Next Article in Journal
The Impact of Sustainability Knowledge Sharing on Service Innovation in Libyan Banks: The Mediating Role of Intellectual Capital and Organizational Learning
Previous Article in Journal
Modeling Critical Success Factors for Green Energy Integration in Data Centers
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Sustainability
Volume 17
Issue 8
10.3390/su17083544
sustainability-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Spatiotemporal Prediction of the Impact of Dynamic Passenger Flow at Subway Stations on the Sustainable Industrial Heritage Land Use

by
Ke Chen
1,
Fei Fu
1,2,*,
Fangzhou Tian
1,
Liwei Lin
3 and
Can Du
4
1
School of Architecture, Southwest Jiaotong University, 999 Xi’an Road, Chengdu 611756, China
2
Digital and Intelligent Construction Sub-Committee, Association of Sichuan Construction Science and Technology, 111 North Section 1, Second Ring Road, Chengdu 610036, China
3
Chenghua District Planning and Natural Resources Bureau, 33 Huatai Road, Chengdu 610052, China
4
School of Automation Engineering, University of Electronic Science and Technology of China, 2006 Xiyuan Avenue, Chengdu 611731, China
*
Author to whom correspondence should be addressed.
Sustainability 2025, 17(8), 3544; https://doi.org/10.3390/su17083544
Submission received: 11 February 2025 / Revised: 10 April 2025 / Accepted: 12 April 2025 / Published: 15 April 2025
Browse Figures
Versions Notes

Abstract

:
Inefficient land reuse has emerged as a critical pathway for the sustainable development of urban spaces. Efficient land development in megacities’ industrial heritage areas is heavily influenced by the influx of mass passenger flows from new subway stations. To address this issue, a dynamic passenger flow-oriented land use prediction model for subway stations was developed. This model iterates a simulation model for dynamic passenger flow based on tourists and residents with an artificial neural network for land use prediction. By enhancing the kappa coefficient to 0.86, the model accurately simulated pedestrian flow density from stations to streets. Experiments were conducted to predict inefficient land use scenarios, which were then compared with the current state in national industrial heritage areas. The results demonstrated that the AnyLogic-Markov-FLUS Coupled Model outperformed expert experience in objectively assessing dynamic passenger flow impacts on the carrying capacity of old city neighborhoods during peak and off-peak periods at subway stations. This model can assist in resilient urban space planning and decision-making regarding mixed land use.

1. Introduction

Urban land use has emerged as one of the most pressing issues in the study of global change and sustainable development [1]. Industrial heritage land use refers to a specific type of land that was historically employed for industrial purposes, including production, transportation, and storage. Despite the cessation of their original functions, these sites continue to preserve extant structures and facilities that possess historical significance [2]. Efficient land use planning in old city industrial heritage areas is crucial for urban development [3,4]. It can revitalize underutilized land, reshape the spatial interactions within the old city, and preserving its historic character.
Current regeneration planning for old cities prioritizes subway transportation hubs. Therefore, various aspects of industrial heritage areas exhibit significant reliance on the subway, including regional development planning, cultural and tourism integration for industrial heritage revitalization [5], and balancing the flow of tourists and citizens during peak and trough periods [6]. These dependencies pose challenges to the regeneration of the old city industrial heritage areas, particularly concerning mixed development and ensuring efficient accessibility [7,8,9]. Simultaneously, due to issues such as property rights and conflicting interests, old industrial areas lag behind in regional development, show the results of subjective decisions in functional positioning, rely on a single transformation mode, and lack sustainability. Hence, the anticipated evolution of land use around stations within the industrial heritage areas of old cities can pivot towards prioritizing dynamic subway passenger flow over natural evolution. This shift can realize the objective of smart, safe, and efficient spatial planning for integrating stations with the city [10,11,12,13].
Against this backdrop, this study focused on the station within a typical industrial heritage area, exemplified by Chengdu, Sichuan Province, which served as China’s most critical strategic reserve area during the third-line construction period. It investigated the relationship between land use changes around subway stations and industrial heritage sites. Building upon existing studies that predominantly utilize mixed land use as a sole indicator, this research introduces passenger flow simulation as a novel analytical perspective, integrating AnyLogic with the Markov-FLUS model. The model compares land use change under the natural development scenario and the policy planning scenario while predicting future land development patterns, aiming to achieve higher precision in simulation forecasting and more resilient decision support.
The contributions of this study can be summarized as follows. On the one hand, in response to the limitations of the traditional FLUS model in accurately simulating the impact of subway stations on surrounding land use, this study developed a land use prediction model that incorporates the influence of subway passenger flow. Specifically, an artificial neural network (ANN) was integrated into the model, and factors such as site accessibility calculated using the inverse distance weighting (IDW) method, point of interest (POI) kernel density, and street pedestrian density derived from AnyLogic 8.5.0 software were incorporated into the Markov-FLUS model. This study innovatively considered passenger density as a critical influencing factor in quantitatively analyzing land use simulation results under the influence of subway passenger flow, thereby enhancing the accuracy of the kappa coefficient. On the other hand, this study focused specifically on areas surrounding subway stations rather than entire subway lines. It analyzed land use changes around subway stations in industrial heritage areas, addressing the research gap in existing literature regarding land use transitions near subway stations. Compared with conventional land use planning approaches, the proposed method improves prediction accuracy, efficiency and reliability, providing a more scientifically grounded optimization strategy for the sustainable development and spatial transformation of land surrounding subway stations.

2. Literature Review

The correlation between subway systems and land use has long been a research focus. Cervero and Kockelman proposed a transit-oriented development (TOD) model characterized by rational land development intensity, diversified functions, and pedestrian-friendly spatial configurations [14]. With the rapid construction and development of subway stations, scholars have increasingly examined factors influencing land use around stations, including population density [15,16], floor area ratio [17], station location [18], compactness, and accessibility [19]. Existing studies suggest that subway system expansion profoundly impacts land adjacent to transit hubs, affecting land prices [20,21], land use structures, and development intensity [22]. Research on the relationship between subway passenger flow and land use has utilized multiple regression models, cluster analysis methods, and machine learning techniques to analyze connections between ridership patterns [23], temporal characteristics of passenger flow [24], travel distances [25], and land use configurations. While these studies have explored diverse factors influencing land use under subway impacts, they inadequately address the effects of neighborhood-scale pedestrian flow dynamics on land use transitions near stations.
Traditional urban land use planning, relying on governmental and expert experiences [26], often fails to accommodate the requirements of transition periods, such as by using small-scale and refined planning. To address the challenge that those methods hardly cope with the processing and analysis of the involved multidimensional spatiotemporal data, spatial planning techniques have been introduced for large-scale data. Since the introduction of geographic information systems (GISs) in the 1970s [27,28,29], significant progress has been made in urban land use planning. In recent years, the development of the “multiple-planning integration” collaborative platform has been designed to support decision-making in this field [30]. Furthermore, tools for simulating and predicting land use along public transit corridors have evolved, with widespread adoption of CLUE-S, PLUS, FLUS, and CA-Markov models. For instance, the widespread adoption of the cellular automata model has contributed to the development of the CA-Markov model, facilitating the quantitative analysis of land use dynamics around subway stations [31,32,33,34]. Previous studies predominantly selected large-scale regions—such as China’s semi-arid northern zones [35], the Kathmandu Valley and its periphery [36], the Chicago subwaypolitan area [37], Egypt’s northwestern coastal desert [38], and Giza Province in Greater Cairo [39]—as subjects for land use change simulations, while research on small-scale land use transitions remains limited. Academic investigations into subway–land use relationships have emphasized city-scale coordination between rail corridors and land use, with insufficient discussion on localized land use changes near subway stations [40].
In addition, the regional structural attributes of old city industrial heritage areas are notably more intricate than those of other types of areas. As old city renewal continues, the old industrial areas have experienced extensive spatial transformation and adjustments to land regulatory plans. Hence, it is imperative to consider both top-down policy planning and bottom-up natural evolution when assessing the impact of subway stations on surrounding land use [41,42]. Changes in land use around stations are not entirely dominated by rail transit construction and operation. Other factors, such as urban planning and governmental decisions, also play a significant role in affecting land use growth around rail transit [43,44,45]. In summary, current academic research predominantly focuses on the natural evolution of land use along entire subway lines, often overlooking the dynamic influence of subway passenger flows on urban blocks and the role of policy interventions in shaping land use patterns.

3. Materials and Methods

3.1. Study Area

Chengdu City, located in Sichuan Province, served as a critical strategic backup area during China’s third-line construction period. The study area, situated in the industrial site of Balizhuang, Chengdu, exhibits typical land characteristics of urban industrial heritage areas (Figure 1). The Balizhuang Station, part of Chengdu subway Line 7, commenced construction in 2013 and became operational in 2017. Accordingly, this study examined Chengdu subway Balizhuang Station during three distinct periods (2015, 2019, and 2023), using land use data from planning to operation, and evaluated the impact of subway construction on land use in the urban industrial heritage area under policy planning interventions.

3.2. Data and Preprocessing

3.2.1. Data Acquisition

Land use data for the area surrounding Balizhuang Station was extracted from high-resolution historical satellite imagery for the years 2015, 2019, and 2023. Manual visual interpretation of the imagery, supplemented by comprehensive analysis of relevant land development policies and urban planning documents, ensured accurate identification and classification of land use types.

3.2.2. Data Preprocessing

(1)
Spatial Consistency Processing
To standardize the data, the coordinate system was unified to Beijing_1954_3_Degree_GK_Zone_35. Spatial alignment was achieved using the Resample tool in ArcGIS 10.8 software, with all raster data resampled to a uniform resolution of 5 m × 5 m.
(2)
Land Use Reclassification
By considering the scale and functional differences of the study area, and referencing Chinese National Standards such as the Current land use classification (GB/T 21010-2017) [46] and the Code for classification of urban land use and planning standards of development land (GB 50137-2011) [47], the land use types were categorized into ten classes: public service land, commercial land, ecological land, industrial land, transportation land, municipal utility land, second-class residential land, third-class residential land, water bodies, and unused land.
(3)
Data Cleaning
The data cleaning procedure encompassed two critical steps: missing value imputation and anomaly rectification. First, missing values in the original land use raster data caused by cloud cover were repaired using the mode imputation method from adjacent years. Second, ambiguous land types (e.g., construction sites in historical satellite imagery) were resolved by cross-referencing relevant land policies and urban planning documents.

3.2.3. Data Sources

Road data were obtained from both the OpenStreetMap platform (http://www.openstreetmap.org/ “accessed on 11 February 2024”) and Chengdu’s comprehensive traffic planning map.
Elevation data were sourced from the Global Digital Elevation Model, accessible via the Geospatial Data Cloud platform (http://www.gscloud.cn/ “accessed on 11 February 2024”).
Point of interest (POI) data for the station and its surrounding area were acquired from the Baidu Map platform (https://lbsyun.baidu.com/ “accessed on 13 February 2024”).
Station accessibility data were retrieved from the Baidu Web Services API (https://lbsyun.baidu.com/ “accessed on 13 February 2024”).
The passenger flow data were obtained from the average hourly passenger flow during both peak and off-peak hours in 2023, as provided by Guangzhou Subway Design & Research Institute Co., Ltd. (Guangzhou, China).
The relevant land policies and urban planning documents included the National Spatial Master Plan of Chengdu (2021–2035), the Protection and Utilization Plan for Balizhuang’s Industrial Heritage, and the Implementation Plan for the Urban Renewal Unit of Balizhuang’s Industrial Heritage Area.

3.3. Methodology

3.3.1. Preparation of Impact Factors for Simulation of Land Use Evolution Around Subway Stations in Industrial Heritage Areas of Old Cities

Land use dynamics in industrial heritage areas are complex, and decision-makers often struggle to accurately comprehend the evolution mechanisms of land use around subway stations under the influence of subway infrastructure. Previous studies have predominantly relied on static indicators, such as elevation, slope, and POI kernel density, as influencing factors in the Markov-FLUS model. This study introduces an innovative passenger-flow-oriented land use prediction model for subway stations, incorporating street pedestrian density as an additional influencing factor to enhance simulation accuracy and support more resilient decision-making.
The uniform sampling method was employed to collect data on land use and its impact factors. Subsequently, six impact factors, including elevation, slope, proximity to roads, accessibility to subway stations (Figure 2a), kernel density of POIs (Figure 2c), and pedestrian density on roads (Figure 2b), were integrated into a backpropagation artificial neural network (BP-ANN) model. The probability of development for each land type was calculated using an ANN, and the probability of suitability for each land type was then obtained. Future land use was predicted using the Markov model, and the coupled future land use simulation model was adopted to calculate the distribution probability. The future land use for each land use type was predicted by combining the quantity of each type of land use with its spatial distribution.
(1) Passenger flow simulation of neighborhoods around subway stations using AnyLogic software
AnyLogic simulation software applied the widely accepted social forces model for pedestrian dynamics, which more accurately represented the continuous movement of pedestrians. Specifically, this study refined pedestrian flow density in street areas, thus obtaining a more accurate depiction of population gathering and congestion in the study area.
(2) Kernel density set of the dynamic POIs
Utilizing the kernel density of POIs to examine land use around subway stations offers insights into urban functional accumulation at a microscopic level [48]. By employing the kernel density analysis tool in ArcGIS, we performed operations such as mask extraction and reclassification. The kernel density values were subsequently categorized into five classes according to the natural break classification and then imported into the Markov-FLUS model.
(3) Accessibility of dynamic passenger flow to subway stations
To quantify the accessibility challenges faced by residents and tourists in reaching subway stations within the study area, this study employed the inverse distance weighting method for interpolation using ArcGIS software. Subsequently, the resulting raster image was extracted based on the land use image of the research area using a mask, and the projected coordinate system was standardized. Visualizing the point data through the ArcGIS platform provided an intuitive representation of station accessibility [49], which was a core impact factor in the coupled model.

3.3.2. Development of AnyLogic-Markov-FLUS Coupled Model

The Markov-FLUS model surpasses the CA-Markov model in terms of accuracy, particularly in simulating land use changes during rapid urban development. The AnyLogic-Markov-FLUS model was employed, representing a synergistic integration of the dynamic passenger flow simulation and land use prediction models. Future land use quantities were predicted with the assistance of the Markov model, and the distribution probabilities of various land types were determined through the incorporation of the FLUS model. The dynamic passenger flow distribution and density layers were generated by enhancing the AnyLogic model. Through merging the quantities of each land use type with its spatial distribution, the prediction and simulation of future land use scenarios for each type were enabled by the coupled model.
Markov is a statistical model commonly employed in research on predicting land use change [50,51]. The calculation principle is as follows:
S ( t + 1 ) = S ( t ) × P i j
P i j = P 11 P 12 . . . P 1 n P 21 P 22 . . . P 2 n . . . . . . . . . . . . P n 1 P n 2 . . . P n n
where S(t+1) and S(t) denote the state of the land use type at moment t + 1 and at moment t, respectively, n denotes the number of land use types, i and j represent the land use types at the initial and final stages of the study period, respectively, and Pij denotes the land use state transfer matrix.
The FLUS model addresses the uncertainty of land class conversion competition by incorporating an ANN model represented by the following equation [52,53,54]:
p   ( p , k , t ) = ∑ j w j k × 1 1 + e − n e t j ( p , t )
where p (p, k, t) denotes the distributional fitness probability of the transformation of cell p into land use type k at time t; wjk denotes the weights of the hidden layer and output layer; and netj (p, t) denotes the signals received by neuron j from all input neurons on cell p at time t.
For neighborhood factor parameters, this study referenced existing research results and utilized the 3 × 3 Moore neighborhood model to calculate the following equation [55]:
Ω g , k t = ∑ 3 × 3 c o n   ( c g t − 1 = k ) 3 × 3 − 1 × w k
where c o n   ( c g t − 1 = k ) is the total number of cellulars occupied by station type k at the last iteration t − 1; wk is the neighborhood factor parameter for each type of station; and Ω g , k t is the neighborhood influence factor of tuple g at moment t.

3.3.3. Construction of Suitability Map Using the AnyLogic-Markov-FLUS Model

In the context of old industrial areas undergoing transformation, the land within industrial heritage zones was typically in a transitional phase, from industrial use to other land classifications. The fluctuating trend of land change around subway stations resulted in rapid alterations in land properties and spatial patterns over short periods of time. Consequently, accurately simulating a region’s evolution and development could require consideration of multiple impact factors rather than relying on a single factor. Therefore, the suitability probability atlas was constructed using 2019 as the base year, with 2019 land use data employed to simulate the land use scenario for 2023. The 2023 land use simulation data under the two scenarios were compared with the actual 2023 land use data to validate the accuracy and reliability of the AnyLogic-Markov-FLUS model. In this study, the kappa coefficient and root mean square error (RMSE) of the suitability probability atlas were employed to comprehensively evaluate the model’s reliability. The kappa coefficient quantifies the degree of agreement between the model predictions and the observed data. A higher kappa coefficient indicates stronger consistency between the model predictions and the observed data, reflecting greater model reliability. The root mean square error (RMSE) of the suitability probability atlas measures the average deviation between the predicted suitability probability distribution and the observed data. A lower RMSE value indicates a closer match between the predicted probabilities and the observed data, demonstrating stronger spatial simulation capabilities of the model [56].
The simulation results revealed that under the natural development scenario, a substantial portion of industrial land remained in the study area by 2023 (Figure 3a), significantly deviating from the actual situation. The kappa coefficient was below 0.75, and the RMSE of the suitability probability atlas exceeded 0.5, indicating suboptimal model performance. Under the policy planning scenario, the attributes of land under construction were adjusted in accordance with the regulatory plan for the study area. Other land types were restricted from conversion to industrial land, resulting in a kappa coefficient of 0.86 and an RMSE of the suitability probability atlas of 0.155, demonstrating strong model performance (Figure 3b). These results suggest that the model exhibits high reliability in optimizing policy-planning scenarios. Therefore, the AnyLogic-Markov-FLUS coupled model is suitable for simulating and predicting land use evolution in the study area through 2027.

3.3.4. Design of a Dynamic Passenger Flow-Oriented Land Use Prediction Model Based on Tourists and Residents from Subway Stations

Figure 4 shows the research framework. A dynamic passenger flow-oriented land use prediction model was innovatively designed based on tourists and residents from subway stations, and certain influencing factors, such as accessibility to subway stations, street pedestrian density, and kernel density of POIs, were imported into the Markov-FLUS model. The spatiotemporal dynamic evolution of land use around Balizhuang Station from planning to operation stages was simulated. The 2023 land use status quo was compared with simulations under natural development and policy planning scenarios, resulting in a kappa coefficient of 0.86 under the optimal scenario (i.e., policy planning). Additionally, hourly station entry and exit passenger flows during peak and trough periods were batch-imported into the AnyLogic software to visualize hotspots in the street space of the industrial heritage neighborhood. Finally, the land use around Balizhuang Station in 2027 was predicted. The simulation results elucidated the impact of subway stations on spatiotemporal land use patterns in urban industrial heritage areas, providing a reference to local governments in formulating urban development policies related to urban rail transit.

4. Results

4.1. Historical Evolution of Land Use Around Stations

The validation results of the optimization scenarios revealed significant variations in land use types along the subway line in 2015, reflecting the typical characteristics of old industrial areas. Subsequently, from 2015 to 2023, there were substantial changes in land use around the stations as they transitioned from the planning to operational phases. Notably, within the research area, the most substantial changes occurred in industrial, second-class residential, and commercial lands. The shift in transportation modes and widespread factory demolitions drove a significant conversion of industrial and mining storage land to residential and commercial uses. Furthermore, the proportion of ecological land increased by 8.32%, whereas the changes in other land areas were minimal. In summary, the overarching trend in land use changes within an 800 m radius around Balizhuang Station was as follows. First, the land area allocated to low-income, low-density industrial and mining storage has significantly decreased. Conversely, the area of high-yield, high-density land, particularly two types of residential land and commercial service facility land, has increased. Second, the ecological land was experiencing a gradual increase and broader distribution, and was emerging as a vital element of urban public land. Additionally, as land use mixing increased in the station vicinity, the spatial structure was transferred from a singular to a mixed pattern, encompassing combinations like residential mixed commercial and industrial mixed residential, demonstrating efficient urban land utilization. With the progress of old city renewal, land use around subway stations gravitates towards high-density, high-profit, and high-quality types [57], aligning with established urban land use development patterns influenced by subway interventions.

4.2. Spatial Optimization Response of Street Spatial Carrying Capacity Under the Influence of Dynamic Passenger Flow

Although simulating land use evolution around subway stations can aid long-term planning decisions in old city industrial heritage areas from a macroscopic perspective, it may fail to accurately capture the effects of dynamic passenger flows on neighborhood public space carrying capacity during peak and off-peak periods at subway stations. To explore the subway’s construction and operation impacts on the spatial structure around stations in the old city’s industrial heritage areas, this study adopted two approaches. In this study, the average passenger flow density was utilized as the core impact factor for land use prediction in the research area. Additionally, the social force modeling theory was investigated to analyze pedestrian flow characteristics and interactions. Through the application of the AnyLogic pedestrian simulation software, the neighborhood pedestrian density was visually analyzed to study the spatial structures around subway stations. Figure 5a and Figure 5b depict the simulation scenarios of Balizhuang Station during peak and off-peak hours in 2023, respectively.
First, during the peak operational hours of subway stations in 2023, a surge in passenger flow into the industrial heritage zones of the old city occurred instantaneously, causing congestion at certain neighborhood locations. This scenario presented challenges to the carrying capacity of the old city’s neighborhoods. Based on the peak period passenger flow data (2081 passengers per hour), this study conducted dynamic passenger flow simulations, identifying approximately 19 locations with a congestion probability exceeding 90% (Figure 6a). These congestion points were primarily located at the intersections of passenger flows entering and exiting the station, at street corners in residential and functional mixed areas, or at other narrow sections of roadways. Second, the opening of subway stations in the old city’s industrial heritage area reshaped the spatial structure, creating new hubs for pedestrian flow and fostering new consumption scenarios. Overlaying the simulated diagrams with the distribution maps of industrial heritage reconstruction revealed that the commercial and mixed land use along the subway line experienced the highest congestion. Closer proximity to subway lines correlated with the higher degree of reuse of the industrial heritage areas. Comparing the crowd activity diagrams during the construction period of Balizhuang subway station in 2019 with daily crowd density diagrams of the research area in 2023 (Figure 6b,c), the interactions between crowd activities influenced by subway stations and the regeneration of old city industrial heritage areas became apparent. However, these areas with iconic industrial heritage attract tourists who often chart their own paths and create new focal points for foot traffic. In addition, visitors brought by subway stations may interact with or conflict with local residents in terms of activity space. The industrial heritage sites around subway stations can be scattered, with the land attributes belonging to the period including commercial, ecological, and residential land.

4.3. Spatiotemporal Evolution Prediction of the Mixed Land Use Pattern Around Stations Under Transit-Oriented Development (TOD)

The prediction results demonstrated a constant reduction in industrial land by 2027, with residential land dominating the district. The commercial land distributed along the subway line was expected to increase further (Figure 7). The model predictions aligned with the policies, and the transformation of the old industrial area illustrated the impact of subway operations on the surrounding environment. Although the land around the stations began to transition to a more efficient pattern during the subway planning and construction period, external factors such as property rights and topography constrained this transition, resulting in minimal changes in land area. Following the commencement of subway operations, the development of high-density residential and commercial land has been incentivized through economic measures such as tax incentives, subsidies, and investment incentives. The significant intensification of land development, driven by government regulations and economic incentives alongside improved infrastructure, has substantially contributed to the transformation of station functions [58,59,60].
By 2027, industrial and unutilized land around subway stations will have accounted for only 2.3% of the total research area (Figure 8), predominantly situated alongside old settlements near the stations, resulting in scattered unused land in the community. Industrial land will be transformed into second-class residential and commercial land, comprising 38.5% and 26% of the transformed land area, respectively (Figure 9). The subway has presented a catalytic function, effectively facilitating the transformation of underutilized and inefficiently used land around stations into mixed-use areas encompassing residential, commercial, office, cultural, and other functions. Meanwhile, residential land areas have gradually merged with other land types in the vicinity, diversifying the area from single-use residential attributes to a mixed pattern of commercial and residential land along the subway line. In the relevant urban planning policy documents, there was a proposal to “support the integrated use of land” [61,62,63]. This aimed to advance the multifaceted form and function of land holistically, thereby improving land use efficiency. These policies are consistent with our predictions of future development trends in the old industrial areas. Although the rapid expansion of the subway network has not reduced or fragmented the ecological landscape areas along its routes, it failed to fully achieve the optimal distribution of public open spaces. Notably, a significant concentration of industrial heritage sites awaiting transformation within the study area did not meet the higher-level planning requirements. Consequently, the public space environment surrounding these stations requires further enhancement.

5. Discussion

5.1. Influencing Factors and Simulation Results of the AnyLogic-Markov-FLUS Coupled Model

5.1.1. Influencing Factors of the AnyLogic-Markov-FLUS Coupled Model

The selection of influencing factors in the AnyLogic-Markov-FLUS coupled model directly influences the simulation results of land use. Currently, there is a scarcity of relevant studies focusing on land use prediction simulation at the regional scale around subway stations. Moreover, there is a significant lack of studies examining the impact of passenger flow from subways on land use prediction outcomes. The AnyLogic-Markov-FLUS coupled model can more precisely capture the current state of land use intensive development guided by transit-oriented development, considering influencing factors such as the transportation road network, point of interest kernel density, and station accessibility when predicting small-scale land use around the Balizhuang Station. The simulation outcomes can serve as a scientific foundation for urban planning in the industrial heritage area.

5.1.2. The Impact of Dynamic Passenger Flows Influenced by Subways on Land Use

The passenger flow density influenced by subways is one of the main driving forces for the change of land use in the surrounding areas of stations. The simulation results fully demonstrate the impact of subway operation on the surrounding areas, especially in terms of the income and distribution of plots. Specifically, under the influence of subway stations, the low-efficiency land use around the stations has been transformed into high-density residential and commercial land use, and the degree of land use mixture has increased. During the planning and construction period of rail transit, the land use types began to shift towards a more efficient model. However, a series of external factors during the construction process initially limited this transformation to the increase or decrease of a small number of plots. After the subway operation, the degree of land use mixture and development intensity around the stations have significantly improved. There is a non-linear relationship between the degree of land use mixture around the stations and the pedestrian flow in the blocks [64]. The operation of subway stations can promote the high-density development of the land around the stations, which is in line with the concept of compact cities. In addition, except for industrial land, the conversion ratio of second-class residential land and commercial land is significantly higher than that of other land use types, revealing the high sensitivity of residential and commercial functions to the influence of subways. Therefore, the future trend of planning and updating the surrounding areas of stations should focus on small-scale and micro-updates. It is necessary to control the quantity and proportion of various types of land use, and at the same time carry out gradient control of land use planning to avoid too many single development functions around the stations.
Against the background of urban renewal, the connection of subway stations in old industrial areas can reconstruct the regional spatial structure, form new nodes of pedestrian aggregation, and develop complex economic scenarios. Conducting pedestrian flow simulation analysis at the street scale can use simulation technology to assess the traffic conditions of blocks and determine the distribution and aggregation patterns of pedestrian flow in the station area. By precisely simulating the pedestrian flow density from subway stations to surrounding street spaces, multiple congestion nodes can be identified. Combined with the human–scene interaction effect, this can provide a basis for formulating efficient, flexible, and intelligent land use strategies in the station area, promoting the integrated development of subway stations and the urban environment.

5.1.3. Simulation Results of the AnyLogic-Markov-FLUS Coupled Model Under Policy Planning Scenarios

During the application of the AnyLogic-Markov-FLUS coupled model simulation, due to the complexity of the model’s transformation rules, the influences of natural, social, and economic factors on land use changes should be comprehensively considered [50]. This study set two scenarios of cellular transformation rules and compared the prediction results of the AnyLogic-Markov-FLUS coupled model under the natural development scenario and the policy planning scenario. It was found that the coupled model under the policy planning scenario could more accurately reflect the land use changes around metro stations after the advent of subway access, indicating that the land use changes around metro stations are significantly influenced by policies.
Under the traditional model of single industrial land use, it is difficult to meet the current urban development requirements. The simulation results show that under the influence of policy planning, whether the land use attributes around the stations change mainly depends on the major construction projects planned by the government along the subway operation lines. The land use in areas not involved in the projects mainly converts to commercial and residential land, serving the development of regional clusters. The land use types gradually mix, with the emergence of functionally compatible land such as residential and commercial, and the differences in land use types on both sides of the metro lines gradually decrease. It is predicted that by 2026, the fragmented land resources along the metro lines will be unified and integrated to form a systematic commercial area, and gradually promote the industrial and cultural transformation and integration with tourism. The analysis of land use changes around post-planning stations revealed the pivotal period between station completion and operation, gradually establishing stable spatial patterns and land use characteristics [65]. Future regeneration trends should shift the focus from overall area planning to intelligent micro-renewal strategies [66]. Furthermore, confronted with the phenomenon of tourist play spaces overlapping with public spaces essential for local residents’ daily lives, it is imperative to promote the integrated utilization of land based on the characteristics of urban industrial heritage zones [67,68,69]. During the refurbishment of public spaces in the area, it was essential to enrich interactive zones for both tourists and local inhabitants, enhance access to repurposed industrial heritage sites, and explore the untapped potential of idle spaces in industrial neighborhoods.

5.2. Application of Research Results

Currently, urban land planning near old city subway stations relies primarily on governmental and expert human intervention. To support government and expert decision-making, this study introduced a systematic workflow for “land planning around old subway stations and spatial reuse of industrial heritage” (Figure 10). Within this workflow, historical image data of the target area were put into a passenger flow-oriented land use prediction model for the subway station. This process adjusted the land use data produced by the ANN to generate a future land planning prediction atlas for the vicinity of the station. Subsequently, the data on passenger flow into and out of the subway station during peak and off-peak hours, supplied by the subway operator, were imported into the model. These data were adopted to simulate the walking paths of crowds and forecast future instant spatial pedestrian density in the surrounding area. Finally, this method provided a step-by-step predictive dataset, from long-term land planning around old city subway stations to short-term spatial reuse of industrial heritage, offering valuable insights to government officials and experts.
(1)
By conducting a visual analysis of historical changes and the current status of land use around the site, future land use changes are simulated and predicted to assess the feasibility of current policy planning directions. Recommendations are proposed for future planning in the area to prevent policy disconnection.
(2)
During the early stages of site construction, the impact of site planning on old city reconstruction is evaluated, including changes in regional population structure, economic conditions, and the job–housing balance. Through comprehensive analysis, the rationality of the policy is assessed.
(3)
The efficient and refined implementation of policies should be encouraged. By analyzing crowd dynamics around subway stations, policy implementation can be dynamically adjusted. Future renewal efforts should prioritize small-scale and micro-renewal strategies within the broader regional planning framework, fostering wider social participation, driving area renewal, and reconstructing the regional spatial structure.

5.3. Optimization Strategy for Land Use Around Stations

Urban land use change is influenced by a variety of factors under the guidance of urban planning, resulting in the outward expansion of urban spatial boundaries and the renewal of land within the city. The relationship between rail transit and land use is intricate and multifaceted. Passenger flow from stations serves as a critical link between the two, significantly impacting the determination of urban land use scale, intensity, and spatial distribution. Based on these considerations, the following strategies are proposed:
(1)
Develop an integrated station-city planning framework to promote mixed-use land development. In old industrial areas, increase the allocation of mixed-use land parcels. Following the principles of functional compatibility, mutual non-interference, and shared infrastructure, facilitate the rational conversion of abandoned industrial land into other land types, thereby enhancing both the morphological and functional integration of land use.
(2)
Consolidate fragmented and inefficient land to achieve comprehensive revitalization of old industrial areas. Classify and evaluate underutilized land and low-value industrial heritage sites. Leverage the guiding role of rail transit in shaping urban development patterns to activate idle land resources within the region. Through comprehensive planning of the aboveground and underground spaces surrounding the subway station, the comprehensive development of the city is facilitated, thereby reshaping the spatial form of the old industrial area.
(3)
Continuously advance urban micro-renovation initiatives while optimizing the urban ecological system. In the future, land use in old industrial areas will shift from large-scale development to urban micro-renewal. Therefore, it is crucial to fully leverage residual urban spaces to increase the provision of green spaces, plazas, and public service facilities. Ecological conservation measures will be rigorously implemented during rail transit construction, while enhancing the strategic coordination and regulatory functions of territorial spatial planning to ensure green and low-carbon development objectives.

5.4. Contributions and Limitations

The renewal planning of industrial heritage areas in old cities is a long-term process. In this study, a passenger flow-oriented land use prediction model was innovatively developed for station areas, utilizing street pedestrian density derived from the AnyLogic model as an influencing factor in land use evolution. Building on the AnyLogic-Markov-FLUS coupling model and existing research on mixed land use, this study adopted a unique perspective of dynamic passenger flow to predict future land development scenarios, aiming to achieve higher simulation accuracy and more resilient decision-making support, while proposing optimization strategies for land and transportation development in urban industrial heritage areas. Traditionally, this task relied heavily on the expertise of governmental and human specialists. Notably, our model enhanced the planning support with the real-time iteration of influencing factors to increase accuracy and comprehensiveness.
Future efforts should expand the sample size to refine our model further, such as identifying subway station impact zones more distinctly or incorporating a broader array of sample types. Moreover, simultaneously considering the interactive dynamics of passenger flow among multiple stations could optimize the synergistic effects on land use and spatial planning across the entire old industrial area of the city [12]. Although our model included objective indicators such as subway station passenger flow, station accessibility, and POI kernel density, planning for the renewal of industrial heritage areas in old cities also necessitates the integration of subjective factors, such as industrial culture, historical significance, and emotional connections. Incorporating these indicators into our research framework can facilitate a more nuanced refinement of the overall process.

6. Conclusions

The integration of urban rail transit systems and land use is crucial for sustainable urban development. Therefore, throughout the entire process of subway planning, construction, completion, and operation, urban industrial heritage areas should actively guide the optimization and adjustment of land use around stations. This study employs the AnyLogic-Markov-FLUS coupled model. Building on the traditional FLUS model, street pedestrian density under the influence of stations is incorporated as an influencing factor to enhance the accuracy of land use simulation and prediction around subway stations. Through the simulation and prediction results of the coupled model, it is found that under the influence of subway stations, the low-efficiency land around the stations is transformed into high-density residential and commercial land, the land use mix degree increases, and new pedestrian aggregation nodes are formed. Under policy intervention, it is predicted that by 2027, the fragmented land resources along the subway lines will be unified and integrated, further promoting industrial transformation. The model framework can be extended to other old industrial areas to evaluate the impact of urban transportation systems on land development, visualize future land use scenarios, and provide effective spatial planning intervention strategies for sustainable urban development.
In the future, urban planning and construction around subway stations should focus on a more in-depth analysis of the impact of subway systems on land use changes. This will facilitate the formulation of integrated development plans that harmonize station and city functions within urban industrial heritage areas, thereby promoting the efficient and composite utilization of land resources. For instance, it is essential to fully utilize inefficient land, opportunistic spaces, and other idle public areas to increase space designated for public activities, while reinforcing the cultural memory of these locations.

Author Contributions

Conceptualization, F.F.; formal analysis, K.C.; resources, L.L.; software, K.C. and C.D.; supervision, F.F.; validation, F.T.; visualization, K.C.; writing—original draft, K.C.; writing—review and editing, F.T. All authors have read and agreed to the published version of the manuscript.

Funding

This research was funded by Science and Technology Project of the Sichuan Provincial Department of Housing and Urban-Rural Development in China, National Social Science Foundation of China under Grant No. 19BSH101, Development of a Photovoltaic and AI-Driven Smart Energy Management System for High-Speed Railway Hubs, and Research on the Application of Green Energy Systems in Urban Renewal Projects.

Institutional Review Board Statement

Not applicable.

Informed Consent Statement

Not applicable.

Data Availability Statement

The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request.

Conflicts of Interest

The authors declare no conflict of interest.

Code Availability

Codes and materials used to produce this work are available upon request.

References

  1. Xie, H. Towards Sustainable Land Use in China: A Collection of Empirical Studies. Sustainability 2017, 9, 2129. [Google Scholar] [CrossRef]
  2. Jin, L.S.; Chen, C. Study on the Protective Development Strategy of the Industrial Land of the Remaining Type of Northeast Pharmaceutical Factory under the Background of Stock Renewalban. Ind. Constr. 2021, 51, 81–86+80. [Google Scholar] [CrossRef]
  3. Gao, J.; O’Neill, B.C. Mapping global urban land for the 21st century with data-driven simulations and Shared Socioeconomic Pathways. Nat. Commun. 2020, 11, 2302. [Google Scholar] [CrossRef] [PubMed]
  4. Bibri, S.E.; Krogstie, J.; Kärrholm, M. Compact city planning and development: Emerging practices and strategies for achieving the goals of sustainability. Dev. Built Environ. 2020, 4, 100021. [Google Scholar] [CrossRef]
  5. Yang, X.S.; Xu, H.; Wall, G. Creative destruction: The commodification of industrial heritage in Nanfeng Kiln District, China. Tour. Places Asia 2021, 11, 54–77. [Google Scholar] [CrossRef]
  6. Peng, H.; Wang, H.F.; Du, B.; Bhuiyan, M.Z.A.; Ma, H.Y.; Liu, J.W.; Wang, L.H.; Yang, Z.Y.; Du, L.F.; Wang, S.Z.; et al. Spatial temporal incidence dynamic graph neural networks for traffic flow forecasting. Inf. Sci. 2020, 521, 277–290. [Google Scholar] [CrossRef]
  7. Lin, D.; Broere, W.; Cui, J.Q. Metro systems and urban development: Impacts and implications. Tunn. Undergr. Space Technol. 2022, 125, 104509. [Google Scholar] [CrossRef]
  8. Weiss, D.J.; Nelson, A.; Gibson, H.S.; Temperley, W.; Peedell, S.; Lieber, A.; Hancher, M.; Poyart, E.; Belchior, S.; Fullman, N.; et al. A global map of travel time to cities to assess inequalities in accessibility in 2015. Nature 2018, 553, 333–336. [Google Scholar] [CrossRef]
  9. Hong, X.; Ji, X. Prediction of Underground Space Development Function of Existing Industrial District in City Based on CA-Markov Model. E3S Web Conf. 2021, 237, 04019. [Google Scholar] [CrossRef]
  10. Chen, Y.L.; Chen, Z.L.; Guo, D.J.; Zhao, Z.W.; Lin, T.; Zhang, C.H. Underground space use of urban built-up areas in the central city of Nanjing: Insight based on a dynamic population distribution. Undergr. Space 2022, 7, 748–766. [Google Scholar] [CrossRef]
  11. Son, T.H.; Weedon, Z.; Yigitcanlar, T.; Sanchez, T.; Corchado, J.M.; Mehmood, R. Algorithmic urban planning for smart and sustainable development: Systematic review of the literature. Sustain. Cities Soc. 2023, 94, 104562. [Google Scholar] [CrossRef]
  12. Liu, L.W.; Zhang, M.; Xu, T. A conceptual framework and implementation tool for land use planning for corridor transit oriented development. Cities 2020, 107, 102939. [Google Scholar] [CrossRef]
  13. Ibraeva, A.; Correia, G.H.D.; Silva, C.; Antunes, A.P. Transit-oriented development: A review of research achievements and challenges. Transp. Res. Part A Policy Pract. 2020, 132, 110–130. [Google Scholar] [CrossRef]
  14. Cervero, R.; Kockelman, K. Travel demand and the 3ds: Density, diversity, and design. Transp. Res. Part D Transp. Environ. 1997, 2, 199–219. [Google Scholar] [CrossRef]
  15. Calvo, F.J.; Oña, J.D.; Arán, F. Impact of the Madrid subway on population settlement and land use. Land Use Policy 2013, 31, 627–639. [Google Scholar] [CrossRef]
  16. Sekar, S.P.; Gangopadhyay, D. Impact of rail transit on land use and development: Case study of suburban rail in Chennai. J. Urban Plan. Dev. 2017, 143, 04016038. [Google Scholar] [CrossRef]
  17. Kuang, M.Y.; Fu, F.; Tian, F.Z.; Lin, L.W.; Du, C.; Zhang, Y.S. Study on Subway Station Street Block-Level Land Use Pattern and Plot Ratio Control Based on Machine Learning. Land 2025, 14, 416. [Google Scholar] [CrossRef]
  18. Li, L.; Li, H. A study on fuzhou-xiamen high speed rail route and station site specification. Planners 2016, 32, 28–33. [Google Scholar] [CrossRef]
  19. Ma, X.L.; Chen, X.; Li, X.P.; Ding, C.; Wang, Y.H. Sustainable station-level planning: An integrated transport and land use design model for transit-oriented development. J. Clean. Prod. 2018, 170, 1052–1063. [Google Scholar] [CrossRef]
  20. Celik, H.; Yankaya, U. The impact of rail transit investment on the residential property values in developing countries: The case of Izmir Subway, Turkey. Prop. Manag. 2011, 24, 369–382. [Google Scholar] [CrossRef]
  21. Kang, C.D. A Study of Effects of Accessibility of Street Networks to Seoul Subway System on Land Price: By Applying Urban Network Analysis and Multi-Level Regression Analysis. J. Real Estate Anal. 2021, 7, 1–24. [Google Scholar] [CrossRef]
  22. Higgins, C.D.; Kanaroglou, P.S. Unbundling the Hedonic Price Effects of Rapid Transit and Transit-Oriented Development in Toronto. In Proceedings of the Transportation Research Board( TRB) 95th Annual Meeting Compendium of Papers, Washington, DC, USA, 10–14 January 2016. [Google Scholar]
  23. Lee, S.; Yi, C.; Hong, S.P. Urban structural hierarchy and the relationship between the ridership of the Seoul subwaypolitan Subway and the land-use pattern of the station areas. Cities 2013, 35, 69–77. [Google Scholar] [CrossRef]
  24. Deng, J.; Xu, M. Characteristics of subway station ridership with surrounding land use: A case study in Beijing. In Proceedings of the 2015 International Conference on Transportation Information and Safety (ICTIS), Wuhan, China, 330–336 June 2015; IEEE: Piscataway, NJ, USA, 2015. [Google Scholar] [CrossRef]
  25. Li, P.K.; Yang, Q.T.; Lu, W.B. Nonlinear Relationship of Multi-Source Land Use Features with Temporal Travel Distances at Subway Station Level: Empirical Study from Xi’an City. Land 2024, 13, 1021. [Google Scholar] [CrossRef]
  26. Zheng, Y.; Lin, Y.M.; Zhao, L.; Wu, T.H.; Jin, D.P.; Li, Y. Spatial planning of urban communities via deep reinforcement learning. Nat. Comput. Sci. 2023, 3, 748–762. [Google Scholar] [CrossRef]
  27. Xia, H.S.; Liu, Z.S.; Efremochkina, M.; Liu, X.T.; Lin, C.X. Study on city digital twin technologies for sustainable smart city design: A review and bibliometric analysis of geographic information system and building information modeling integration. Sustain. Cities Soc. 2022, 84, 104009. [Google Scholar] [CrossRef]
  28. Mosadeghi, R.; Warnken, J.; Tomlinson, R.; Mirfenderesk, H. Comparison of Fuzzy-AHP and AHP in a spatial multi-criteria decision making model for urban land-use planning. Comput. Environ. Urban Syst. 2015, 49, 54–65. [Google Scholar] [CrossRef]
  29. Firoozi, F.; Mahmoudi, P.; Amir Jahanshahi, S.M.A.; Tavousi, T.; Liu, Y. Evaluating various methods of vegetative cover change trend analysis using satellite remote sensing productions (case study: Sistan Plain in Eastern Iran). Carpath. J. Earth Environ. Sci. 2020, 15, 211–222. [Google Scholar] [CrossRef]
  30. Fu, F.; Li, Y.J.; Zhang, Y.Z.; Yang, Y. Multi-Plan Integration: A Pilot Study of Mianzhu, Sichuan Province. China City Plan. Rev. 2018, 27, 6–15. [Google Scholar]
  31. Fu, F.; Jia, X.; Zhao, Q.J.; Tian, F.Z.; Wei, D.; Zhao, Y.; Zhang, Y.Z.; Zhang, J.; Hu, X.; Yang, L.C. Predicting land use change around railway stations: An enhanced CA-Markov model. Sustain. Cities Soc. 2024, 101, 105138. [Google Scholar] [CrossRef]
  32. Zhao, M.; Tong, H.Y.; Li, B.; Duan, Y.Q.; Li, Y.B.; Wang, J.P.; Lei, K.X. Analysis of Land Use Optimization of Metro Station Areas Based on Two-Way Balanced Ridership in Xi’an. Land 2022, 11, 1124. [Google Scholar] [CrossRef]
  33. Liang, X.; Guan, Q.; Clarke, K.C.; Liu, S.; Yao, Y. Understanding the drivers of sustainable land expansion using a patch-generating land use simulation (PLUS) model: A case study in Wuhan, China. Comput. Environ. Urban Syst. 2021, 85, 101569. [Google Scholar] [CrossRef]
  34. Li, S.P.; Cao, Y.G.; Liu, J.L.; Wang, S.F. Simulating land use change for sustainable land management in China’s coal resource-based cities under different scenarios. Sci. Total Environ. 2024, 916, 170126. [Google Scholar] [CrossRef]
  35. Li, S.X.; Yang, H.; Lacayo, M.; Liu, J.G.; Lei, G.C. Impacts of Land-Use and Land-Cover Changes on Water Yield: A Case Study in Jing-Jin-Ji, China. Sustainability 2018, 10, 960. [Google Scholar] [CrossRef]
  36. Rimal, B.; Zhang, L.F.; Keshtkar, H.; Haack, B.N.; Rijal, S.; Zhang, P. Land Use/Land Cover Dynamics and Modeling of Urban Land Expansion by the Integration of Cellular Automata and Markov Chain. ISPRS Int. J. Geo-Inf. 2018, 7, 154. [Google Scholar] [CrossRef]
  37. Pan, H.Z.; Deal, B.; Chen, Y.; Hewings, G.F. A reassessment of urban structure and land-use patterns: Distance to CBD or network-based?—Evidence from Chicago. Reg. Sci. Urban Econ. 2018, 70, 215–228. [Google Scholar] [CrossRef]
  38. Halmy, M.W.A.; Gessler, P.E.; Hicke, J.A.; Salem, B.B. Land use/land cover change detection and prediction in the north-western coastal desert of Egypt using Markov-CA. Appl. Geogr. 2015, 63, 101–112. [Google Scholar] [CrossRef]
  39. Osman, T.; Divigalpitiya, P.; Arima, T. Using the SLEUTH urban growth model to simulate the impacts of future policy scenarios on land use in the Giza Governorate, Greater Cairo Metropolitan region. Int. J. Urban Sci. 2016, 20, 407–426. [Google Scholar] [CrossRef]
  40. Yang, Y.N.; Zeng, J.C.; Yin, J.F.; Wu, P.R.; Xu, G.Y.; Jing, C.B.; Zhou, J.; Wen, X.; Reinders, J.; Amatyakul, W.; et al. Metro Stations as Catalysts for Land Use Patterns: Evidence from Wuhan Line 11. Sustainability 2024, 16, 6320. [Google Scholar] [CrossRef]
  41. Liang, X.; Liu, X.P.; Li, D.; Zhao, H.; Chen, G.Z. Urban growth simulation by incorporating planning policies into a CA-based future land-use simulation model. Int. J. Geogr. Inf. Sci. 2018, 32, 2294–2316. [Google Scholar] [CrossRef]
  42. Assaf, C.; Adams, C.; Ferreira, F.F.; França, H. Land use and cover modeling as a tool for analyzing nature conservation policies—A case study of Juréia-Itatins. Land Use Policy 2021, 100, 104895. [Google Scholar] [CrossRef]
  43. Bhattacharjee, S.; Goetz, A.R. The rail transit system and land use change in the Denver metro region. J. Transp. Geogr. 2016, 54, 440–450. [Google Scholar] [CrossRef]
  44. Hersperger, A.M.; Oliveira, E.; Pagliarin, S.; Palka, G.; Verburg, P.; Bolliger, J.; Gradinaru, S. Urban land-use change: The role of strategic spatial planning. Glob. Environ. Chang. 2018, 51, 32–42. [Google Scholar] [CrossRef]
  45. Colsaet, A.; Laurans, Y.; Levrel, H. What drives land take and urban land expansion? A systematic review. Land Use Policy 2018, 79, 339–349. [Google Scholar] [CrossRef]
  46. GB/T 21010-2017; Current Land Use Classification. Standards Press of China: Beijing, China, 2017.
  47. GB 50137-2011; Code for Classification of Urban Land Use and Planning Standards of Development Land. China Architecture & Building Press: Beijing, China, 2010.
  48. Li, Q.; Cui, C.H.; Liu, F.; Wu, Q.R.; Run, Y.D.; Han, Z.G. Multidimensional urban vitality on streets: Spatial patterns and influence factor identification using multisource urban data. ISPRS Int. J. Geo-Inf. 2021, 11, 2. [Google Scholar] [CrossRef]
  49. Wang, J.F.; Feng, Y.J.; Ye, Z.; Tong, X.H.; Wang, R.; Gao, C.; Chen, S.R.; Lei, Z.K.; Liu, S.; Jin, Y.M. Simulating the effect of urban light rail transit on urban development by coupling cellular automata and conjugate gradients. Geocarto Int. 2022, 37, 2346–2364. [Google Scholar] [CrossRef]
  50. Zhou, L.; Dang, X.W.; Sun, Q.K.; Wang, S.H. Multi-scenario simulation of urban land change in Shanghai by random forest and CA-Markov model. Sustain. Cities Soc. 2020, 55, 102045. [Google Scholar] [CrossRef]
  51. Ghosh, S.; Chatterjee, N.D.; Dinda, S. Urban ecological security assessment and forecasting using integrated DEMATEL-ANP and CA-Markov models: A case study on Kolkata Metropolitan Area, India. Sustain. Cities Soc. 2021, 68, 102773. [Google Scholar] [CrossRef]
  52. Wang, X.D.; Yao, Y.; Ren, S.L.; Shi, X.G. A Coupled FLUS and Markov approach to simulate the spatial pattern of land use in rapidly developing cities. J. Geo-Inf. Sci. 2022, 24, 100–113. [Google Scholar]
  53. Chen, G.Z.; Li, X.; Liu, X.P.; Chen, Y.M.; Liang, X.; Leng, J.Y.; Xu, X.C.; Liao, W.L.; Qiu, Y.A.; Wu, Q.L.; et al. Global projections of future urban land expansion under shared socioeconomic pathways. Nat. Commun. 2020, 11, 537. [Google Scholar] [CrossRef]
  54. Liu, X.Y.; Wei, M.; Li, Z.G.; Zeng, J. Multi-scenario simulation of urban growth boundaries with an ESP-FLUS model: A case study of the Min Delta region, China. Ecol. Indic. 2022, 135, 108538. [Google Scholar] [CrossRef]
  55. Zhao, G.W.; Chen, Y.B.; Li, J.T. Spatial scale sensitivity of CA-Markov model. Sci. Geogr. Sin. 2011, 31, 897–902. [Google Scholar] [CrossRef]
  56. Huo, J.E.; Shi, Z.Q.; Zhu, W.B.; Xue, H.; Chen, X. A Multi-Scenario Simulation and Optimization of Land Use with a Markov–Flus Coupling Model: A Case Study in Xiong’an New Area, China. Sustainability 2022, 14, 2425. [Google Scholar] [CrossRef]
  57. Liu, Z.S.; Xia, H.S.; Zhang, T. A review of research methods on the coupling relationship between urban rail transit and urban space: Revealing spatiotemporal relationships through big data. Int. J. Digit. Earth 2024, 17, 2339363. [Google Scholar] [CrossRef]
  58. Volovski, M.; Grillo, N.; Varga, C.; Saeed, T.U.; El-Hakim, M. Subway Ridership: Accounting for Regional Variation across Land-Use and Socioeconomic Settings. J. Infrastruct. Syst. 2021, 27, 04021010. [Google Scholar] [CrossRef]
  59. Wang, H.B.; Li, H.; Ming, H.B.; Hu, Y.H.; Chen, J.K.; Zhao, B. Past land use decisions and socioeconomic factors influence urban greenbelt development: A case study of Shanghai, China. Landsc. Ecol. 2014, 29, 1759–1770. [Google Scholar] [CrossRef]
  60. Ministry of Natural Resources of the People ’s Republic of China. Planning and Land Policy Guidelines for Supporting Urban Renewal (2023 Edition). Available online: https://www.gov.cn/zhengce/zhengceku/202311/content_6916516.htm (accessed on 3 December 2024).
  61. Ministry of Natural Resources of the People ’s Republic of China. Official Notice Regarding the Implementation of Pilot Programs for the Redevelopment of Inefficiently Utilized Land. Available online: https://gi.mnr.gov.cn/202309/t20230914_2800228.html (accessed on 3 December 2024).
  62. Ministry of Natural Resources of the People ’s Republic of China. Land Acquisition and Development Criteria. Available online: https://www.gov.cn/zhengce/zhengceku/202312/content_6918723.htm (accessed on 3 December 2024).
  63. Ministry of Natural Resources of the People ’s Republic of China. Official Notice on Further Guaranteeing the Essential Elements of Land and Marine Resource Utilization. Available online: https://www.gov.cn/zhengce/zhengceku/202306/content_6886744.htm (accessed on 3 December 2024).
  64. Xu, Q.; Li, W.X.; Chen, Y.; Hu, J.J.; Liang, X. Nonlinear and Threshold Effects of Built Environment on Origin-destination Flows of Urban Rail Transit. J. Transp. Syst. Eng. Inf. Technol. 2023, 23, 290–297. [Google Scholar] [CrossRef]
  65. Domingo, D.; Palka, G.; Hersperger, A.M. Effect of zoning plans on urban land-use change: A multi-scenario simulation for supporting sustainable urban growth. Sustain. Cities Soc. 2021, 69, 102833. [Google Scholar] [CrossRef]
  66. Bibri, S.E.; Krogstie, J. Smart sustainable cities of the future: An extensive interdisciplinary literature review. Sustain. Cities Soc. 2017, 31, 183–212. [Google Scholar] [CrossRef]
  67. Martinović, A.; Ifko, S. Industrial heritage as a catalyst for urban regeneration in post-conflict cities Case study: Mostar, Bosnia and Herzegovina. Cities 2018, 74, 259–268. [Google Scholar] [CrossRef]
  68. Rhodes, M.A., II; Price, W.R. “A nation built on coal”: Transcalar memory work at the Big Pit. Tour. Geogr. 2023, 26, 755–777. [Google Scholar] [CrossRef]
  69. Wu, W.J.; Chen, W.Y.; Yun, Y.W.; Wang, F.L.; Gong, Z.Y. Urban greenness, mixed land-use, and life satisfaction: Evidence from residential locations and workplace settings in Beijing. Landsc. Urban Plan. 2022, 224, 104428. [Google Scholar] [CrossRef]
Sustainability 17 03544 g001
Figure 1. Location of the Balizhuang Station.
Figure 1. Location of the Balizhuang Station.
Sustainability 17 03544 g001
Sustainability 17 03544 g002
Figure 2. (a) Station accessibility, (b) street pedestrian density, (c) and POI kernel density around Balizhuang Station. (Note: The geometric center of the figure represents the location of Balizhuang Station).
Figure 2. (a) Station accessibility, (b) street pedestrian density, (c) and POI kernel density around Balizhuang Station. (Note: The geometric center of the figure represents the location of Balizhuang Station).
Sustainability 17 03544 g002
Sustainability 17 03544 g003
Figure 3. Land use change around Balizhuang Station from 2015 to 2023 (a) under the policy planning scenario (b) and under the natural development scenario. (Note: The geometric center of the figure represents the location of Balizhuang Station).
Figure 3. Land use change around Balizhuang Station from 2015 to 2023 (a) under the policy planning scenario (b) and under the natural development scenario. (Note: The geometric center of the figure represents the location of Balizhuang Station).
Sustainability 17 03544 g003
Sustainability 17 03544 g004
Figure 4. The research framework.
Figure 4. The research framework.
Sustainability 17 03544 g004
Sustainability 17 03544 g005
Figure 5. Pedestrian flow density of streets around Balizhuang Station during (a) peak periods (b) and off-peak periods. (Note: The geometric center of the figure represents the location of Balizhuang Station).
Figure 5. Pedestrian flow density of streets around Balizhuang Station during (a) peak periods (b) and off-peak periods. (Note: The geometric center of the figure represents the location of Balizhuang Station).
Sustainability 17 03544 g005
Sustainability 17 03544 g006
Figure 6. (a) The congested locations around Balizhuang Station during peak periods in 2023, and the gathering locations during off-peak period (b) in 2023 and (c) 2019.
Figure 6. (a) The congested locations around Balizhuang Station during peak periods in 2023, and the gathering locations during off-peak period (b) in 2023 and (c) 2019.
Sustainability 17 03544 g006
Sustainability 17 03544 g007
Figure 7. Simulation and prediction results of land use around Balizhuang Station under the policy planning scenario in 2027. (Note: The geometric center of the figure represents the location of Balizhuang Station.)
Figure 7. Simulation and prediction results of land use around Balizhuang Station under the policy planning scenario in 2027. (Note: The geometric center of the figure represents the location of Balizhuang Station.)
Sustainability 17 03544 g007
Sustainability 17 03544 g008
Figure 8. Changes in the area of different land use types around Balizhuang Station under the policy planning scenario from 2015 to 2027.
Figure 8. Changes in the area of different land use types around Balizhuang Station under the policy planning scenario from 2015 to 2027.
Sustainability 17 03544 g008
Sustainability 17 03544 g009
Figure 9. (a) The change trend of industrial land use (b) and proportion of industrial land converted to other land types around Balizhuang Station under the policy planning scenario.
Figure 9. (a) The change trend of industrial land use (b) and proportion of industrial land converted to other land types around Balizhuang Station under the policy planning scenario.
Sustainability 17 03544 g009
Sustainability 17 03544 g010
Figure 10. The systematic workflow for land planning around old subway stations and spatial reuse of industrial heritage.
Figure 10. The systematic workflow for land planning around old subway stations and spatial reuse of industrial heritage.
Sustainability 17 03544 g010
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Chen, K.; Fu, F.; Tian, F.; Lin, L.; Du, C. Spatiotemporal Prediction of the Impact of Dynamic Passenger Flow at Subway Stations on the Sustainable Industrial Heritage Land Use. Sustainability 2025, 17, 3544. https://doi.org/10.3390/su17083544

AMA Style

Chen K, Fu F, Tian F, Lin L, Du C. Spatiotemporal Prediction of the Impact of Dynamic Passenger Flow at Subway Stations on the Sustainable Industrial Heritage Land Use. Sustainability. 2025; 17(8):3544. https://doi.org/10.3390/su17083544

Chicago/Turabian Style

Chen, Ke, Fei Fu, Fangzhou Tian, Liwei Lin, and Can Du. 2025. "Spatiotemporal Prediction of the Impact of Dynamic Passenger Flow at Subway Stations on the Sustainable Industrial Heritage Land Use" Sustainability 17, no. 8: 3544. https://doi.org/10.3390/su17083544

APA Style

Chen, K., Fu, F., Tian, F., Lin, L., & Du, C. (2025). Spatiotemporal Prediction of the Impact of Dynamic Passenger Flow at Subway Stations on the Sustainable Industrial Heritage Land Use. Sustainability, 17(8), 3544. https://doi.org/10.3390/su17083544

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop