Intelligent evaluation method and system for green space supplement cost based on vacancy probability

Abstract

The application discloses a green space supplement cost intelligent evaluation method and system based on vacancy probability, and relates to the technical fields of urban and rural planning, landscape architecture and artificial intelligence. The application comprises the following steps: receiving a remote sensing image of a target area unit land, identifying city vacancy land and low-efficiency construction land based on the remote sensing image, and collecting the city vacancy land and the low-efficiency construction land to obtain an overall vacancy land identification result. The application can identify two types of vacancy land, i.e., city outdoor vacant land and low-efficiency construction land, by comprehensively using remote sensing images and multi-source data, the identification range of the vacancy land is more comprehensive, the vacancy probability can be predicted by using a random forest regression algorithm, the dynamic prediction of the vacancy state of the land can be realized, the green space supplement priority is determined based on the vacancy probability and the supplement cost, and the feasibility of a green space supplement scheme is improved based on the green supplement cost evaluation.

Description

TECHNICAL FIELD

[0001] The present application relates to the fields of urban and rural planning, landscape architecture and artificial intelligence, in particular to a green space supplement cost intelligent evaluation method and system based on vacancy probability. BACKGROUND

[0002] In recent years, urban shrinkage has spread in China and will become the norm of urban development in the future. In this process, urban vacant land has increased and caused multiple problems in ecological environment and social economy. Green space has been proven to be one of the effective means to solve the problems brought by urban vacant land, and has multiple roles in improving the level of ecosystem services, alleviating social problems, and driving economic development.

[0003] The existing patent (publication number: CN116310786A) discloses a street-side micro-green space supplement potential identification and / or implementation method based on deep learning. For street-side micro-green space supplement, based on street view images, the spatial conditions, demand conditions, facility conditions, and perception conditions of potential supplement points are evaluated, and the supplement potential evaluation results of street-side micro-green space are obtained by comprehensively evaluating the results of multiple aspects. However, the evaluation method based on spatial conditions, demand conditions, facility conditions, and perception conditions using street view images, although to some extent reflects the construction feasibility of the site, is limited by the coverage of street view images and cannot evaluate the green space supplement conditions of areas lacking street view coverage. Moreover, it only focuses on the pattern optimization before and after green space supplement and cannot reflect the cost feasibility of green space supplement. Therefore, we propose a green space supplement cost intelligent evaluation method and system based on vacancy probability. SUMMARY

[0004] The purpose of the present application is to provide a green space supplement cost intelligent evaluation method and system based on vacancy probability, which can predict the future land vacancy probability based on historical and current vacant land conditions, evaluate the green space supplement potential by combining green space supplement cost, and provide an optimization direction for subsequent green space supplement. The optimization scheme proposed fully considers the development background of urban shrinkage, and the optimization direction is highly targeted.

[0005] According to the first aspect of the present application, in order to achieve the above-mentioned purpose, the present application provides the following technical scheme: a green space supplement cost intelligent evaluation method based on vacancy probability, comprising the following steps:

[0006] Receiving remote sensing images of target area unit land, identifying urban vacant land and low-efficiency construction land based on remote sensing images, and obtaining overall vacant land identification results by summarizing urban vacant land and low-efficiency construction land;

[0007] According to the overall vacant land identification results, the driving factors are calculated by using a random forest regression algorithm (x) a relationship model between the expansion of vacant land, driving factor values Input the final constructed relationship model to obtain the probability of non-vacant land being converted into vacant land;

[0008] Calculate the green space supplement cost of the target regional unit land, wherein the green space supplement cost includes land acquisition cost, land remediation cost, and green space construction optimization cost;

[0009] According to the probability of being converted into vacant land and the green space supplement cost, calculate the unit supplement potential, determine the green space supplement priority of the unit land according to the calculation result, and according to the priority from high to low, sequentially convert the unit land into green space, determine the form of the converted green space according to the type of the unit land, calculate the supplement cost of the green space supplement scheme, if the supplement cost is lower than the supplement budget, the scheme is included in the selected supplement scheme, otherwise the supplement scheme is modified until the supplement scheme meets the supplement budget requirement.

[0010] Further, the remote sensing image is from Google Maps, Tianditu, or high-resolution optical remote sensing satellite, and the screening standard of the remote sensing image is that the cloud cover is less than 10% and the spatial resolution is not less than 2.5 m.

[0011] Further, based on the remote sensing image, the urban vacant land and the low-efficiency construction land are identified, and the urban vacant land and the low-efficiency construction land are summarized to obtain the overall vacant land identification result, which is as follows:

[0012] (31) Urban vacant land identification based on remote sensing image, specifically including:

[0013] (31.1) According to the definition of urban vacant land and the actual situation of the research site, a land type system is constructed:

[0014] The urban vacant land is divided into n types, according to the definition of land type, using ArcGISpro classification tool to frame the training sample, based on the sample to automatically classify, using precision evaluation tool to evaluate the classification precision;

[0015] The land type system includes subdivided bare land, natural grassland, artificial grassland, natural shrub, forest land, construction area, residential land, commercial land, industrial land, hard square, and water body;

[0016] (31.2) Using ArcGISpro image classification tool, the number of samples is 50 per type, and each sample is uniformly distributed in the target region, selecting support vector machine as the classifier, selecting the sample as the training sample, identifying the land type of the remote sensing image, and using the precision evaluation tool to evaluate the identification result;

[0017] (31.3) Input the study unit, which is the smallest grid unit for green space addition. The grid size is 10m-20m. Use the majority resampling method to resample the land use data to the grid size.

[0018] (32) Identification of inefficient construction land based on multi-source data:

[0019] (32.1) Based on the land use data of the research units identified in (31), the construction land type units are extracted and an evaluation system for the inefficiency of each construction land type is constructed, including:

[0020] (32.11) Extract construction land type units, including residential land units, commercial and office land units, and industrial land units;

[0021] (32.12) Establish an evaluation system for inefficiency of various types of construction land:

[0022] For each type of construction land, set n evaluation indicators (X1, X2, ...X n ), for this type of land unit, the unit's low efficiency is the unit's evaluation index value (x1, x2, ...x n ), the specific expression is as follows:

[0023]

[0024] In the formula, C represents the low efficiency of the construction land type unit, and n represents the number of evaluation indicators;

[0025] (32.2) After completing the low efficiency assessment of each construction land type unit, the low efficiency is normalized and a certain proportion of land is selected as low-efficiency construction land;

[0026] (33) Summary of vacant land identification results:

[0027] The urban vacant land identified in (31) and the inefficient construction land identified in (32) are aggregated, and the distribution locations of urban vacant land and inefficient construction land are obtained respectively.

[0028] Furthermore, in step (32), the evaluation indicators of the residential land unit include road intersection density, service facility density, and night light index; the evaluation indicators of the commercial land unit include popularity index and commercial facility density; and the evaluation indicators of the industrial land unit include building density and GDP.

[0029] Furthermore, based on the overall vacant land identification results, the random forest regression algorithm was used to calculate the driving factors The relationship model between the expansion of vacant land and the driving factor value The probability of non-empty land use transforming into empty land use in the final constructed relationship model is obtained, and the specific process is as follows:

[0030] (51) Superimpose the urban empty land distribution position and the low-efficiency construction land distribution position obtained in (33) to obtain the area of empty land expansion. A relationship model between the driving factors and the empty land expansion is constructed by using a random forest regression algorithm, and the specific process is as follows:

[0031] (51.1) For the research unit i, the research unit of the expanded empty land is assigned a value of 1, and the remaining research units are assigned a value of 0. Whether to expand is taken as the dependent variable, and all driving factors are normalized. The normalized driving factors are taken as the independent variables;

[0032] (51.2) The independent variables and dependent variables of all research units in the target area are collected to form a training sample set. The training sample set is divided into a training set and a test set. The random forest regression algorithm is trained with the training set, and the training result is evaluated with the test set;

[0033] (51.3) In the training process, the performance of the random forest regression algorithm is adjusted by adjusting the number of decision trees, the maximum depth of the decision tree, the minimum number of samples for node splitting, the minimum number of samples for leaf nodes, and the number of features for node splitting;

[0034] The basic formula of the random forest regression algorithm is:

[0035]

[0036] Where X = {X1, X2, … X n} is a feature vector containing n driving factors, M is the number of decision trees, T m (X) is the predicted value of the mth decision tree for the input feature vector X. Each decision tree T m (X)

[0037] According to its tree structure and splitting rule, the input features are processed to finally give a predicted value;

[0038] (51.4) After each round of training, the test set is used for evaluation. The explanatory power of the constructed regression model is evaluated by mean square error, mean absolute error, and R-square index. All models with R-square greater than a threshold value are output, and the model with the smallest mean square error and mean absolute error is selected as the final constructed relationship model;

[0039] The calculation method of the mean square error is:

[0040]

[0041] Where y i is the actual value of the test set, is the value calculated based on the random forest regression model, and n is the number of samples in the test set;

[0042] The calculation method of the root mean square error (RMSE) is:

[0043]

[0044] where y i is the actual value of the test set, is the value calculated based on the random forest regression model, and n is the number of samples in the test set;

[0045] The calculation method of the R-square is:

[0046]

[0047] where y i is the actual value of the test set, is the value calculated based on the random forest regression model, and n is the number of samples in the test set;

[0048] (52) Vacancy probability calculation:

[0049] For each non-vacant land research unit, input all the driving factor values X into the finally constructed relationship model, which is the probability Pi of the research unit transferring to vacant land:

[0050] The formula of the relationship model is:

[0051] where X = {X1, X2, … X n} is a feature vector containing n driving factors, M is the number of decision trees in the finally determined relationship model, T m (X) is the predicted value of the mth decision tree for the input feature vector X;

[0052] For the research unit whose current status is vacant land, the probability of transferring to vacant land in the future is 1.

[0053] Further, the green land supplement cost of the target regional unit land is calculated, which is as follows:

[0054] C = C1 + C2 + C3

[0055] where C represents the green land supplement cost, C1 represents the land acquisition cost, C2 represents the land remediation cost, and C3 represents the green land construction optimization cost.

[0056] Further, according to the probability of conversion into vacant land and the green space supplement cost, the unit supplement potential is calculated, the unit land green space supplement priority is determined according to the calculation result, the green space supplement scheme is formulated according to the priority, the green space supplement scheme is supplemented, and the supplement cost is calculated, which is specifically as follows:

[0057] (71) Unit supplement potential evaluation:

[0058] The cost is normalized to obtain the final comprehensive cost C i The normalization formula is:

[0059]

[0060] In the formula, C i is the unit green space supplement cost, C min is the minimum value of the green space supplement cost in all units, C max is the maximum value of the green space supplement cost in all units, and C i is the normalized comprehensive cost.

[0061] The unit supplement potential calculation formula is:

[0062] T i = P i *(1-C i ')

[0063] (72) Unit supplement priority

[0064] According to the unit supplement potential calculation result T, the priority is formulated, the unit green space supplement priority is higher for the unit with higher unit supplement potential, and the priority is divided into 5 levels, from low to high, which are:

[0065] very low [0, 0.2), low [0.2, 0.4), medium [0.4, 0.6), high [0.6, 0.8), and very high [0.8, 1.0].

[0066] (73) Green space supplement scheme verification

[0067] According to the unit green space supplement priority, the green space supplement scheme is formulated, according to the priority from high to low, the unit is converted into green space in turn, according to the unit surrounding land type, the converted green space form is determined, after completing the green space supplement scheme formulation each time, the green space supplement cost required by the scheme is calculated, and compared with the supplement budget, if it is lower than the supplement budget requirement, the scheme is included in the selected supplement scheme, otherwise the supplement scheme is modified, until the scheme meets the supplement budget requirement.

[0068] According to a second aspect of the present application, the present application provides a green space supplement cost intelligent evaluation system based on vacancy probability, which is used to implement the green space supplement cost intelligent evaluation method based on vacancy probability.

[0069] The vacancy land identification module is configured to receive a remote sensing image of the target regional unit land, identify urban vacancy land and low-efficiency construction land based on the remote sensing image, and obtain an overall vacancy land identification result by summarizing the urban vacancy land and the low-efficiency construction land.

[0070] The vacancy probability prediction module is configured to calculate driving factor values between the urban vacancy land and the low-efficiency construction land and between the urban vacancy land and the low-efficiency construction land expansion based on the overall vacancy land identification result by using a random forest regression algorithm. The relationship model between the driving factor values and the vacancy land expansion is input into the finally constructed relationship model to obtain a probability of the non-vacancy land being converted into the vacancy land. The supplement cost calculation module is configured to calculate a green land supplement cost of the target regional unit land, wherein the green land supplement cost includes a land acquisition cost, a land remediation cost, and a green land construction optimization cost.

[0071] The supplement scheme derivation and verification module is configured to calculate a unit supplement potential based on the probability of being converted into the vacancy land and the green land supplement cost, determine a unit land green space supplement priority based on the calculation result, convert the unit land into the green space in sequence from high to low according to the priority, determine a converted green space form according to a unit land type, calculate a supplement cost of the green space supplement scheme, and if the supplement cost is lower than a supplement budget, the scheme is included in a selected supplement scheme, otherwise, the supplement scheme is modified until the supplement scheme meets the supplement budget requirement.

[0072] According to a third aspect of the present application, the present application provides a terminal device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the memory stores a computer program capable of running on the processor, and when the processor loads and executes the computer program, the green space supplement cost intelligent evaluation method based on vacancy probability is adopted.

[0073] According to a fourth aspect of the present application, the present application provides a storage medium containing computer executable instructions, which are used to execute the green space supplement cost intelligent evaluation method based on vacancy probability when executed by a computer processor.

[0074] The present application at least has the following beneficial effects:

[0075]

[0076] ​1.The present application can identify two types of vacant land, including urban outdoor space and inefficient construction land, by using remote sensing images and multi-source data comprehensively. The identified vacant land includes completely vacant land without development purposes, abandoned and vacant land from construction development purposes, and land that has been developed but is not fully utilized. The identification of vacant land is more comprehensive.

[0077] 2.Compared with previous solutions that only consider the current land use situation, the present application uses a random forest regression algorithm to predict the vacancy probability, which can analyze the land vacancy mechanism and further calculate the vacancy probability of the land, thereby realizing dynamic prediction of the vacancy state of the land.

[0078] 3.The present application determines the priority of green space supplementation based on vacancy probability and supplementary cost, and improves the feasibility of the green space supplementation scheme based on green supplementary cost evaluation. Compared with the prior art which only considers the benefits after green land construction, the construction feasibility is fully considered.

[0079] Of course, any product implementing the present application does not necessarily need to achieve all the advantages described above. BRIEF DESCRIPTION OF DRAWINGS

[0080] Figure 1 The flowchart of the method described in the embodiments of the present application is shown.

[0081] Figure 2 The frame principle diagram of the structure of the method described in the embodiments of the present application is shown. DETAILED DESCRIPTION

[0082] The technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all. Based on the embodiments in the present disclosure, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present disclosure.

[0083] Embodiment one:

[0084] Please refer to Figure 1 and Figure 2 The present application provides a technical solution: intelligent evaluation method of green space supplementation cost based on vacancy probability, including the following steps:

[0085] S1: vacant land identification

[0086] Vacant land identification includes S11 urban vacant land identification based on remote sensing images, S12 inefficient construction land identification based on multi-source data, and S13 vacant land distribution summary.

[0087] S11: Urban vacant land identification based on remote sensing images, specifically including:

[0088] (S11.1) Collect remote sensing images of the study area that meet the study period and accuracy requirements:

[0089] Obtain high-resolution remote sensing images within the study area (target area). Remote sensing images can come from free high-resolution data such as Google Maps, Esri World Image, and Tianditu, or paid high-resolution data such as Gaofen, GeoEye, Quickbird, and Ikonos.

[0090] Data screening requirements include cloud cover less than 10%, spatial resolution not less than 2.5m. For the technical solution of this example, 17-level Google Maps remote sensing images with a spatial resolution of 2.15m are selected,

[0091] Download remote sensing images of the study area for 2023 and 2017;

[0092] (S11.2) According to the definition of urban vacant land (urban vacant land) and the actual situation of the research site, construct a land use type system:

[0093] According to the definition of urban vacant land and the actual situation of the research site, urban land is divided into n types. According to the definition of land use type, use the ArcGISpro classification tool to frame the training sample, and based on the sample, perform automatic classification, and use the precision evaluation tool to evaluate the classification accuracy.

[0094] It needs to be further explained that in this example, the land use type system is subdivided into bare land, natural grassland, artificial grassland, natural shrub, forest land, construction area, residential land, commercial land, industrial land, hard square, water body, etc. 14 types; According to the definition of urban vacant land, it is the land within the city that is completely vacant and has no development purpose, as well as the land that is abandoned, vacant or not fully utilized from construction purposes; Among them, bare land, natural grassland, artificial grassland, natural shrub, forest land, and construction area all belong to the type of urban vacant land, and residential land, commercial land, and industrial land belong to the type of construction land.

[0095] (S11.3) using the ArcGISpro image classification tool, the number of samples is 50 per type, and each sample is uniformly distributed in the target area, selecting support vector machine (Support Vector Machine) as the classifier, selecting the delineated sample as the training sample, identifying the land use type of the remote sensing image to be identified, and using the precision evaluation tool to evaluate the identification result, in this example, the output model accuracy is more than 80% land use type identification result, the identification accuracy is consistent with the spatial resolution of the input image;

[0096] It should be noted that the support vector machine is a tab in the ArcGISpro image classification tool, which can be directly called;

[0097] (S11.4) input the research unit, which is the smallest grid unit for subsequent green space supplement, the grid size is determined according to the research needs, preferably 10m-20m, the land use data is resampled to the grid size using the mode resampling method, in this embodiment, the land use data is resampled to 10m using the mode resampling method;

[0098] S12: identification of low-efficiency construction land based on multi-source data, specifically including:

[0099] (S12.1) based on the land use data of the research unit identified in S11, extracting the construction land type unit, and constructing a low-efficiency condition evaluation system for each construction land type:

[0100] Extracting the construction land type unit, in this example, including residential land, commercial land, and industrial land unit;

[0101] Constructing a low-efficiency condition evaluation system for each construction land type, for each type of construction land, according to the existing research, n evaluation indexes (X1, X2, … Xn) are set, for this type of land, the low-efficiency degree of the unit is the equal-weighted superposition of the evaluation index values (x1, x2, … xn) of the unit, the expression is as follows: n n

[0102]

[0103] In the formula, C represents the low-efficiency degree of the construction land type unit, and n represents the number of evaluation indexes;

[0104] ​​It needs to be further explained that in the present example, the evaluation index of residential land includes road intersection density, service facility density, and night light index, wherein the road intersection data comes from OSM road network, the intersection of the road network is extracted by ArcGIS, the service facility density comes from Gaode map, and the POIs of "catering service, shopping service, life service, sports and leisure service, and medical care service" are screened out, and the night light index comes from NPP / VIIRS data; the evaluation index of commercial land includes popularity index and commercial facility density, wherein the popularity index comes from Baidu heat map, and the commercial facility density data comes from Gaode map; the evaluation index of industrial land includes building density and GDP, wherein the building density comes from remote sensing satellite image, and the GDP data comes from resource and environment science data platform;

[0105] (S12.2) After completing the low efficiency evaluation of the construction land type unit, the low efficiency is normalized respectively, and a certain proportion of land is selected as low-efficiency construction land. In the present example, according to the actual situation, the units whose low-efficiency evaluation is located in the last 10% of each type are selected as low-efficiency construction land;

[0106] S13: Summary of vacant land identification results

[0107] The urban vacant land identified in S11 and the low-efficiency construction land in S12 are included in the urban vacant land unit, and the distribution positions of the vacant land in two periods are obtained respectively;

[0108] S2: Vacant probability prediction, according to the overall vacant land identification result, the driving factor value is calculated by using the random forest regression algorithm between the relationship model of vacant land expansion, the driving factor value is input into the finally constructed relationship model, the probability of non-vacant land transforming into vacant land is obtained, which specifically includes S21 exploration of change mechanism and S22 vacant probability measurement, as follows:

[0109] S21: Change mechanism exploration

[0110] The distribution positions of the vacant land in two periods obtained in S13 are superimposed to obtain the area of vacant land expansion, and the relationship between the driving factors and the vacant land expansion is constructed by using the regression algorithm, as follows:

[0111] For the research unit i, the research unit of the expanded vacant land is assigned a value of 1, and the remaining research units are assigned a value of 0. Whether to expand is taken as the dependent variable, all driving factors are normalized, and the normalized driving factors are taken as the independent variables;

[0112] The independent variables and dependent variables of all the research units in the research area are aggregated to form a training sample set, the training sample set is randomly divided into a training set and a test set according to a certain proportion, the random forest regression algorithm is trained with the training set, and the training result is evaluated with the test set;

[0113] In the training process, the performance of the random forest regression algorithm is adjusted by adjusting the number of decision trees (n_estimators), the maximum depth of the decision tree (max_depth), the minimum number of samples for node splitting (min_samples_split), the minimum number of samples for leaf node (min_samples_leaf), and the number of features for node splitting (max_features);

[0114] The basic formula of the random forest regression algorithm is:

[0115]

[0116] Where X = {X1, X2, … X n} is a feature vector containing n driving factors, M is the number of decision trees, T m (X) is the prediction value of the mth decision tree for the input feature vector X, each decision tree T m (X) processes the input features according to its own tree structure and splitting rules and finally gives a prediction value. In the actual training process, the RandomForestRegressor function of the Python scikitlearn library is directly called for calculation;

[0117] After each round of training, the test set is used for evaluation, the Mean Squared Error (MSE), Mean Absolute Error (MAE), R-squared (R2) and other indicators are used to evaluate the explanatory power of the constructed regression model, all models with R-squared greater than a certain threshold are output, and the model with the smallest mean squared error and mean absolute error is selected as the final constructed relationship model; the calculation method of mean squared error is:

[0118]

[0119] Where y i is the actual value of the test set, is the value calculated based on the random forest regression model, and n is the number of test set samples;

[0120] In the actual training process, the mean squared error is directly calculated by calling the mean_squared_error function of the Python scikitlearn library;

[0121] The calculation method of the mean absolute error (RMSE) is:

[0122]

[0123] where y i is the actual value of the test set, is the value calculated based on the random forest regression model, and n is the number of samples in the test set;

[0124] The calculation method of R-square is:

[0125]

[0126] where y i is the actual value of the test set, is the value calculated based on the random forest regression model, and n is the number of samples in the test set;

[0127] In this example, the ArcGIS "Erase" tool is used to output the location of the vacant land expansion;

[0128] Further, in this example, referring to the related research on the change evolution mechanism of construction land in shrinking cities, the slope (x1), water sensitivity (x2), distance from the city center (x3), commercial facility density (x4), traffic facility density (x5), house price (x6), population density (x7), and hard surface ratio (x8) are selected as driving factors;

[0129] In this example, the R-square is greater than the threshold value of 0.7;

[0130] It should be further noted that the regression algorithm used can be a random forest regression algorithm, a Markov transition matrix algorithm, or an artificial neural network algorithm. However, the artificial neural network algorithm has a long training time and is prone to overfitting, which is not suitable for limited data conditions and is difficult to explain the influence of different factors on the vacancy probability. The Markov transition matrix algorithm is based on the transition probability of different land use types converting to vacant land in the previous period to predict the conversion in the next period. This prediction method ignores the influence of factors other than land use on land vacancy, so the random forest regression algorithm is used in this example to predict the future state of land vacancy.

[0131] S22: Vacancy probability estimation

[0132] For each non-vacant land research unit, input all driving factor values X into the finally constructed relationship model, which is the probability Pi of the research unit converting to vacant land:

[0133] The formula of the relationship model is:

[0134] where X = {X1, X2, … Xn} is the feature vector containing n driving factors, M is the number of decision trees in the final determined relational model, T n m (X) is the prediction value of the mth decision tree for the input feature vector X;

[0135] The driving factor values The probability of non-vacant land turning into vacant land is obtained by inputting the final constructed relational model into the vacant land probability, and in actual operation, the trained rf model is calculated by calling the predict method of Python Pi = rf.predict(X);

[0136] For the research unit with vacant land as the present situation, the probability of transferring to vacant land in the future is 1;

[0137] S3: Supplementary cost evaluation

[0138] According to the green space construction life cycle theory, the green space supplement cost (C) is calculated. The green space supplement cost (C) includes land acquisition cost (C1), land remediation cost (C2), and green space construction optimization cost (C3), as follows:

[0139] C = C1 + C2 + C3

[0140] Further, according to the regional situation and the relevant land development and consolidation project budget standard, the land acquisition cost (C1) and the land remediation cost (C2) are determined for the present situation of S1, and the green space construction optimization cost (C3) is determined for the pre-supplemented green space type;

[0141] S4: Supplementary scheme derivation, including S41 unit supplement potential evaluation, S42 unit supplement priority establishment, and S43 supplementary scheme comparison and selection;

[0142] S41 Unit supplement potential evaluation

[0143] The unit supplement potential (T) comprehensively considers the vacancy probability (P) of S2 and the supplementary comprehensive cost (C) calculated by S3. Previous studies have shown that the higher the vacancy probability and the lower the supplementary cost, the higher the feasibility of green space supplement. To unify the statistical dimension, the costs of various types are normalized to obtain the final comprehensive cost C', and the normalization formula is:

[0144]

[0145] where C i is the unit green space supplement cost, C min is the minimum value of the green space supplement cost in all units, and C​max The maximum value of the cost of adding green space to all units, C i The normalized comprehensive cost;

[0146] The unit addition potential calculation formula is:

[0147] T i = P i *(1-C i ')

[0148] S42 Unit Addition Priority Setting

[0149] According to the evaluation result of unit addition potential (T), the higher the unit addition potential, the higher the priority of green space addition in the unit;

[0150] In this example, according to the unit addition potential (T), the green space addition priority is divided into 5 levels with an interval of 0.2, from low to high: very low [0, 0.2), low [0.2, 0.4), medium [0.4, 0.6), high [0.6, 0.8), and very high [0.8, 1.0];

[0151] S43 Green Space Addition Scheme Verification

[0152] According to the unit green space addition priority, a green space addition scheme is developed, according to the priority from high to low, the units are converted into green space in turn, and according to the unit surrounding land type, the converted green space form is determined. After completing the green space addition scheme each time, the addition cost required by the scheme is calculated according to S3, and compared with the addition budget. If it is lower than the addition budget requirement, the scheme is included in the alternative addition scheme, otherwise the addition scheme is modified until the scheme meets the addition budget requirement.

[0153] It should be noted that the technical scheme of the embodiment can also realize cost evaluation of vacant land conversion to other land types by modifying the S3 addition cost evaluation item. For example, by calculating the cost of building a new commercial facility, the addition cost evaluation of commercial facilities can be realized.

[0154] In summary, by comprehensively using remote sensing images and multi-source data, the vacant land types including urban outdoor open space and low-efficiency construction land can be identified, the identified vacant land includes completely vacant land without development purpose, abandoned and vacant land from construction development purpose, and land which has been developed but not fully utilized, the identification range of the vacant land is more comprehensive, compared with the previous solution which only considers the current land use situation, the random forest regression algorithm is used to predict the vacancy probability, the land vacancy mechanism can be analyzed, and the vacancy probability of the land is calculated, the dynamic prediction of the vacancy state of the land is realized, the green space supplement priority is determined based on the vacancy probability and the supplement cost, and the feasibility of the green space supplement scheme is improved based on the green supplement cost evaluation, compared with the existing technology which only considers the benefit after the green land construction, the construction feasibility is fully considered.

[0155] Embodiment two:

[0156] The embodiment provides a green space supplement cost intelligent evaluation system based on vacancy probability, which is used for realizing the green space supplement cost intelligent evaluation method based on vacancy probability described in embodiment one, and comprises:

[0157] The vacant land identification module is used for receiving remote sensing images of target regional unit land, identifying urban vacant land and low-efficiency construction land based on the remote sensing images, and obtaining overall vacant land identification results by summarizing the urban vacant land and the low-efficiency construction land.

[0158] The vacancy probability prediction module is used for calculating driving factor values between the relationship model of the relationship between the vacant land expansion and the relationship model, inputting the driving factor values into the finally constructed relationship model, and obtaining the probability that the non-vacant land is converted into vacant land.

[0159] The supplement cost calculation module is used for calculating the green land supplement cost of the target regional unit land, wherein the green land supplement cost comprises land acquisition cost, land reclamation cost and green land construction optimization cost.

[0160] The supplement scheme derivation and verification module is used for calculating the unit supplement potential according to the probability of being converted into vacant land and the green land supplement cost, determining the green space supplement priority of the unit land according to the calculation result, sequentially converting the unit land into green space according to the priority from high to low, determining the form of the converted green space according to the type of the unit land, calculating the supplement cost of the green space supplement scheme, if the supplement cost is lower than the supplement budget, the scheme is included in the selected supplement scheme, otherwise the supplement scheme is modified, until the supplement scheme meets the supplement budget requirement.

[0161] Specifically, the above-mentioned vacant land identification module, vacancy probability prediction module, supplementary cost calculation module and supplementary scheme derivation and verification module can be embedded in a computer processing system. The computer calls the above-mentioned modules to complete the task of evaluating the green space supplementary scheme according to the above-mentioned intelligent evaluation method of green space supplementary cost based on vacancy probability. The above-mentioned vacant land identification module, vacancy probability prediction module, supplementary cost calculation module and supplementary scheme derivation and verification module can perform operations according to the specific steps given by the above-mentioned intelligent evaluation method of green space supplementary cost based on vacancy probability.

[0162] It should be noted that the division of each module of the above system is only a logical functional division. In actual implementation, all or part of the modules can be integrated into one physical entity, or can be physically separated, and the modules can all be implemented in the form of software called by a processing element; all can be implemented in the form of hardware; some modules can be implemented in the form of software called by a processing element, and some modules can be implemented in the form of hardware. For example, the vacant land identification module can be a separately established processing element, or can be integrated into a chip of the above-mentioned device. In addition, the vacant land identification module can also be stored in the memory of the above-mentioned device in the form of program code, and the function of the above-mentioned signal processing module can be called and executed by a processing element of the above-mentioned device. The implementation of other modules is similar. In addition, all or part of the modules can be integrated together, or can be independently implemented. The processing element described herein can be an integrated circuit having signal processing capability. In the implementation process, each step of the above-mentioned method or each of the above-mentioned modules can be completed by the integrated logic circuit of the hardware in the processing element or the instructions in the form of software.

[0163] For example, the above-mentioned modules can be one or more integrated circuits configured to implement the above-mentioned method, such as one or more application specific integrated circuits (ASICs), or one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs), etc. For another example, when a certain module above is implemented in the form of program code called by a processing element, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, the modules can be integrated together to implement in the form of a system on a chip (SOC).

[0164] Embodiment three:

[0165] The application provides a terminal device, including a memory, a processor and a computer program stored in the memory and capable of running on the processor, the memory stores a computer program capable of running on the processor, and when the processor loads and executes the computer program, the above-mentioned intelligent evaluation method for green space supplement cost based on vacancy probability is adopted.

[0166] It should be noted that the terminal device can adopt a computer device such as a desktop computer, a notebook computer or a cloud server, and the terminal device includes but is not limited to a processor and a memory, for example, the terminal device can also include an input / output device, a network access device and a bus, etc.

[0167] Further, the processor can adopt a central processing unit (CPU), of course, according to the actual use condition, other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), ready-to-program gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. can also be adopted, the general-purpose processor can adopt a microprocessor or any conventional processor, etc., and the present application does not make any limitation.

[0168] Embodiment four:

[0169] The application provides a storage medium containing computer executable instructions, which are used for executing the above-mentioned intelligent evaluation method for green space supplement cost based on vacancy probability when executed by a computer processor.

[0170] The computer program can be stored in a computer readable medium, the computer program includes computer program code, the computer program code can be in the form of source code, object code, executable file or some middleware form, etc., the computer readable medium includes any entity or device, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier wave signal, telecommunication signal and software distribution medium, etc. capable of carrying the computer program code, and it should be noted that the computer readable medium includes but is not limited to the above components.

[0171] It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting; it is not intended that the scope of the application be limited to the detailed description contained herein or the specific examples given herein, but rather that the scope of the application be determined by the appended claims, and their equivalents.

[0172] Those skilled in the art will appreciate that the above described terms are to be construed in accordance with their ordinary meaning in the present invention. When an element is referred to as being "connected", "coupled", "fixed", or "attached" to another element, it can be directly connected, coupled, fixed, or attached to the other element, or intervening elements can be present. When an element is referred to as being "connected" to another element, it can be directly connected to the other element, or intervening elements can be present. The terms "vertical", "horizontal", "upper", "lower", "left", "right", and similar terms as used herein are for descriptive purposes only and not meant to be limiting.

[0173] While embodiments of the application have been shown and described, it is to be understood that various modifications, substitutions, combinations, and variations can be made therein and by those skilled in the art without departing from the spirit and scope of the present application, which is defined by the following claims and their equivalents.

[0174] In the description of the specification, reference can be made to terms such as "one embodiment", "an example", "a specific example", etc. which indicates that the particular feature, structure, material, or characteristic following the phrase is included in at least one embodiment or example of the present disclosure. The illustrative examples described herein should not be construed as being exhaustive, limiting, or restrictive. Rather, these examples are intended to be illustrative only, and the scope of the present disclosure is defined by the appended claims and their equivalents.

Claims

1. An intelligent evaluation method for green space supplementary cost based on vacancy probability, characterized by: The following steps are involved: Receive remote sensing images of unit land in the target area, obtain urban vacant land and inefficient construction land based on remote sensing image recognition, and summarize urban vacant land and inefficient construction land to obtain the overall vacant land identification result; Based on the overall vacant land identification results, the driving factors were calculated using the random forest regression algorithm. The relationship model between the expansion of vacant land and the driving factor value Input the final constructed relationship model to obtain the probability of non-vacant land being converted into vacant land; Calculate the green space supplement cost of the unit land in the target area, where the green space supplement cost includes land acquisition cost, land remediation cost and green space construction optimization cost; The unit supplement potential is calculated based on the probability of conversion to vacant land and the green space supplement cost. The priority of green space supplement for unit land is determined based on the calculation result. Unit land is converted into green space in descending order of priority. The form of converted green space is determined according to the unit land type. The supplement cost of the green space supplement plan is calculated. If the supplement cost is lower than the supplement budget, the plan will be included in the alternative supplement plan. Otherwise, the supplement plan will be modified until the supplement plan meets the supplement budget requirements.

2. The intelligent green space supplement cost assessment method based on vacancy probability according to claim 1 is characterized by: The remote sensing images are from Google Maps, Tiandi Map or Gaofen series optical remote sensing satellites. The screening criteria for remote sensing images are that the cloud cover of the image is less than 10% and the spatial resolution is not less than 2.5m.

3. The intelligent evaluation method for green space supplementary cost based on vacancy probability according to claim 2 is characterized in that: Based on remote sensing image recognition, urban vacant land and inefficient construction land are obtained. The overall vacant land identification results are summarized by summarizing urban vacant land and inefficient construction land, as follows: (31) Identification of urban vacant land based on remote sensing images, specifically including: (31.1) Based on the definition of urban vacant land and the actual conditions of the research site, a land use classification system is constructed: Urban vacant land is divided into n types. Based on the land use type definition, the ArcGIS Pro classification tool is used to select training samples, automatically classify based on the samples, and use the accuracy assessment tool to evaluate the classification accuracy. The land use type system includes one or more of bare land, natural grassland, artificial grassland, natural shrub, woodland, area under construction, residential land, commercial and office land, industrial land, hard square, and water body; (31.2) Use the ArcGIS Pro image classification tool to delineate 50 samples of each type, evenly distributed within the target area. Select a support vector machine as the classifier, select the delineated samples as training samples, identify land use types from remote sensing images, and evaluate the identification results using the accuracy assessment tool. (31.3) Input the study unit, which is the smallest grid unit for green space addition. The grid size is 10m-20m. Use the majority resampling method to resample the land use data to the grid size. (32) Identification of inefficient construction land based on multi-source data: (32.1) Based on the land use data of the research units identified in (31), the construction land type units are extracted and an evaluation system for the inefficiency of each construction land type is constructed, including: (32.11) Extract construction land type units, including residential land units, commercial and office land units, and industrial land units; (32.12) Establish an evaluation system for inefficiency of various types of construction land: For each type of construction land, set n evaluation indicators (X1, X2, ...X n ), for this type of land unit, the unit's low efficiency is the unit's evaluation index value (x1, x2, … x n ), the specific expression is as follows: In the formula, C represents the low efficiency of the construction land type unit, and n represents the number of evaluation indicators; (32.2) After completing the low efficiency assessment of each construction land type unit, the low efficiency is normalized and a certain proportion of land is selected as low-efficiency construction land; (33) Summary of vacant land identification results: The urban vacant land identified in (31) and the inefficient construction land identified in (32) are aggregated, and the distribution locations of urban vacant land and inefficient construction land are obtained respectively.

4. The intelligent evaluation method for green space supplementary cost based on vacancy probability according to claim 3 is characterized in that: In step (32), the evaluation indicators of residential land units include one or more of road intersection density, service facility density, and night light index; the evaluation indicators of commercial land units include popularity index and / or commercial facility density; and the evaluation indicators of industrial land units include building density and / or GDP.

5. The intelligent evaluation method for green space supplementary cost based on vacancy probability according to claim 4 is characterized in that: Based on the overall vacant land identification results, the driving factors were calculated using the random forest regression algorithm. The relationship model between the expansion of vacant land and the driving factor value Input into the final constructed relational model to obtain the probability of non-vacant land being converted into vacant land, as follows: (51) The distribution of urban vacant land and inefficient construction land obtained in (33) are superimposed to obtain the area of ​​vacant land expansion. The relationship model between driving factors and vacant land expansion is constructed using the random forest regression algorithm, as follows: (51.1) For study unit i, the study unit with expanded vacant land is assigned a value of 1, and the rest of the study units are assigned a value of 0. Whether it is expanded is used as the dependent variable, all driving factors are normalized, and the normalized driving factors are used as the independent variables; (51.2) Aggregate the independent variables and dependent variables of all research units in the target area to form a training sample set, divide the training sample set into a training set and a test set, use the training set to train the random forest regression algorithm, and use the test set to evaluate the training results; (51.3) During the training process, the performance of the random forest regression algorithm was adjusted by adjusting the number of decision trees, the maximum depth of the decision tree, the minimum number of samples for node splitting, the minimum number of samples for leaf nodes, and the number of features for node splitting; The basic formula of the random forest regression algorithm is: Where X={X1,X2,…X n } is a feature vector containing n driving factors, M is the number of decision trees, T m (X) is the predicted value of the mth decision tree for the input feature vector X. Each decision tree T m (X) Process the input features according to its own tree structure and splitting rules, and finally give a predicted value; (51.4) After each round of training, the test set is used for evaluation. The explanatory power of the constructed regression model is evaluated by the mean square error, mean absolute error, and R-squared indicators. All models with R-squared greater than the threshold are output, and the model with the smallest mean square error and mean absolute error is selected as the final constructed relationship model. The mean square error is calculated as: Where y i is the actual value of the test set, is the value calculated based on the random forest regression model, and n is the number of test set samples; The mean absolute error (RMSE) is calculated as: Where y i is the actual value of the test set, is the value calculated based on the random forest regression model, and n is the number of test set samples; The calculation method of R squared is: Where y i is the actual value of the test set, is the value calculated based on the random forest regression model, and n is the number of test set samples; (52) Vacancy probability calculation: For each non-vacant land research unit, all driving factor values ​​X are input into the final constructed relationship model, which is the probability Pi of the research unit being converted into vacant land: The formula for the relational model is: Where X={X1,X2,…X n } is a feature vector containing n driving factors, M is the number of decision trees in the final determined relationship model, T m (X) is the predicted value of the mth decision tree for the input feature vector X; For a research unit that is currently vacant land, the probability that it will be converted into vacant land in the future is 1.

6. The intelligent evaluation method for green space supplementary cost based on vacancy probability according to claim 5 is characterized in that: The additional cost of green space for unit land in the target area is calculated as follows: C=C1+C2+C3 In the formula, C represents the green space supplement cost, C1 represents the land acquisition cost, C2 represents the land remediation cost, and C3 represents the green space construction optimization cost.

7. The intelligent evaluation method for green space supplementary cost based on vacancy probability according to claim 6 is characterized in that: The unit supplement potential is calculated based on the probability of conversion to vacant land and the cost of green space supplementation. The priority of green space supplementation for unit land is determined based on the calculation results. A green space supplementation plan is formulated based on the priority, and the supplementation cost of the green space supplementation plan is calculated as follows: (71) Evaluation of unit supplement potential: Normalize the cost to get the final comprehensive cost C i ', the normalization formula is: Where C i is the additional cost of green space per unit, C min is the minimum value of green space supplement cost in all units, C max is the maximum value of green space supplement cost in all units, C i ' is the normalized comprehensive cost; The formula for calculating unit supplementation potential is: T i =P i *(1-C i ') (72) Priority setting for unit supplementation Priorities are set based on the calculation result T of the unit supplementation potential. The higher the unit supplementation potential, the higher the priority of the green space supplement. The priorities are divided into 5 levels, from low to high: Very low [0, 0.2), low [0.2, 0.4), medium [0.4, 0.6), high [0.6, 0.8), very high [0.8, 1.0]; (73) Verification of green space supplement plan Formulate a green space supplement plan based on the unit green space supplement priority, convert the units into green spaces in order from high to low priority, and determine the form of converted green space based on the land use type around the unit. After each green space supplement plan is formulated, calculate the green supplement cost required for the plan and compare it with the supplement budget. If it is lower than the supplement budget requirement, the plan will be included in the alternative supplement plan. Otherwise, modify the supplement plan until the plan meets the supplement budget requirement.

8. A system for intelligently evaluating the supplementary cost of green space based on vacancy probability, for implementing the intelligent evaluation method for the supplementary cost of green space based on vacancy probability according to any one of claims 1 to 7, characterized in that: include: The vacant land identification module is used to receive remote sensing images of unit land in the target area, obtain urban vacant land and inefficient construction land based on remote sensing image recognition, and summarize urban vacant land and inefficient construction land to obtain the overall vacant land identification result; The vacancy probability prediction module is used to calculate the driving factors based on the overall vacant land identification results using the random forest regression algorithm The relationship model between the expansion of vacant land and the driving factor value Input the final constructed relationship model to obtain the probability of non-vacant land being converted into vacant land; The supplementary cost calculation module is used to calculate the green space supplementary cost of the target area unit land, where the green space supplementary cost includes land acquisition cost, land remediation cost and green space construction optimization cost; The supplementary scheme derivation and verification module is used to calculate the unit supplementary potential based on the probability of conversion to vacant land and the green space supplementary cost, determine the green space supplementary priority of the unit land based on the calculation results, convert the unit land into green space in order from high to low priority, determine the form of converted green space according to the unit land type, and calculate the supplementary cost of the green space supplementary scheme. If the supplementary cost is lower than the supplementary budget, the scheme will be included in the alternative supplementary scheme. Otherwise, the supplementary scheme will be modified until the supplementary scheme meets the supplementary budget requirements.

9. A terminal device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that: The memory stores a computer program that can be run on the processor. When the processor loads and executes the computer program, the intelligent evaluation method for green space supplementary cost based on vacancy probability according to any one of claims 1 to 7 is adopted.

10. A storage medium containing computer-executable instructions, characterized in that: When the computer executable instructions are executed by a computer processor, the computer executable instructions are used to perform the intelligent evaluation method for green space supplementary cost based on vacancy probability according to any one of claims 1 to 7.

Images