Markov Transition Probability Research Articles

Forecasting Non-stationary Time Series Using Deep Learning in a Fuzzy Time Series Framework and its Application to Stock Markets

Non-stationary time series prediction is challenging due to its dynamic and complex nature. Fuzzy time series models offer a promising solution for forecasting such data, but a key challenge lies in partitioning the universe of discourse, which significantly impacts forecasting accuracy. Traditional fuzzy time series models often use equal-length interval partitioning, which is more suited for stationary data and limits their adaptability to non-stationary time series. This paper introduces a novel variable-length interval partitioning method designed specifically for non-stationary time series. The developed method combines a Long Short-Term Memory (LSTM) Autoencoder with K-means clustering, enabling dynamic, data-driven partitioning that adapts to the changing characteristics of the data. The LSTM Autoencoder encodes the time series, which is clustered using K-means, and intervals are defined based on cluster centers. Furthermore, the Variable Length Interval Partitioning-based Fuzzy Time Series model (VLIFTS) is developed by incorporating this partitioning method and the concepts of Markov chain and transition probability matrix. In this model, fuzzy sets are viewed as states of a Markov chain, and transition probabilities are used in the forecasting phase. The model is validated on stock market indices Nifty 50, NASDAQ, S&P 500, and Dow Jones. Stationarity and heteroscedasticity are tested using Augmented Dickey-Fuller (ADF) and Levene's tests respectively. Statistical forecast accuracy metrics Root Mean Squared Error (RMSE) and Mean Absolute Percent Error (MAPE) show that VLIFTS significantly improves forecasting accuracy over traditional models. This hybrid approach enhances fuzzy time series modelling and can be applied to various non-stationary time series forecasting problems.

A lightweight progressive joint transfer ensemble network inspired by the Markov process for imbalanced mechanical fault diagnosis

Owing to safety limitations and data collection costs, scenarios with imbalanced data usually arise, posing a great challenge for precise fault diagnosis. Targeting imbalanced fault diagnosis and the high computational cost of mainstream ensemble learning methods currently used, this article proposes a lightweight and accurate scheme based on a progressive joint-transfer ensemble network (PJTEN) and a Markov-lightweight strategy (MLS). Specifically, a PJTEN is developed, incorporating a multiple excitation-channel attention basic estimator and progressive joint-transfer strategy (PJTS) to maintain diversity of basic estimators better and focus more on key information from minority classes. Besides, the MLS guided by Markov transition probabilities is for the first time constructed for ensemble learning to reduce the network redundancy by alternating optimization. Using a standard dataset and a brand-new dataset of a real ship propulsion system, the proposed method achieves leading results in Accuracy, F1 score and MCC, compared with eight cutting-edge methods, thereby validating its substantial value. In terms of lightweight operation, such as temporal complexity (TC), spatial complexity (SC), and time efficiency, it is also ahead of the latest ensemble-based methods.

Simulation of geological uncertainty based on improved three-dimensional coupled Markov chain model

The natural stratigraphic distribution is uncertain due to the geological tectonic movements and sedimentation. It is a challenge for traditional deterministic models to capture geological uncertainty. The objective of this study is to develop an improved three-dimensional coupled Markov chain (ICMC3D) model based on limited boreholes. The proposed method enhances the traditional three-dimensional coupled Markov chain model by modifying the transition probability equation for predicting unknown elements. The dip data is added to estimate the transition probability matrix with the borehole information. On this basis, a back analysis method is proposed for estimating the horizontal transition probability matrics. The method makes the predicted results more suitable for the possible stratigraphic distribution. The accuracy of the proposed method is verified through some applications. In this paper, an improved three-dimensional coupled Markov chain model and transition probability matrix estimation method are illustrated by the borehole data collected from a tunnel project in Qingdao. The results show that the presented method can reflect the asymmetry, continuity and anisotropy of the three-dimensional stratum. The exceedance probability is proposed to predict the fault zone development range in order to reduce the geological uncertainty.

Research on the coupling coordination characteristics and convergence of digital finance and regional sustainable development: evidence from Chinese city clusters

The study examines the digital finance (DF) and regional sustainable development (RSD) across 90 cities within six major city clusters in China over the period from 2011 to 2020. By constructing an evaluation index system for DF and RSD, we employed the entropy value method to assess their levels, and the coupling coordination degree (CCD) model to evaluate their interplay. Our analysis extended to temporal and spatial disparities, distribution dynamics, and the convergence of CCD through kernel density estimation, Markov chain analysis, σ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\sigma$$\\end{document}-convergence, and β\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\beta$$\\end{document}-convergence techniques. The results indicate a consistent upward trend in CCD, yet it remains at a low level with pronounced regional disparities and temporal characteristics. The kernel density distribution’s central tendency has shifted rightward progressively, albeit with a decelerating pace annually. The Markov transition probability matrix suggests a stable CCD across various levels, hinting at “club convergence”. Furthermore, both σ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\sigma$$\\end{document}-convergence and β\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\beta$$\\end{document}-convergence analyses reveal significant convergence trends in CCD, enhanced by economic growth factors. Using the Quadratic Assignment Procedure (QAP) method, we found that regional economic growth disparities significantly influence the CCD’s regional variances.

The relationship between renewable energy attention and volatility: A HAR model with markov time-varying transition probability

This study investigated whether a renewable energy attention (REA) index, based on natural language processing, Google search volume data, and dimensionality reduction methodology, can predict crude oil volatility. Considering the possible non-linear and time-varying effects, we adopted the time-varying transition probability Markov switching heterogeneous autoregressive-realized volatility (TVTP-MS-HAR-realized volatility (RV)) model. To further represent the impacts of REA, we developed an asymmetric TVTP-MS-HAR-RV model based on this model framework, i.e., the ASTVTP-MS-HAR-RV model. According to the results, the in-sample estimates indicated that West Texas Intermediate (WTI) volatility is more affected by negative REA shocks than by positive ones. Moreover, REA predicted WTI volatility better during low-volatility periods than in high ones. According to the out-of-sample findings, the ASTVTP-MS-HAR-RV-F model outperformed other competing models, indicating that time-varying transition probabilities and REA information can significantly improve volatility forecasting performance.

Markov-Embedded Affinity Learning with Connectivity Constraints for Subspace Clustering

Subspace clustering algorithms have demonstrated remarkable success across diverse fields, including object segmentation, gene clustering, and recommendation systems. However, they often face challenges, such as omitting cluster information and the neglect of higher-order neighbor relationships within the data. To address these issues, a novel subspace clustering method named Markov-Embedded Affinity Learning with Connectivity Constraints for Subspace Clustering is proposed. This method seamlessly embeds Markov transition probability information into the self-expression, leveraging a fine-grained neighbor matrix to uncover latent data structures. This matrix preserves crucial high-order local information and complementary details, ensuring a comprehensive understanding of the data. To effectively handle complex nonlinear relationships, the method learns the underlying manifold structure from a cross-order local neighbor graph. Additionally, connectivity constraints are applied to the affinity matrix, enhancing the group structure and further improving the clustering performance. Extensive experiments demonstrate the superiority of this novel method over baseline approaches, validating its effectiveness and practical utility.

Research on fault diagnosis method based on the Markov transition field with enhanced properties and AM-MSCNN under different external environmental interference

The mechanical equipment often faces complex working environments in practical operating conditions, and the external environmental interference generated by operating conditions, environmental factors and other components causes the vibration signals to exhibit characteristics with frequency distortion and multi-modality. The existing fault diagnosis methods rarely consider the issue of external environmental interference. Aiming at the background of fault diagnosis under external environment interference, a fault diagnosis method based on Markov transfer field (MTF) with enhanced properties and multi-scale convolutional neural network with attention mechanism (AM-MSCNN) is proposed. The fault features embedded in vibration signals under external environmental interference can be extracted, and an important contribution to the fault diagnosis method under external environmental interference can be made. Firstly, an interference mode selection model based on symplectic geometry modal decomposition is constructed to address the issues of distortion and multi-modality caused by external environmental interference. Next, a two-dimensional feature extraction method based on the MTF with enhanced properties is established. The challenge of extracting temporal correlation features from one-dimensional vibration signals affected by external environmental interference is addressed by Markov transition probability. The impact of external environmental interference can be mitigated, and that has strong anti-interference capability and robustness. Finally, an attention mechanism that can adaptively assign weights is designed, and the AM-MSCNN model is designed to effectively extract global features by incorporating attention mechanisms in the parallel layers of MSCNN and the attention mechanism helps to suppress external environmental interference and improve the diagnostic results. An experimental platform for simulating the typical faults under external environmental interference is constructed, and the experimental results demonstrate that the proposed method exhibits superior generalization performance under varying degrees of different interference environments. The overall average accuracy reaches 92.2%, and the highest accuracy reaches 94.0% for external interference working conditions.

Widowhood and multidimensional poverty: Evidence from Nigeria

AbstractPoverty among widows has received little empirical attention in Africa despite women's severe vulnerability to death shock. We provided empirical evidence on widow households' transition in and out of poverty and factors influencing their probability of being in poverty. The Markov transition probabilities show moderate but increasing positive transitions for severely poor widows. Non‐poor widows are stayers who primarily sustain their non‐poor class. The ordered logit estimation shows that higher dependency ratio increases the chances of a widow being severely poor. Being an older widow and having literacy skills reduced the probability that a widow household will be severely poor. Household size and dependency ratio are noted to play important roles in the probability of transitions across poverty classes as shown by the estimated multinomial logit model. These findings are robust to alternative poverty measure, estimation method and different set of weights. Generally, the results echo the need for social safety nets to cushion widows' financial strains. Life insurance policy for spouses, increased sensitization of widows of their rights and adult education programmes targeted at widows could mitigate the negative impact of widowhood on women.

Dynamics of production and export of potato from India: Markov chain approach

The present study was conducted to know the growth in area, production, productivity, and export of potatoes from India as well as to understand the change in direction and magnitude of the export of Indian potatoes to different countries. The study is based on secondary data collected from different e-resources like APEDA (Agricultural and Processed Food Export Development Authority) and Indiastat. The data was collected for a period of 15 years from 2006- 07 to 2020-21. The study revealed that all the variables like area, production, productivity, export quantity, and export values showed positive growth rates and were found to be significant at 1 percent. Markov chain analysis and transition probability matrix indicated that Nepal, Oman, and other minor countries pooled under the category “other” were found loyal to India in importing Indian potatoes since they retained a considerable share of their trade whereas Saudi Arabia is less stable and Malaysia is least stable among the competing countries considered over the study period of 15 years. Hence India can rely upon Nepal, Oman, and other minor countries in the export of its potato and therefore policies need to be oriented towards these countries in the export of potatoes in the near future.

PREDICTIONS FOR DEMENTIA PREVALENCE IN CHINA BY 2050: A MARKOV MODELING STUDY

Abstract Dementia brings a heavy burden on older adults, their family and the society at large. Accurate prediction of dementia prevlance is important for preventive strategy for fast- ageing China. The purpose of this study is to predict dementia prevalence in China by 2050, taking into account variations in dementia incidence rates and mortality rates in future. Based on two nationally representative Chinese ageing cohorts (i.e. CLHLS, CHARLS), a ten-state Markov model (IMPACT-CAM), including prevalence, transition probability and mortality rate of dementia and its associated cardiovaiscualr diseases and disability, was constructed to predict dementia prevalence in people aged above 60 years by 2050, with different assumptions on the furture trends of dementia incidence and mortality rates. IMPACT-CAM projected there were approximately 57.9 million (95% uncententiy interval 56.3-59.6 m) people with dementia by 2050, assuming constant incidence rate of dementia and declining mortality rates over coming years. In comparison with this assumption, if the incidence rate of dementia decreasing by 1.0% annually coupled with declining mortality rates, the projected number of dementia cases would be 9.8 million less; if dementia incidence and mortality rates both remained constant since 2022, the projection would be 18.5 million less. The estimated dementia prevlance for people aged 60 years in 2050 were 12.0%, 9.9% and 9.5%, respectively. Alongside the irreversible population ageing trend, the number of people with dementia in China is likely to increase rapidly in the near furture. Nevertheless, effective preventing measures of dementia would restrain the surge substantially.

Modelling of Prosumer Behaviour in Peer-to-Peer Energy Trading Environment Through Markov Chain Analysis

The emergence of distributed generation has become significant over the last few years, bringing several challenges to traditional grid-connected electricity distribution systems. Technical limitations of integrating these new renewable distributed generation to the existing electricity grid made new avenues to change the way of energy consumption, which converted traditional consumers to prosumers. Peer-to-peer energy trading platforms enable these prosumers to trade electricity with their neighbours in microgrids where new electricity markets emerge with new technologies. This research introduces a concept of peer-to-peer energy trading for grid-connected electricity distribution networks. In its initial phase, the study models prosumer load sharing for households equipped with solar PV and battery energy storage. This modelling employs a Markov chain, where energy share states are determined by parameters in a Markov transition probability matrix. These parameters are varied during different time intervals of the day, reflecting varying cost components under a Time-of-Use (TOU) tariff structure. This approach enables prosumers to meet their load demand cost-effectively, fostering engagement in peer-to-peer energy exchanges. The proposed Markov model is simulated with 15-minute spot pricing intervals, demonstrating effective management of prosumer load demands in the peer-to-peer market environment, showcasing the potential benefits of this innovative energy trading approach.

Feedback control strategy of networked multi-LSRMs system with semi-Markov topology switching and time delay

This paper studies the networked control system (NCS) with semi-Markov topology switching and network delay. The time delays of the system are considered in the measurement and control channels. The control channel is between the controller and the actuator, the measurement channel is between the sensor and the controller. The topology switching and the transition process among modes are described by semi-Markov sojourn-time probability density function and Markov transition probability matrix respectively. The mean square stability conditions for the networked multi-LSRMs system are obtained by constructing a new Lyapunov function. To ensure the σ-error mean square stability of the closed loop system, a state feedback controller is designed by combining the variation technique of inequalities and Lyapunov stability theory. Finally, several experiments results verify the effectiveness and rationality of the proposed control strategy.

Time-series forecasting of road distress parameters using dynamic Bayesian belief networks

PurposeTo proactively draw efficient maintenance plans, road agencies should be able to forecast main road distress parameters, such as cracking, rutting, deflection and International Roughness Index (IRI). Nonetheless, the behavior of those parameters throughout pavement life cycles is associated with high uncertainty, resulting from various interrelated factors that fluctuate over time. This study aims to propose the use of dynamic Bayesian belief networks for the development of time-series prediction models to probabilistically forecast road distress parameters.Design/methodology/approachWhile Bayesian belief network (BBN) has the merit of capturing uncertainty associated with variables in a domain, dynamic BBNs, in particular, are deemed ideal for forecasting road distress over time due to its Markovian and invariant transition probability properties. Four dynamic BBN models are developed to represent rutting, deflection, cracking and IRI, using pavement data collected from 32 major road sections in the United Arab Emirates between 2013 and 2019. Those models are based on several factors affecting pavement deterioration, which are classified into three categories traffic factors, environmental factors and road-specific factors.FindingsThe four developed performance prediction models achieved an overall precision and reliability rate of over 80%.Originality/valueThe proposed approach provides flexibility to illustrate road conditions under various scenarios, which is beneficial for pavement maintainers in obtaining a realistic representation of expected future road conditions, where maintenance efforts could be prioritized and optimized.

Passivity-based finite-region control of 2-D hidden Markov jump Roesser systems with partial statistical information

The problem of the finite-region passive control for 2-D Markov jump Roesser systems, in which the partial statistical information issues on Markov parameters and transition probabilities are considered simultaneously. To model this situation, a 2-D hidden Markov model with partial statistical information is established. The purpose of this paper is to design a controller based on the 2-D hidden Markov model such that both the horizontal states and vertical states of 2-D Markov jump Roesser systems are bounded in finite-time and a passive performance is met. Based on the Lyapunov function method, the criteria for the finite-region boundedness of 2-D Markov jump Roesser systems are established and the design method of the 2-D hidden Markov model-based asynchronous controller is presented. The effectiveness of the design method is verified by an illustrative example.

Economic Resilience and Sustainable Finance Path to Development and Convergence in Romanian Counties

Economic resilience and sustainable finance are two interlinked and crucial issues for development and convergence in Romania’s counties increasing cohesion. These issues can contribute to sustainable and balanced growth of local and regional economies and to the reduction of inequalities in regional development. Economic resilience in counties refers to their capacity to adapt and survive in the face of unforeseen economic shocks or challenges, and sustainable finance refers to ensuring responsible management of financial resources to support long-term development and protect the environment. Identifying and understanding the significant variations in economic resilience and sustainable financing between counties is essential for the formulation of regional development policies and strategies. These variations provide valuable information about the vulnerabilities and opportunities of individual counties and guide resource allocation and investment decisions. The research provides new data and relevant information on the significant variations among counties in economic resilience and sustainable financing, using a Markov transition probability matrix and exploratory–visual method. This study on Romanian counties aims to provide valuable information for the formulation of public policies to support balanced economic development across the country. The results showed that economic diversification is essential to increase the resilience of the economy to shocks and fluctuations. Counties that have a diversified economic structure, with multiple sources of income and economic activities, are less vulnerable to the negative impact of economic or natural events. Governance and political stability are key factors in creating a favorable environment for investment and economic development. Well-managed government policies can help maintain macroeconomic stability and increase the resilience of the economy to external fluctuations.

Spatiotemporal Evolution, Coupling Coordination Degree and Obstacle Factors of Urban High-Quality Development: A Case Study of Anhui Province

Anhui Province is located in the superposition area of the “Strategy of the Rise of Central China” and the “Strategy of Integrated Development of the Yangtze River Delta”. Analyzing the high-quality development of Anhui Province is crucial for regional development. This paper proposes a comprehensive evaluation system based on the “New development philosophy”. Then, the information entropy method is applied to measure the high-quality development index (HQDI). The Markov transition probability matrix is used to explore the evolutionary trend of the HQDI. This paper also analyzes the coupling coordination relationships between high-quality development subsystems. Finally, the obstacle factor diagnostic model is adopted to find the factors that impede high-quality development. The result shows that: (1) There exists a significant spatial gradient difference in Anhui Province. The overall spatial distribution of the HQDI shows a pattern of “high in the central and east, low in the north and south”. (2) The “club convergence effect” and the “Matthew effect” of urban high-quality development are observed. (3) Subsystem analysis verified the existence of regional differences. Hefei has the leading position in all development subsystems. (4) The coupling coordination degree of subsystems is relatively low, and the problem of disorder development within Anhui Province is significant. (5) The fixed assets’ investment, the total amount of imports and exports, the GDP, the total urban wastewater treatment and the urban road passenger volume are the main obstacle factors.

Investigating Profit Persistence Among Hungarian Plastic Manufacturing Companies

This study examines the competitive nature of the Hungarian plastics industry sector based on 2010-2019 data from the Crefoport database.. The aim of the study is to examine that how close the market of plastic industry companies is to perfect competition. Market efficiency was investigated using a Markov chain and profit persistence estimation (Arellano & Bond, 1991). Corporate profitability was measured using the ROA indicator. Variables reflecting industry and market effects are also included in the analysis as controls. Based on the Markov transition probability matrix, market competition is harmed. Based on the panel model estimation, the profit persistence value shows a low value (0.129) compared to the existing literature. The profitability of plastic companies can be statistically proven to be affected by company size (p = -0.046), short (p = 0.016) and long risk (p=-0.093), and the volatility of profitability (p = 0.633). Among the exogenous variables, industry income (p=0.081) and market concentration (p = 0.974) have a significant effect on the profitability of companies. Limited market competition reduces overall social benefit and efficiency in several ways: it reduces price competition, quality orientation, and the pursuit of innovations. Therefore, from the point of view of economic policy , it is definitely justified that the sector receives subsidies in an appropriate amount that improves the efficiency and productivity of small and medium-sized enterprises, as well as encourage technological development and innovation.

Modelling spatiotemporal tendencies of climate types by Markov chain approach : A case study in Sanliurfa province in the south-eastern of Turkey

Identification of spatiotemporal tendencies of climate types may help water managers mitigate the negative impacts of droughts on water-demanding sectors. The primary objective of this study was to figure out the spatiotemporal tendencies of climatetypes in Sanliurfa province by using Erinc’s aridity index (EDI). To that end, long-term (1965-2018) annual precipitation and average annual maximum temperature series of meteorological stations were obtained and utilized to calculate the EDI series on a yearly basis. The EDI series of each station was divided into three periods, non-overlapping and successive, i.e., P1 (1965-1981), P2 (1982-1999) and P3 (2000-2018). Outliers were detected, andremoved from the EDI series; missing data were completed by regression analysis. The Markov transition probability matrix of the climate classes for the three periods was estimated for each station. Maps of the initial probability vectors and steady-state probabilities for the three periods of each climate class were generated by the inverse distance-weighted technique. Hypsometric curves for each climate class, as well as period, were developed and areal coverage of occurrence probabilities (OP) was determined. Results indicated that, as time progressed, the areal extent of severe-arid and arid climatic classes continued consistently to spread from the south to the north. Areas of semi-arid climate type showed a slight tendency towards the arid-climate type. Construction of large dams in the region could not prevent the shifts in the climate in favour of developing arid zones. The humid climate class is likely to vanish away in the future. Research led us to conclude that the expansion of the aridzone from south to northhas been alarming in terms of the adequacy of water resources. It is strongly recommended that spatiotemporal climate change studies should be periodically conducted in tandem with forest management practices for the region.

Navigating nature’s toll: Assessing the ecological impact of the refugee crisis in Cox’s Bazar, Bangladesh

The Rohingya crisis in Myanmar’s Rakhine state has resulted in a significant influx of refugees into Cox’s Bazar, Bangladesh. However, the ecological impact of this migration has received limited attention in research. This study aimed to address this gap by utilizing remote sensing data and machine learning techniques to model the ecological quality (EQ) of the region before and after the refugee influx. To quantify changes in land use and land cover (LULC), three supervised machine learning classification methods, namely artificial neural networks (ANN), support vector machines (SVM), and random forests (RF), were applied. The most accurate LULC maps obtained from these methods were then used to assess changes in ecosystem service valuation and function resulting from the land use changes. Furthermore, fuzzy logic models were employed to examine the EQ conditions before and after the Rohingya influx. The findings of the study indicate that the increased number of Rohingya refugees has led to a 9.58% decrease in forest area, accompanied by an 8.25% increase in settlement areas. The estimated total ecosystem services value (ESV) in the research area was $67.83 million in 2017 and $67.78 million in 2021, respectively. The ESV for forests experienced a significant decline of 21.97%, equivalent to a decrease of $5.33 million. Additionally, the reduction in forest lands has contributed to a 13.58% decline in raw materials and a 14.57% decline in biodiversity. Furthermore, utilizing a Markovian transition probability model, our analysis reveals that the EQ conditions in the area have deteriorated from “very good” or “good” to “bad” or “very bad” following the Rohingya influx. The findings of this study emphasize the importance of integrating ecological considerations into decision-making processes and developing proactive measures to mitigate the environmental impact of such large-scale migrations.

Dynamic evolution characteristics and driving factors of carbon emissions in prefecture-level cities in the Yellow River Basin of China.

This paper focuses on the spatiotemporal evolution characteristics, as well as the driving factors, of carbon emissions in the prefecture-level cities in the Yellow River Basin (YB). The paper's findings will aid in promoting ecological conservation and high-quality development in the region. The initiatives undertaken in the YB are a significant national strategy towards achieving carbon peaking and carbon neutrality. To fully investigate the spatiotemporal evolution process, as well as the typical characteristics of their carbon emissions, conventional, and spatial Markov transition probability matrices were developed utilizing YB's panel data for 55 prefecture-level cities from 2003 to 2019. The generalized Divisia index decomposition method (GDIM) cleverly uses this data to conduct a complete analysis of the dynamics and driving processes influencing the change in carbon emissions in these cities. However, the evolution of carbon emissions in prefecture-level cities has reached a point of stability that maintains the original state, making it challenging to make meaningful short-term progress. The data indicates that prefecture-level cities in the YB are emitting more carbon dioxide on average. Neighborhood types in these cities significantly influence the transformation of carbon emissions. Low-emission areas can encourage a reduction in carbon emissions, whereas high-emission areas can encourage an increase. The spatial organisation of carbon emissions exhibits a "high-high convergence, low-low convergence, high-pulling low, low-inhibiting high" club convergence phenomenon. Carbon emissions rise with per capita carbon emissions, energy consumed, technology, and output scale, whereas it falls with carbon technology intensity and output carbon intensity. Hence, instead of enhancing the role of increase-oriented variables, prefecture-level cities in the YB should actively engage these reduction-oriented forces. The YB's key pathways for lowering carbon emissions include boosting research and development, promoting and applying carbon emission reduction technologies, lowering output carbon intensity and energy intensity, and improving energy use effectiveness.