A multi-dimensional and multi-granularity environmental impact assessment method for ecologically sensitive areas

Abstract

The present invention relates to the technical field of environmental assessment, and discloses a multi-dimensional and multi-granularity environmental impact assessment method for ecological sensitive areas. The method includes: constructing an environmental assessment index system for ecological sensitive areas, collecting index data according to the index system and performing preprocessing; improving the data quality of the preprocessed index data; performing multi-level filtering on the enhanced index data to obtain the filtered key index data; and using the environmental assessment model for ecological sensitive areas to receive the key index data and conduct environmental impact assessment. The present invention selects multi-granularity environmental assessment indicators for ecological sensitive areas from multiple dimensions such as pollution control, ecological environment, resource environment, environmental planning, and environmental quality of ecological regions, sequentially performs cleaning of abnormal data and cleaning of redundant or non-critical indicators on the index data, and performs convolution, mapping, and correction processing on the cleaning results to obtain an environmental impact assessment result representing the ecological sensitivity of the region.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental assessment, and particularly to a multi-dimensional and multi-granularity environmental impact assessment method for ecologically sensitive areas. Background Art

[0002] Ecologically sensitive areas refer to areas in the natural environment where the ecosystem is fragile and sensitive, with a low resistance to external disturbances, and where the ecosystem functions are relatively important. These areas often carry rich biodiversity and ecological functions, and have extremely high ecological protection value. They cover a variety of ecosystem types, including but not limited to wetlands, forests, grasslands, deserts, coastal zones, and specific habitats of certain species. These areas not only play an important role in maintaining regional ecological balance, regulating climate, conserving water sources, maintaining soil fertility, and preventing soil erosion, but also provide a large number of ecological service functions, such as tourism, scientific research, and education. However, with the intensification of human activities, these ecologically sensitive areas are facing increasingly severe environmental pressures, such as resource development, land use change, and pollution. Therefore, it is particularly important to conduct environmental impact assessments on ecologically sensitive areas. Existing environmental impact assessment methods are often too single, lacking comprehensiveness and systematicness. Traditional assessment methods mainly rely on on-site investigations and laboratory analyses, and it is difficult to comprehensively and accurately reflect the complex environmental conditions and diverse impacts of ecologically sensitive areas. For example, some assessment methods only consider one aspect of the ecosystem, such as water quality, air quality, or soil pollution, while ignoring the integrity and comprehensiveness of the ecosystem. Summary of the Invention

[0003] In view of this, the present invention provides a multi-dimensional and multi-granularity environmental impact assessment method for ecologically sensitive areas, aiming to: select multi-granularity environmental assessment indicators for ecologically sensitive areas from multiple dimensions such as pollution control, ecological environment, resource environment, environmental planning, and environmental quality in the ecological region, sequentially perform cleaning of abnormal data and cleaning of redundant or non-critical indicators on the indicator data, and perform convolution, mapping, and correction processing on the cleaning results to obtain an environmental impact assessment result representing the ecological sensitivity of the region.

[0004] To achieve the above object, a multi-dimensional and multi-granularity environmental impact assessment method for ecologically sensitive areas provided by the present invention includes the following steps:

[0005] S1: Construct an environmental assessment index system for ecologically sensitive areas, collect index data according to the index system and perform preprocessing to obtain preprocessed index data;

[0006] S2: Improve the data quality of the preprocessed index data to obtain enhanced index data;

[0007] S3: Perform multi-level filtering on the enhanced indicator data to obtain the filtered key indicator data;

[0008] S4: Construct an environmental assessment model for ecologically sensitive areas, and use the environmental assessment model for ecologically sensitive areas to receive the key indicator data and conduct environmental impact assessment.

[0009] As a further improved method of the present invention:

[0010] Optionally, in the step S1 of constructing the environmental assessment index system for ecologically sensitive areas, it includes:

[0011] Construct an environmental assessment index system for ecologically sensitive areas, where the set of environmental assessment indicators for ecologically sensitive areas in the environmental assessment index system for ecologically sensitive areas is:

[0012] ;

[0013] Wherein:

[0014] represents the m-th environmental assessment indicator for ecologically sensitive areas under the n-th environmental indicator;

[0015] N represents the number of environmental indicators, N = 5, and the 1st - 5th environmental indicators are pollution control indicators, ecological environment indicators, resource environment indicators, environmental planning indicators, and environmental quality indicators in sequence;

[0016] M represents the number of environmental assessment indicators for ecologically sensitive areas under each environmental indicator, M = 4;

[0017] In sequence are reduction amount, reduction amount, emission limit of atmospheric pollutants, and industrial wastewater treatment rate;

[0018] In sequence are the number of nature reserves, proportion of environmental water resources, soil type, and ecological water consumption; In the embodiment of the present invention, the soil type includes construction land, water area, cultivated land, grassland, and forest land, and the ecological sensitivity ranking of different soil types is: construction land < water area < cultivated land < grassland < forest land, where the higher the ecological sensitivity, the higher the possibility of ecological environment problems when encountering the same degree of natural and human activity interference;

[0019] In sequence are fuel resource carrying capacity, atmospheric environment carrying capacity, water resource carrying capacity, and water consumption per unit power generation;

[0020] In sequence are the land proportion of prohibited development areas, land proportion of ecological function areas, land proportion of agricultural product production areas, and forest land proportion;

[0021] In sequence, annual average value, annual average value, annual average value and annual average value of inhalable particulate matter;

[0022] Collect index data according to the index system, and preprocess the collected index data to obtain the preprocessed index data.

[0023] Optionally, the collecting index data according to the index system includes:

[0024] The collected index data is:

[0025] ;

[0026] ;

[0027] ;

[0028] Wherein:

[0029] represents the collected index data;

[0030] represents the index correlation data of the d-th region for the collected index;

[0031] represents the index correlation data of the d-th region under the n-th environmental index;

[0032] represents the index correlation data of the m-th ecological sensitive area environmental assessment index of the d-th region under the n-th environmental index.

[0033] Optionally, the preprocessing the collected index data to obtain the preprocessed index data includes:

[0034] Preprocess the collected index data to obtain the preprocessed index data, where the preprocessing process of the index data data is:

[0035] S11: Calculate the maximum and minimum values of the index correlation data corresponding to different ecological sensitive area environmental assessment indexes in the index data data, where the maximum value of the m-th ecological sensitive area environmental assessment index under the n-th environmental index is and the minimum value is ;

[0036] S12: Normalize the index correlation data of any ecological sensitive area environmental assessment index in the index data data, where the index correlation data The normalization formula is as follows:

[0037] ;

[0038] Where:

[0039] represents the index correlation data of the normalization result;

[0040] S13: Constitutes the preprocessed index data :

[0041] ;

[0042] ;

[0043] ;

[0044] Where:

[0045] represents the index correlation data of the preprocessing result;

[0046] represents the index correlation data of the preprocessing result;

[0047] represents the index correlation data of the preprocessing result.

[0048] Optionally, in step S2, data quality improvement is performed on the preprocessed index data, including:

[0049] Data quality improvement is performed on the preprocessed index data, where the data quality improvement process is:

[0050] S21: Convert the index data to the covariance matrix C:

[0051] ;

[0052] ;

[0053] Where:

[0054] C represents the covariance matrix corresponding to the index data ;

[0055] represents the mean of the index correlation data of D regions;

[0056] T represents the transpose;

[0057] S22: Perform eigenvalue decomposition on the covariance matrix C to obtain G eigenvalues and eigenvectors of the covariance matrix C, and select the eigenvectors corresponding to the top 2 largest eigenvalues of the covariance matrix C , and the eigenvector corresponding to the smallest eigenvalue of the covariance matrix C ;

[0058] S23: Reconstruct the eigenvectors into a quadratic surface function:

[0059] ；

[0060] where:

[0061] represents the quadratic surface function, and x represents the independent variable of the quadratic surface function;

[0062] S24: Calculate the distances between the index correlation data in different regions. The distance between the index correlation data in the d-th region and the index correlation data in the e-th region is:

[0063] ;

[0064] where:

[0065] represents the distance between the index correlation data and the index correlation data ;

[0066] represents the exponential function with the natural constant as the base;

[0067] represents the L2 norm;

[0068] S25: Calculate the distance sequence of the index correlation data in any region to the index correlation data in other regions. The distance sequence corresponding to the index correlation data is:

[0069] ;

[0070] where:

[0071] represents the distance sequence corresponding to the index correlation data ;

[0072] S26: Calculate the amount of information indicating anomalies in the index correlation data corresponding to different regions based on the distance sequence. The amount of information indicating anomalies in the index correlation data is ;

[0073] S27: Filter the abnormal index correlation data with information volume higher than the preset threshold to obtain the index data with improved data quality:

[0074] ;

[0075] Among them:

[0076] represents the index data with improved data quality;

[0077] represents the index correlation data of the kth reserved area, and K represents the total number of index correlation data without abnormalities.

[0078] Optionally, the information volume of abnormalities in the index correlation data corresponding to different regions calculated based on the distance sequence in step S26 includes:

[0079] Index correlation data The information volume of abnormalities is:

[0080] ;

[0081] Among them:

[0082] represents the index correlation data The information volume of abnormalities;

[0083] represents the distance sequence The mean value of.

[0084] Optionally, the multi-level filtering of the enhanced index data in step S3 includes:

[0085] Perform multi-level filtering on the enhanced index data, and the multi-level filtering process is:

[0086] S31: Calculate the average data corresponding to the environmental assessment indicators of different ecological sensitive areas in the index data Among them, the average data corresponding to the environmental assessment indicators of ecological sensitive areas The corresponding average data is:

[0087] ;

[0088] Among them:

[0089] represents the average data corresponding to the environmental assessment indicators of ecological sensitive areas ;

[0090] represents the index correlation data The index correlation data of the m-th ecological sensitive area environmental assessment index under the n-th environmental index;

[0091] S32: For the index data Perform centering processing on the index correlation data of any ecological sensitive area environmental assessment index, where the index correlation data The centering processing formula is:

[0092] ;

[0093] S33: Reconstruct the centered index correlation data, where the reconstruction result is:

[0094] ;

[0095] Where:

[0096] Represents the reconstruction result;

[0097] S34: Calculate the covariance matrix of the reconstruction result y ;

[0098] S35: Perform eigenvalue decomposition on the covariance matrix To obtain the eigenvalue sequence of the covariance matrix :

[0099] ;

[0100] Where:

[0101] Is the eigenvalue corresponding to the ecological sensitive area environmental assessment index ;

[0102] S36: Calculate the contribution weights of different ecological sensitive area environmental assessment indexes, where the contribution weight of the ecological sensitive area environmental assessment index Is:

[0103] ;

[0104] Where:

[0105] Represents the contribution weight of the ecological sensitive area environmental assessment index ;

[0106] S37: Calculate the redundancy factors of different ecological sensitive area environmental assessment indexes, where the redundancy factor of the ecological sensitive area environmental assessment index Is:

[0107] ;

[0108] ;

[0109] Wherein:

[0110] represents the Pearson similarity between sequence and sequence ;

[0111] represents the redundancy factor of the environmental assessment index of the ecologically sensitive area ;

[0112] T represents transpose;

[0113] S38: Calculate the filtering level index of the environmental assessment index of different ecologically sensitive areas by using a multi-level filtering method, where the filtering level index of the environmental assessment index of the ecologically sensitive area is:

[0114] ;

[0115] Wherein:

[0116] represents the filtering level index of the environmental assessment index of the ecologically sensitive area;

[0117] S39: Clean the index-related data corresponding to the environmental assessment index of the ecologically sensitive area with a filtering level index higher than the preset threshold from the index data to obtain the key index data:

[0118] ;

[0119] Wherein:

[0120] represents the key index data;

[0121] represents the key index-related data of the kth reserved area.

[0122] Optionally, in the S4 step, constructing an environmental assessment model for ecologically sensitive areas includes:

[0123] Construct an environmental assessment model for ecologically sensitive areas, where the environmental assessment model for ecologically sensitive areas takes the key index data as input and the environmental impact assessment of different areas as output, and the environmental assessment model for ecologically sensitive areas includes an input layer, an environmental impact assessment layer, and a correction layer;

[0124] The input layer is used to receive key indicator data and divide the key indicator data into key indicator associated data in different regions;

[0125] The environmental impact assessment layer consists of a convolutional layer, a residual unit, and a fully connected layer in a convolutional neural network, and is used to perform residual convolution calculation on the key indicator associated data to obtain key indicator associated features and map the key indicator associated features to environmental impact assessment results;

[0126] The correction layer is used to correct the environmental impact assessment results in different regions and output the corrected environmental impact assessment results;

[0127] The ecological sensitive area environmental assessment model is used to receive key indicator data and conduct environmental impact assessment.

[0128] Optionally, the using the ecological sensitive area environmental assessment model to receive key indicator data and conduct environmental impact assessment includes:

[0129] Using the ecological sensitive area environmental assessment model to receive key indicator data and conduct environmental impact assessment, where the environmental impact assessment process is as follows:

[0130] S41: The input layer receives key indicator data , and divides the key indicator data into key indicator associated data in different regions, where the key indicator associated data in the k-th region is ;

[0131] S42: The environmental impact assessment layer performs residual convolution calculation on the key indicator associated data to obtain key indicator associated features, where the key indicator associated features corresponding to the key indicator associated data are:

[0132] ;

[0133] Where:

[0134] represents the key indicator associated features corresponding to the key indicator associated data ;

[0135] represents the convolution weight matrix, represents the convolution operation;

[0136] represents the activation function; in the embodiments of the present invention, the selected activation function is the ReLU function;

[0137] S43: Map the key indicator associated features to environmental impact assessment results, where the mapping formula of the key indicator associated features is:

[0138] ;

[0139] Wherein:

[0140] represents a mapping weight matrix;

[0141] represents the key index correlation feature corresponding to the environmental impact assessment result;

[0142] S44: The correction layer corrects the environmental impact assessment results of different regions and outputs the corrected environmental impact assessment results, where the environmental impact assessment result has the following correction formula:

[0143] ;

[0144] Wherein:

[0145] represents the correction value of the environmental impact assessment result ;

[0146] represents the environmental impact assessment result of the nearest region of the k-th region;

[0147] Among them, the higher the corrected environmental impact assessment result, the higher the ecological sensitivity of the region, and the higher the possibility of ecological environment problems occurring when encountering natural and human activity interferences of the same degree.

[0148] To solve the above problems, the present invention provides an electronic device, and the electronic device includes:

[0149] a memory storing at least one instruction;

[0150] a communication interface for realizing the communication of the electronic device; and

[0151] a processor for executing the instructions stored in the memory to implement the above-mentioned multi-dimensional and multi-granularity environmental impact assessment method for ecological sensitive regions.

[0152] To solve the above problems, the present invention further provides a computer-readable storage medium, and at least one instruction is stored in the computer-readable storage medium, and the at least one instruction is executed by a processor in an electronic device to implement the above-mentioned multi-dimensional and multi-granularity environmental impact assessment method for ecological sensitive regions.

[0153] Compared with the prior art, the present invention proposes a multi-dimensional and multi-granularity environmental impact assessment method for ecological sensitive regions, and this technology has the following advantages:

[0154] First, this solution selects multi-granularity ecological sensitive area environmental assessment indicators from multiple dimensions such as pollution control, ecological environment, resource environment, environmental planning, and environmental quality of ecological regions, constructs an ecological sensitive area environmental assessment index system, and collects index correlation data of different regions to form index data. Principal component analysis is performed on the index data to obtain a quadratic surface representing the direction of the index data. Based on the distance from different index correlation data to the quadratic surface, the distance between the index correlation data is calculated, and the distance is mapped to the information volume where the index correlation data is abnormal, realizing the cleaning process of abnormal index correlation data and improving the data quality of the index data.

[0155] Meanwhile, based on the variance contribution weights of different ecological sensitive area environmental assessment indicators and the similarity of data between different ecological sensitive area environmental assessment indicators, this solution obtains the filtering level index of different ecological sensitive area environmental assessment indicators. The index correlation data corresponding to the ecological sensitive area environmental assessment indicators with a filtering level index higher than the preset threshold is cleaned from the index data, realizing the data cleaning of redundant indicators or non-critical indicators to form key index data. The ecological sensitive area environmental assessment model is used to perform convolution, mapping, and correction processing on the key index correlation data of different regions to obtain the environmental impact assessment results representing the regional ecological sensitivity. Description of the Drawings

[0156] Figure 1 It is a schematic flowchart of a multi-dimensional and multi-granularity ecological sensitive area environmental impact assessment method provided by an embodiment of the present invention;

[0157] Figure 2 It is a schematic structural diagram of an electronic device for implementing the multi-dimensional and multi-granularity ecological sensitive area environmental impact assessment method provided by an embodiment of the present invention.

[0158] In the figure: 1 is an electronic device, 10 is a processor, 11 is a memory, 12 is a program, and 13 is a communication interface.

[0159] The realization, functional characteristics, and advantages of the purpose of the present invention will be further described with reference to the embodiments and the drawings. Detailed Embodiments

[0160] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0161] An embodiment of this application provides a multi - dimensional and multi - granularity method for assessing the environmental impact of ecological sensitive areas. The execution subject of the multi - dimensional and multi - granularity method for assessing the environmental impact of ecological sensitive areas includes, but is not limited to, at least one of electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided in the embodiment of this application. In other words, the multi - dimensional and multi - granularity method for assessing the environmental impact of ecological sensitive areas can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to: a single server, a server cluster, a cloud server, or a cloud server cluster, etc.

[0162] Embodiment 1:

[0163] S1: Construct an environmental assessment index system for ecological sensitive areas, collect index data according to the index system and perform pre - processing to obtain pre - processed index data.

[0164] In the S1 step of constructing the environmental assessment index system for ecological sensitive areas, it includes:

[0165] Construct an environmental assessment index system for ecological sensitive areas, where the set of environmental assessment indexes for ecological sensitive areas in the environmental assessment index system for ecological sensitive areas is:

[0166] ;

[0167] Where:

[0168] represents the m - th environmental assessment index for ecological sensitive areas under the n - th environmental index;

[0169] N represents the number of environmental indexes, N = 5, and the 1st - 5th environmental indexes are pollution control index, ecological environment index, resource environment index, environmental planning index, and environmental quality index in sequence;

[0170] M represents the number of environmental assessment indexes for ecological sensitive areas under each environmental index, M = 4;

[0171] In sequence are reduction amount, reduction amount, atmospheric pollutant emission limit, and industrial wastewater treatment rate;

[0172] In sequence are the number of nature reserves, the proportion of environmental water resources, soil type, and ecological water consumption;

[0173] In sequence are fuel resource carrying capacity, atmospheric environment carrying capacity, water resource carrying capacity, and water consumption per unit power generation;

[0174] In sequence, they are the land proportion of the prohibited development area, the land proportion of the ecological function area, the land proportion of the agricultural product production area, and the forest land proportion;

[0175] In sequence, the annual average value, the annual average value, the annual average value, and the annual average value of inhalable particulate matter;

[0176] Collect index data according to the index system, and preprocess the collected index data to obtain the preprocessed index data.

[0177] The collecting of index data according to the index system includes:

[0178] The collected index data are:

[0179] ;

[0180] ;

[0181] ;

[0182] Among them:

[0183] represents the collected index data;

[0184] represents the index correlation data of the d-th area for the collected indexes;

[0185] represents the index correlation data of the d-th area under the n-th environmental index;

[0186] represents the index correlation data of the m-th ecological sensitive area environmental assessment index of the d-th area under the n-th environmental index.

[0187] The preprocessing of the collected index data to obtain the preprocessed index data includes:

[0188] Preprocess the collected index data to obtain the preprocessed index data, where the preprocessing process of the index data data is:

[0189] S11: Calculate the maximum and minimum values of the index correlation data corresponding to different ecological sensitive area environmental assessment indexes in the index data data, where the maximum value of the m-th ecological sensitive area environmental assessment index under the n-th environmental index is and the minimum value is ;

[0190] S12: Normalize the index correlation data of any environmental assessment index in the index data data, where the index correlation data has the following normalization formula:

[0191] ;

[0192] where:

[0193] represents the normalized result of the index correlation data ;

[0194] S13: Compose the preprocessed index data :

[0195] ;

[0196] ;

[0197] ;

[0198] where:

[0199] represents the preprocessing result of the index correlation data ;

[0200] represents the preprocessing result of the index correlation data ;

[0201] represents the preprocessing result of the index correlation data ;

[0202] S2: Improve the data quality of the preprocessed index data to obtain enhanced index data.

[0203] In the S2 step, improving the data quality of the preprocessed index data includes:

[0204] Improve the data quality of the preprocessed index data, where the data quality improvement process is:

[0205] S21: Convert the index data into the covariance matrix C:

[0206] ;

[0207] ;

[0208] where:

[0209] C represents the index data The corresponding covariance matrix;

[0210] Indicates the mean of the index correlation data for D regions;

[0211] T represents the transpose;

[0212] S22: Perform eigenvalue decomposition on the covariance matrix C to obtain G eigenvalues and eigenvectors of the covariance matrix C, and select the eigenvectors corresponding to the top 2 largest eigenvalues of the covariance matrix C , and the eigenvector corresponding to the smallest eigenvalue of the covariance matrix C ;

[0213] S23: Reconstruct the eigenvectors into a quadratic surface function:

[0214] ；

[0215] Where:

[0216] Represents the quadratic surface function, and x represents the independent variable of the quadratic surface function;

[0217] S24: Calculate the distances between the index correlation data of different regions. The distance between the index correlation data of the d-th region and the index correlation data of the e-th region is:

[0218] ;

[0219] Where:

[0220] Represents the distance between the index correlation data and the index correlation data ;

[0221] Represents the exponential function with the natural constant as the base;

[0222] Represents the L2 norm;

[0223] S25: Calculate the distance sequence from the index correlation data of any region to the index correlation data of other regions. The distance sequence corresponding to the index correlation data is:

[0224] ;

[0225] Where:

[0226] Represents the index correlation data The corresponding distance sequence;

[0227] S26: Calculate the information volume of anomalies in the index correlation data corresponding to different regions based on the distance sequence, where the index correlation data The information volume of anomalies is ;

[0228] S27: Filter out the abnormal index correlation data with information volume higher than the preset threshold to obtain the index data with improved data quality:

[0229] ;

[0230] Where:

[0231] Represents the index data with improved data quality;

[0232] Represents the index correlation data of the kth region retained, where K represents the total number of index correlation data without anomalies.

[0233] In the step S26, calculating the information volume of anomalies in the index correlation data corresponding to different regions based on the distance sequence includes:

[0234] The index correlation data The information volume of anomalies is:

[0235] ;

[0236] Where:

[0237] Represents the information volume of anomalies in the index correlation data ;

[0238] Represents the distance sequence The mean value of

[0239] S3: Perform multi-level filtering on the enhanced index data to obtain the filtered key index data.

[0240] In the step S3, performing multi-level filtering on the enhanced index data includes:

[0241] Perform multi-level filtering on the enhanced index data, where the multi-level filtering process is:

[0242] S31: Calculate the average data corresponding to the environmental assessment indicators of different ecologically sensitive regions in the index data , where the average data corresponding to the environmental assessment indicators of the ecologically sensitive regions Is:

[0243] ;

[0244] Wherein:

[0245] represents the average data of the environmental assessment indicators of the ecologically sensitive area; the corresponding average data;

[0246] represents the index correlation data of the m-th environmental assessment indicator of the ecologically sensitive area under the n-th environmental indicator in the index correlation data;

[0247] S32: Centralize the index correlation data of any environmental assessment indicator of the ecologically sensitive area in the data, where the centralization processing formula of the index correlation data is:

[0248] ;

[0249] S33: Reconstruct the centralized index correlation data, where the reconstruction result is:

[0250] ;

[0251] Wherein:

[0252] represents the reconstruction result;

[0253] S34: Calculate the covariance matrix of the reconstruction result y ;

[0254] S35: Perform eigenvalue decomposition on the covariance matrix to obtain the eigenvalue sequence of the covariance matrix :

[0255] ;

[0256] Wherein:

[0257] is the eigenvalue corresponding to the environmental assessment indicator of the ecologically sensitive area ;

[0258] S36: Calculate the contribution weights of different environmental assessment indicators of the ecologically sensitive area, where the contribution weight of the environmental assessment indicator of the ecologically sensitive area is:

[0259] ;

[0260] Wherein:

[0261] Indicates the contribution weight of the environmental assessment index for the ecologically sensitive area ;

[0262] S37: Calculate the redundancy factor of the environmental assessment index for different ecologically sensitive areas, where the redundancy factor of the environmental assessment index for the ecologically sensitive area is:

[0263] ;

[0264] ;

[0265] where:

[0266] represents the Pearson similarity between the sequence and the sequence ;

[0267] Indicates the redundancy factor of the environmental assessment index for the ecologically sensitive area ;

[0268] T represents the transpose;

[0269] S38: Calculate the filtration level index of the environmental assessment index for different ecologically sensitive areas using a multi-level filtration method, where the filtration level index of the environmental assessment index for the ecologically sensitive area is:

[0270] ;

[0271] where:

[0272] represents the filtration level index of the environmental assessment index for the ecologically sensitive area ;

[0273] S39: Clean the associated data of the indicators corresponding to the environmental assessment indicators of the ecologically sensitive areas whose filtration level index is higher than the preset threshold from the indicator data to obtain the key indicator data:

[0274] ;

[0275] where:

[0276] represents the key indicator data;

[0277] represents the associated data of the key indicators of the k-th area retained.

[0278] S4: Construct an environmental assessment model for ecologically sensitive areas, and use the environmental assessment model for ecologically sensitive areas to receive key indicator data and conduct environmental impact assessments.

[0279] In the S4 step, constructing an environmental assessment model for ecologically sensitive areas includes:

[0280] Construct an environmental assessment model for ecologically sensitive areas. The environmental assessment model for ecologically sensitive areas takes key indicator data as input and environmental impact assessments of different regions as output. The environmental assessment model for ecologically sensitive areas includes an input layer, an environmental impact assessment layer, and a correction layer;

[0281] The input layer is used to receive key indicator data and divide the key indicator data into key indicator correlation data for different regions;

[0282] The environmental impact assessment layer consists of a convolutional layer, a residual unit, and a fully connected layer in a convolutional neural network, and is used to perform residual convolution calculations on the key indicator correlation data to obtain key indicator correlation features and map the key indicator correlation features to environmental impact assessment results;

[0283] The correction layer is used to correct the environmental impact assessment results of different regions and output the corrected environmental impact assessment results;

[0284] Use the environmental assessment model for ecologically sensitive areas to receive key indicator data and conduct environmental impact assessments.

[0285] The use of the environmental assessment model for ecologically sensitive areas to receive key indicator data and conduct environmental impact assessments includes:

[0286] Use the environmental assessment model for ecologically sensitive areas to receive key indicator data and conduct environmental impact assessments. The environmental impact assessment process is as follows:

[0287] S41: The input layer receives key indicator data and divides the key indicator data into key indicator correlation data for different regions. The key indicator correlation data for the kth region is ;

[0288] S42: The environmental impact assessment layer performs residual convolution calculations on the key indicator correlation data to obtain key indicator correlation features. The key indicator correlation features corresponding to the key indicator correlation data are:

[0289] ;

[0290] Among them:

[0291] represents the key indicator correlation data The corresponding key index associated features;

[0292] represents the convolutional weight matrix, represents the convolutional operation;

[0293] represents the activation function; in the embodiments of the present invention, the selected activation function is the ReLU function;

[0294] S43: Map the key index associated features to the environmental impact assessment result, where the key index associated features The mapping formula is:

[0295] ;

[0296] Where:

[0297] represents the mapping weight matrix;

[0298] represents the environmental impact assessment result corresponding to the key index associated features ;

[0299] S44: The correction layer corrects the environmental impact assessment results of different regions and outputs the corrected environmental impact assessment results, where the environmental impact assessment result The correction formula is:

[0300] ;

[0301] Where:

[0302] represents the correction value of the environmental impact assessment result ;

[0303] represents the environmental impact assessment result of the nearest neighboring region of the kth region;

[0304] Among them, the higher the corrected environmental impact assessment result, the higher the ecological sensitivity of the region, and the higher the possibility of ecological environment problems when encountering natural and human activity interferences of the same degree.

[0305] Embodiment 2:

[0306] As Figure 2 shown, it is a schematic structural diagram of an electronic device for implementing the multi-dimensional and multi-granularity ecological sensitive area environmental impact assessment method provided by an embodiment of the present invention.

[0307] The electronic device 1 may include a processor 10, a memory 11, a communication interface 13, and a bus. It may also include a computer program stored in the memory 11 and executable on the processor 10, such as program 12.

[0308] Among them, the memory 11 includes at least one type of readable storage medium, which includes flash memory, mobile hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, magnetic disk, optical disc, etc. In some embodiments, the memory 11 may be an internal storage unit of the electronic device 1, such as the mobile hard disk of the electronic device 1. In some other embodiments, the memory 11 may also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the electronic device 1. Further, the memory 11 may also include both an internal storage unit and an external storage device of the electronic device 1. The memory 11 can be used not only to store application software installed on the electronic device 1 and various types of data, such as the code of program 12, etc., but also to temporarily store data that has been output or will be output.

[0309] In some embodiments, the processor 10 may be composed of integrated circuits. For example, it may be composed of a single packaged integrated circuit, or may be composed of multiple integrated circuits with the same or different functions, including a combination of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control core (Control Unit) of the electronic device, connecting various components of the entire electronic device through various interfaces and lines, and by running or executing programs or modules stored in the memory 11 (such as program 12 for realizing the environmental impact assessment of multi-dimensional and multi-granularity ecological sensitive areas), and calling data stored in the memory 11, to execute various functions of the electronic device 1 and process data.

[0310] The communication interface 13 may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), and is generally used to establish a communication connection between the electronic device 1 and other electronic devices, and to achieve connection communication between internal components of the electronic device.

[0311] The bus can be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to implement connection communication between the memory 11 and at least one processor 10, etc.

[0312] Figure 2 Only the electronic device with components is shown. Those skilled in the art can understand that Figure 2 The shown structure does not constitute a limitation on the electronic device 1, and it may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0313] For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for powering each component. Preferably, the power source can be logically connected to the at least one processor 10 through a power management device, so as to implement functions such as charge management, discharge management, and power consumption management through the power management device. The power source may also include any components such as one or more DC or AC power sources, a recharge device, a power failure detection circuit, a power converter or inverter, and a power status indicator. The electronic device 1 may also include various sensors, a Bluetooth module, a Wi-Fi module, etc., which will not be elaborated here.

[0314] Optionally, the electronic device 1 may further include a user interface. The user interface can be a display, an input unit (such as a keyboard), and optionally, the user interface can also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display can be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) toucher, etc. Among them, the display can also be appropriately referred to as a display screen or a display unit, which is used to display the information processed in the electronic device 1 and to display a visual user interface.

[0315] It should be understood that the above embodiments are only for illustration purposes and are not limited by this structure in the scope of the patent application.

[0316] The program 12 stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can implement:

[0317] Construct an environmental assessment index system for ecologically sensitive areas, collect index data according to the index system and perform preprocessing to obtain the preprocessed index data;

[0318] Improve the data quality of the preprocessed index data to obtain enhanced index data;

[0319] Perform multi-level filtering on the enhanced index data to obtain the filtered key index data;

[0320] Construct an environmental assessment model for ecologically sensitive areas, and use the environmental assessment model for ecologically sensitive areas to receive the key index data and conduct environmental impact assessment.

[0321] Specifically, the specific implementation method of the above instructions by the processor 10 can refer to Figures 1 to 2 the description of the relevant steps in the corresponding embodiments, which will not be elaborated here.

[0322] It should be noted that the serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. And the terms "including", "comprising" or any other variant thereof in this article are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, device, article or method. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of another identical element in the process, device, article or method including the element.

[0323] Through the description of the above embodiments, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions for causing a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in various embodiments of the present invention.

[0324] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be included in the patent protection scope of the present invention in the same way.

Claims

1. A multi-dimensional and multi-granular ecologically sensitive area environmental impact assessment method, characterized in that: The method comprises: S1: Construct an environmental assessment index system for ecologically sensitive areas, collect index data according to the index system and pre-process them to obtain pre-processed index data; S2: Improve the data quality of the preprocessed indicator data to obtain enhanced indicator data; The data quality improvement process is as follows: S21: Convert the indicator data DATA into the covariance matrix C: in: C represents the covariance matrix corresponding to the indicator data DATA; mean represents the mean of the indicator-related data of D regions; T stands for transpose; S22: Perform eigendecomposition on the covariance matrix C to obtain G eigenvalues ​​and eigenvectors of the covariance matrix C, and select the eigenvectors α1 and α2 corresponding to the first two eigenvalues ​​of the covariance matrix C, and the eigenvector α corresponding to the minimum eigenvalue of the covariance matrix C; S23: Reconstruct the eigenvector into a quadratic surface function: F(x)=x T α1x+(α2) T x+a in: F(x) represents the quadratic surface function, and x represents the independent variable of the quadratic surface function; S24: Calculate the distance between the indicator-related data of different regions, where the indicator-related data DATA of the dth region d Data associated with the indicator of the e-th region DATA e The distance between them is: in: dis(DATA d ,DATA e ) indicates indicator-related data DATA d Data associated with the indicator e The distance between exp(·) represents an exponential function with a natural constant as the base; ||·||2 represents the L2 norm; S25: Calculate the distance sequence from the indicator-related data of any region to the indicator-related data of other regions, where the indicator-related data DATA d The corresponding distance sequence is: dis d =(dis(DATA d ,DATA1),dis(DATA d ,DATA2),...,dis(DATA d ,DATA D )) in: dis d Indicates indicator-related data DATA d The corresponding distance sequence; S26: Based on the distance sequence, the amount of abnormal information in the indicator-related data corresponding to different regions is calculated, where the indicator-related data DATA d The amount of abnormal information is H d ; S27: Filter abnormal indicator-related data with information volume higher than a preset threshold to obtain indicator data with improved data quality: DATA ′ ={DATA ′ k |k∈[1,K]} in: DATA ′ Indicator data indicating improvement in data quality; DATA ′ k represents the indicator-related data of the k-th region that is retained, and K represents the total number of indicator-related data without abnormalities; The information amount of abnormality in the indicator association data corresponding to different regions obtained by calculating based on the distance sequence includes: Indicator related data DATA d The amount of abnormal information is: in: H d Indicates indicator-related data DATA d There is an abnormal amount of information; mean(dis d ) represents the distance sequence dis d The mean of S3: Perform multi-level filtering on the enhanced indicator data to obtain filtered key indicator data; S4: Construct an environmental assessment model for ecologically sensitive areas, and use the environmental assessment model for ecologically sensitive areas to receive key indicator data and conduct environmental impact assessment.

2. A multi-dimensional and multi-granular ecologically sensitive area environmental impact assessment method as claimed in claim 1, characterized in that: The ecologically sensitive area environmental assessment indicator system is constructed in step S1, including: Construct an ecologically sensitive area environmental assessment indicator system, where the set of ecologically sensitive area environmental assessment indicators in the ecologically sensitive area environmental assessment indicator system is: {x nm |n∈[1,N],m∈[1,M]} in: x nm It represents the mth ecologically sensitive area environmental assessment index under the nth environmental index; N represents the number of environmental indicators, N=5, and the first to fifth environmental indicators are pollution control indicators, ecological environment indicators, resource and environmental indicators, environmental planning indicators, and environmental quality indicators; M represents the number of environmental assessment indicators for ecologically sensitive areas under each environmental indicator, M = 4; x 11 ,x 12 ,x 13 ,x 14 They are SO2 reduction, NO2 reduction, air pollutant emission limits and industrial wastewater treatment rate; x 21 ,x 22 ,x 23 ,x 24 They are the number of nature reserves, the proportion of environmental water resources, soil types, and ecological water consumption; x 31 ,x 32 ,x 33 ,x 34 They are fuel resource carrying capacity, atmospheric environment carrying capacity, water resource carrying capacity and water consumption per unit of power generation; x 41 ,x 42 ,x 43 ,x 44 The percentage of land in the prohibited development area, the percentage of land in the ecological function area, the percentage of land in the agricultural product production area and the percentage of forest land; x 51 ,x 52 ,x 53 ,x 54 They are the annual average values ​​of SO2, NO2, NO and inhalable particulate matter; Collect indicator data according to the indicator system.

3. A multi-dimensional and multi-granular ecologically sensitive area environmental impact assessment method as claimed in claim 2, characterized in that: The collecting of indicator data according to the indicator system includes: The collected indicator data are: data={data d |d∈[1,D]} in: data represents the collected indicator data; data d Indicates the index-related data collected for the dth area; It represents the indicator association data of the dth area under the nth environmental indicator; Indicator association data representing the mth ecologically sensitive area environmental assessment indicator under the nth environmental indicator for the dth area; The collected indicator data are preprocessed to obtain preprocessed indicator data.

4. A multi-dimensional and multi-granular ecologically sensitive area environmental impact assessment method as claimed in claim 3, characterized in that: The preprocessing of the collected indicator data to obtain the preprocessed indicator data includes: The collected indicator data is preprocessed to obtain preprocessed indicator data, wherein the preprocessing process of the indicator data is as follows: S11: Calculate the maximum and minimum values ​​of the indicator-related data corresponding to the environmental assessment indicators of different ecologically sensitive areas in the indicator data data, where the maximum value of the environmental assessment indicator of the mth ecologically sensitive area under the nth environmental indicator is The minimum value is S12: Normalize the indicator-related data of any ecologically sensitive area environmental assessment indicator in the indicator data data, where the indicator-related data The normalized formula is: in: Indicates indicator-related data The normalized result of S13: Constructing pre-processed index data DATA: DATA={DATA d |d∈[1,D]} in: DATA d Indicates indicator-related data data d The preprocessing results; Indicates indicator-related data The preprocessing results; Indicates indicator-related data The preprocessing results.

5. A multi-dimensional and multi-granular ecologically sensitive area environmental impact assessment method as claimed in claim 1, characterized in that: In the step S3, the enhanced indicator data is subjected to multi-level filtering, including: The enhanced indicator data is filtered at multiple levels, and the multi-level filtering process is as follows: S31: Calculate and obtain indicator data DATA ′ The average data corresponding to the environmental assessment indicators of different ecologically sensitive areas, among which the environmental assessment indicators of ecologically sensitive areas x nm The corresponding average data is: in: μ nm Represents the environmental assessment index x for ecologically sensitive areas nm The corresponding average data; Indicates indicator-related data DATA ′ k The indicator-related data of the mth ecologically sensitive area environmental assessment indicator under the nth environmental indicator; S32: Index data DATA ′ The indicator-related data of any ecologically sensitive area environmental assessment indicator in the The centralization formula is: S33: Reconstruct the indicator-related data after the centralization process, where the reconstruction result is: in: y represents the reconstruction result; S34: Calculate and obtain the covariance matrix Cov(y) of the reconstruction result y; S35: Perform eigendecomposition on the covariance matrix Cov(y) to obtain the eigenvalue sequence of the covariance matrix Cov(y): in: Environmental assessment index for ecologically sensitive areas x nm The corresponding eigenvalues; S36: Calculate the contribution weights of environmental assessment indicators for different ecologically sensitive areas, where the environmental assessment indicator x nm The contribution weight is: in: w nm Represents the environmental assessment index x for ecologically sensitive areas nm The contribution weight of S37: Calculate the redundancy factors of environmental assessment indicators for different ecologically sensitive areas, where the environmental assessment indicator x nm The redundancy factor is: in: Representation sequence with sequence Pearson similarity between ; σ nm Represents the environmental assessment index x for ecologically sensitive areas nm The redundancy factor of T stands for transpose; S38: The filtering level index of environmental assessment indicators of different ecologically sensitive areas is calculated by multi-level filtering method, where the environmental assessment index of ecologically sensitive areas x nm The filter level index is: in: Represents the environmental assessment index x for ecologically sensitive areas nm The filter level index; S39: Filter the ecologically sensitive area environmental assessment indicators whose level index is higher than the preset threshold, and the corresponding indicator-related data from the indicator data DATA ′ Cleaning in the middle, get the key indicator data: in: DATA * Indicates key indicator data; Indicates the key indicator associated data of the k-th region that is retained.

6. A multi-dimensional and multi-granular ecologically sensitive area environmental impact assessment method as claimed in claim 1, characterized in that: The step S4 constructs an ecologically sensitive area environmental assessment model, including: Constructing an ecologically sensitive area environmental assessment model, wherein the ecologically sensitive area environmental assessment model takes key indicator data as input and takes environmental impact assessment of different areas as output, wherein the ecologically sensitive area environmental assessment model includes an input layer, an environmental impact assessment layer, and a correction layer; The input layer is used to receive key indicator data and divide the key indicator data into key indicator related data of different regions; The environmental impact assessment layer consists of a convolutional layer, a residual unit, and a fully connected layer in a convolutional neural network, which is used to perform residual convolution calculations on key indicator-related data to obtain key indicator-related features, and map the key indicator-related features to environmental impact assessment results; The correction layer is used to correct the environmental impact assessment results of different regions and output the corrected environmental impact assessment results; Receive key indicator data and conduct environmental impact assessment using the ecologically sensitive area environmental assessment model.

7. A multi-dimensional and multi-granular ecologically sensitive area environmental impact assessment method as claimed in claim 6, characterized in that: The method of using the ecologically sensitive area environmental assessment model to receive key indicator data and conduct environmental impact assessment includes: The ecologically sensitive area environmental assessment model is used to receive key indicator data and conduct environmental impact assessment, where the environmental impact assessment process is as follows: S41: Input layer receives key indicator data DATA * , and divide the key indicator data into key indicator related data of different regions, where the key indicator related data of the kth region is S42: The environmental impact assessment layer performs residual convolution calculation on the key indicator related data to obtain key indicator related features, where the key indicator related data The corresponding key indicator association characteristics are: in: Indicates key indicator related data Corresponding key indicator association characteristics; W1 represents the convolution weight matrix, * represents the convolution operation; δ(·) represents the activation function; S43: Map the key indicator correlation characteristics to the environmental impact assessment results, where the key indicator correlation characteristics The mapping formula is: in: W2 represents the mapping weight matrix; Indicates key indicator related characteristics The corresponding environmental impact assessment results; S44: The correction layer corrects the environmental impact assessment results of different regions and outputs the corrected environmental impact assessment results. The correction formula is: in: Indicates the results of the environmental impact assessment Correction value of represents the environmental impact assessment results of the nearest neighboring area of ​​the kth area; The higher the revised environmental impact assessment result, the higher the ecological sensitivity of the area, and the higher the possibility of ecological and environmental problems occurring when encountering the same degree of interference from natural and human activities.

Images