Estimation Results Of Model Research Articles

Estimation of Arterial Path Flow Considering Flow Distribution Consistency: A Data-Driven Semi-Supervised Method

To implement fine-grained progression signal control on arterial, it is essential to have access to the time-varying distribution of the origin–destination (OD) flow of the arterial. However, due to the sparsity of automatic vehicle identification (AVI) devices and the low penetration of connected vehicles (CVs), it is difficult to directly obtain the distribution pattern of arterial OD flow (i.e., path flow). To solve this problem, this paper develops a semi-supervised arterial path flow estimation method considering the consistency of path flow distribution by combining the sparse AVI data and the low permeability CV data. Firstly, this paper proposes a semi-supervised arterial path flow estimation model based on multi-knowledge graphs. It utilizes graph neural networks to combine some arterial AVI OD flow observation information with CV trajectory information to infer the path flow of AVI unobserved OD pairs. Further, to ensure that the estimation results of the multi-knowledge graph path flow estimation model are consistent with the distribution of path flow in real situations, we introduce a generative adversarial network (GAN) architecture to correct the estimation results. The proposed model is extensively tested based on a real signalized arterial. The results show that the proposed model is still able to achieve reliable estimation results under low connected vehicle penetration and with less observed label data.

Factors hindering and boosting SDG7 implementation in EU countries

One of the sustainable development goals (SDG7) is to ensure access to clean and affordable energy, which is related to most other SDGs and plays a crucial role in economic development and human well-being. The aim of the article is to identify factors that enhance and delay one of the most crucial goals of sustainable development, SDG7. The study’s originality lies in the spatiotemporal approach to analysing the impact of selected factors on the development of green energy and increasing its availability. Three groups of potential SDG7 determining factors have been identified: ecological, social and economic. The proposed approach and the use of sensitivity analysis to variables weighting and ranking constructions of EU countries is an innovative aspect of the work and fills the gap in research on SDG7. The study showed that Denmark and Sweden occupy leading positions in the rankings based on the extent of SDG7 implementation. In contrast, Bulgaria, Cyprus and Lithuania occupied one of the last positions. The results of panel-data model estimations showed that in each estimated model, the same “indispensable variables” significantly affect the implementation of SDG7. Among these variables, only the unemployment rate significantly negatively impacted the SDG7 execution.

A multifaceted analysis of pesticide utilization in market gardening along the Ruzizi plain: Exploring factors, farmer perceptions & media influence

Along the Ruzizi plain, subsistence agriculture constitutes households' primary food source. Regardless of the environment, the low level of pesticide use ensures less effective disease and pest control. This is why a study was carried out in the Ruzizi plain to identify the main determinants of pesticide use on vegetable crops for effective control of diseases and pests that significantly reduce the yield of these crops, which play an economically important role for producers and the role of the media in this context. The data was collected using a closed-type survey questionnaire on 90 market gardeners distributed equally between localities applying the probit model. The results of the probit model estimation reveal that about nine factors positively influence the use of pesticides: membership in a cooperative (p=0.0012), access to agricultural credit (p=0.0153), experience in agriculture (p=0.0008), experience in market gardening (p=0.0197), standard of living (p=0.0139), yield (p=0.0001), capacity building (p=0.0035), the area exploited (p=0.0011) and the cultivation system (p=0.0233). In addition, tomatoes are the leading vegetable crop grown by many market gardeners (61.1%), followed by amaranth (20%) and onions (18.9%). Also, 67.8% of market gardeners use pesticides compared to 32.2% who do not use them. Thus, considering these factors would contribute to decision-making when carrying out certain activities to improve market gardening, contributing considerably to the fight against food insecurity. Also, it is advised that the media work harder to inform rural residents and areas about the agenda for rural development.

An investigation of perceived risk dimensions in acceptability of shared autonomous vehicles, a mediation-moderation analysis

The integration of shared and autonomous mobility has led to the emergence of shared autonomous vehicles with ride-sharing services (SAVWRS), which have the potential to significantly reduce private car usage and promote sustainable transportation. Despite numerous studies on this topic, there is still no research examining the impact of all dimensions of perceived risk theory on usage intention. Therefore, we aim to investigate these relationships and gain deeper insights by examining the mediating effect of trust and the moderating effect of generation (Millennials vs. Baby Boomers) to address potential disparities across generations. To gather insights, we design an online survey that was completed by a random sample of 723 individuals in 2021. The estimation results of the structural equation model reveal that all perceived risk dimensions (social, performance, time, physical, security, and financial risks, in descending order) are negatively related to consumers’ intention. Additionally, trust fully mediates the relationships between performance, physical, financial, and security risks and usage intention, whereas it partially mediates the relationships between social and time risks and the intention to use. Furthermore, moderation analysis revealed that Millennials are less concerned about most dimensions of perceived risk theory, except for social and time risks. In conclusion, our study contributes to a deeper understanding of the complex relationships between perceived risk dimensions, trust, and usage intention in SAVWRS. Our findings suggest that policymakers and industry stakeholders should consider strategies to address these concerns to promote widespread acceptance of SAVWRS.

Bitcoin, Fintech, Energy Consumption, and Environmental Pollution Nexus: Chaotic Dynamics with Threshold Effects in Tail Dependence, Contagion, and Causality

The study investigates the nonlinear contagion, tail dependence, and Granger causality relations with TAR-TR-GARCH–copula causality methods for daily Bitcoin, Fintech, energy consumption, and CO2 emissions in addition to examining these series for entropy, long-range dependence, fractionality, complexity, chaos, and nonlinearity with a dataset spanning from 25 June 2012 to 22 June 2024. Empirical results from Shannon, Rényi, and Tsallis entropy measures; Kolmogorov–Sinai complexity; Hurst–Mandelbrot and Lo’s R/S tests; and Phillips’ and Geweke and Porter-Hudak’s fractionality tests confirm the presence of entropy, complexity, fractionality, and long-range dependence. Further, the largest Lyapunov exponents and Hurst exponents confirm chaos across all series. The BDS test confirms nonlinearity, and ARCH-type heteroskedasticity test results support the basis for the use of novel TAR-TR-GARCH–copula causality. The model estimation results indicate moderate to strong levels of positive and asymmetric tail dependence and contagion under distinct regimes. The novel method captures nonlinear causality dynamics from Bitcoin and Fintech to energy consumption and CO2 emissions as well as causality from energy consumption to CO2 emissions and bidirectional feedback between Bitcoin and Fintech. These findings underscore the need to take the chaotic and complex dynamics seriously in policy and decision formulation and the necessity of eco-friendly technologies for Bitcoin and Fintech.

Reproductive intentions of Russians in 2022—2023: Тhe role of subjective factors

This study examines how the reproductive intentions of Russians changed during the socio-economic shocks in 2022—2023 basing on the data from a representative survey of respondents of reproductive age conducted in May 2023. We used multiple-choice models to identify the factors that influenced changes in fertility decisions. Most individuals who had planned to have children before the crisis did not change their plans (60.2%), 9.5% of respondents decided not to have children, while, on the contrary, 9.2% decided to have children earlier. The rest of the respondents postponed having children. The econometric model included both objective and subjective characteristics of respondents. Objective factors included income, housing availability, health, family status, and the presence of children. Subjective factors comprised emotions such as anxiety, fear, appeasement, happiness, and attitude to the political course of the country. The study found that psychological factors played a more significant role in decision-making. Anxiety and fear as well as disagreement with the country’s political course led respondents to postpone having children for an indefinite period. Conversely, a positive emotional background and the presence of a partner encouraged respondents to have children earlier. The decision not to have children was mainly explained by physiological limitations and attitudes to political course, while the income and emotional indicators had a more minor but significant influence. The results of model estimates are consistent with the cluster analysis of answers to the openended question about changes in reproductive intentions. We also discovered significant differences in decision-making for respondents before and after the age of 30 as well as for those with and without children. A series of demographic and social policy recommendations are suggested.

The Role of Smart Travel Service in Intercity Travel Satisfaction: Does Traveler Heterogeneity Matter?

With the increasing intercity communications and the widespread application of smart travel technologies, it is of great significance to understand the mechanism of how the attributes of smart travel service affect the travel satisfaction among intercity travelers and the potential heterogeneity. This paper establishes a conceptual model with hypotheses from two paths: smart travel service and smart travel experience. Based on the intercity travel survey data of the Guanzhong Plain urban agglomeration in China, a latent class structural equation model is employed to divide the samples into “cold”, “rational”, and “enthusiastic” potential groups based on the use and attitude of smart travel services. From the model estimation results, this study confirms that smart travel service and travel experience satisfaction have significant positive impacts on the overall intercity travel satisfaction of travelers. However, the impact of smart travel satisfaction varies due to group heterogeneity. For the “cold” group, the impact of smart travel service satisfaction on the overall satisfaction of intercity travel is not significant, and smart travel service satisfaction only has a significant impact on the smart travel experience satisfaction of “enthusiastic” travelers. This study puts forward the importance of enhancing the quality of smart travel services and promoting travel experience through smart travel technologies and proposes measures for different groups from the perspective of market segmentation, which provides theoretical and practical value for the promotion of sustainable development of intercity transportation.

Chinese consumers' valuation for prepared plant-based meat products: Does environmental information matter?

Despite the growing interest in innovative nonanimal protein-prepared foods, knowledge about consumer demand for these newly prepared foods and their potential scope in the market could be improved. This study reports the results of a discrete choice experiment on consumers' (n=1245) willingness to pay (WTP) for prepared plant-based meat (PPBM) in the context of Chinese food culture. Consumers were randomly assigned to a treated group with additional environmental information about PPBM. The estimation results of the random parameter logit model showed that when environmental information was provided, consumer preferences and WTP for frozen meatballs with mixed meat (beef-based and soy protein-based meat) and PBM (pure soy protein-based meat) significantly increased. However, their preference and WTP for food quality and safety attributes of meatballs decreased. Simultaneously, the availability of information reveals the heterogeneity of preferences. This study found that positive WTP for PPBM was limited to consumers with a low degree of food technology neophobia (FTN) and that consumers with a high degree of FTN may avoid purchasing meatballs made from PBM. In contrast, consumers with a higher time preference (i.e., impatient consumers) were likelier to pay for PPBM meatballs. PRACTICAL APPLICATION: PPBM is especially valuable in developing innovative nonanimal protein-prepared foods, and China has the potential to become the largest PPBM food market. Understanding consumers' preference for PPBM products and the impact of information provision on their WTP will assist food companies in devising suitable strategies for the development of new PPBM products. The findings of this study provide targeted market insights for the food industry to help guide the development of plant-based meat products more effectively.

Optimisation of biochar dose in anaerobic co-digestion of green algae and cattle manure using artificial neural networks and response surface methodology

This study aimed to optimise and model biogas yields using artificial neural networks (ANN) and response surface method (RSM) of biogas yields after adding different doses of ozonation and ultrasonic pretreated biochar (BC) doses to the co-digestion of cattle manure and green algae substrates, with and without S.Parkle culture in the environment. The results of the RSM-D optimal design indicated that, in the absence of S.Parkle culture in the environment, the optimum ultrasonic pretreated biochar (UPBC) doses were 29.23 mg (for 100 mL digestion volume) and the corresponding optimum biogas yield was 340.50 mL/g volatile solids (VS). In the case of S.Parkle culture in the environment, the optimum ozonation pretreated biochar (OPBC) dose was 55.96 mg and the corresponding optimum biogas yield was 660.40 mL/g VS. ANN and RSM model performances were analyzed using different statistical indicators and ANN result obtain showed absolute percentage error (MAPE) value of 2.1, mean average error (MAE) value of 0.347, standard error of prediction (SEP) value of 0.590, and root-mean-square error (RMSE) value of 0.55, mean squared error (MSE) value of 0.31, the sum of the squared estimate of errors (SSE) value of 4.9 and coefficient of determination (R2) value of 0.9999, and RSM result reveals MAPE of 0.0030, MAE value of 30.693, SEP value of 45.57, RMSE of 42.63, MSE value of 1817.6, SSE value of 29,081 and R2 of 0.9612. The model performance indicators and estimation results indicate that the ANN performs relatively better than the RSM in modelling the process. It is recommended that the optimum OPBC and UPBC doses be tested and verified on different substrates.

Modelling elderly users’ perceived level of satisfaction with bus transit service: A case study of Patna city

Participating in activities can significantly enhance the life satisfaction of older adults, aged 60 and above. Limited access to transportation can have several negative effects on older adults. The present-day public transit system primarily serves young and middle-aged individuals, which results in a lack of comfort and safety for the elderly. This study aims to model elderly users’ perceived level of satisfaction with bus transit service using the ordered probit model. The study area for our research is the city of Patna, which is the capital of Bihar, India. An extensive perception survey of 416 elderly users populates the database for the present study. According to model estimation results, increasing the number of seats reserved for the elderly and improving the condition of bus stops will increase the perceived level of satisfaction and will lead to attract more elderly passengers to bus transit service. Marginal effects were calculated to evaluate the impact of each independent variable on the perceived level of satisfaction. The overall prediction success rate is 60%. The result of the study will be helpful in better understanding the elderly users’ perception of bus transit service and accordingly will be helpful in planning and management of the bus transit service to meet the expectations of the elderly.

Agricultural carbon emission efficiency and agricultural practices: Implications for balancing carbon emissions reduction and agricultural productivity increment

The current Ukraine War underlines the importance of grain self-sufficiency. After the adoption of the Paris Agreement, two major challenges developing countries are facing in the coming decades are increasing agricultural production to ensure food security and reducing carbon emissions (CE). The key to such an “environment-development dilemma” is to improve agricultural carbon emission efficiency (CEE). Using China as the study site, we systematically analyze the impacts of agricultural management activities on agricultural CEE from 1997 to 2019. Global and local Moran's I index tests provide evidence of a positive spatial dependence of agricultural CEE. Using the LISA cluster map, we observe that high CEE regions tend to be distributed together, dominated by environmental conditions. However, with the promotion of agricultural management activities, such a clustering pattern vanished. Our spatial Durbin model (SDM) estimation results indicate that there are significant nonlinear relationships between agricultural practices and agricultural CEE. While the consumption of fertilizers and pesticides has economies of scale effects, the deployment of agricultural machinery and irrigation have diseconomies of scale effects on local CEE. Based on the SDM results, the direct and indirect effect estimation results suggest that the significant direct and spillover effects of many practices on agricultural CEE have opposite nonlinear shapes, implying a more complicated situation in promoting these activities, as the positive regional effect of an agricultural activity might have a negative impact on adjacent regions. All the results indicate that local policymakers should carefully tailor agricultural development policies based on local environmental conditions.

Risk Factors Associated with Mortality in Hospitalized COVID-19 Patients: A Case Study from Southeast Iran

Background: This study aimed to identify mortality risk factors among hospitalized COVID-19 patients in southeast Iran. Methods: This cross-sectional study used data from the COVID-19 patients admitted to Afzalipour teaching hospital in Kerman, Iran, from February 2020 to September 2021. The demographic and clinical data of 6,057 patients were analyzed using Bayesian network and logistic regression models. Results: Out of 6,057 patients, 333 (5.5%) died. The most important risk factors for COVID-19 mortality were age, gender, fever, headache, decreased level of consciousness (LoC), chronic liver disease, blood oxygen level (BOL), admission season, and length of stay (LoS). Fever, headache, and longer LoS were protective and mortality-reducing variables. Conclusion: Following model estimation results, it is recommended that older male patients with low oxygen levels and a lower LoC, as well as patients with chronic liver disease, receive additional medical care and not be discharged prematurely. Early medical interventions for high-risk patients may reduce COVID-19 mortality risk.

Computer Modeling Analysis of Electric Vehicle's Choice Behavior Considering Latent Variables

At present, there are few researches on the influence of psychological latent variables on the choice behavior of electric vehicles, and lack of consideration of individual heterogeneity. In this study, computer modeling was used to construct not only a traditional discrete choice model that takes into account individual heterogeneity, but also a hybrid choice model,which takes into account psychological latent variables are constructed to explore the mutual effects of observable personal attributes, vehicle attributes and difficult to directly observe psychological latent variables on consumers’ choice behavior of electric vehicles. The estimation results of hybrid choice model with psychological latent variables and the traditional discrete choice model without considering psychological latent variables are compared. The result show that perceived usefulness, perceived risk and purchasing attitude have a significant impact on consumers’ choice behavior of electric vehicles. Compared with traditional discrete choice model, the hybrid choice model, which takes into account psychological latent variables has significantly higher prediction accuracy and has better interpretation ability and fitting effect. The research results can provide theoretical support for further expanding the electric vehicle market and formulating relevant policieshe usage of the word Power quality in recent times acquired intensified interest due to the complex industrial processes. The usage of intelligent tools to improve power quality is increasing day by day, as assumption of present day power system as a linear model is unsatisfactory. This paper deals with analysis of Differential Evolution (DE), Hybrid Differential Evolution (HDE) and Variable Scaling Hybrid Differential Evolution for harmonic reduction in the source current with optimal tuning of PI controller gain values. Shunt Active power Filter is one of the better solution to suppress the source current harmonics which are induced into power system because of nonlinear loads. Current controller called HBCC is considered for gating operation of switches in Voltage Source Inverter. The Intelligent tuned PQ theory is used for reference current generation. The then obtained compensating currents are injected at point of common coupling for current disturbance mitigation. Simulations of MATLAB/SIMULINK environment of the present work shows the efficacy.

Effects of autonomous driving on residential location choice behavior: A travel-based multitasking perspective

Fully autonomous vehicles (AVs) allow users to engage in multitasking behavior while traveling, potentially inducing longer travel because multitasking in AVs would generate a positive utility. Eventually, this may further induce residential relocation, as positive utility virtually reduces the value of time. Such influence may vary depending on whether the AV is used individually or with others (i.e., ride-sharing), as well as the type and amount of multitasking activities carried out in the vehicle. This study examines the influence of the type of AV (ride-sharing or individually used) and the type and amount of in-vehicle multitasking activities on residential location choice behavior through a pivoted stated preference survey. Residential location choice behavior is represented by a panel binary mixed logit model. The model estimation results indicate that the willingness to pay for monthly rent to shorten commuting time is significantly lower when individually used AVs are introduced, compared to non-AVs (i.e., existing automobiles) and ride-shared AVs. Hence, further urban sprawl could occur if individually used AVs become prevalent. Such negative impacts on urban form, however, would be substantially small when AV is introduced under the ride-sharing scheme. It was also found that individuals who can engage in more multitasking behavior in an AV will accept longer travel regardless of the type of AV (ride-sharing or individually used), while individuals who can hardly perform in-car activities tend to resist additional commuting travel time. Moreover, the impact of automated driving at the city scale was examined by running simulations of residential choice in Hiroshima City as a case study. The results suggest that multitasking behaviors in AVs would have modest impacts on urban structure.

미시자료를 이용한 개별 경종 농가와 생산지의 품목 특화 이득 분석

This study empirically investigates the impacts of crop specialization on farm performance in Korea. A census data set of about 230,000 crop-producing farms is used, and the crop diversities within farms (α-diversity), among farms (β-diversity), and of the regions (γ-diversity) were measured for the analysis. The regional diversity (γ) is partitioned into the average diversity within farms (α) and among farms (β). Our estimation results of the interval regression model show that both individual and regional specializations contribute to farm performance. That is, individual farm revenue decreases both in the α and γ diversities but increases in the β diversity when controlled by the farm input usages, farm household characteristics, and regional socio-economic-climate conditions. It is also found that farms choosing crop selections similar to those of their regions tend to achieve higher performance. We confirm the existence of the gains from specializations by estimating a propensity score model with a continuous treatment as well. We insist that our findings are quite consistent with the observed trends, specializing in a small number of crops despite the potential gains from diversification.

An investigation of heterogeneous impact, temporal stability, and aggregate shift in factors affecting the driver injury severity in single-vehicle rollover crashes

Single-vehicle rollover crashes have been acknowledged as a predominant highway crash type resulting in serious casualties. To investigate the heterogeneous impact of factors determining different injury severity levels in single-vehicle rollover crashes, the random parameters logit model with unobserved heterogeneity in means and variances was employed in this paper. A five-year dataset on single-vehicle rollover crashes, gathered in California from January 1, 2013, to December 31, 2017, was utilized. Driver injury severities that were determined to be outcome variables include no injury, minor injury, and severe injury. Characteristics pertaining to the crash, driver, temporal, vehicle, roadway, and environment were acknowledged as potential determinants. The results showed that the gender indicator specified to minor injury was consistently identified as a significant random parameter in four years’ models and the joint five-year model, excluding the 2016 crash model where the night indicator associated with no injury was observed to produce the random effect. Additionally, two series of likelihood ratio tests were conducted to assess the year-to-year and aggregate-to-component temporal stability of model estimation results. Marginal effects of explanatory variables were also calculated and compared to analyze the temporal stability and interpret the results. The findings revealed an overall temporal instability of model specifications across individual years, while there is no significant aggregate-to-component variation. Injury severities were observed to be stably affected by several variables, including improper turn indicator, under the influence of alcohol indicator, old driver indicator, seatbelt indicator, insurance indicator, and airbag indicator. Furthermore, the year-to-year and aggregate-to-component shift was quantified and characterized by calculating the differences in probabilities between within-sample observations and out-of-sample predictions. The overall results imply that continuing to expand and refine the model to incorporate more comprehensive datasets can result in more robust and stable injury severity prediction, thus benefiting in mitigating the associated driver injury severity.

Spatial Analysis of High-Tech Export Performance of the Eastern European Member States of the EU

Some Central and East European countries have integrated into the European Union after 2004 and followed free market economy principles. This paper studies the spatial spillovers effects of high-tech export, Gross Domestic Product per capita, research and development expenditure, number of research and development full time equivalent, and technology accumulation among European Union member Central and East European countries over the period 2007-2020 by using spatial panel estimation models. The main purpose of the paper is to investigate whether high-tech export of European Union member Central and East European countries has a dependency and interaction with each other after EU membership. The estimation results of spatial panel model results reveal that an increment in high-tech exports of adjacent countries increases the high-tech exports of other regional countries. Our results also provide evidence on Gross Domestic Product per capita, and research and development expenditure of European Union member transition economies have positive and significant impacts on high-tech exports of those countries.

Emerging ICT clusters in the Western Balkans: A convergence model based on financial statement analysis

The Western Balkans is experiencing an ongoing inflow of foreign direct investments (FDI) in the information and communications technology (ICT) industry as several European enterprises have already established their presence in the region. These inflows have generated large-scale ICT investments in the region, creating new knowledge-based clusters and technology spillovers in regional economies. On the basis of financial statement indicators collected for 327 European and regional ICT enterprises and on panel data estimation, this paper tries to estimate technology transfer in the Western Balkan region. Specifically, the proposed model examines cluster spillover effects in improving the absorptive capacity of the Western Balkan region in creating a pool of specialized local suppliers and a talented regional labor force. Model estimation results indicate that limited spillover effects have occurred from the newly created clusters of European ICT enterprises in the regional economy of the Western Balkan region. Spillovers related to improved technical capabilities, increased labor productivity, higher resource efficiency, and flexible operational structures require further stimulation to speed up convergence and integration of the local ICT industry in the corresponding European value chain. Finally, this paper concludes that competitive advantages such as a cheap labor force are no longer feasible for sustainable development. To narrow down the existing know-how gap, particular efforts are required regarding policies focused on educating human capital and transforming regional enterprises to successfully compete in the European market.

Short-term and long-term effects of Chinese and global economic policy uncertainty and geopolitical risks on Chinese tourism

This paper focuses on the short-term and long-term effects of Chinese and global economic policy uncertainties (CNEPU and GEPU) and geopolitical risks (CNGPR and GGPR) on the growth of inbound tourism in China. Using the ARDL and NARDL models as well as a monthly series of Chinese inbound tourism revenue and arrivals, we observed several interesting empirical findings. We find significant effects of CNGPR, GGPR and GEPU on the growth of inbound tourism in Hainan Province and even in China nationwide, while the impact of CNEPU is limited. Among these influencing variables, GEPU always has a significant long-term negative impact on inbound tourism growth (both revenue and arrivals). CNGPR has a significant short-term negative impact on inbound tourism growth in China nationwide; however, it has a significant long-term negative impact on inbound tourism growth in Hainan Province. In addition, the estimation results of the NARDL model further reveal the significant short-term effects of GEPU and GGPR on the growth of inbound tourism arrivals in Hainan Province and even in China nationwide, and these short-term effects are always significantly asymmetric. Specifically, the negative components of GGPR always influence the growth of inbound tourism arrivals more strongly. However, the positive components of GEPU influence inbound tourism arrivals more strongly in Hainan Province, but the negative components of GEPU influence the growth of inbound tourism arrivals more broadly in China.

Comparison of the CASA and InVEST models’ effects for estimating spatiotemporal differences in carbon storage of green spaces in megacities

Urban green space is a direct way to improve the carbon sink capacity of urban ecosystems. The carbon storage assessment of megacity green spaces is of great significance to the service function of urban ecosystems and the management of urban carbon zoning in the future. Based on multi-period remote sensing image data, this paper used the CASA model and the InVEST model to analyze the spatio-temporal variation and driving mechanism of carbon storage in Shenzhen green space and discussed the applicability of the two models to the estimation of carbon storage in urban green space. The research results showed that, from 2008 to 2022, in addition to the rapid expansion of construction land, the area of green space and other land types in Shenzhen showed a significant decrease trend. The estimation results of the carbon storage model showed that the carbon storage of green space shows a significant trend of reduction from 2008 to 2022, and the reduction amounts are 0.8 × 106 t (CASA model) and 0.64 × 106 t (InVEST model), respectively. The evaluation results of the model show that, in megacities, the spatial applicability of InVEST model is lower than that of CASA model, and the CASA model is more accurate in estimating the carbon storage of urban green space. The research results can provide a scientific basis for the assessment of the carbon sink capacity of megacity ecosystems with the goal of "dual carbon".