Land space planning risk assessment method based on multi-dimensional analysis

Abstract

The invention discloses a territorial space planning risk assessment method based on multi-dimensional analysis, relates to the technical field of Internet, and aims to obtain and pre-process data from different sources, ensure the consistency and reliability of the data, simulate city expansion, predict future expansion areas and trends, and combine ecological environment data to evaluate the risk of territorial space planning. According to the method, an ecological sensitive area is further marked, necessary space information is provided for subsequent risk assessment, in a multi-dimensional risk assessment model, a comprehensive risk assessment index ZR is obtained by comprehensively considering multiple aspects of biological habitats, ecological connectivity and water resource flow, the possible influence of urban expansion on the ecological environment is comprehensively reflected, and the risk assessment efficiency is improved. Through comparison with a preset risk assessment threshold value Zth, the risk level of urban expansion is effectively assessed, potential ecological crisis is found in time, the model is optimized through continuous verification and assessment, and sustainability of urban expansion and protection of the ecological environment are ensured.

Description

Technical Field

[0001] The present invention relates to the field of Internet technology, and in particular to a land space planning risk assessment method based on multi-dimensional analysis. Background Art

[0002] With the rapid development of society and the accelerating urbanization process, the importance of national land space planning has become increasingly prominent. National land space planning not only involves the use and allocation of land, but also includes various aspects of work such as resource protection and ecological environment coordination. As a broad field, the core goal of national land space planning is to achieve sustainable development of society, economy and environment. In this context, urban planning, as an important part of national land space planning, faces increasingly complex challenges, especially in the balance between ecological protection and urban expansion.

[0003] With the advancement of urbanization, how to ensure that urban expansion does not cause excessive damage to the ecosystem has become a key issue that needs to be urgently addressed in urban planning. In particular, the impact on ecological networks, such as the loss of biological habitats and the breakdown of ecological connectivity, has often not received sufficient attention.

[0004] In addition, due to the complexity and dynamism of the urban ecological environment, traditional assessment methods cannot accurately predict ecological risks under different expansion scenarios. This not only leads to the lag of ecological damage, but also makes it difficult for planning schemes to adapt to changes in actual conditions during implementation. Therefore, existing methods lack sufficient accuracy and comprehensiveness when assessing the relationship between urban expansion and ecological networks. There is no sufficient risk warning mechanism, and it is also impossible to scientifically predict and optimize the sustainability of urban planning from the perspective of ecological protection.

[0005] Among them, during the process of urban expansion, if the damage to the ecological network is not assessed in time, the following abnormal situations may occur. First, ecologically sensitive areas or biological habitats are misjudged or ignored during urban expansion, resulting in the loss of a large number of natural habitats, affecting the survival and reproduction of species. This habitat loss may not only be limited to the reduction in area, but may also lead to a decline in ecological functions, such as the loss of water conservation capacity and carbon storage function, further aggravating environmental degradation. Secondly, urban expansion often destroys the connectivity of ecological networks, and the migration channels of species are blocked, resulting in a reduction in gene flow, which in turn threatens the maintenance of biodiversity. The formation of ecological islands will greatly reduce the adaptability and resilience of ecosystems, and increase the ecological risks brought about by future environmental changes. Summary of the invention

[0006] In view of the shortcomings of the prior art, the present invention provides a land space planning risk assessment method based on multi-dimensional analysis, which solves the problems mentioned in the background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a land space planning risk assessment method based on multi-dimensional analysis, comprising the following steps:

[0008] S1. Obtain data through multiple channels, including land use data, climate data, ecological environment data and socio-economic data, and then pre-process them to form a collection data group;

[0009] S2. Simulate urban expansion by collecting data sets, predict the predicted area and trend area information of urban expansion, and mark ecologically sensitive areas (x, y) in combination with ecological and environmental data;

[0010] S3. Construct a multidimensional risk assessment model based on the marked ecologically sensitive areas (x, y) to assess the ecological and environmental impact information generated by urban expansion, including the biological habitat assessment index Rh, the ecological connectivity assessment index Rc and the water resource flow assessment index Rw, and conduct a comprehensive analysis to obtain the comprehensive risk assessment index ZR;

[0011] S4. Obtain the risk assessment result of the urban expansion area by comparing the preset risk assessment threshold Zth with the comprehensive risk assessment index ZR;

[0012] S5. Conduct continuous verification and evaluation based on the risk assessment results of urban expansion areas, including iterative optimization of the risk assessment results of urban expansion areas and the comprehensive risk assessment index ZR.

[0013] Preferably, said S1 includes S11 and S12;

[0014] S11. Obtain data through multiple channels, including land use data, climate data, ecological environment data, and socio-economic data;

[0015] Among them, different types of land are classified based on satellite images obtained by remote sensing satellites through a land classification algorithm, and the land classification algorithm includes a support vector machine and a random forest algorithm. The different types of land include area data of farmland, urban land and non-cultivated land;

[0016] The climate data is obtained by using weather station data and MODIS climate data sets to obtain regional climate data, including temperature, precipitation and wind speed climate data, to obtain predicted climate change data, including future climate forecast data provided by WorldClim, including future trend data on temperature and precipitation;

[0017] The ecological environment data is obtained by obtaining species distribution and habitat data from the Global Biodiversity Information Facility (GBIF) to obtain ecological protection area distribution data, including ecological protection area area data released by IUCN;

[0018] The socio-economic data is obtained by obtaining socio-economic data related to population density, economic development level and urbanization process through public data from the National Bureau of Statistics and local governments to obtain urban planning information, including planning data on urban expansion area and infrastructure construction.

[0019] Preferably, S12, preprocessing the land use data, climate data, ecological environment data and socio-economic data to form a collection data group;

[0020] Preprocessing includes unit conversion and normalization preprocessing of land use data to obtain information including farmland area, urban land area and non-cultivated land area;

[0021] The climate data is subjected to data cleaning, missing value processing and normalization preprocessing to obtain information including temperature, precipitation and wind speed;

[0022] The ecological environment data is preprocessed by data cleaning and data standardization to obtain information including habitat area and ecological protection area area;

[0023] The socio-economic data is pre-processed by data cleaning and normalization to obtain information including population density, economic level and urban expansion area.

[0024] Preferably, S2 includes S21 and S22;

[0025] S21. Simulate urban expansion by collecting data sets, simulate future urban expansion trends by using Markov chain models and automaton models, mark the expected urban expansion areas, output urban expansion area prediction values ​​Cp and urban expansion trend area values ​​Ct, and predict the prediction areas and trend area information of urban expansion.

[0026] Preferably, S22, by combining ecological environment data, climate data and urban expansion area prediction value Cp, substituting into the established ecological region sensitivity assessment formula for calculation, obtaining the ecological sensitivity index Se, identifying and marking ecological sensitive areas (x, y), including ecological protection areas, protected animal and plant habitats and climate vulnerable areas;

[0027] Among them, the identification of the ecologically sensitive area (x, y) is performed by comparing and judging the ecological sensitivity index Se with the preset ecologically sensitive area assessment threshold Sth, and obtaining the identification result of the area (x, y). When the ecological sensitivity index Se≥the ecologically sensitive area assessment threshold Sth, the identification result of the area (x, y) is obtained as a sensitive result, and the area (x, y) is marked as an ecologically sensitive area.

[0028] Preferably, said S3 includes S31 and S32;

[0029] S31. Construct a multi-dimensional risk assessment model based on the marked ecologically sensitive areas (x, y) to assess the ecological and environmental impact information generated by urban expansion, including the biological habitat assessment index Rh, the ecological connectivity assessment index Rc and the water resource flow assessment index Rw;

[0030] The biological habitat assessment index Rh is used to assess the impact of urban expansion on biological habitats in ecologically sensitive areas (x, y), reflecting the loss, fragmentation and degradation of habitats. Specifically, the risk of habitat damage is quantified by comparing the original habitat area with the expanded habitat area and the degree of habitat fragmentation, wherein the degree of habitat fragmentation is obtained by statistically calculating the proportion of the number of habitat divisions.

[0031] The ecological connectivity assessment index Rc is used to evaluate the impact of urban expansion on the connectivity between various areas in the ecosystem, measure the interconnection and permeability between ecologically sensitive areas (x, y), and affect the migration and exchange of ecological species;

[0032] The water resource flow assessment index Rw is used to measure the impact of urban expansion on water resource flow. The water resource mobility in the ecologically sensitive area (x, y) is obtained by analyzing the direction of water flow, flow changes and water source coverage.

[0033] Preferably, S32, based on the obtained biological habitat assessment index Rh, ecological connectivity assessment index Rc and water resource flow assessment index Rw, a comprehensive weighted processing analysis is performed to obtain a comprehensive risk assessment index ZR, which comprehensively reflects the overall impact of urban expansion on the ecological environment.

[0034] Preferably, the S4 includes S41;

[0035] S41. By comparing the preset risk assessment threshold Zth with the comprehensive risk assessment index ZR, the risk status of the ecologically sensitive area (x, y) is determined, and the risk assessment result of the urban expansion area is obtained;

[0036] The risk assessment results of the urban expansion area are obtained by the following comparison method:

[0037] When the comprehensive risk assessment index ZR ≥ the comprehensive risk assessment index ZR, the ecologically sensitive area (x, y) is determined to be a risk area. The ecologically sensitive area (x, y) will be affected by urban expansion, and the risk assessment result of the urban expansion area is a risk result.

[0038] When the comprehensive risk assessment index ZR<comprehensive risk assessment index ZR, the ecologically sensitive area (x, y) is determined to be a risk-free area. The ecologically sensitive area (x, y) will not be affected by urban expansion, and the risk assessment result of the urban expansion area is a risk-free result.

[0039] Preferably, said S5 includes S51 and S52;

[0040] S51, by using remote sensing satellite images and ground monitoring data, comparing the predicted value Cp of the urban expansion area with the data of the actual urban expansion area, and then calculating and evaluating to obtain the deviation value D, and by comparing it with the preset allowable deviation threshold Dth, obtaining the urban expansion area risk assessment result to continuously verify the result;

[0041] The continuous verification results are obtained by the following comparison method:

[0042] When the deviation value D ≥ the allowable deviation threshold Dth, the continuous verification result is obtained as a deviation result, triggering the adjustment mechanism;

[0043] When the deviation value D is less than the allowable deviation threshold Dth, the continuous verification result is obtained as a deviation-free result, and the adjustment mechanism is not triggered.

[0044] Preferably, S52, the continuous verification results trigger an iterative optimization adjustment mechanism for the urban expansion area risk assessment results and the comprehensive risk assessment index ZR, including proportionally adjusting the Markov chain model, the automaton model, the comprehensive risk assessment index ZR and the comprehensive risk assessment index ZR according to the deviation value D.

[0045] The present invention provides a land space planning risk assessment method based on multi-dimensional analysis, which has the following beneficial effects:

[0046] (1) By acquiring and preprocessing data from different sources to ensure data consistency and reliability, urban expansion is simulated and future expansion areas and trends are predicted. Combined with ecological and environmental data, ecologically sensitive areas are further marked to provide necessary spatial information for subsequent risk assessment. In the multidimensional risk assessment model, a comprehensive risk assessment index ZR is obtained by comprehensively considering biological habitats, ecological connectivity, and water resource flow. It fully reflects the impact that urban expansion may have on the ecological environment. By comparing it with the preset risk assessment threshold Zth, the risk level of urban expansion is effectively assessed and potential ecological crises are discovered in a timely manner. The model is optimized through continuous verification and evaluation to ensure the sustainability of urban expansion and the protection of the ecological environment. It can accurately identify the specific impact of urban expansion on the ecological environment, especially ecologically sensitive areas that may be neglected in the urbanization process. These aspects are often not fully considered in traditional urban expansion assessments. It can clearly point out which areas have higher expansion risks, thereby providing a scientific basis for policymakers and promoting ecological protection and sustainable development in the process of urban expansion.

[0047] (2) Through the calculation and comprehensive analysis of the biological habitat assessment index Rh, the ecological connectivity assessment index Rc and the water resource flow assessment index Rw, a more comprehensive ecological risk assessment is provided. By evaluating the loss and fragmentation of biological habitats, the specific impact of urban expansion on the habitats in ecologically sensitive areas (x, y) can be accurately identified, and the overall impact of urban expansion on the ecological environment can be fully reflected. It can timely identify potential ecological and environmental risks in the process of urbanization, especially providing in-depth quantitative analysis in terms of multi-dimensional and systematic environmental impacts. It can not only predict the ecological risks of urban expansion, but also provide an operational decision-making basis for urban planning. Compared with the traditional single-dimensional assessment, this method can more accurately grasp the comprehensive ecological risks brought about by urban expansion through the comprehensive analysis of multiple indicators, ensuring that while promoting urban development, the sustainability of the ecological environment is protected to the maximum extent.

[0048] (3) By comparing and analyzing the comprehensive risk assessment index ZR with the preset risk assessment threshold Zth, an accurate risk assessment of the urban expansion area is achieved, and it is effectively determined whether the ecologically sensitive area (x, y) is threatened by urban expansion, thus avoiding unnecessary resource investment. This process provides an accurate basis for decision-making on ecological environmental protection during urban expansion, ensuring the coordination between environment and development. By using remote sensing satellite images and ground monitoring data to compare and analyze the predicted value Cp of the urban expansion area with the actual urban expansion area, the deviation value D can be obtained to further verify the accuracy of the model. The parameters of the risk assessment model can be dynamically optimized. The introduction of this mechanism significantly improves the reliability and accuracy of risk assessment, ensuring the sustainability and accuracy of the urban expansion decision-making process. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a schematic diagram of the steps of a land space planning risk assessment method based on multi-dimensional analysis of the present invention. DETAILED DESCRIPTION

[0050] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0051] Example 1

[0052] The present invention provides a land space planning risk assessment method based on multi-dimensional analysis. Figure 1 , including the following steps:

[0053] S1. Obtain data through multiple channels, including land use data, climate data, ecological environment data and socio-economic data, and then pre-process them to form a collection data group;

[0054] S2. Simulate urban expansion by collecting data sets, predict the predicted area and trend area information of urban expansion, and mark ecologically sensitive areas (x, y) in combination with ecological and environmental data;

[0055] S3. Construct a multidimensional risk assessment model based on the marked ecologically sensitive areas (x, y) to assess the ecological and environmental impact information generated by urban expansion, including the biological habitat assessment index Rh, the ecological connectivity assessment index Rc and the water resource flow assessment index Rw, and conduct a comprehensive analysis to obtain the comprehensive risk assessment index ZR;

[0056] S4. Obtain the risk assessment result of the urban expansion area by comparing the preset risk assessment threshold Zth with the comprehensive risk assessment index ZR;

[0057] S5. Conduct continuous verification and evaluation based on the risk assessment results of urban expansion areas, including iterative optimization of the risk assessment results of urban expansion areas and the comprehensive risk assessment index ZR.

[0058] In this embodiment, a comprehensive framework for assessing the impact of urban expansion and ecological environment is constructed. The method first obtains and preprocesses data from different sources to ensure the consistency and reliability of the data, and then simulates urban expansion and predicts future expansion areas and trends. Combined with ecological and environmental data, ecologically sensitive areas are further marked to provide necessary spatial information for subsequent risk assessment. In the multidimensional risk assessment model, the comprehensive risk assessment index ZR is obtained by comprehensively considering biological habitats, ecological connectivity and water resource flow, which fully reflects the impact that urban expansion may have on the ecological environment. By comparing with the preset risk assessment threshold Zth, the risk level of urban expansion is effectively assessed, and potential ecological crises are discovered in a timely manner. The model is optimized through continuous verification and evaluation to ensure the sustainability of urban expansion and the protection of the ecological environment. Through multidimensional analysis, the specific impact of urban expansion on the ecological environment can be accurately identified, especially in ecologically sensitive areas that may be neglected in the urbanization process. These aspects are often not fully considered in traditional urban expansion assessments. It can clearly point out which areas have higher expansion risks, thereby providing a scientific basis for policy makers and promoting ecological protection and sustainable development in the process of urban expansion.

[0059] Example 2

[0060] This embodiment is explained in Example 1, please refer to Figure 1 , specifically: S1 includes S11 and S12;

[0061] S11. Obtain data through multiple channels, including land use data, climate data, ecological environment data, and socio-economic data;

[0062] Among them, different types of land are classified based on satellite images obtained by remote sensing satellites through a land classification algorithm, and the land classification algorithm includes a support vector machine and a random forest algorithm. The different types of land include area data of farmland, urban land and non-cultivated land;

[0063] Climate data: The climate data of the region is obtained through weather station data and MODIS climate data sets, including temperature, precipitation and wind speed climate data, to obtain predicted climate change data, including future climate forecast data provided by WorldClim, including future trend data on temperature and precipitation;

[0064] Ecological and environmental data: By obtaining species distribution and habitat data from the Global Biodiversity Information Facility (GBIF), we can obtain ecological protection area distribution data, including ecological protection area area data published by IUCN.

[0065] Socioeconomic data related to population density, economic development level and urbanization process are obtained through public data from the National Bureau of Statistics and local governments to obtain urban planning information, including planning data on urban expansion area and infrastructure construction.

[0066] S12, pre-processing the land use data, climate data, ecological environment data and social economic data to form a collection data group;

[0067] Preprocessing includes unit conversion and normalization preprocessing of land use data to obtain farmland area Ac, urban land area Au and non-cultivated land area An, wherein the satellite image is classified by using SVM or random forest algorithm to output the pixel area of ​​each land type, for example, the area of ​​each land type is identified using the image classification results;

[0068] The climate data was cleaned, missing values ​​processed and normalized to obtain temperature Tt, precipitation Pp and wind speed Vw. The temperature, precipitation and wind speed data of each region were extracted from the meteorological station data and MODIS climate data set. At the same time, the future climate prediction values ​​were obtained from the WorldClim data set.

[0069] The ecological environment data is preprocessed by data cleaning and data standardization to obtain the habitat area Hh and the ecological protection area Hp. The species distribution data is obtained from the GBIF database to extract the habitat range and its characteristics. For example, the distribution area of ​​a certain species is extracted and the area of ​​the area (x, y) is calculated. The ecological protection area extraction obtains the distribution information of the ecological protection area from the IUCN database to identify the land area within the protection area.

[0070] The socio-economic data were cleaned and normalized before being preprocessed to obtain population density Sp, economic level Se and urban expansion area Su. The population density and economic level were extracted by extracting regional population density and economic development level data from the National Bureau of Statistics and local government data, and the urban expansion area was extracted by extracting urban expansion areas and infrastructure construction plans from urban planning data.

[0071] S2 includes S21 and S22;

[0072] S21, simulating urban expansion by collecting data groups, simulating future urban expansion trends by using Markov chain models and automaton models, marking the expected urban expansion areas, outputting urban expansion area prediction values ​​Cp and urban expansion trend area values ​​Ct, and predicting the prediction areas and trend area information of urban expansion;

[0073] Among them, the collected data set is used as a basic data set to provide support for the subsequent urban expansion model. The data itself does not directly participate in certain calculation processes, but they are used as background data to limit the real situation of the simulation of urban expansion, and to set boundaries for the accuracy of subsequent result calculations and the actual situation of urban expansion. Through these data, the model can simulate the urban expansion process based on spatial dimensions and environmental changes, and then predict the future urban expansion area and its ecological impact;

[0074] The predicted value Cp of the urban expansion area is obtained through the following simulation formula:

[0075] Cp=f(Au,Pt(x,y),T(i,j));

[0076] Wherein, Au represents the urban land area, f represents the algorithm simulation function, including the calculation function of the Markov chain model and the automaton model, Pt(x, y) represents the urbanization probability at the current moment, specifically represents the urbanization probability at the region (x, y), specifically based on the distribution of existing urban land, estimates the probability of future urban expansion, for example, the area around the current urban land may be more likely to be converted into urban land, T(i, j) represents the element in the transition probability matrix, specifically represents the transition probability from land type i to land type j, specifically represents the transition probability of urban expansion from the current type to the urban land type, specifically based on historical land use data, calculates the number of transitions from land type i to land type j within a certain time range, and this transition frequency represents the element in the transition probability matrix. The purpose of this formula is to obtain the predicted value Cp of the urban expansion area at the region (x, y), which represents the possibility of urbanization of the region (x, y) in the future;

[0077] The urban expansion trend area value Ct is obtained by the following calculation formula:

[0078] Ct=max(Pt(x,y)-Cp(x,y),0);

[0079] Where Cp(x, y) represents the predicted value of the urban expansion area of ​​region (x, y), and max represents the larger of the two values ​​and 0, ensuring that when the predicted urbanization probability is lower than the expansion area, the trend value will not be negative. The purpose of this formula is to obtain the urban expansion trend area value Ct at region (x, y), indicating that the location of region (x, y) is more likely to expand in the future but has not yet been completely transformed into an urban area.

[0080] S22. By combining ecological environment data, climate data and the predicted value of urban expansion area Cp, the ecological sensitivity index Se is obtained by substituting them into the established ecological region sensitivity assessment formula for calculation, and ecological sensitivity index Se is obtained to identify and mark ecological sensitive areas (x, y), including ecological protection areas, protected animal and plant habitats and climate vulnerable areas;

[0081] The ecological sensitivity index Se is obtained by the following calculation formula:

[0082] Se=f(Cp(x,y),Hp(x,y),Tt(x,y),Pp(x,y));

[0083] In the formula, Cp(x, y) represents the predicted value of the urban expansion area of ​​the region (x, y), Hp(x, y) represents the ecological protection area Hp of the region (x, y), Tr(x, y) represents the temperature Tt of the region (x, y), Pp(x, y) represents the precipitation of the region (x, y), and f represents the comprehensive calculation function, which is specifically a weighted function. The purpose of this formula is to obtain the ecological sensitivity index Se at the region (x, y), which represents the ecological vulnerability of the region (x, y);

[0084] Among them, the ecologically sensitive area (x, y) is identified by comparing the ecological sensitivity index Se with the preset ecologically sensitive area assessment threshold Sth to obtain the identification result of the area (x, y). When the ecological sensitivity index Se ≥ the ecologically sensitive area assessment threshold Sth, the identification result of the area (x, y) is a sensitive result, and the area (x, y) is marked as an ecologically sensitive area.

[0085] In this embodiment, through the integration of multiple data channels, especially the preprocessing of land use data, climate data, ecological environment data and socio-economic data, the method provides a solid foundation for simulating urban expansion and predicting changes in future urban expansion areas. By using the Markov chain model and the automaton model, the expansion trend of urban land can be accurately simulated, thereby predicting the urban expansion area prediction value Cp and the urban expansion trend area value Ct, providing a clear expansion direction for urban planners. In addition, by combining the ecological environment data and climate change information, an ecological regional sensitivity assessment model is established, and the calculated ecological sensitivity index Se can accurately identify ecological sensitive areas. This sensitive area identification and assessment provides specific quantitative information on environmental impacts during urban expansion, and provides a basis for ecological protection and rational resource allocation. The unique advantage of this method is that it not only considers the spatial changes of urban expansion, but also combines the fragility of the ecological environment for multi-dimensional risk assessment, especially by accurately calculating the ecological sensitivity index Se, and incorporating ecological protection areas, protected animal and plant habitats, and climate-vulnerable areas into urban planning considerations. Through the comprehensive calculation of the urban expansion area prediction value Cp, the regional trend of future urban expansion can be predicted in real time, thereby more effectively guiding the coordination of urban planning and ecological protection. More importantly, when identifying ecologically sensitive areas, the method can compare the preset ecologically sensitive area assessment threshold Sth with the ecological sensitivity index Se, accurately mark those areas that may face major ecological risks, and thus provide accurate risk warnings for urban expansion decisions. This process not only helps to avoid the negative impact of excessive urbanization on the ecological environment, but also achieves a balance between urban development and ecological protection, and promotes a more sustainable urbanization process.

[0086] Example 3

[0087] This embodiment is explained in Example 2. Please refer to Figure 1 , specifically: S3 includes S31 and S32;

[0088] S31. Construct a multi-dimensional risk assessment model based on the marked ecologically sensitive areas (x, y) to assess the ecological and environmental impact information generated by urban expansion, including the biological habitat assessment index Rh, the ecological connectivity assessment index Rc and the water resource flow assessment index Rw;

[0089] Among them, the biological habitat assessment index Rh is used to evaluate the impact of urban expansion on biological habitats in ecologically sensitive areas (x, y), reflecting the loss, fragmentation and degradation of habitats. Specifically, it quantifies the risk of habitat damage by comparing the original habitat area with the expanded habitat area and the degree of habitat fragmentation. The degree of habitat fragmentation is obtained by counting the proportion of the number of habitat divisions.

[0090] The biological habitat assessment index Rh is obtained by the following calculation formula:

[0091]

[0092] In the formula, Ahab represents the effective habitat area in the ecologically sensitive area (x, y), Aorig represents the initial preset habitat area, Chab represents the fragmentation degree of the ecologically sensitive area (x, y), which is obtained by the number of habitat divisions, and Corig represents the initial preset habitat fragmentation degree;

[0093] The ecological connectivity assessment index Rc is used to evaluate the impact of urban expansion on the connectivity between various regions in the ecosystem, measure the interconnection and permeability between ecologically sensitive areas (x, y), and affect the migration and exchange of ecological species;

[0094] The ecological connectivity assessment index Rc is obtained by the following calculation formula:

[0095]

[0096] In the formula, p and q represent the pth and qth ecologically sensitive areas (x, y), respectively; w(p, q) represents the preset weight value between the pth ecologically sensitive area (x, y) and the qth ecologically sensitive area (x, y), which is specifically evaluated and set by the user according to the functional importance of the habitat and the degree of ecological impact; d(p, q) represents the connectivity index between the pth ecologically sensitive area (x, y) and the qth ecologically sensitive area (x, y); Dmax represents the maximum connectivity distance in the ecological network of the ecologically sensitive area (x, y); the purpose of this formula is to evaluate the size of the ecological connectivity index Rc, indicating that the stronger the connectivity between ecologically sensitive areas (x, y), the greater the possibility of maintaining the stability of the ecosystem and biodiversity; a low value indicates that the connectivity of the ecosystem is poor, which may lead to obstruction of species migration and gene flow;

[0097] The water resource flow assessment index Rw is used to measure the impact of urban expansion on water resource flow, especially the water resource mobility within ecologically sensitive areas (x, y), which is obtained by analyzing the direction of water flow, flow changes and water source coverage;

[0098] The water resource flow assessment index Rw is obtained by the following calculation formula:

[0099]

[0100] Where Wi represents the water resource flow in the i-th ecologically sensitive area (x, y), and Wmax represents the upper limit of water flow in the ecological network of the ecologically sensitive area (x, y). The purpose of this formula is to achieve the following: the higher the value of the water resource flow assessment index Rw, the stronger the water resource mobility, and the water resource flow in the ecosystem is not hindered by urban expansion. A low value indicates that the water resource mobility is limited, which may lead to water shortage or water cycle problems in the ecosystem.

[0101] S32. Based on the obtained biological habitat assessment index Rh, ecological connectivity assessment index Rc and water resource flow assessment index Rw, a comprehensive weighted processing analysis is performed to obtain a comprehensive risk assessment index ZR, which comprehensively reflects the overall impact of urban expansion on the ecological environment;

[0102] The comprehensive risk assessment index ZR is obtained through the following calculation formula:

[0103] ZR=z1*Rh+z2*Rc+z3*Rw;

[0104] Wherein, z1, z2 and z3 represent the preset weight values ​​of the biological habitat assessment index Rh, the ecological connectivity assessment index Rc and the water resource flow assessment index Rw, respectively, and z1+z2+z3=1, and the specific value is set by the user.

[0105] In this embodiment, a more comprehensive ecological risk assessment is provided by calculating and comprehensively analyzing the biological habitat assessment index Rh, the ecological connectivity assessment index Rc and the water resource flow assessment index Rw. By evaluating the loss and fragmentation of biological habitats, the specific impact of urban expansion on the habitats in ecologically sensitive areas (x, y) can be accurately identified, and the overall impact of urban expansion on the ecological environment can be fully reflected. Potential ecological and environmental risks can be identified in a timely manner in the urbanization process, especially in terms of multi-dimensional and systematic environmental impacts. In-depth quantitative analysis is provided. Not only can the ecological risks of urban expansion be predicted, but also an operational decision-making basis can be provided for the formulation of urban planning, and the coordinated development of urban planning and ecological protection can be promoted. Compared with the traditional single-dimensional assessment, this method can more accurately grasp the comprehensive ecological risks brought about by urban expansion through the comprehensive analysis of multiple indicators, ensuring that while promoting urban development, the sustainability of the ecological environment is protected to the maximum extent.

[0106] Example 4

[0107] This embodiment is explained in Example 3, please refer to Figure 1 , specifically: S4 includes S41;

[0108] S41. By comparing the preset risk assessment threshold Zth with the comprehensive risk assessment index ZR, the risk status of the ecologically sensitive area (x, y) is determined, and the risk assessment result of the urban expansion area is obtained;

[0109] The risk assessment results of urban expansion areas are obtained through the following comparison methods:

[0110] When the comprehensive risk assessment index ZR ≥ the comprehensive risk assessment index ZR, the ecologically sensitive area (x, y) is determined to be a risk area. The ecologically sensitive area (x, y) will be affected by urban expansion, and the risk assessment result of the urban expansion area is a risk result.

[0111] When the comprehensive risk assessment index ZR<comprehensive risk assessment index ZR, the ecologically sensitive area (x, y) is determined to be a risk-free area. The ecologically sensitive area (x, y) will not be affected by urban expansion, and the risk assessment result of the urban expansion area is a risk-free result.

[0112] S5 includes S51 and S52;

[0113] S51, by using remote sensing satellite images and ground monitoring data, comparing the predicted value Cp of the urban expansion area with the data of the actual urban expansion area, and then calculating and evaluating to obtain the deviation value D, and by comparing it with the preset allowable deviation threshold Dth, obtaining the urban expansion area risk assessment result to continuously verify the result;

[0114] The continuous verification results are obtained by comparing:

[0115] When the deviation value D ≥ the allowable deviation threshold Dth, the continuous verification result is obtained as a deviation result, triggering the adjustment mechanism;

[0116] When the deviation value D is less than the allowable deviation threshold Dth, the continuous verification result is obtained as a deviation-free result, and the adjustment mechanism is not triggered.

[0117] S52. Continuous verification results are used to trigger an iterative optimization adjustment mechanism for the urban expansion area risk assessment results and the comprehensive risk assessment index ZR, including proportionally adjusting the Markov chain model, the automaton model, the comprehensive risk assessment index ZR and the comprehensive risk assessment index ZR according to the deviation value D, wherein the adjustment of the Markov chain model and the automaton model specifically includes adjusting the transfer probability related model calculation parameters.

[0118] In this embodiment, by comparing and analyzing the comprehensive risk assessment index ZR with the preset risk assessment threshold Zth, an accurate risk assessment of the urban expansion area is achieved, and it is effectively determined whether the ecologically sensitive area (x, y) is threatened by urban expansion. When the comprehensive risk assessment index ZR is greater than or equal to the preset threshold, the risk area can be accurately marked, reflecting the possible negative impact of urban expansion on the ecological environment; on the contrary, when the comprehensive risk assessment index ZR is less than the threshold, it indicates that the area is not affected, avoiding unnecessary resource investment. This process provides an accurate basis for decision-making on ecological and environmental protection during urban expansion, ensuring the coordination between environment and development. By using remote sensing satellite images and ground monitoring data to compare and analyze the predicted value Cp of the urban expansion area with the actual urban expansion area, the deviation value D can be obtained, and by comparing with the preset allowable deviation threshold Dth, the accuracy of the model can be further verified. If the deviation value D exceeds the threshold Dth, the adjustment mechanism is triggered, which helps to optimize the calculation parameters of the Markov chain model and the automaton model to ensure that the prediction of urban expansion is more in line with the actual situation. Through this continuous verification and adjustment process, the parameters of the risk assessment model can be dynamically optimized, improving its adaptability and prediction accuracy to the urban expansion process, thereby avoiding potential risks caused by model errors. The introduction of this mechanism significantly improves the reliability and accuracy of risk assessment, ensures the sustainability and accuracy of urban expansion decision-making, and can better adapt to future changes in urban development needs and environmental protection requirements.

[0119] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A land space planning risk assessment method based on multi-dimensional analysis, characterized by: The following steps are involved: S1. Obtain data through multiple channels, including land use data, climate data, ecological environment data and socio-economic data, and then pre-process them to form a collection data group; S2. Simulate urban expansion by collecting data sets, predict the predicted area and trend area information of urban expansion, and mark ecologically sensitive areas (x, y) in combination with ecological and environmental data; S3. Construct a multidimensional risk assessment model based on the marked ecologically sensitive areas (x, y) to assess the ecological and environmental impact information generated by urban expansion, including the biological habitat assessment index Rh, the ecological connectivity assessment index Rc and the water resource flow assessment index Rw, and conduct a comprehensive analysis to obtain the comprehensive risk assessment index ZR; S4. Obtain the risk assessment result of the urban expansion area by comparing the preset risk assessment threshold Zth with the comprehensive risk assessment index ZR; S5. Conduct continuous verification and evaluation based on the risk assessment results of urban expansion areas, including iterative optimization of the risk assessment results of urban expansion areas and the comprehensive risk assessment index ZR.

2. The method for risk assessment of national land space planning based on multi-dimensional analysis according to claim 1 is characterized by: Said S1 includes S11 and S12; S11. Obtain data through multiple channels, including land use data, climate data, ecological environment data, and socio-economic data; Among them, different types of land are classified based on satellite images obtained by remote sensing satellites through a land classification algorithm, and the land classification algorithm includes a support vector machine and a random forest algorithm. The different types of land include area data of farmland, urban land and non-cultivated land; Climate data: The climate data of the region is obtained through weather station data and MODIS climate data sets, including temperature, precipitation and wind speed climate data, to obtain predicted climate change data, including future climate forecast data provided by WorldClim, including future trend data on temperature and precipitation; Ecological and environmental data: By obtaining species distribution and habitat data from the Global Biodiversity Information Facility (GBIF), we can obtain ecological protection area distribution data, including ecological protection area area data published by IUCN. Socioeconomic data related to population density, economic development level and urbanization process are obtained through public data from the National Bureau of Statistics and local governments to obtain urban planning information, including planning data on urban expansion area and infrastructure construction.

3. The method for risk assessment of national land space planning based on multi-dimensional analysis according to claim 2 is characterized by: S12, pre-processing the land use data, climate data, ecological environment data and social economic data to form a collection data group; The preprocessing includes unit conversion and normalization preprocessing of land use data to obtain information including farmland area, urban land area and non-cultivated land area; The climate data is subjected to data cleaning, missing value processing and normalization preprocessing to obtain information including temperature, precipitation and wind speed; The ecological environment data is preprocessed by data cleaning and data standardization to obtain information including habitat area and ecological protection area area; The socio-economic data is pre-processed by data cleaning and normalization to obtain information including population density, economic level and urban expansion area.

4. The method for risk assessment of national land space planning based on multi-dimensional analysis according to claim 3 is characterized by: The S2 includes S21 and S22; S21. Simulate urban expansion by collecting data sets, simulate future urban expansion trends by using Markov chain models and automaton models, mark the expected urban expansion areas, output urban expansion area prediction values ​​Cp and urban expansion trend area values ​​Ct, and predict the prediction areas and trend area information of urban expansion.

5. The method for risk assessment of national land space planning based on multi-dimensional analysis according to claim 4 is characterized by: S22. By combining ecological environment data, climate data and the predicted value of urban expansion area Cp, the ecological sensitivity index Se is obtained by substituting them into the established ecological region sensitivity assessment formula for calculation, and ecological sensitivity index Se is obtained to identify and mark ecological sensitive areas (x, y), including ecological protection areas, protected animal and plant habitats and climate vulnerable areas; Among them, the identification of the ecologically sensitive area (x, y) is performed by comparing and judging the ecological sensitivity index Se with the preset ecologically sensitive area assessment threshold Sth, and obtaining the identification result of the area (x, y). When the ecological sensitivity index Se≥the ecologically sensitive area assessment threshold Sth, the identification result of the area (x, y) is obtained as a sensitive result, and the area (x, y) is marked as an ecologically sensitive area.

6. The method for risk assessment of national land space planning based on multi-dimensional analysis according to claim 5 is characterized by: The S3 includes S31 and S32; S31. Construct a multi-dimensional risk assessment model based on the marked ecologically sensitive areas (x, y) to assess the ecological and environmental impact information generated by urban expansion, including the biological habitat assessment index Rh, the ecological connectivity assessment index Rc and the water resource flow assessment index Rw; The biological habitat assessment index Rh is used to assess the impact of urban expansion on biological habitats in ecologically sensitive areas (x, y), reflecting the loss, fragmentation and degradation of habitats. Specifically, the risk of habitat damage is quantified by comparing the original habitat area with the expanded habitat area and the degree of habitat fragmentation, wherein the degree of habitat fragmentation is obtained by statistically calculating the proportion of the number of habitat divisions. The ecological connectivity assessment index Rc is used to evaluate the impact of urban expansion on the connectivity between various areas in the ecosystem, measure the interconnection and permeability between ecologically sensitive areas (x, y), and affect the migration and exchange of ecological species; The water resource flow assessment index Rw is used to measure the impact of urban expansion on water resource flow. The water resource mobility in the ecologically sensitive area (x, y) is obtained by analyzing the direction of water flow, flow rate changes and water source coverage.

7. The method for risk assessment of national land space planning based on multi-dimensional analysis according to claim 6 is characterized by: S32. Based on the obtained biological habitat assessment index Rh, ecological connectivity assessment index Rc and water resource flow assessment index Rw, a comprehensive weighted processing analysis is carried out to obtain the comprehensive risk assessment index ZR, which comprehensively reflects the overall impact of urban expansion on the ecological environment.

8. The method for risk assessment of national land space planning based on multi-dimensional analysis according to claim 7 is characterized by: The S4 includes S41; S41. By comparing the preset risk assessment threshold Zth with the comprehensive risk assessment index ZR, the risk status of the ecologically sensitive area (x, y) is determined, and the risk assessment result of the urban expansion area is obtained; The risk assessment results of the urban expansion area are obtained by the following comparison method: When the comprehensive risk assessment index ZR ≥ the comprehensive risk assessment index ZR, the ecologically sensitive area (x, y) is determined to be a risk area. The ecologically sensitive area (x, y) will be affected by urban expansion, and the risk assessment result of the urban expansion area is a risk result. When the comprehensive risk assessment index ZR<comprehensive risk assessment index ZR, the ecologically sensitive area (x, y) is determined to be a risk-free area. The ecologically sensitive area (x, y) will not be affected by urban expansion, and the risk assessment result of the urban expansion area is a risk-free result.

9. The method for risk assessment of national land space planning based on multi-dimensional analysis according to claim 1 is characterized by: The S5 includes S51 and S52; S51, by using remote sensing satellite images and ground monitoring data, comparing the predicted value Cp of the urban expansion area with the data of the actual urban expansion area, and then calculating and evaluating to obtain the deviation value D, and by comparing it with the preset allowable deviation threshold Dth, obtaining the urban expansion area risk assessment result to continuously verify the result; The continuous verification results are obtained by the following comparison method: When the deviation value D ≥ the allowable deviation threshold Dth, the continuous verification result is obtained as a deviation result, triggering the adjustment mechanism; When the deviation value D is less than the allowable deviation threshold Dth, the continuous verification result is obtained as a deviation-free result, and the adjustment mechanism is not triggered.

10. The method for risk assessment of national land space planning based on multi-dimensional analysis according to claim 9 is characterized in that: S52. Continuous verification results are used to trigger an iterative optimization adjustment mechanism for the urban expansion area risk assessment results and the comprehensive risk assessment index ZR, including proportionally adjusting the Markov chain model, the automaton model, the comprehensive risk assessment index ZR and the comprehensive risk assessment index ZR according to the deviation value D.

Images