carbon emissions by 11.0677 million tons;(3)The Chengdu metropolitan area is projected to reach a carbon peak by 2030, with the multi-factor coordinated optimization (MFO) model representing the most favorable trajectory, with a projected peak of approximately 15.6998 million tons. However, to achieve carbon neutrality by 2060, there is still a surplus of approximately 10.4808 million tons.

Exploring the realization pathway of carbon peak and carbon neutrality in the provinces around the Yangtze river of China

As major strategic development areas in China, the provinces around the Yangtze River are facing the pressure of large aggregate CO2 emissions and high per capita CO2 emissions. The study on the pathway of reducing CO2 emissions and increasing carbon sequestration will help China better clarify the ways realize the goals of carbon peak and carbon neutrality as soon as possible. In this paper, the extended STIRPAT model and OLS regression were used to establish a prediction model to estimate the CO2 emissions during 2010–2060 under different scenarios. Meanwhile, the InVEST model was used to estimate the carbon sequestration, and the comparison with the CO2 emissions was analyzed. The results show that Qinghai and Yunnan have achieved the goal of carbon neutrality in 2010. Under the low-carbon and energy-saving scenario and the baseline scenario, all provinces within the study area are anticipated to attain their emissions peak by 2030 or earlier, and the CO2 emissions peak value of the whole study area is 3111 Mt and 3199 Mt, respectively. While under the high emissions scenario, only Chongqing and Qinghai will reach the emissions peak in 2030, and the whole study area will reach the emissions peak in 2040, with peak value of 3470 Mt. Under the three scenarios, the whole study area cannot achieve carbon neutrality before 2060. Only Sichuan and Hubei can achieve carbon neutrality in 2050 and 2060 under the low-carbon and energy-saving scenario. All provinces and municipalities in the lower reaches of the Yangtze River are facing huge pressure of emissions reduction. The research reveals that the goals of carbon peak and carbon neutrality should be achieved by developing clean energy, transforming industrial structure, increasing carbon sequestration and improving carbon emissions trading system.

Exploring Sustainable Planning Strategies for Carbon Emission Reduction in Beijing’s Transportation Sector: A Multi-Scenario Carbon Peak Analysis Using the Extended STIRPAT Model

The transportation sector plays a pivotal role in China’s efforts to achieve CO2 reduction targets. As the capital of China, Beijing has the responsibility to lead the era’s demand for low-carbon development and provide replicable and scalable low-carbon transportation development experience and knowledge for other cities in China. This study calculates the CO2 emissions of the transportation sector in Beijing from 1999 to 2019, constructs an extended STIRPAT model (population, affluence, technology, and efficiency), employs ridge regression to mitigate the effects of multicollinearity among the eight indicators, reveals the extent and direction of influence exerted by different indicators on CO2 emissions, and predicts the development trends, peak times, and quantities of transportation CO2 emissions in nine scenarios for Beijing from 2021 to 2035. Finally, adaptive low-carbon planning strategies are proposed for Beijing pertaining to population size and structure, industrial layout optimization, urban functional reorganization and adjustment, transportation infrastructure allocation, technological research and promotion, energy transition planning, and regional collaborative development. The results are as follows: (1) The total amount of CO2 emissions from Beijing’s transportation sector exhibits a trend of gradually stabilizing in terms of growth, with a corresponding gradual deceleration in the rate of increase. Kerosene, gasoline, and diesel are the main sources of transportation CO2 emissions in Beijing, with an annual average proportion of 95.78%. (2) The degree of influence of the indicators on transportation CO2 emissions, in descending order, is energy intensity, per capita GDP, population size, GDP by transportation sector, total transportation turnover, public transportation efficiency, possession of private vehicles, and clean energy structure. Among them, the proportion of clean energy structure and public transportation efficiency are negatively correlated with transportation CO2 emissions, while the remaining indicators are positively correlated. (3) In the nine predicted scenarios, all scenarios, except scenario 2 and scenario 4, can achieve CO2 emission peaks by 2030, while scenarios 7 and 9 can reach the peak as early as 2025. (4) The significant advancement and application of green carbon reduction technologies have profound implications, as they can effectively offset the impacts of population, economy, and efficiency indicators under extensive development. Effective population control, sustainable economic development, and transportation efficiency improvement are viable means to help achieve carbon peaking and peak value in the transportation sector.

The Impact of Foreign Direct Investment, Green Technology Innovation and GDP on CO2 Emissions in Western China: A Static Panel Data Analysis

This study investigates the impact of FDI, green technology innovation and GDP on CO2 emissions in the western region of China. This study applies the extended STIRPAT model, selects the relevant data of nine provinces in western China from 2000 to 2019, applies the static panel data analysis method, compares and analyses the estimation methods of Pooled OLS, fixed effect and random effect, and finally adopts the robust standard error estimation method of fixed effect. The results of the robust standard error estimation indicate that, in addition to the negative impact of green technology innovation on CO2 emissions, CO2 emissions are positively impacted by FDI, GDP, population, and the proportion of the secondary and tertiary industries. Therefore, reasonable introduction of FDI and improving green technology innovation levels are crucial in reducing CO2 emissions in the western region of China.

The effectiveness of environmental protection policies on greenhouse gas emissions

In Canada, greenhouse gas (GHG) emissions continue to remain high despite the federal government's commitment to reduce GHG emissions. Environmental policy across Canadian provinces has largely lacked consistency with some provinces implementing targeted policy such as carbon taxes while others have strongly resisted the federal government's attempts to encourage such policy. This study examines the impact of environmental policy on GHG gas emissions across Canadian provinces with policy uniquely measured by public and business sector spending on environmental protection as well as notable province-specific policies. An extended STIRPAT model is specified with the inclusion of proxies for environmental policy using panel data from Canada's ten provinces from 1995 to 2019. The cointegration and the error correction modelling approaches are employed to estimate the non-stationary panel data. A pooled mean group estimation is applied to provide short run and long run coefficients. The findings indicate that although per capita GDP is the main driver of GHG emissions in Canada, environmental policy has a significant mitigating effect, as shown by the negative association between emissions and private and public sector spending on environmental protection in the long run. Furthermore, provinces with targeted policies, such as Ontario's coal phase-out and British Columbia's carbon tax, experienced significant emissions reductions. The theoretical implication is the successful addition of policy variables to the STIRPAT model, providing the model a new application for future research.

Spatiotemporal characteristics and driving factor analysis of embodied CO2 emissions in China's building sector

Since the embodied emissions of the building sector play a pivotal role in the total emission profile of developing countries, represented by China, it is crucial to uncover its emission characteristics and the underlying drivers. Most existing studies focus on building operational emissions, and there is a lack of in-depth studies on embodied emissions, especially in spatiotemporal heterogeneity and spatial correlation. Thus, this study calculates embodied emissions of the building sector in China's 29 provinces during 2011–2020 and develops an innovative factor analysis model that integrates the extended STIRPAT model, network analysis, and spatial Durbin model to explore the influence mechanisms of various factors on emissions from local, spillover, overall and temporal perspectives. The empirical results reveal notable spatiotemporal differences and spatial dependence across regions. The area has consistently been the most crucial driver. The building performance demands are increasingly influencing emissions through direct and spillover effects. The slowdown decarbonization of the material industry diminishes its impact. Limited technical improvement and regional shifts of carbon-intensive enterprises have weakened the technological emission reduction effects. Therefore, regulating ineffective construction, discouraging excessive building performance, implementing demand-side material efficiency strategies, bolstering interregional coordination, and developing low-carbon technologies are keys to cutting emissions.

Assessing the impact of incentive coordination effect on the equilibrium of agricultural water usage by China's South-to-North Water Diversion Middle Route Project.

In recent years, the sustainable development of agricultural water resources has received much attention. The mismatch between agricultural water distribution patterns, land resources, and socioeconomics threatens food production, especially in vast water-scarce plains. Therefore, monitoring agricultural water spatial equilibrium (AWRSE) is necessary. Based on equilibrium theory and information entropy, in this study, the AWRSE evaluation model is constructed from three aspects: agricultural water resources, land resources, and socioeconomics. In addition, the relationship between social factors with cropping pattern as the primary explanatory variable and AWRSE was examined in conjunction with the extended STIRPAT model and applied to the water-receiving area of the Middle Route of South-to-North Water Diversion Project (MR-SNWDP). The results show that compared with the pre-diversion period, the AWRSE of 75% of the water-receiving cities has been significantly improved by the MR-SNWTP water supply. The MK test z value of the overall regional AWRSE has changed from - 0.328 to - 2.65, and the AWRSE development has shifted from not significantly better to significantly better. The cropping pattern shows a positive response to this development, and this effect can be mitigated in the late stage of water transfer; when the proportion of food crop cultivation increases by 1%, the sub-regional AWRSE value will increase by 0.347%. The evaluation model demonstrates a broad range of inclusiveness and application potential; it provides novel insights for examining agroecological, social, and economic stability.

An evaluation concentrated on post-peak carbon trend scenarios designing and carbon neutral pathways in Hebei Province, China

China has committed to peak carbon emissions by 2030 and become carbon neutral by 2060. Hebei, as a major energy province in China, has more challenging carbon peaking and carbon neutrality targets. Based on the extended STIRPAT model, this paper evaluates the time to peak carbon and post-peak carbon trend changes in Hebei province under different scenarios from 2020 to 2060. Based on the support vector machine model with particle swarm optimization, this paper evaluates the carbon neutral pathways under different scenarios in Hebei province from 2020 to 2060 in terms of forests, croplands, wetlands, grasslands and Carbon Capture, Utilization and Storage (CCUS). The results show that a monotonically flat trend without inflection point, a single-inflection-point plateau-period trend and a multi-inflection-point inverted U-wave trend occur after carbon peaks. Hebei Province can achieve carbon neutrality by 2060 under the policy scenario and the enhanced scenario, and the enhanced scenario is better. Comparing with existing studies, the innovation of this paper is to design different trends of changes after carbon peak, combining carbon absorption and carbon emission, and providing more diversified development paths for carbon neutral strategies through a more integrated perspective and multi-scenario comprehensive analysis. Therefore, In the future, Hebei Province should establish a platform for carbon emissions monitoring and carbon footprint assessment, and set up an early warning and assessment mechanism for carbon peaking, so as to prevent a rebound trend in carbon emissions after peaking. At the same time, it should introduce and develop carbon capture and conversion technologies and promote the low-carbon transformation of the industrial and energy sectors, thereby forcing the early realization of peak carbon. Pay attention to the role of forestry resources in carbon neutrality, increase carbon sink resources such as forests and wetlands, promote the development of CCUS, and enhance the implementation of the policy.

Study on carbon emission reduction countermeasures based on carbon emission influencing factors and trends.

The carbon mitigation response encompasses a variety of strategies aimed at mitigating greenhouse gas emissions resulting from human activities. These measures are crafted to address the challenges posed by climate change and facilitate the transition of businesses towards a low-carbon paradigm. Leveraging the analytical outcomes of the extended STIRPAT model and the PSO-BP prediction model, this paper suggests countermeasures for reducing carbon emissions in China's metal smelting industry. The overarching objective is to contribute to China's attainment of the "dual carbon objectives." The study identifies key factors influencing carbon emissions in the metal smelting industry, ranked in descending order of sensitivity: population, coal consumption, urbanization rate, total metal production, carbon intensity, proportion of secondary industry, and GDP per capita. Results from three established scenarios-namely, low carbon, standard, and high carbon-indicate a consistent decline in carbon emissions from China's metal smelting industry over the next 15 years. This research not only enhances the findings of existing studies on carbon emissions in the metal smelting sector but also introduces an innovative approach to carbon emission reduction within China's metal smelting industry.

华中地区碳达峰预测——基于扩展的STIRPAT模型

华中地区碳达峰预测——基于扩展的STIRPAT模型

Drivers, scenario prediction and policy simulation of the carbon emission system in Fujian Province (China)

In response to the looming problems induced by climate change and the Paris Climate Summit, China has committed to capping the carbon-emission peak in 2030 and attaining carbon neutrality by 2060. Fujian Province is tasked with a demonstration and leading pilot duty to meet the national goal and international obligation. It aimed to realize a greener economic growth mode and contribute to reducing carbon emissions. This study explored key carbon-emission drivers in Fujian, applying the extended STIRPAT model. Five scenarios were developed to project future carbon emissions. The results pinpointed Fujian's carbon-emission drivers, namely industrial structure (the most important), accompanied by population, GDP per capita, energy intensity, and energy structure. The system dynamics model forecasted development scenarios and policy simulation of carbon emissions, which identified and evaluated the optimal path to reduce carbon emissions and achieve the peak carbon target. The baseline scenario failed to attain the peak carbon emissions by 2030. The green scenario was rated as the optimal path to reach peak carbon emissions of 339.922 million tons by 2028. The findings can reinforce the conceptual and empirical basis in formulating the best option in quantitative terms for Fujian to attain carbon emission, peak, and neutrality goals.

Land-use carbon emissions and built environment characteristics: A city-level quantitative analysis in emerging economies

Rapid urbanization and subsequent urban land expansions have led to land use changes, emerging as a prominent source of anthropogenic carbon emissions in the developing world. While numerous studies have quantified land-use carbon emissions (LUCE), there is still a lack of rigorous statistical analyses examining the driving factors of LUCE, particularly in the post-2015 era, when stringent environmental pollution regulations and carbon emission reduction policies have been implemented worldwide. This study aims to assess city-level LUCE in emerging economies and to further investigate the drivers of inter-city variations in LUCE through an extended STIRPAT model, taking Guangdong Province in China as an example. The results indicate a substantial increase in LUCE from 2000 to 2020, reflecting a surge in energy consumption associated with land-use transitions from natural land to construction land. The growing disparity between direct and indirect carbon emissions underscores the increasing significance of construction land planning and management in achieving emission reduction goals. Furthermore, our findings from the extended STIRPAT model shed light on carbon neutrality pathways by revealing the potential for LUCE reduction through adopting sustainable built environment planning.

Driving factors and clustering analysis of expressway vehicular CO2 emissions in Guizhou Province, China.

Expressways are essential for intercounty trips of passenger travel and freight mobility, which are also an important source of vehicular CO2 emissions in transportation sector. This study takes the expressway system of Guizhou Province as the research objective, and establishes the multi-year expressway vehicular CO2 emission inventories at the county level from 2011 to 2019. We employ the extended STIRPAT model incorporating ridge regression to identify driving factors from six different aspects, and then utilize the affinity propagation cluster method to conduct the differentiation research by dividing Guizhou's counties into four clusters. Based upon clustering analysis, localized and targeted policies are formulated for each cluster to reduce expressway vehicular CO2 emissions. The results indicate that generally: (1) Guizhou's expressway vehicular CO2 emissions manifest a continuously upward trend during 2011-2019. Small-duty passenger vehicle (SDV), light-duty truck (LDT), and heavy-duty truck (HDT) contribute to the largest CO2 emissions in eight vehicle types. (2) GDP and population are the foremost two positive driving factors, followed by urbanization rate and expressway length. The proportion of secondary industry is also a positive driver, but that of tertiary industry exhibits an opposite effect. (3) Regional disparity exists in four county clusters of Guizhou Province. Efficient policies are proposed, such as improving the layout and infrastructure of transportation hubs, promoting multimodal integration, and implementing industrial upgrading as per regional advantages. Sustainable expressway vehicular CO2 emission reduction is realized from both the source of industry and low-carbon modes of transport.

Multi-Scenario Prediction Analysis of Carbon Peak Based on STIRPAT Model-Take South-to-North Water Diversion Central Route Provinces and Cities as an Example

With the increase in energy demand, environmental issues such as carbon emissions are becoming more and more prominent. China will scale its intended nationally determined contributions by adopting more vigorous policies and measures. China aims to have CO2 emissions peak before 2030 and achieve carbon neutrality before 2060. The current challenge and priority of China’s high-quality development is to ensure a harmonious balance between the ecological environment and the economy. The South-to-North Water Diversion Project passes through Beijing, Tianjin, Henan, and Hebei, which were chosen as the study sites. The carbon emission data was from the China Carbon Emission Database 2000–2019. Decoupling modeling using statistical yearbook data from four provinces and municipalities. KMO and Bartlett’s test used SPSS 27 software. The selection of indicators was based on relevance. Analyses were performed using the extended STIRPAT model and ridge regression. Moreover, projections of carbon peaks in the study area for 2020–2035 under different rates of change were simulated by the scenario analysis method. The results show that: (1) The decoupling analysis of the four provinces and cities from 2000-2019 gradually shifts to strong decoupling; (2) Resident population, energy structure, and secondary industry as a proportion of GDP significantly impact carbon emissions; (3) From 2000–2035, Beijing and Henan experienced carbon peaks. The peak time in Beijing was 96.836 million tons in 2010. The peak time in Henan was 654.1004 million tons in 2011; (4) There was no peak in Hebei from 2000–2035.

Forecasting urban carbon emissions using an Adaboost-STIRPAT model

Solving outstanding environmental issues, reducing carbon emissions, and promoting green development are necessary ways to achieve carbon neutrality and carbon peak goals. It is also an important issue faced by society today. This paper uses the Kaya identity combined with the logarithmic mean Divisia index (LMDI) decomposition method to analyze the factors affecting carbon emissions, and uses the Pearson correlation coefficient to screen out eight highly correlated features to construct an extended STIRPAT model. In order to further improve the accuracy of the model in predicting carbon emissions, this paper introduces the Adaboost algorithm from machine learning to enhance the STIRPAT model. Finally, scenario analysis is used to predict and analyze carbon emissions in Shandong Province from 2020 to 2050. The results show that: 1) The main factors affecting urban carbon emissions from 1998 to 2019 are economic growth effects, followed by energy structure effects and energy consumption effects. 2) Under three different development scenarios, Shandong Province can achieve carbon peak between 2030–2035, but there are differences in peaking time and peak values.