[Retracted] A Dynamic Econometric Analysis of Urbanization and Ecological Environment in Silk Road Economic Belt

Li, Xing; Luo, Fuzhou

doi:https://doi.org/10.1155/2022/4895213

Scientific Programming

On this page

Abstract Introduction Conclusion Data Availability Conflicts of Interest Acknowledgments References Copyright Related Articles

Research Article Retraction

!

This article has been Retracted. To view the article details, please click the ‘Retraction’ tab above.

Special Issue

Artificial Intelligence Approaches for Bridging Business Processes and Internet of Things and Big Data

View this Special Issue

Research Article | Open Access

Volume 2022 | Article ID 4895213 | https://doi.org/10.1155/2022/4895213

[Retracted] A Dynamic Econometric Analysis of Urbanization and Ecological Environment in Silk Road Economic Belt

Xing Li¹and Fuzhou Luo¹

Academic Editor: Sikandar Ali

Received31 Dec 2021

Revised29 Jan 2022

Accepted02 Feb 2022

Published08 Mar 2022

Abstract

On the basis of the construction of urbanization and ecology index system, this study takes the core area of Silk Road Economic Belt, Gansu, as the research object and creates the coordination evaluation model between urbanization and ecological environment in Gansu; meanwhile, it uses BP neural network to predict the coordinated development of urbanization and ecology in Gansu Province. Finally, the aforesaid model is validated by means of empirical evidence. The results show that Gansu, in the Silk Road Economic Belt, has accelerated its urbanization level in the 10-year period from 2010 to 2019 in the context of the Belt and Road Initiative, especially in Jiayuguan and Lanzhou, mainly due to its industrialization-led urbanization； meanwhile, in terms of coupling degree, most of them are between 0.45 and 0.55, and most of them are out-of-frequency pro-disorder recession type, indicating that under the background of urbanization, the ecology of each city and prefecture in Gansu is also under great pressure. At the same time, through the forecast, Gansu is considered to be in the red light in 2019, as the endangered disorder recession B environmental lagging type, indicating that Lanzhou is facing great ecological pressure, but in general, the relationship between human and land is gradually developing in harmony.

1. Introduction

Urbanization involves multiple elements such as population, economy, and society, and large-scale migration of population, change in production, lifestyle, and land use occur during the urbanization process. The urbanization level of China was only 19.39% in 1980, and after that, driven by the policy of reformation and opening, the urbanization process of China has been accelerating and by 2020 it has risen to 63.89%, with a total of 687 cities and towns nationwide [1–5]. Accelerated urbanization has also caused multiple problems, including climate change, waste of resources, and ecological degradation, which pose serious challenges to the modernization of our economy and society. For example, Huang Jinchuan developed a coupling harmonious degree model to quantitatively define the level of ecology, the level of urbanization, and the coupling between the two systems in Kazakhstan and confirmed that ecological factors such as ecological land per capita, arable land area per capita, forest cover, and per capita available resources play a key influence on the degree of coupling coordination between urbanization and ecology in Kazakhstan [6]; by means of a case study, Zhenfeng Shao first established a special comprehensive evaluation index system, then invoked the entropy-weighted TOPSIS technique for comprehensive evaluation, and found that the coupling coordination degree of urbanization and ecology in the Yangtze River Delta region maintained an incremental trend, changing from an unbalanced state in 2008 (0.604) to a basically balanced state in 2017 (0.753) [7]. Zheng Ji conducted extensive social research on urbanization in the Russian Far East and found that Russia's increasing investment in urbanization in the Far East has improved the coupling coordination degree between urbanization and ecological environment, from a slight imbalance at the beginning of the survey to a barely balanced state at present [8]. This study focuses on Gansu Province, the central core of the Silk Road, as the research area, and integrates machine learning prediction method and quantitative analysis to assess the coordinated development of urbanization and ecology in Gansu Province, hoping to provide reference for the future development strategy of Gansu Province, to improve the status of Gansu Province in the Silk Road Economic Belt.

1.1. Establishment of the Assessment Indicator System for the Coupling Degree of Urbanization and Ecology

1.1.1. Principles for Constructing the Indicator System

The construction of evaluation indicators should consider the diversity of indicators and the correlation between indicators, to build a scientific and reasonable indicator system for appraising the coordination between urbanization and ecology. Therefore, the index system built by this study also follows the following principles [9–11].

First, the principle of comprehensiveness: as two typical integrated systems, attention should be paid to the comprehensiveness of the selected indicators when constructing the indicator system. Among them, the level of urbanization is reflected in four aspects: population, economy, society, and space, and the ecology level is reflected in three aspects: state, pressure, and response. The selected indicators should cover these aspects comprehensively.

Second, the principle of scientificity: to objectively reflect the essential properties of things, we should choose some common general indicators and some special indicators according to the actual local situation. This will ensure that the constructed index system is scientific in nature.

Third, representativeness principle: the indexes that can reflect the level of urbanization and the quality of living conditions are relatively abundant, but there are correlations among many of them, which require that when constructing the indicator system, the most representative indicators should be selected from the many correlated indicators, and these indicators have the best evaluation effect.

Fourth, the principle of operability: the indicators selected into the indicator system must be able to easily obtain the indicator data, to ensure that the indicators have practical significance; on the contrary, if the indicator data are not available or difficult to obtain, the indicator system will lose its value of existence. Therefore, the availability of data is considered in the selection of indicators, to ensure that the established indicator system is operable.

1.2. Urbanization Indicator System

With the definition of “urbanization” in urban geography as the support, the level of urbanization is comprehensively evaluated in four aspects [12–17], including population, economy, space, and society; the ecological pressure is evaluated in three aspects, including ecological pressure (Y1), ecological state (Y2), and ecological response (Y3). The overall evaluation indicator system is presented in Table 1.

2. Research Methods

2.1. Evaluation Model Construction of Coupling Coordination Development between Urbanization and Ecology

2.1.1. Comprehensive Level Evaluation Model

To assess Gansu’s comprehensive level, which is the key Economic Belt of the Silk Road, the comprehensive level evaluation model of (1) is used to measure the level of coordinated development of urbanization and ecology in Gansu during 2010–2019.where Yi1 denotes the comprehensive evaluation level of urbanization in year i (i = 1,2,3,.,20); Yi2 denotes the comprehensive evaluation level of ecological environment in year i (i = 1,2,3,.,10); and Aij indicates the standardized value of the jth index in year i.

2.1.2. Coupling Degree Model

To better represent the degree of disorder among the urbanization subsystem and the ecology subsystem in Table 1, the coupling degree model of (2) is introduced [18]as follows:

According to (3), U₁ is equivalent to and U₂ is equivalent to . When n = 2, then there is a coupling degree function of urbanization and ecology, as follows:

2.1.3. Coupling Coordination Development Model

The coupling degree can only reveal the closeness degree, i.e., development order, between the two systems of urbanization and ecology, but cannot confirm the coordination effect among the two systems. In this regard, it is necessary to characterize this by invoking the coupling coordination development degree shown as follows:where C indicates the coupling degree of urbanization and ecology; D indicates coupling coordination development degree; T denotes the composite reconciliation index, ; and and are undetermined coefficients, .

In addition, this study classifies the harmonious development status of urbanization and ecology into three grades: unacceptable interval (0–0.4); excessive interval (0.4–0.6); and acceptable interval (0.6–1.0).

2.2. Coordination Evaluation Model Construction of BP Neural Network

2.2.1. Structure of BP Neural Network

In order to better coordinate the relationship between urbanization and ecology in the Gansu region, based on the measurement of coupling coordination degree, the coordinated development of urbanization and ecology in the Gansu region of the Silk Road Economic Belt is predicted by using the BP neural network, which can provide more reference for the development of the Silk Road Economic Belt. The BP neural network structure is presented in Figure 1 [19–22].

In the structural system shown in Figure 1, neighboring levels are linked by nodes, and nodes within the same level and between different levels can also interact with each other, but a node can only exert influence on a node in the next level. Therefore, based on this principle, the BP neural network first analyzes and organizes the input historical data and passes them downward step by step until output results. The output value is compared with the ideal value, and if the difference between them is greater than some set error, the inverse adjustment is executed to find the error upward step by step, and finally, a reasonable sample is selected and the weights are updated. The above process is repeated, and finally, the result that meets the accuracy requirement is output.

The above process is sorted out and refined into three steps as follows:(1)Determine the input data of the nodes in the hidden layer : where p denotes the number of neural nodes in the hidden layer and denotes the range value of neuron j in the hidden layer.(2)Determine the output data for each node in the hidden layer :(3)Determine the model output values for the output layer.

2.2.2. A Coordination Forecasting Model Based on BP Neural Network

To better analyze the Gansu region in the Silk Road Economic Belt, BP neural network is applied to predict the coordination degree of urbanization and ecology, which consists of the following 3 steps:(1)Sample classification: the base data are standardized for extreme differences, and the appropriate amount of sample data is randomly chosen to form the training sample, while the remaining data are formed into the test sample.(2)Network design: the number of neurons in the input layer, output layer, and hidden layer is set to 5, 1, and 11, respectively. The network training target is set to 1e⁻⁶, the momentum constant is 0.8, the maximum number of network training is 5000, and the learning rate is 0.1. The “tansig” function and the “logsig” function are selected for the hidden layer and output layer transfer functions, respectively.(3)Network training: the network is trained using training samples until the optimal number of training times.

3. Method Validation and Result Analysis

To verify the feasibility and scientificity of the above methods, a combination of empirical evidence and simulation is used to validate the above model.

3.1. Data Source

From the Gansu Development Yearbook (2010–2019), the China City Statistical Yearbook (2010–2019), the official website of the National Bureau of Statistics, and the Gansu Provincial Economic Information Network, we obtained 30 sets of relevant data for Gansu Province during 2010–2019 as the base data.

3.2. Data Preprocessing

The base data need to be standardized for extreme differences by the following formula, to eliminate the effects of the difference in dimension and magnitude [23–25]:

Here, and indicate the maximum and minimum values of the jth indicator data in year i of each region, respectively; indicates the original data of the jth indicator in year i; and indicates normalized value by the extreme difference.

In addition, the index weights are derived by the entropy weight method, which is based on the idea that the greater the entropy of information, the more information there is, and vice versa. The entropy weight method is calculated by the formula [26]:where indicates the entropy value of the jth index in year and denotes the weight of the jth indicator in all indicators in year.

3.3. Evaluation Results

3.3.1. Integrated Level Assessment of Urbanization Subsystems

After solving the weights of each indicator in the urbanization subsystem, the comprehensive evaluation level of urbanization of each region during the survey period is determined by weighting and summing them with the standard values of each indicator. The specific results are illustrated in Figure 2.

From the growth rate of urbanization development, Jiayuguan is a city with the highest urbanization level and the fastest growth rate of urbanization in Gansu Province, mainly due to its more mature industrial base under the Silk Road Economic Belt, and the fact that Jiayuguan is a prefecture-level city without a municipal district, with a smaller urban area, regional economy, and urban population, which ultimately shows a higher level of urbanization; the urbanization level of Lanzhou City ranks second. It is the capital city of Gansu Province and has comparative advantages in terms of economic development, transportation facilities, geographical location, and public infrastructure driven by the Silk Road Economic Belt, so it has more room for future development and a more rapid urbanization rate.

In terms of location, the urbanization level of the area north of Lanzhou is greater than that of the area south of Lanzhou. The reason is that cities north of Lanzhou, such as Jiuquan, Baiyin, Zhangye, Wuwei, and Jinchang, are mostly energy-based cities, and industrialization has driven urbanization, so the urbanization level of these cities is overall higher than that of cities south of Lanzhou. Among the regions south of Lanzhou, Tianshui has the highest level of urbanization, which is mainly due to its advantages of economic development, geographical location, and climatic conditions under the Silk Road Economic Belt. Besides, under the Silk Road Economic Belt development, the cities of Longnan, Dingxi, Gannan, Pingliang, and Linxia Prefecture have lower urbanization levels restricted by the natural environment and geographical location.

3.3.2. Comprehensive Level Evaluation of Ecological Environment

Similarly, the comprehensive evaluation level of ecological environment of each region during the survey period was determined by the method of Section 3.3.1, and the specific results are illustrated in Figure 3.

As shown in Figure 3, Lanzhou is a city with an overall high level of ecological environment in Gansu Province; particularly, after the national Belt and Road Initiative was proposed, Lanzhou City has vigorously tackled the air pollution problem through coal-to-gas policy, energy structure adjustment policy, etc., and relocated Lanzhou Petrochemical to Lanzhou New District. These initiatives have controlled the coal-fired dust at source and also significantly reduced industrial waste emissions, making the ecological environment level in Lanzhou City climb rapidly; the integrated level of ecological environment in Baiyin has increased from 0.38 in 2010 to 0.54 in 2019, which is the largest increase and shows the efforts made by Baiyin in ecological environment protection; Jiayuguan and Jinchang are lagging behind in the overall ecological environment ranking because they are located in the western part of Gansu Province, the ecological environment is fragile, natural conditions are extremely poor, and industry is their pillar industry, so urbanization has caused heavy pressure on the ecological environment. Located in southern Gansu, Longnan City has relatively good natural conditions, but by geographical factors and economic level constraints, Longnan City will be mainly devoted to urbanization development business, resulting in its ecological environment comprehensive level being low. The ecological environment level of the remaining cities and states fluctuates around 0.6, and the level of urbanization is lower than its ecological environment level, and the level of urbanization and ecological environment development does not match each other.

3.3.3. Coupling Coordination Development Degree Analysis

According to (4), as well as combining the relevant data in Figures 1 and 2, the coupling degree of urbanization and ecology of each city in Gansu is measured. The results are illustrated in Figure 3.

Combined with Figure 4, it is seen that except for Jiayuguan, Lanzhou, Qingyang, and Jiuquan, the degree of coupling coordination development of urbanization and ecology in other cities and states is in the excessive range.

3.4. Coordination Degree Prediction Results of BP Neural Network

3.4.1. Determination of Early Warning Limits

To better predict the development level of coordination degree in Gansu in the Silk Road Economic Belt, the data in Figure 3 are used as the basis, and the coordination degrees measured in the previous 7 years are used as the training data, and the coordination degree data measured in 2017, 2018, and 2019 are used as the test data for prediction. At the same time, to judge the development of Gansu cities and states, early warning limits are set to divide the level of coordination degree of urbanization and ecology. Referring to the previous discussions and combining with the calculation results of this study on the coordination degree of urbanization and ecology, the warning limit division interval in Table 1 is determined, where C represents noncooperative scheduling.

Table 2 shows that as the warning light transitions from “blue light” to “red light,” it means that the coordination between urbanization and ecology is deteriorating, changing from quality coordination in the no-alarm state to serious imbalance in the mega-alarm state.

3.4.2. Results and Analysis

(1) BP Analysis Results. Based on the above data, the neural network toolbox of MATLAB was used. The coordination data of Lanzhou, Jiayuguan, and Jinchang cities were input into the trained BP network, and the prediction results in Table 3 were obtained.

(2) Analysis of BP Prediction Results. Based on the same method as above, the early warning signals for the coordinated development of urbanization and ecology in Gansu between 1992 and 2010 are listed in Table 4.

The analysis shows that the prediction results are that the early warning signal of Gansu in 2017 and 2018 is the green light, when urbanization remains moderately coordinated with the ecological environment, and a red light in 2019. It can be expected that under the background of the Silk Road Economic Belt development, the urbanization process in Gansu will continue to accelerate, with numerous rural laborers flocking to the city. While accelerating the urbanization process, it has also caused more serious production and domestic pollution. In addition, the urban population explosion will cause a variety of problems such as insufficient urban domestic water, deterioration of urban domestic water quality, deterioration of urban air quality, and shrinking of urban green space per capita, leading to further deterioration of the coordination between urbanization and ecology.

4. Conclusion

The above study suggests that the coordinated development of Gansu in the Silk Road Economic Belt in recent years has been evaluated in a quantitative manner. The results indicate that the coupling degree of urbanization and ecology in most cities and states in Gansu Province fluctuates above and below 0.48, with a small gap between them, while urbanization brings certain negative effects to the ecological environment; the data from 2010 to 2019 are also used as the basis for predicting the coordinated development level of urbanization and ecology in Gansu, the key region in the Silk Road Economic Belt. The results also show that urbanization has accelerated damaging ecological environment. The above study provides both quantitative analysis and prediction, which provides a new reference for the development of Gansu, a core region of the Silk Road Economic Belt.

Data Availability

The experimental data used to support the findings of this study are available from the corresponding author upon request.

Conflicts of Interest

The authors declare that they have no conflicts of interest regarding this work.

Acknowledgments

This study was supported by the grant from the National Natural Science Foundation of China:Study on the Dynamic Mechanism and Policy of Cultural Industry Agglomeration in the Tibetan-Qiang-Yi Corridor Based on the Economic Geography (71974155), Key Industry Innovation Chain (group): Social Development Fund Project of Shaanxi Provincial Science and Technology Department: Construction and Demonstration of Green Eco-Industrial Chain in Han River Economic Zone (2019ZDLSF06-07), and the Basic Competence Improvement Project for Middle and Young Teachers in the Universities and Colleges of Guangxi: Application and Practice of BIM in Informatization Treatment of Quality Control in Assembly Construction (Grant no. 2018KY1010).

References

L. Lin and T. Zhang, “A study on the coupling coordination relationship between urbanization and ecological system in heilongjiang Province,” International Journal of Social Science and Education Research, vol. 3, no. 3, pp. 128–135, 2020.
View at: Google Scholar
Z. Wang, L. Liang, Z. Sun, and X. Wang, “Spatiotemporal differentiation and the factors influencing urbanization and ecological environment synergistic effects within the Beijing-Tianjin-Hebei urban agglomeration,” Journal of Environmental Management, vol. 243, pp. 227–239, 2019.
View at: Publisher Site | Google Scholar
J. Ye, “Quantitative evaluation and analysis on the coordinated development of the urbanization and ecological environment in Xining city,” E3S Web of Conferences, vol. 131, Article ID 01051, 2019.
View at: Publisher Site | Google Scholar
C. Y. Liu, Y. Y. Liu, and R. G. Ding, “Coupling analysis between new-type urbanization and ecological environment in Fujian Pro-vince, China.,” Journal of Applied Ecology, vol. 29, no. 9, pp. 3043–3050, 2018.
View at: Publisher Site | Google Scholar
Z. Gong, R. Mao, and J.J. Jiang, “Coupling and coordination degree between urbanization and ecological environment in guizhou, China,” Discrete Dynamics in Nature and Society, vol. 2021, Article ID 8436938, 10 pages, 2021.
View at: Publisher Site | Google Scholar
J. Huang, Y. Na, and Y. Guo, “Spatiotemporal characteristics and driving mechanism of the coupling coordination degree of urbanization and ecological environment in Kazakhstan,” Journal of Geographical Sciences, vol. 30, no. 11, pp. 1802–1824, 2020.
View at: Publisher Site | Google Scholar
Z. Shao, L. Ding, D. Li, O. Altan, M. E. Huq, and C. Li, “Exploring the relationship between urbanization and ecological environment using remote sensing images and statistical data: a case study in the Yangtze River Delta, China,” Sustainability, vol. 12, no. 14, p. 5620, 2020.
View at: Publisher Site | Google Scholar
J. Zheng, Y. Hu, T. Boldanov et al., “Comprehensive assessment of the coupling coordination degree between urbanization and ecological environment in the Siberian and Far East Federal Districts, Russia from 2005 to 2017,” PeerJ, vol. 8, Article ID e9125, 2020.
View at: Publisher Site | Google Scholar
J. Liu, C. Li, J. Tao, Y. Ma, and X. Wen, “Spatiotemporal coupling factors and mode of tourism industry, urbanization and ecological environment: a case study of Shaanxi, China,” Sustainability, vol. 11, no. 18, p. 4923, 2019.
View at: Publisher Site | Google Scholar
M. Yang, C. Jia, and Y. Zhou, “Comprehensive evaluation model of maritime industrial economic activities based on an AHP and BP neural network[J],” Journal of Coastal Research, vol. 111, no. sp1, pp. 178–182, 2020.
View at: Publisher Site | Google Scholar
X. Wu and F. Hu, “Analysis of ecological carrying capacity using a fuzzy comprehensive evaluation method,” Ecological Indicators, vol. 113, no. C, Article ID 106243, 2020.
View at: Publisher Site | Google Scholar
J. Guo, J. Ren, X. Huang, G. He, Y. Shi, and H. Zhou, “The dynamic evolution of the ecological footprint and ecological capacity of qinghai Province,” Sustainability, vol. 12, no. 7, p. 3065, 2020.
View at: Publisher Site | Google Scholar
B. Xu and J. Pan, “Estimation of potential ecological carrying capacity in China,” Environmental Science and Pollution Research, vol. 27, no. 15, Article ID 18044, 2020.
View at: Publisher Site | Google Scholar
M. Salemi, S. A. Jozi, S. Malmasi, and S. Rezaian, “A new model of ecological carrying capacity for developing ecotourism in the protected area of the north karkheh, Iran,” Journal of the Indian Society of Remote Sensing, vol. 47, no. 11, pp. 1937–1947, 2019.
View at: Publisher Site | Google Scholar
J. Hu, Y. Huang, and J. Du, “The impact of urban development intensity on ecological carrying capacity: a case study of ecologically fragile areas,” International Journal of Environmental Research and Public Health, vol. 18, no. 13, p. 7094, 2021.
View at: Publisher Site | Google Scholar
C. Chen, Z. Qiao, and H. Sun, “The coupling coordination degree measurement of society-economy-ecosystem of regional national forest park in heilongjiang Province,” Tehnički Vjesnik, vol. 28, no. 3, pp. 779–785, 2021.
View at: Publisher Site | Google Scholar
X. Xia, H. Sun, J. Gao, F. Chen, and C. Zhou, “Spatiotemporal differentiation of coupling and coordination relationship of tourism–urbanization–ecological environment system in China’s major tourist cities,” Sustainability, vol. 13, no. 11, p. 5867, 2021.
View at: Publisher Site | Google Scholar
X. Wu, H. Niu, X.-J. Li, and Y. Wu, “A study on the GA-BP neural network model for surface roughness of basswood-veneered medium-density fiberboard,” Holzforschung, vol. 74, no. 10, pp. 979–988, 2020.
View at: Publisher Site | Google Scholar
Z. Zhang, “BP neural network trade volume prediction and enterprises HRM optimization model based on ES-LM training,” Journal of Intelligent and Fuzzy Systems, vol. 39, no. 4, pp. 5883–5894, 2020.
View at: Publisher Site | Google Scholar
Y. Wan, J. Wu, R. Chu et al., “Prediction of BP neural network and preliminary application for suppression of low‐temperature oxidation of coal stockpiles by pulverized coal covering,” Canadian Journal of Chemical Engineering, vol. 98, no. 12, pp. 2587–2598, 2020.
View at: Publisher Site | Google Scholar
W. Wang, Y. Liu, F. Bai, and G. Xue, “Capture power prediction of the frustum of a cone shaped floating body based on BP neural network,” Journal of Marine Science and Engineering, vol. 9, no. 6, p. 656, 2021.
View at: Publisher Site | Google Scholar
Li Yang, H. Guo, and J. Wang, “An automatic crisis information recognition model based on BP neural networks,” Journal of Ambient Intelligence and Humanized Computing, pp. 1–12, 2021.
View at: Publisher Site | Google Scholar
R. Luo, Y. Cao, S. Cui, and Y. Cao, “An Improved Constitutive Model Based on BP Artificial Neural Network and 3D Processing Maps of a Spray-Formed Al–Cu–Li Alloy,” Transactions of the Indian Institute of Metals, vol. 74, no. 7, pp. 1–9, 2021.
View at: Publisher Site | Google Scholar
Z. S. Peng, H. C. Ji, W. C. Pei, B. Y. Liu, and G. Song, “Constitutive relationship of TC4 titanium alloy based on back propagating (BP) neural network (NN),” Metalurgija, vol. 60, no. 3-4, pp. 277–280, 2021.
View at: Google Scholar
H. Liu, J. Liu, Y. Wang, Y. Xia, and Z. Guo, “Identification of grouting compactness in bridge bellows based on the BP neural network,” Structures, vol. 32, pp. 817–826, 2021.
View at: Publisher Site | Google Scholar
Y. Tang, J. Su, and A. K. K. Muazzam, “Research on Sentiment Analysis of Network Forum Based on BP Neural Network,” Mobile Networks and Applications, vol. 26, no. 11, pp. 1–10, 2020.
View at: Publisher Site | Google Scholar

Copyright

Copyright © 2022 Xing Li and Fuzhou Luo. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

PDF Download Citation

Download other formats

Order printed copies