Cross-border ecological economic zoning method

Abstract

The invention discloses a cross-border ecological economy zoning method. The method comprises the following steps: S1, constructing a cross-border ecological economy zoning index system; s2, a PartitioningAround Medoid clustering algorithm, namely a PAM clustering algorithm, is divided around the central point, and the PartitioningAround Medoid clustering algorithm is divided around the central point; and S3, selecting the optimal clustering number. According to the method, multidisciplinary theories and methods of geography, resource science, ecology, environmental science, economics, sociology and the like are crossly fused, a national boundary system is broken through, an ecological economy division scheme of a cross-administrative region boundary based on a grid scale is completed, and a certain method and theoretical reference is provided for cross-border region ecological economy division and collaborative development mode research.

Description

Technical Field

[0001] The present invention relates to the field of economic technology, and in particular to a cross-border ecological and economic zoning method. Background Art

[0002] The Sino-Russian Northeast-Far East cross-border region, as the region with the most extensive borders between China and Russia, the closest economic, trade, and cultural cooperation, and a high concentration of transportation ports and cross-border transport hubs, has become a pioneering core area for in-depth cooperation between the two countries and a potentially important region influencing the geo-economic landscape of Northeast Asia. This region exhibits significant spatial heterogeneity in its geographical pattern, ecological foundation, and industrial structure, profoundly influencing the structure and function of the regional ecological and economic system. However, as a crucial component of the Heilongjiang-Amur River Basin, it encompasses transnational ecological units such as the Sanjiang Plain and the Sikhote-Sikhote-Mountains. Precious natural resources such as water and black soil are distributed across borders; ecosystems such as wetlands and lakes extend across borders; and rare species such as tigers and leopards inhabit these regions. As an ecological security barrier for northern and northeastern my country, it constitutes an indivisible ecological entity. Therefore, innovative spatial planning techniques are urgently needed to conduct ecological and economic zoning research in the Sino-Russian Northeast-Far East cross-border region, which transcends national borders and administrative boundaries.

[0003] As a scientific language that describes the fundamental characteristics of the Earth's surface, eco-economic zoning provides scientific support for sustainable development at different spatial scales by revealing the regional differentiation patterns of complex natural, social, and economic systems. While existing research has developed a multi-level research system encompassing "province, country-city, county-watershed, and physical geographic units," it often focuses on a single national or provincial, city-county, and county-level administrative unit, with insufficient attention paid to cross-border regions. Furthermore, current eco-economic zoning research generally uses administrative units as a benchmark for division. While this approach facilitates policy implementation and management to a certain extent, it can also lead to the artificial fragmentation of ecosystem integrity and exacerbate the contradiction between the mobility of economic factors and the rigidity of administrative boundaries.

[0004] Therefore, it is necessary to propose a cross-border ecological and economic zoning method to solve the above problems. Summary of the Invention

[0005] In response to the problem that current ecological and economic zoning pays insufficient attention to cross-border regions, and that ecological and economic zoning research generally divides regions based on administrative units, resulting in the artificial fragmentation of ecosystem integrity and exacerbating the contradiction between the mobility of economic factors and the rigidity of administrative boundaries, this paper proposes a cross-border ecological and economic zoning method.

[0006] This cross-border eco-economic zoning method includes the following steps:

[0007] S1. Construction of cross-border ecological and economic zoning indicator system;

[0008] S2, PartitioningAroundMedoid clustering algorithm around the center point, namely PAM clustering algorithm;

[0009] S3. Optimal number of clusters selection.

[0010] In a preferred embodiment of the present invention, the cross-border ecological and economic zoning indicators in S1 include nature, ecology, economy, society, and resources.

[0011] Furthermore, nature includes local conditions of the natural environment, and the indicators of the local conditions of the natural environment include: air temperature, accumulated temperature >10°C, precipitation, elevation, slope, frozen soil distribution, number of heating months, and NDVI vegetation cover index;

[0012] Ecology includes the importance of ecosystem function services. The indicators of the importance of ecosystem function services include: distribution of protected areas, abundance of endangered species, importance of water conservation function, and importance of soil and water conservation function;

[0013] Economy includes GDP and population. The GDP indicator is the GDP per unit area, and the population indicator is the population density.

[0014] Society includes locational advantages, where the indicator of locational advantages is the density of the transportation network;

[0015] Resources include available resource volume and environmental capacity overload. The indicators of available resource volume include forest resource distribution, cultivated land resource distribution, and mineral point distribution. The indicators of environmental capacity overload include air pollution PM2.5, soil erosion, and fire occurrence.

[0016] In a preferred embodiment of the present invention, the PAM clustering algorithm in S2 includes the following steps:

[0017] (1) Randomly select K observations, each of which is called a center point;

[0018] (2) Calculate the distance / dissimilarity between the observation value and each center;

[0019] (3) Assign each observation to the nearest center point;

[0020] (4) Calculate the sum of the distances from each center point to each observation, i.e., the total cost;

[0021] (5) Select a point in the class that is not the center and swap it with the center point;

[0022] (6) Reassign each point to the center point closest to it;

[0023] (7) Calculate the total cost again;

[0024] (8) If the total cost is less than the total cost calculated in step (4), take the new point as the center point;

[0025] (9) Repeat steps (5) to (8) until the center point no longer changes.

[0026] Furthermore, in step (2), when measuring the distance / dissimilarity between observations and each center, since the 21 zoning indicators have been reclassified, they need to be treated as nominal variables and the distance / dissimilarity between samples is measured using the Gower distance. ij (Similarity) is defined as:

[0027]

[0028] Among them, d ij yes The weighted average of In this scheme, k =1; for is 0 or 1 when the variable x[,k] is missing in any one or two rows. is 0, and all other cases are 1. In this solution, missing data has been preprocessed and there is no missing data. are all 1; for is the distance between elements i and j on k variables, that is, the distance between x[i, k] and x[j, k]. If x[i, k] is equal to x[j, k], then is 0 if yes, otherwise it is 1.

[0029] In a preferred embodiment of the present invention, the specific method for selecting the optimal number of clusters in S3 is:

[0030] Since the goal of clustering is to make the total sum of squares of errors from each sample point to the nearest cluster center, that is, the cost function of clustering, denoted as SSE, as small as possible; try to find a certain K value, requiring that when K is greater than this value, the amplitude or speed of the decrease in SSE becomes significantly smaller; that is, when K exceeds a certain number, the degree of aggregation of each cluster is no longer significantly improved, at this time it can be considered that the optimal K value has been found; by drawing a line graph of different K values ​​and SSE values, if there is an elbow point in the process of SSE value decline, that is, the inflection point where the rate of decline suddenly decreases, the K value corresponding to this point is the appropriate number of clusters; the formula for calculating the sum of squares of errors SSE for the entire data is:

[0031]

[0032] Where, d(x, C i) is the Euclidean distance between the data object and the cluster center in space, where x is the data object C i is the i-th cluster center, m is the dimension of the data object, C ij For x and C i The j-th attribute value of ; the size of SSE indicates the quality of the clustering result, and k is the number of clusters.

[0033] The implementation of the embodiments of the present invention has the following beneficial effects:

[0034] This invention cross-integrates theories and methods from multiple disciplines such as geography, resource science, ecology, environmental science, economics, and sociology, breaks through the national boundary system, and completes an ecological and economic zoning scheme across administrative boundaries based on a grid scale, providing certain methods and theoretical references for the research on ecological and economic zoning and coordinated development models in cross-border regions.

[0035] This paper takes the Northeast-Far East cross-border region of China and Russia as the research area, adopts a multi-scale and multi-factor integration method, and constructs a more scientific and applicable cross-administrative ecological and economic zoning scheme based on the grid scale based on an improved spatial clustering algorithm. It can break through the traditional administrative boundary constraints to promote the sustainable development and collaborative governance of cross-border regions. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 Schematic diagram of data structure;

[0038] Figure 2 This is the cluster SSE map of the ecological and economic zoning of the Northeast-Far East Economic Corridor between China and Russia;

[0039] Figure 3 Box plots of 21 indicators in 8 clusters in the Northeast-Far East cross-border region between China and Russia. DETAILED DESCRIPTION

[0040] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0041] The present invention discloses a cross-border ecological and economic zoning method, comprising the following steps:

[0042] S1. Construction of cross-border ecological and economic zoning indicator system;

[0043] Specifically, cross-border eco-economic zoning indicators include nature, ecology, economy, society, and resources.

[0044] Nature includes local conditions of the natural environment, and the indicators of local conditions of the natural environment include: air temperature, accumulated temperature >10°C, precipitation, elevation, slope, frozen soil distribution, number of heating months, and NDVI vegetation cover index;

[0045] Ecology includes the importance of ecosystem function services. The indicators of the importance of ecosystem function services include: distribution of protected areas, abundance of endangered species, importance of water conservation function, and importance of soil and water conservation function;

[0046] Economy includes GDP and population. The GDP indicator is the GDP per unit area, and the population indicator is the population density.

[0047] Society includes locational advantages, where the indicator of locational advantages is the density of the transportation network;

[0048] Resources include available resources and environmental capacity overload. Available resource indicators include forest resource distribution, cultivated land resource distribution, and mineral resource distribution. Environmental capacity overload indicators include PM2.5 levels, soil erosion, and fire. See Table 1 for the grading standards and data sources for each indicator.

[0049] Table 1 Cross-border ecological and economic zoning indicator system

[0050]

[0051]

[0052] S2, Partitioning Around Medoid clustering algorithm, also known as PAM clustering algorithm, specifically includes the following steps:

[0053] (1) Randomly select K observations, each of which is called a center point.

[0054] (2) Calculate the distance / dissimilarity between the observation value and each center;

[0055] When measuring the distance / dissimilarity between observations and each center, since the 21 zoning indicators have been reclassified, they need to be treated as nominal variables and the distance / dissimilarity between samples is measured using the Gower distance. ij(Similarity) is defined as:

[0056]

[0057] Among them, d ij yes The weighted average of In this scheme, k =1; for is 0 or 1 when the variable x[,k] is missing in any one or two rows. is 0, and all other cases are 1. In this solution, missing data has been preprocessed and there is no missing data. are all 1; for is the distance between elements i and j on k variables, that is, the distance between x[i, k] and x[j, k]. If x[i, k] is equal to x[j, k], then 0 if yes, otherwise 1. Figure 1 , Figure 1 A diagram of the data structure.

[0058] (3) Assign each observation to the nearest center point.

[0059] (4) Calculate the sum of the distances from each center point to each observation, i.e. the total cost.

[0060] (5) Select a point in the class that is not the center and swap it with the center point.

[0061] (6) Reassign each point to the center point closest to it.

[0062] (7) Calculate the total cost again.

[0063] (8) If the total cost is less than the total cost calculated in step (4), take the new point as the center point.

[0064] (9) Repeat steps (5) to (8) until the center point no longer changes.

[0065] S3. Select the optimal number of clusters. The specific method is:

[0066] Since the goal of clustering is to make the total sum of squares of errors from each sample point to the nearest cluster center, that is, the cost function of clustering, denoted as SSE, as small as possible; try to find a certain K value, requiring that when K is greater than this value, the amplitude or speed of the decrease in SSE becomes significantly smaller; that is, when K exceeds a certain number, the degree of aggregation of each cluster is no longer significantly improved, at this time it can be considered that the optimal K value has been found; by drawing a line graph of different K values ​​and SSE values, if there is an elbow point in the process of SSE value decline, that is, the inflection point where the rate of decline suddenly decreases, the K value corresponding to this point is the appropriate number of clusters; the formula for calculating the sum of squares of errors SSE for the entire data is:

[0067]

[0068] Where, d(x, C i ) is the Euclidean distance between the data object and the cluster center in space, where x is the data object C i is the i-th cluster center, m is the dimension of the data object, C ij For x and C i The j-th attribute value of ; the size of SSE indicates the quality of the clustering result, and k is the number of clusters. Specific embodiments

[0070] According to the above method, the final number of clusters for the ecological and economic zoning of the Northeast-Far East cross-border region of China and Russia is 8. Figure 2 , Figure 2 This is the SSE map of the ecological and economic zoning cluster of the Northeast-Far East Economic Corridor between China and Russia.

[0071] 1. China-Russia Northeast-Far East cross-border region

[0072] This ecological and economic zoning study focuses on the Sino-Russian Northeast-Far East cross-border region, a core pilot zone for the China-Mongolia-Russia Economic Corridor. This region encompasses the cross-border link between Heilongjiang and Jilin provinces in Northeast my country and four leagues and municipalities in eastern Inner Mongolia, and five provinces in the Russian Far East: Primorsky Krai, Khabarovsk Krai, Jewish Oblast, Amur Oblast, and Trans-Baikal Krai. The region covers an area of ​​2.9 million square kilometers (1.78 million square kilometers in Russia and 1.12 million square kilometers in China), has a total population of 71 million in 2021 (5 million in Russia and 65 million in China), a 4,273-kilometer border, and hosts all 20 Sino-Russian land ports.

[0073] The region is a crucial component of the ecological security barrier and a treasure trove of natural resources for northern and northeastern my country. Precious natural resources like water and black soil are distributed across borders; ecosystems like wetlands and lakes extend across borders; and rare species like tigers and leopards inhabit these borders, forming an indivisible system of natural elements.

[0074] 2. Clustering results of ecological and economic factors in the Northeast-Far East cross-border region between China and Russia

[0075] Based on the above clustering method, the ecological and economic zoning scheme for the Northeast-Far East cross-border region of China and Russia was obtained. In order to clarify the key characteristics of different ecological and economic zones that are different from other clusters, this paper draws a box plot of 21 indicator values ​​for 8 clusters. Please refer to Figure 3 .

[0076] The First Ecological and Economic Zone is primarily located in central Heilongjiang Province, China, and its border with Hulunbuir City in the Inner Mongolia Autonomous Region. This low-altitude, flat-slope area boasts high annual accumulated temperatures, suitable for growing nearly 20 crops. It serves as a vital water conservation zone, boasts high vegetation coverage, a large distribution of cultivated land, a relatively developed economy, and a dense road network. It is prone to wildfires, boasts a high species richness, but has a low level of endangered species protection requirements, and exhibits high soil erosion.

[0077] The Second Ecological and Economic Zone is primarily located in Chifeng and Tongliao cities in Inner Mongolia Autonomous Region, China, and western Jilin Province. This low-altitude, flat slope area boasts high annual accumulated temperatures, suitable for growing nearly 20 crops. It boasts extensive arable land and is a key crop-growing region. It has low levels of endangered species and species richness, placing low ecological conservation requirements. It also boasts a developed economy and a dense road network, but also suffers from severe air pollution, is prone to wildfires, and has low soil erosion resistance.

[0078] The third ecological and economic zone is primarily located in the Trans-Baikal Territory, northern Amur Oblast and its border areas, and central Khabarovsk Territory. This region is characterized by high altitudes and gentle slopes, discontinuous frozen ground and permafrost, and extremely low annual accumulated temperatures. While these conditions are better than those in Cluster 5, they still barely meet the thermal requirements of crops. The economy is underdeveloped, and the road network density is extremely low. A high concentration of endangered species exists, necessitating conservation efforts.

[0079] The fourth ecological and economic zone is primarily located in central Amur Oblast, Russia, stretching along the Amur River to Khabarovsk Krai. This low-altitude, flat-slope region boasts moderate annual accumulated temperatures, providing sufficient heat for eight crops, including corn, soybeans, and potatoes. It also serves as a vital water conservation zone. Mineral deposits are concentrated, but economic development is moderate, and road density is low. It is home to a high concentration of endangered species, necessitating greater conservation efforts. Its soil is highly erodible.

[0080] The fifth ecological and economic zone is located primarily in the northern Khabarovsk Territory of Russia. This region is characterized by high altitudes and gentle slopes, discontinuous frozen ground and permafrost, and extremely low annual temperatures, which barely meet the thermal requirements of crops. The economy is underdeveloped, and the road network density is extremely low. The high density of endangered species creates a need for conservation.

[0081] The Sixth Ecological and Economic Zone is primarily located in the western and southern parts of Russia's Trans-Baikal Territory and the northern part of Hulunbuir City in China's Inner Mongolia Autonomous Region. This region is located at high altitudes and on gentle slopes. Annual accumulated temperatures are low, meeting the thermal requirements of only three crops: soybeans, spring wheat, and potatoes. Discontinuous permafrost and permafrost are common. Mineral deposits are concentrated, but economic development is moderate, and road density is low. Species richness is high, but endangered species protection is low. Soil erosion is high.

[0082] The seventh ecological and economic zone is primarily located in western Hulunbuir City, Inner Mongolia Autonomous Region, China. This high-altitude, gently sloping area boasts high annual temperatures, suitable for growing nearly 20 crops. It also includes discontinuous frozen and permafrost areas, and boasts a high species richness and abundance of endangered species, necessitating high conservation efforts.

[0083] The Eighth Ecological and Economic Zone is primarily located in the Primorsky Krai of Russia, southeastern Jilin Province of China, and parts of Heilongjiang Province of China. This low-altitude, flat-slope region boasts high annual temperatures, suitable for growing nearly 20 crops. It also boasts high forest cover, a relatively developed economy, and a dense road network. It also boasts a high species richness, but low endangered species protection requirements. Its soils are highly erodible.

[0084] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A cross-border ecological and economic zoning method, characterized by: The following steps are involved: S1. Construction of cross-border ecological and economic zoning indicator system; S2, PartitioningAroundMedoid clustering algorithm around the center point, namely PAM clustering algorithm; S3. Optimal number of clusters selection.

2. The cross-border ecological and economic zoning method according to claim 1 is characterized in that: The cross-border eco-economic zoning indicators in S1 include nature, ecology, economy, society, and resources.

3. The cross-border ecological and economic zoning method according to claim 2 is characterized in that: The natural environment includes local conditions of the natural environment, and the indicators of the local conditions of the natural environment include: air temperature, accumulated temperature >10°C, precipitation, elevation, slope, frozen soil distribution, number of heating months, and NDVI vegetation cover index; The ecology includes the importance of ecosystem function services, and the indicators of the importance of ecosystem function services include: distribution of protected areas, richness of endangered species, importance of water conservation function, and importance of soil and water conservation function; The economy includes GDP and population, the GDP indicator is the GDP per unit area value, and the population indicator is the population density; The society includes locational advantages, and the indicator of the locational advantages is the density of the transportation network; The resources include the amount of available resources and the degree of environmental capacity overload. The indicators of the amount of available resources include the distribution of forest resources, the distribution of cultivated land resources, and the distribution of mineral points. The indicators of the degree of environmental capacity overload include air pollution PM2.5, soil erosion, and fire occurrence.

4. The cross-border ecological and economic zoning method according to claim 1 is characterized in that: The PAM clustering algorithm in S2 includes the following steps: (1) Randomly select K observations, each of which is called a center point; (2) Calculate the distance / dissimilarity between the observation value and each center; (3) Assign each observation to the nearest center point; (4) Calculate the sum of the distances from each center point to each observation, i.e., the total cost; (5) Select a point in the class that is not the center and swap it with the center point; (6) Reassign each point to the center point closest to it; (7) Calculate the total cost again; (8) If the total cost is less than the total cost calculated in step (4), take the new point as the center point; (9) Repeat steps (5) to (8) until the center point no longer changes.

5. The cross-border ecological and economic zoning method according to claim 4 is characterized in that: In step (2), when measuring the distance / dissimilarity between the observation value and each center, for any two rows of elements i, j, the distance d ij Defined as: Among them, d ij yes The weighted average of In this scheme, k =1; for is 0 or 1 when the variable x[,k] is missing in any one or two rows. is 0, and all other cases are 1. In this solution, missing data has been preprocessed and there is no missing data. are all 1; for is the distance between elements i and j on the variables, that is, the distance between x[i, k] and x[j, k]. If x[i, k] is equal to x[j, k], then is 0 if yes, otherwise it is 1.

6. The cross-border ecological and economic zoning method according to claim 1 is characterized in that: The specific method for selecting the optimal number of clusters in S3 is: Since the goal of clustering is to make the total sum of squares of errors from each sample point to the nearest cluster center, that is, the cost function of clustering, denoted as SSE, as small as possible; try to find a certain K value, requiring that when K is greater than this value, the amplitude or speed of the decrease in SSE becomes significantly smaller; that is, when K exceeds a certain number, the degree of aggregation of each cluster is no longer significantly improved, at this time it can be considered that the optimal K value has been found; by drawing a line graph of different K values ​​and SSE values, if there is an elbow point in the process of SSE value decline, that is, the inflection point where the rate of decline suddenly decreases, the K value corresponding to this point is the appropriate number of clusters; the formula for calculating the sum of squares of errors SSE for the entire data is: Where, d(x,C i ) is the Euclidean distance between the data object and the cluster center in space, where x is the data object C i is the i-th cluster center, m is the dimension of the data object, C ij For x and C i The j-th attribute value of ; the size of SSE indicates the quality of the clustering result, and k is the number of clusters.

Images