Ecological restoration effectiveness monitoring method and system based on big data analysis

Abstract

The present invention provides an ecological restoration effectiveness monitoring method and system based on big data analysis, which relates to the field of ecological management technology. The method includes: marking missing areas in the target area and collecting basic ecological monitoring data of normal areas; supplementing the ecological monitoring data of the missing areas to obtain supplementary ecological monitoring data; collecting missing feature information of the missing areas, performing ecological impact analysis, and obtaining ecological impact parameters; according to the location information of the missing areas, indexing and obtaining multiple adjacent ecological monitoring data, performing ecological impact analysis of the missing areas on the normal areas, correcting the ecological impact parameters, analyzing and generating missing ecological monitoring data, and analyzing and obtaining ecological restoration effectiveness monitoring results. The present invention achieves the technical effect of improving the integrity and accuracy of ecological restoration effectiveness monitoring analysis when there are missing areas where ecological data cannot be collected.

Description

Technical Field

[0001] The present invention relates to the field of ecological management technology, and in particular to an ecological restoration effectiveness monitoring method and system based on big data analysis. Background Art

[0002] Currently, ecological restoration projects are widely carried out to address the problems of ecological imbalance and environmental degradation. However, traditional ecological restoration effectiveness monitoring methods usually rely on manual surveys and field sampling, which have disadvantages such as long data acquisition cycle, high cost, and limited coverage, making it difficult to comprehensively and timely evaluate the effectiveness of ecological restoration. With the development of big data and machine learning technology, methods based on remote sensing images, environmental sensor networks, and multi-source data fusion have gradually become the main means of ecological monitoring. However, due to many reasons, there is an incomplete collection of ecological data. For example, there are data missing areas in the region where ecological data cannot be collected due to planning, construction, etc., and ecological data cannot be collected in data missing areas, which affects the comprehensiveness and accuracy of ecological restoration effectiveness analysis. Summary of the invention

[0003] The present application provides an ecological restoration effectiveness monitoring method and system based on big data analysis, which is used to solve the technical problems of incomplete and inaccurate ecological restoration effectiveness monitoring and analysis in the prior art.

[0004] The first aspect of the present application provides an ecological restoration effectiveness monitoring method based on big data analysis, the method comprising:

[0005] Identify and mark missing areas in target areas for ecological restoration effectiveness monitoring, and collect ecological monitoring data from normal areas outside the missing areas to obtain basic ecological monitoring data;

[0006] According to the basic ecological monitoring data, supplementary processing is performed on the ecological monitoring data of the missing area to obtain supplementary ecological monitoring data, wherein the supplementary processing includes basic supplementary processing and historical supplementary processing;

[0007] Based on big data, missing feature information of the missing area is collected, ecological impact analysis is performed, and ecological impact parameters are obtained, wherein the ecological impact parameters include multiple range ecological impact coefficients within multiple distance ranges;

[0008] According to the location information of the missing area, a plurality of adjacent areas are divided in the target area, a plurality of adjacent ecological monitoring data of the plurality of adjacent areas are obtained by indexing, and the adjacent areas are divided into a plurality of range ecological monitoring data sets according to the distance from the missing area;

[0009] According to the plurality of range ecological monitoring data sets, an ecological impact analysis of the missing area on the normal area is performed, and the ecological impact parameters are corrected;

[0010] According to the revised ecological impact parameters combined with the supplementary ecological monitoring data, the missing ecological monitoring data are analyzed and generated. Combined with the basic ecological monitoring data, the current ecological monitoring data of the target area is generated, and the ecological restoration effectiveness monitoring results are analyzed and obtained.

[0011] The second aspect of the present application provides an ecological restoration effectiveness monitoring system based on big data analysis, the system comprising:

[0012] The missing area identification module is used to identify and mark the missing areas of the target areas for ecological restoration effectiveness monitoring, and collect ecological monitoring data of normal areas outside the missing areas to obtain basic ecological monitoring data;

[0013] An ecological data supplementation module, used to supplement the ecological monitoring data of the missing area according to the basic ecological monitoring data to obtain supplementary ecological monitoring data, wherein the supplementary processing includes basic supplementary processing and historical supplementary processing;

[0014] An ecological impact analysis module, for collecting missing feature information of the missing area based on big data, performing ecological impact analysis, and obtaining ecological impact parameters, wherein the ecological impact parameters include multiple range ecological impact coefficients within multiple distance ranges;

[0015] A neighboring data indexing module is used to divide and obtain multiple neighboring areas in the target area according to the location information of the missing area, index and obtain multiple neighboring ecological monitoring data of the multiple neighboring areas, and divide them into multiple range ecological monitoring data sets according to the distance from the missing area;

[0016] An ecological impact correction module, used to analyze the ecological impact of the missing area on the normal area according to the multiple range ecological monitoring data sets, and correct the ecological impact parameters;

[0017] The ecological restoration analysis module is used to analyze and generate missing ecological monitoring data based on the corrected ecological impact parameters in combination with the supplementary ecological monitoring data, generate the current ecological monitoring data of the target area in combination with the basic ecological monitoring data, and analyze and obtain the ecological restoration effectiveness monitoring results.

[0018] According to a third aspect of the present application, a computer device is provided, comprising a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the steps of the method in the first aspect are implemented.

[0019] According to a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method in the first aspect are implemented.

[0020] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0021] The technical solution provided by this application is to identify and mark the missing areas of the target area to be monitored for the effectiveness of ecological restoration, and collect ecological monitoring data of normal areas outside the missing areas to obtain basic ecological monitoring data. Based on the basic ecological monitoring data, the ecological monitoring data of the missing areas are supplemented and processed to obtain supplementary ecological monitoring data, and then ecological impact analysis is performed based on the missing characteristic information of the missing areas to obtain ecological impact parameters, and further combined with multiple adjacent ecological monitoring data of multiple adjacent areas of the current missing area, the accuracy of the ecological impact parameters is analyzed and corrected, and then combined with the supplementary ecological monitoring data, the missing ecological monitoring data is analyzed and generated to analyze the effectiveness of ecological restoration. This application takes into account the problem of areas that cannot be collected in the ecological restoration analysis, supplements and corrects the ecological monitoring data for the missing areas, and by considering the characteristics of regional ecological data, sets specific strategies to improve the accuracy of the missing ecological monitoring data, comprehensively and accurately evaluates the ecological restoration effectiveness of the target area, improves the accuracy and efficiency of the monitoring and analysis of the effectiveness of ecological restoration, provides a scientific basis for ecological restoration decision-making, and achieves the technical effect of improving the accuracy of the monitoring and analysis of the effectiveness of ecological restoration. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A flowchart of an ecological restoration effectiveness monitoring method based on big data analysis provided for this application;

[0023] Figure 2 A schematic diagram of the process of correcting ecological impact parameters in an ecological restoration effectiveness monitoring method based on big data analysis provided in this application;

[0024] Figure 3 A schematic diagram of the structure of an ecological restoration effectiveness monitoring system based on big data analysis provided for this application;

[0025] Figure 4 A schematic diagram of the structure of an exemplary computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0026] The present application provides an ecological restoration effectiveness monitoring method and system based on big data analysis, which is used to solve the technical problem of incomplete and inaccurate ecological restoration effectiveness monitoring and analysis in the prior art. Example 1

[0027] like Figure 1 As shown, the present application provides an ecological restoration effectiveness monitoring method based on big data analysis, the method comprising:

[0028] S101: Identify and mark missing areas in the target areas for ecological restoration effectiveness monitoring, and collect ecological monitoring data of normal areas outside the missing areas to obtain basic ecological monitoring data;

[0029] In the embodiment of the present application, the target area is an area where ecological restoration has been carried out and where ecological restoration effectiveness monitoring and analysis is to be performed, for example, an area with any terrain, such as an area in a desert Gobi where afforestation and ecological restoration are being carried out.

[0030] When monitoring the effectiveness of ecological restoration, there will be problems in some areas where ecological monitoring data cannot be collected. For example, some areas become private areas or areas where ecological data cannot be collected due to development, planning, use, construction, etc., thus forming areas where ecological monitoring data is missing. Ecological monitoring data cannot be collected in missing areas, which affects the accuracy of the ecological restoration effectiveness analysis.

[0031] Identify and mark the missing areas in the target area to determine the missing areas where ecological data cannot be collected, and then collect ecological monitoring data from other normal areas, that is, the areas in the target area outside the missing areas, to obtain basic ecological monitoring data.

[0032] Among them, the collected ecological monitoring data is determined according to the ecological restoration projects in the target areas, such as vegetation coverage, water quality parameters, soil composition, biodiversity and other data.

[0033] Step S101 of the method provided in the embodiment of the present application includes:

[0034] Based on big data, we can identify the target area for ecological data collection and identify the areas where ecological monitoring data cannot be collected as missing areas, and the areas where ecological monitoring data can be collected as normal areas.

[0035] Collect ecological monitoring data of the normal area to obtain basic ecological monitoring data.

[0036] In the embodiment of the present application, based on big data, it is monitored which data in the target area cannot be collected for ecological data, such as private areas or areas where data cannot be collected due to other reasons, and the locations of these areas are further identified, such as using GIS tools to accurately identify and locate the missing areas. These areas are marked on the map, and their spatial coordinates and boundary information are established to obtain the missing areas.

[0037] Other areas where ecological data can be collected are marked as normal areas.

[0038] Collect ecological monitoring data in normal areas, for example, through temperature sensors, humidity sensors, water quality sensors, etc., to monitor environmental parameters in real time, and through satellite remote sensing and drone technology, obtain a wide range of ecological data, including vegetation coverage, terrain characteristics, water body distribution and other ecological data, complete the collection of ecological monitoring data in normal areas, and obtain basic ecological monitoring data.

[0039] S102: supplementing the ecological monitoring data of the missing area according to the basic ecological monitoring data to obtain supplementary ecological monitoring data, wherein the supplementary processing includes basic supplementary processing and historical supplementary processing;

[0040] In the embodiment of the present application, since ecological monitoring data cannot be collected in the missing area, it is necessary to supplement the ecological monitoring data of the missing area to improve the accuracy and comprehensiveness of the analysis of the ecological restoration effectiveness in the target area.

[0041] Specifically, the ecological monitoring data of adjacent areas are correlated, and the ecological monitoring data of the missing area is supplemented and processed based on the basic ecological monitoring data of the normal area.

[0042] In addition, previous ecological monitoring data of an area is also correlated with current ecological monitoring data.

[0043] Therefore, based on the basic ecological monitoring data and the ecological monitoring data that could have been collected in the missing areas before, such as the ecological data during the time before the missing areas were planned as areas where ecological data could not be collected, supplementary processing of the ecological monitoring data of the missing areas is carried out.

[0044] Exemplarily, the supplementation process includes a basic supplementation process and a historical supplementation process.

[0045] For example, the ecological data of the missing area can be supplemented by spatial interpolation. Spatial interpolation uses mathematical algorithms, such as inverse distance weighted method, natural neighbor interpolation, nearest neighbor interpolation, etc., based on the ecological monitoring data of the normal area to infer the ecological data of the missing area. And based on the previous ecological monitoring data of the missing area, through time series analysis, such as time series analysis using machine learning, the ecological data of the missing area at the current time is predicted to supplement the ecological monitoring data of the current missing area.

[0046] Step S102 in the method provided in the embodiment of the present application includes:

[0047] Collecting regional characteristic information of the missing area and indexing to obtain multiple homologous areas;

[0048] Collecting a set of sample ecological monitoring data sequences for the plurality of homogeneous areas, and collecting a set of sample historical supplementary ecological monitoring data;

[0049] Using the sample ecological monitoring data sequence set and the sample historical supplementary ecological monitoring data set to train a historical ecological data compensation branch;

[0050] According to the historical ecological monitoring data of the target area, the missing ecological monitoring data sequence of the missing area is collected and input into the historical ecological data compensation branch, and the historical supplementary ecological monitoring data is obtained through supplementary analysis;

[0051] The ecological monitoring data of the missing area are subjected to basic supplementary processing to obtain basic supplementary ecological monitoring data, which are combined with the historical supplementary ecological monitoring data to obtain supplementary ecological monitoring data by calculation.

[0052] In the embodiment of the present application, the regional characteristic information of the missing area is collected by means of remote sensing images, geographic information system (GIS), field survey, etc. Among them, the missing area is preferably a private area where ecological data cannot be collected due to production planning, such as a corporate area or a residential area.

[0053] Collect regional characteristic information of the missing area, such as enterprise type information, enterprise scale information, emission scale information, etc. Also, collect previous geographical characteristic information of the missing area, such as topography, climate, vegetation type, soil composition, water resource conditions, etc., and add it to the regional characteristic information.

[0054] Based on the collected regional characteristic information, a cluster analysis or classification algorithm, such as a KNN algorithm, is used to analyze the similarity between the regional characteristic information, and regions with similar characteristics are identified as homogeneous regions, such as regions in other regions. Multiple homogeneous regions have similar private region characteristic information, as well as similar ecological environment and characteristic information.

[0055] The missing ecological monitoring data are supplemented by the historical ecological monitoring data collected in the previous period when ecological data monitoring and collection was available in the missing area. The missing ecological monitoring data of the missing area are predicted based on the sample data of the same ethnic area.

[0056] In multiple homogeneous regions, we use sensor networks, field sampling, remote sensing technology and other means to collect sample ecological monitoring data in historical time. These data include time series data, which reflect the ecological data status of homogeneous regions in different time periods, and obtain a sample ecological monitoring data series set. We also collect ecological monitoring data at the current time nodes of multiple homogeneous regions as sample data for current ecological monitoring data prediction and obtain a sample historical supplementary ecological monitoring data set.

[0057] The sample ecological monitoring data series set and the sample historical supplementary ecological monitoring data set are used to train the historical ecological data compensation branch. First, the training data is preprocessed, including data cleaning, standardization, and normalization, to ensure data quality and consistency.

[0058] Select a suitable machine learning model, such as a BP neural network, as a network model for predicting and supplementing current ecological monitoring data based on historical ecological monitoring data, use a sample ecological monitoring data sequence set and a sample historical supplementary ecological monitoring data set to train the model, use the sample ecological monitoring data sequence set as the model input, and use the sample historical supplementary ecological monitoring data set as the model output and supervision, adjust the model parameters through training methods such as gradient descent in existing technologies for supervised training, so that it can gradually accurately predict and compensate for the missing ecological monitoring data until the convergence requirements are met, such as the accuracy rate reaches 95%, and a historical ecological data compensation branch is obtained.

[0059] Based on the historical ecological monitoring data of the target area, historical ecological monitoring data of the missing area that has not been formed before is collected to obtain the missing ecological monitoring data sequence, which is input into the historical ecological data compensation branch to predict and supplement the current ecological monitoring data, and supplementary analysis is performed to obtain historical supplementary ecological monitoring data.

[0060] The historical supplementary ecological monitoring data supplemented by historical data analysis also needs to be supplemented with missing data based on the basic ecological monitoring data of other areas in the current target area to obtain basic supplementary ecological monitoring data to improve accuracy. For example, supplementary processing can be performed through spatial interpolation, machine learning and other methods. Combined with the historical supplementary ecological monitoring data supplemented by historical data, the supplementary ecological monitoring data is calculated.

[0061] Exemplarily, the mean of the ecological monitoring data in the historical supplementary ecological monitoring data and the basic supplementary ecological monitoring data is calculated, or a weighted calculation is performed to obtain ecological monitoring data based on the fusion of historical ecological monitoring data and ecological monitoring data in other adjacent areas. In this way, the ecological monitoring data of the missing areas are supplemented with higher accuracy.

[0062] The step of "performing basic supplementary processing on the ecological monitoring data of the missing area" in the method provided in the embodiment of the present application includes:

[0063] According to the location information of the missing area, multiple boundary areas farthest from the missing area are indexed in the target area, and multiple boundary ecological monitoring data are indexed in the basic ecological monitoring data;

[0064] Collect multiple sample boundary ecological monitoring data sets and sample base supplementary ecological monitoring data sets based on historical ecological monitoring data of the target area;

[0065] Using the plurality of sample boundary ecological monitoring data sets and the sample basic supplementary ecological monitoring data sets, training to obtain a basic ecological data compensation branch;

[0066] Based on the basic ecological data compensation branch, basic supplementary processing is performed according to the multiple boundary ecological monitoring data to obtain basic supplementary ecological monitoring data.

[0067] In an embodiment of the present application, according to the geographical location information of the missing area identified in the foregoing content, including its boundary and center coordinates, multiple boundary areas farthest from the missing area are identified within the target area based on the geographic information system (GIS) and spatial analysis tools. These boundary areas should be the areas farthest from the missing area. For example, the target area can be divided into regions, such as according to geographical features or according to regional area, and then the distance between each area and the missing area is calculated, and the multiple areas with the largest distance are used as multiple boundary areas. In the basic ecological monitoring data, according to the location coordinates of multiple boundary areas, the ecological monitoring data of these boundary areas are indexed and extracted to obtain multiple boundary ecological monitoring data.

[0068] Due to the reasons for the formation of missing areas, such as planning of enterprises and residences in the missing areas, human activities in the missing areas will have an impact on the ecological monitoring data of the surrounding areas. Therefore, the ecological monitoring data of the boundary areas far away from the missing areas are used to supplement the ecological monitoring data of the missing areas. The ecological monitoring data of the boundary areas are least affected by the missing areas, and the accuracy of supplementing the ecological monitoring data of the missing areas is the highest.

[0069] Based on the historical ecological monitoring data of the target area, the previous historical ecological monitoring data of multiple boundary areas and the previous historical ecological monitoring data of missing areas are collected. During the collection process, it is ensured that a sufficiently long time span and frequency are covered to improve the accuracy of the supplementary processing, and multiple sample boundary ecological monitoring data sets for multiple boundary areas and sample-based supplementary ecological monitoring data sets for missing areas are obtained.

[0070] The multiple sample boundary ecological monitoring data sets and the sample basic supplementary ecological monitoring data sets are used as training data, and a machine learning model, such as a BP neural network, is used to construct and supervise the training of a basic ecological data compensation branch until the requirements are met. Multiple sample boundary ecological monitoring data sets are used as model input, and the sample basic supplementary ecological monitoring data set is used as model output and supervision. The gradient descent training method in the prior art can be used for supervised training, and the model parameters are adjusted according to the error until the training meets the requirements, such as convergence or the accuracy rate meets 95%, to obtain a trained basic ecological data compensation branch.

[0071] Furthermore, the cross-validation method can be used to evaluate the performance of the basic ecological data compensation branch and make parameter adjustments to ensure the generalization ability and prediction accuracy of the model.

[0072] Based on the basic ecological data compensation branch that has been trained, the current multiple boundary ecological monitoring data are input and basically supplemented, the current ecological monitoring data of the missing area is predicted, and the basic supplementary ecological monitoring data for the missing area based on the current ecological monitoring data of multiple boundary areas is obtained. The historical supplementary ecological monitoring data is further combined to obtain the supplementary ecological monitoring data of the missing area, for example, the mean of the vegetation coverage, water quality data, etc. in the historical supplementary ecological monitoring data and the supplementary ecological monitoring data is calculated to obtain the supplementary ecological monitoring data.

[0073] S103: Based on the big data, missing feature information of the missing area is collected, ecological impact analysis is performed, and ecological impact parameters are obtained, wherein the ecological impact parameters include multiple range ecological impact coefficients within multiple distance ranges;

[0074] In the embodiments of the present application, the ecological monitoring data of the missing area is supplemented based on historical ecological data and ecological data of other regions in the aforementioned content, and the ecological monitoring data of the missing area is obtained without being affected by human activities. However, due to human activities in the missing area, the ecology of the missing area will be affected. Therefore, it is necessary to analyze the impact of the missing area on the ecological data, and then conduct a post-impact analysis on the supplemented ecological monitoring data to improve the accuracy of the supplementation under the influence of the ecological monitoring data of the missing area.

[0075] Based on big data, the missing characteristic information of the missing areas is collected. For example, through the relevant planning data of the missing areas, the characteristic data such as the scale of enterprises or residences in the missing areas, emission information, etc. are obtained to reflect the scale of human activities in the missing areas.

[0076] Based on the missing feature information, an ecological impact analysis is performed to obtain ecological impact parameters, which include the impact parameters of the missing feature information on the missing area and multiple ecological impact coefficients on adjacent areas of different ranges, such as the impact amplitude on vegetation coverage or water quality parameters in the missing area and adjacent areas of different ranges.

[0077] Step S103 in the method provided in the embodiment of the present application includes:

[0078] Based on big data, collecting missing feature information of the missing area;

[0079] According to the sample data of the sample-missing area, a set of sample-missing feature information is collected, and a set of sample ecological impact parameters is collected to train an ecological impact analyzer;

[0080] Based on the ecological impact analyzer, an ecological impact analysis is performed on the missing feature information to obtain ecological impact parameters, wherein the ecological impact parameters include a regional ecological impact coefficient and multiple range ecological impact coefficients within multiple distance ranges.

[0081] In an embodiment of the present application, based on big data, such as planning data of missing areas, public activity data, etc., characteristic information of human activities in missing areas, such as enterprise scale information, residential population information, emission information, etc., is collected as missing characteristic information.

[0082] Select sample missing areas with similar characteristics to the missing areas as training samples. The sample areas should have similar geographical and ecological characteristics to the missing areas, as well as similar human activity characteristic information. Collect characteristic information of these sample missing areas, including enterprise scale information, residential population information, emission information, such as carbon emissions, to form a sample missing characteristic information set.

[0083] According to the ecological impact data of the sample-missing area on its own area and the data on the surrounding ecology, a set of sample ecological impact parameters is collected. For example, the sample ecological impact parameters include the ecological impact coefficient on the local area, such as the magnitude of water quality changes, soil erosion, and vegetation coverage changes, such as the ecological impact coefficient is a 10% reduction in vegetation coverage, etc. In addition, the sample ecological impact parameters include the ecological impact coefficients of surrounding areas with different distance ranges, such as the ecological impact coefficients within 5km and 5km-10km, such as the magnitude of water quality changes, soil erosion, and vegetation coverage changes, such as the ecological impact coefficient is a 7% reduction in vegetation coverage in the area within 5km, etc. In this way, a set of sample ecological impact parameters is obtained.

[0084] Furthermore, based on machine learning, an ecological impact analyzer is constructed to analyze the regional ecological impact coefficient according to the missing feature information of the missing area, for example, it is constructed based on a feedforward neural network, and then the ecological impact analyzer is trained using the sample missing feature information set and the sample ecological impact parameter set. For example, the gradient descent training method in the prior art is used to iteratively adjust the model parameters of the ecological impact analyzer, the sample missing feature information set is used as the input of the ecological impact analyzer, and the sample ecological impact parameter set is used as the output and supervision of the ecological impact analyzer. According to the error between the output data and the supervision data, the parameters of the ecological impact analyzer are iteratively optimized and adjusted to enable it to accurately analyze the ecological impact parameters of the missing area until the accuracy of the ecological impact analyzer meets the requirements, for example, the accuracy reaches 90%.

[0085] Based on the trained ecological impact analyzer, the missing feature information is input and the ecological impact analysis is performed to obtain the ecological impact parameters, so as to obtain the ecological impact coefficient of the missing feature information on the missing area and the surrounding areas within different distance ranges, and obtain the regional ecological impact coefficient and multiple range ecological impact coefficients within multiple distance ranges.

[0086] By analyzing the impact on ecological data in missing areas, this can be used as a basis for adjusting the impact of supplementary data in missing areas, thereby improving the accuracy of ecological monitoring data in missing areas currently obtained under ecological influences.

[0087] S104: According to the location information of the missing area, a plurality of adjacent areas are divided in the target area, multiple adjacent ecological monitoring data of the plurality of adjacent areas are indexed and obtained, and the data are divided into a plurality of range ecological monitoring data sets according to the distance from the missing area;

[0088] In the embodiment of the present application, GIS data and positioning data are used to accurately locate the geographical location of the missing area, including information such as its boundaries and center coordinates.

[0089] According to the location information of the missing area, multiple neighboring areas closest to the missing area in the target area are determined, specifically including multiple neighboring areas with different distances, such as multiple areas within a distance of 5km, and multiple areas within a distance of 5km to 10km, etc., to obtain multiple neighboring areas.

[0090] Further, in the aforementioned basic ecological monitoring data, ecological monitoring data of multiple adjacent areas are indexed to obtain multiple adjacent ecological monitoring data. Then, according to the distances between the multiple adjacent areas and the missing area, the adjacent ecological monitoring data of adjacent areas with the same distance range are classified to obtain multiple range ecological monitoring data sets. Each range ecological monitoring data set includes ecological monitoring data in multiple areas with the same distance range as the missing area.

[0091] S105: Analyzing the ecological impact of the missing area on the normal area according to the multiple range ecological monitoring data sets, and revising the ecological impact parameters;

[0092] In the embodiment of the present application, the ecological monitoring data in multiple neighboring areas are truly affected by human activities in the missing area. Therefore, multiple range ecological monitoring data sets of neighboring areas in multiple different distance ranges can reflect the real ecological impact of the missing area on the surrounding neighboring areas. Therefore, based on the multiple range ecological monitoring data sets, an ecological impact analysis of the missing area on the normal area is performed, and according to the real ecological impact analysis results, the ecological impact parameters are corrected to obtain accurate impact parameters of the missing area on ecological restoration.

[0093] like Figure 2 As shown, step S105 in the method provided in the embodiment of the present application includes:

[0094] Calculating multiple ecological change coefficient sets based on the multiple range ecological monitoring data sets, and performing weighted calculation to obtain multiple ecological change coefficients;

[0095] Calculate multiple accuracy coefficients based on the multiple range ecological impact coefficients and the multiple ecological change coefficients, and perform weighted calculation to obtain a total accuracy coefficient;

[0096] According to the total accuracy coefficient, the regional ecological impact coefficient within the ecological impact parameter is corrected and calculated to obtain a corrected regional ecological impact coefficient.

[0097] In an embodiment of the present application, based on ecological monitoring parameters such as vegetation coverage, water quality parameters, soil composition, etc. in the multiple range ecological monitoring data sets, the change range of the ecological monitoring data at different distance ranges from the missing area is calculated to obtain multiple sets of ecological change coefficients.

[0098] Exemplarily, in one direction, such as the north direction of the missing area, based on the range ecological monitoring data of multiple areas adjacent to the missing area in one direction with different distances from the missing area, such as the range ecological monitoring data of the area within 5 km and the range ecological monitoring data of the area within 5-10 km, the change range of the range ecological monitoring data, such as the change range of vegetation coverage or water quality parameters, is calculated as an ecological change coefficient. For example, the vegetation coverage of the area within 5 km is 25%, and the vegetation coverage of the area within 5-10 km is 30%. Then the ecological change coefficients of the two areas are (30%-25%) / 30%=0.167. Then, the ecological change coefficients of multiple groups of adjacent areas in the north direction can be calculated to obtain a set of ecological change coefficients in the north direction. Further, multiple sets of ecological change coefficients of ecological monitoring data in multiple range areas in all directions of the missing area can be calculated.

[0099] Further, the ecological change coefficients of multiple areas within the same distance range in the multiple ecological change coefficient sets are weighted and calculated to obtain multiple ecological change coefficients. For example, according to the size of multiple areas within the same distance range, the ecological change coefficients of multiple areas within the same distance range are assigned weights and weighted calculations, and the weight size is proportional to the area size. For example, if the area size of two areas within the same distance range is 20 mu and 30 mu, the weights assigned are 0.4 and 0.6 respectively, and then the ecological change coefficients of the two areas are weighted. For example, if the ecological change coefficients of the two areas are 0.167 and 0.2, the weighted calculated ecological change coefficient is 0.4*0.167+0.6*0.2=0.1868. Alternatively, weights and weighted calculations are assigned according to the quality of ecological monitoring data of multiple areas within the same distance range. The better the ecological monitoring data, the greater the weight. In this way, multiple total ecological change coefficients of multiple distance range areas affected by the missing areas are obtained.

[0100] According to the multiple ecological change coefficients, combined with the multiple range ecological impact coefficients in the ecological impact parameters in the aforementioned content, the accuracy of the multiple theoretical range ecological impact coefficients based on the missing feature information analysis is calculated. Among them, the ecological change coefficient reflects the ecological impact coefficient of the actual missing area on the adjacent areas of different distance ranges, and the range ecological impact coefficient is the ecological impact coefficient of the theoretical missing area on the adjacent areas of different distance ranges obtained by the missing feature information analysis. Based on the actual multiple ecological change coefficients, the accuracy of the multiple distance range ecological impact coefficients is calculated, and then the coefficient of the missing feature information in the missing area on the ecological impact of the missing area is corrected.

[0101] For example, the deviation amplitudes of multiple range ecological impact coefficients and multiple ecological variation coefficients of multiple distance ranges are calculated respectively to obtain multiple accuracy coefficients. For example, the difference between multiple range ecological impact coefficients and multiple ecological variation coefficients and the ratio of multiple range ecological impact coefficients are calculated, and then 1 is subtracted from the ratio to obtain multiple accuracy coefficients.

[0102] Further weighted calculation is performed on multiple accuracy coefficients to obtain the total accuracy coefficient of the ecological impact coefficient of the total missing area on the surrounding area. The total accuracy coefficient can reflect the accuracy of the ecological impact parameter, and then the regional ecological impact coefficient can be corrected to improve its accuracy. Exemplarily, weights are assigned according to the distance between multiple distance ranges and the missing area, and multiple accuracy coefficients are weighted and calculated, wherein the smaller the distance range, the greater the weight, and the size of the distance is inversely proportional to the size of the weight. For example, the weights of the distance ranges of 0-5km, 5-10km and 10-15km are 0.5, 0.33 and 0.17 respectively, and the accuracy coefficients of the three distance ranges are 0.8, 0.7 and 0.75 respectively, then the calculated total accuracy coefficient is 0.5*0.8+0.33*0.7+0.17*0.75=0.7585.

[0103] According to the total accuracy coefficient, the regional ecological impact coefficient within the aforementioned ecological impact parameter is corrected and calculated, for example, the product of the regional ecological impact coefficient and the total accuracy coefficient is calculated to obtain a more accurate corrected regional ecological impact coefficient after correction, which reflects the true impact of the missing characteristic information of the missing area on the ecological parameters of the missing area. Among them, for example, the regional ecological impact coefficient of the ecological impact of the missing characteristic information on the missing area (such as the impact on water quality) in the aforementioned content is 0.5 (that is, the water quality of the missing area has decreased by 50% due to human activities), and the total accuracy coefficient is 0.7585, then the corrected regional ecological impact coefficient after calculation is 0.37925.

[0104] By analyzing the real ecological change coefficient based on the range ecological monitoring data of neighboring areas within multiple distance ranges, and then analyzing the accuracy of the ecological impact parameters obtained based on the missing characteristic information analysis, the regional ecological impact coefficient of the missing area's ecological impact on the local area's ecology is corrected, thereby improving the accuracy of the analysis of the actual impact of the missing characteristic information on the missing area's ecology.

[0105] S106: Analyze and generate missing ecological monitoring data based on the revised ecological impact parameters in combination with the supplementary ecological monitoring data. Combined with the basic ecological monitoring data, generate the current ecological monitoring data of the target area, and analyze to obtain ecological restoration effectiveness monitoring results.

[0106] In an embodiment of the present application, the supplementary ecological monitoring data of the missing area is obtained by supplementing the missing area according to the corrected ecological impact parameters combined with the aforementioned content, and the ecological monitoring data after being affected by the missing characteristic information, that is, the ecological monitoring data under the influence of the corrected regional ecological impact coefficient, is analyzed as the missing ecological monitoring data that is actually more accurate for the missing area, thereby completing the ecological monitoring data supplementation of the missing area.

[0107] Then, based on the supplementary missing ecological monitoring data and combined with the basic ecological monitoring data of other normal areas, the current complete ecological monitoring data of the target area is generated to carry out monitoring and analysis of the ecological restoration effects.

[0108] Exemplarily, based on the ecological monitoring data of the target area collected last time, combined with the current ecological monitoring data, and based on their changes, an analysis of the effects of ecological restoration is conducted, such as the degree of vegetation restoration, the degree of water quality restoration, etc., to complete the monitoring and analysis of the effectiveness of ecological restoration.

[0109] Step S106 in the method provided in the embodiment of the present application includes:

[0110] According to the revised regional ecological impact coefficient, combined with the supplementary ecological monitoring data, the missing ecological monitoring data are analyzed and generated;

[0111] Based on the missing ecological monitoring data and basic ecological monitoring data, the current ecological monitoring data of the target area is generated, and an ecological restoration effectiveness analysis is conducted to obtain ecological restoration effectiveness monitoring results.

[0112] In the embodiment of the present application, according to the corrected regional ecological impact coefficient of the missing area, combined with the supplementary ecological monitoring data combined with the historical supplementary processing and the basic supplementary processing in the aforementioned content, the missing ecological monitoring data is analyzed and generated. For example, the product of the supplementary ecological monitoring data and the corrected regional ecological impact coefficient is calculated to obtain the missing ecological monitoring data of the missing area that is more realistic after being affected by the missing characteristic information, such as the corrected vegetation coverage data, water quality data, etc. For example, the corrected regional ecological impact coefficient is 0.37925, and the vegetation coverage in the supplementary ecological monitoring data of the missing area is 20% (which is the ecological monitoring data without considering the impact of the missing characteristics), then the real vegetation coverage after the missing characteristic information (i.e., the characteristic information of human activities) of the missing area is 7.585%, that is, the missing ecological monitoring data.

[0113] Based on the corrected missing ecological monitoring data and basic ecological monitoring data, the current ecological monitoring data of the target area is generated, the ecological restoration effectiveness analysis is carried out, and the ecological restoration effectiveness monitoring results are obtained.

[0114] For example, based on the ecological monitoring data obtained from the last ecological restoration effectiveness monitoring in the target area, combined with the ecological monitoring data currently obtained by processing using the method provided in the embodiment of the present application, an ecological restoration effectiveness analysis is performed to determine the ecological restoration effect, such as whether the vegetation coverage has increased or decreased.

[0115] In summary, the embodiments of the present application have at least the following technical effects:

[0116] The technical solution provided by this application is to identify and mark the missing areas of the target area to be monitored for the effectiveness of ecological restoration, and collect ecological monitoring data of normal areas outside the missing areas to obtain basic ecological monitoring data. Based on the basic ecological monitoring data, the ecological monitoring data of the missing areas are supplemented and processed to obtain supplementary ecological monitoring data, and then ecological impact analysis is performed based on the missing characteristic information of the missing areas to obtain ecological impact parameters, and further combined with multiple adjacent ecological monitoring data of multiple adjacent areas of the current missing area, the accuracy of the ecological impact parameters is analyzed and corrected, and then combined with the supplementary ecological monitoring data, the missing ecological monitoring data is analyzed and generated to analyze the effectiveness of ecological restoration. This application takes into account the problem of areas that cannot be collected in the ecological restoration analysis, supplements and corrects the ecological monitoring data for the missing areas, and by considering the characteristics of regional ecological data, sets specific strategies to improve the accuracy of the missing ecological monitoring data, comprehensively and accurately evaluates the ecological restoration effectiveness of the target area, improves the accuracy and efficiency of the monitoring and analysis of the effectiveness of ecological restoration, provides a scientific basis for ecological restoration decision-making, and achieves the technical effect of improving the accuracy of the monitoring and analysis of the effectiveness of ecological restoration. Example 2

[0117] Based on the same inventive concept as the ecological restoration effectiveness monitoring method based on big data analysis in the aforementioned embodiment, Figure 3 As shown, the present application provides an ecological restoration effectiveness monitoring system based on big data analysis. The specific description of an ecological restoration effectiveness monitoring method based on big data analysis in Example 1 is also applicable to the ecological restoration effectiveness monitoring system based on big data analysis, wherein the system includes:

[0118] The missing area identification module 11 is used to identify and mark the missing area of ​​the target area to be monitored for ecological restoration effectiveness, and collect ecological monitoring data of normal areas outside the missing area to obtain basic ecological monitoring data;

[0119] The ecological data supplementation module 12 is used to supplement the ecological monitoring data of the missing area according to the basic ecological monitoring data to obtain supplementary ecological monitoring data, wherein the supplementary processing includes basic supplementary processing and historical supplementary processing;

[0120] The ecological impact analysis module 13 is used to collect missing feature information of the missing area based on big data, perform ecological impact analysis, and obtain ecological impact parameters, wherein the ecological impact parameters include multiple range ecological impact coefficients within multiple distance ranges;

[0121] A neighboring data indexing module 14 is used to divide and obtain multiple neighboring areas in the target area according to the location information of the missing area, index and obtain multiple neighboring ecological monitoring data of the multiple neighboring areas, and divide them into multiple range ecological monitoring data sets according to the distance from the missing area;

[0122] An ecological impact correction module 15, configured to analyze the ecological impact of the missing area on the normal area according to the plurality of range ecological monitoring data sets, and to correct the ecological impact parameters;

[0123] The ecological restoration analysis module 16 is used to analyze and generate missing ecological monitoring data based on the corrected ecological impact parameters in combination with the supplementary ecological monitoring data, generate the current ecological monitoring data of the target area in combination with the basic ecological monitoring data, and analyze and obtain the ecological restoration effectiveness monitoring results.

[0124] Furthermore, the missing area identification module 11 is also used to implement the following functions:

[0125] Based on big data, we can identify the target area for ecological data collection and identify the areas where ecological monitoring data cannot be collected as missing areas, and the areas where ecological monitoring data can be collected as normal areas.

[0126] Collect ecological monitoring data of the normal area to obtain basic ecological monitoring data.

[0127] Furthermore, the ecological data supplement module 12 is also used to implement the following functions:

[0128] Collecting regional characteristic information of the missing area and indexing to obtain multiple homologous areas;

[0129] Collecting a set of sample ecological monitoring data sequences for the plurality of homogeneous areas, and collecting a set of sample historical supplementary ecological monitoring data;

[0130] Using the sample ecological monitoring data sequence set and the sample historical supplementary ecological monitoring data set to train a historical ecological data compensation branch;

[0131] According to the historical ecological monitoring data of the target area, the missing ecological monitoring data sequence of the missing area is collected and input into the historical ecological data compensation branch, and the historical supplementary ecological monitoring data is obtained through supplementary analysis;

[0132] The ecological monitoring data of the missing area are subjected to basic supplementary processing to obtain basic supplementary ecological monitoring data, which are combined with the historical supplementary ecological monitoring data to obtain supplementary ecological monitoring data by calculation.

[0133] Among them, basic supplementary processing of ecological monitoring data of the missing areas is carried out, including:

[0134] According to the location information of the missing area, multiple boundary areas farthest from the missing area are indexed in the target area, and multiple boundary ecological monitoring data are indexed in the basic ecological monitoring data;

[0135] Collect multiple sample boundary ecological monitoring data sets and sample base supplementary ecological monitoring data sets based on historical ecological monitoring data of the target area;

[0136] Using the plurality of sample boundary ecological monitoring data sets and the sample basic supplementary ecological monitoring data sets, training to obtain a basic ecological data compensation branch;

[0137] Based on the basic ecological data compensation branch, basic supplementary processing is performed according to the multiple boundary ecological monitoring data to obtain basic supplementary ecological monitoring data.

[0138] Furthermore, the ecological impact analysis module 13 is also used to implement the following functions:

[0139] Based on big data, collecting missing feature information of the missing area;

[0140] According to the sample data of the sample-missing area, a set of sample-missing feature information is collected, and a set of sample ecological impact parameters is collected to train an ecological impact analyzer;

[0141] Based on the ecological impact analyzer, an ecological impact analysis is performed on the missing feature information to obtain ecological impact parameters, wherein the ecological impact parameters include a regional ecological impact coefficient and multiple range ecological impact coefficients within multiple distance ranges.

[0142] Furthermore, the ecological impact correction module 15 is also used to implement the following functions:

[0143] Calculating multiple ecological change coefficient sets based on the multiple range ecological monitoring data sets, and performing weighted calculation to obtain multiple ecological change coefficients;

[0144] Calculate multiple accuracy coefficients based on the multiple range ecological impact coefficients and the multiple ecological change coefficients, and perform weighted calculation to obtain a total accuracy coefficient;

[0145] According to the total accuracy coefficient, the regional ecological impact coefficient within the ecological impact parameter is corrected and calculated to obtain a corrected regional ecological impact coefficient.

[0146] Furthermore, the ecological restoration analysis module 16 is also used to implement the following functions:

[0147] According to the revised regional ecological impact coefficient, combined with the supplementary ecological monitoring data, the missing ecological monitoring data are analyzed and generated;

[0148] Based on the missing ecological monitoring data and basic ecological monitoring data, the current ecological monitoring data of the target area is generated, and an ecological restoration effectiveness analysis is conducted to obtain ecological restoration effectiveness monitoring results. Example 3

[0149] like Figure 4 As shown, based on the same inventive concept as an ecological restoration effectiveness monitoring method based on big data analysis in the aforementioned embodiment, the present application also provides a computer device 300, wherein the computer device 300 includes a memory 301 and a processor 302, wherein a computer program is stored in the memory 301, and when the computer program is executed by the processor 302, the steps of a method in an embodiment are implemented.

[0150] The computer device 300 includes: a processor 302, a communication interface 303, and a memory 301. Optionally, the computer device 300 may also include a bus architecture 304. The communication interface 303, the processor 302, and the memory 301 may be interconnected via the bus architecture 304; the bus architecture 304 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus architecture 304 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0151] The processor 302 may be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for controlling the execution of the program of the present application.

[0152] The communication interface 303 uses any transceiver-like device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), wired access networks, etc.

[0153] The memory 301 may be a ROM or other types of static storage devices that can store static information and instructions, a RAM or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read only memory (EEPROM), a compact disc (CD ROM) or other optical disc storage, an optical disc storage (including a compressed optical disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory may exist independently and be connected to the processor via a bus architecture 304. The memory may also be integrated with the processor.

[0154] The memory 301 is used to store computer-executable instructions for executing the solution of the present application, and the execution is controlled by the processor 302. The processor 302 is used to execute the computer-executable instructions stored in the memory 301, thereby realizing an ecological restoration effectiveness monitoring method based on big data analysis provided in the above embodiment of the present application. Example 4

[0155] Based on the same inventive concept as the ecological restoration effectiveness monitoring method based on big data analysis in the aforementioned embodiment, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the method in embodiment one are implemented.

[0156] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. The ecological restoration effectiveness monitoring method based on big data analysis is characterized by: The method comprises: Identify and mark missing areas in target areas for ecological restoration effectiveness monitoring, and collect ecological monitoring data from normal areas outside the missing areas to obtain basic ecological monitoring data; According to the basic ecological monitoring data, supplementary processing is performed on the ecological monitoring data of the missing area to obtain supplementary ecological monitoring data, wherein the supplementary processing includes basic supplementary processing and historical supplementary processing; Based on big data, missing feature information of the missing area is collected, ecological impact analysis is performed, and ecological impact parameters are obtained, wherein the ecological impact parameters include multiple range ecological impact coefficients within multiple distance ranges; According to the location information of the missing area, a plurality of adjacent areas are divided in the target area, a plurality of adjacent ecological monitoring data of the plurality of adjacent areas are obtained by indexing, and the adjacent areas are divided into a plurality of range ecological monitoring data sets according to the distance from the missing area; According to the plurality of range ecological monitoring data sets, an ecological impact analysis of the missing area on the normal area is performed, and the ecological impact parameters are corrected; According to the revised ecological impact parameters combined with the supplementary ecological monitoring data, the missing ecological monitoring data are analyzed and generated, and combined with the basic ecological monitoring data, the current ecological monitoring data of the target area is generated, and the ecological restoration effectiveness monitoring results are analyzed and obtained; Among them, according to the basic ecological monitoring data, the ecological monitoring data of the missing area is supplemented and processed to obtain supplementary ecological monitoring data, including: Collecting regional characteristic information of the missing area and indexing to obtain multiple homologous areas; Collect sample ecological monitoring data in historical time in multiple homogeneous regions. The collected data reflects the ecological data status of homogeneous regions in different time periods, and obtain a sample ecological monitoring data series set. Collect ecological monitoring data at current time nodes in multiple homogeneous regions as sample data for predicting and supplementing current ecological monitoring data, and obtain a sample historical supplementary ecological monitoring data set. The sample ecological monitoring data sequence set and the sample historical supplementary ecological monitoring data set are used to train the historical ecological data compensation branch, wherein the training basic ecological data compensation branch is obtained by using the sample ecological monitoring data sequence set as the model input, using the sample historical supplementary ecological monitoring data set as the model output and supervision, and adjusting the model parameters through gradient descent for supervised training; According to the historical ecological monitoring data of the target area, the missing ecological monitoring data sequence of the missing area is collected and input into the historical ecological data compensation branch, and the historical supplementary ecological monitoring data is obtained through supplementary analysis; Performing basic supplementary processing on the ecological monitoring data of the missing area to obtain basic supplementary ecological monitoring data, and combining the historical supplementary ecological monitoring data to calculate and obtain supplementary ecological monitoring data; Basic supplementary processing of ecological monitoring data of the missing areas is carried out, including: According to the location information of the missing area, multiple boundary areas farthest from the missing area are indexed in the target area, and multiple boundary ecological monitoring data are indexed in the basic ecological monitoring data; According to the historical ecological monitoring data of the target area, collect the previous historical ecological monitoring data of multiple border areas and the previous historical ecological monitoring data of the missing areas. In the collection process, ensure that the preset time span and frequency are covered, and obtain multiple sample border ecological monitoring data sets of multiple border areas and sample basic supplementary ecological monitoring data sets of the missing areas; The multiple sample boundary ecological monitoring data sets and the sample basic supplementary ecological monitoring data sets are used to train and obtain a basic ecological data compensation branch, wherein the training of the basic ecological data compensation branch is obtained by using the multiple sample boundary ecological monitoring data sets as model inputs, using the sample basic supplementary ecological monitoring data sets as model outputs and supervision, and adjusting model parameters through gradient descent for supervised training; Based on the basic ecological data compensation branch, basic supplementary processing is performed according to the multiple boundary ecological monitoring data to obtain basic supplementary ecological monitoring data.

2. The method according to claim 1, characterized in that Identify and mark missing areas in the target areas for ecological restoration effectiveness monitoring, and collect ecological monitoring data from normal areas outside the missing areas, including: Based on big data, we can identify the target area for ecological data collection and identify the areas where ecological monitoring data cannot be collected as missing areas, and the areas where ecological monitoring data can be collected as normal areas. Collect ecological monitoring data of the normal area to obtain basic ecological monitoring data.

3. The method according to claim 1, characterized in that Based on big data, the missing feature information of the missing area is collected, and ecological impact analysis is performed to obtain ecological impact parameters, including: Based on big data, collecting missing feature information of the missing area; According to the sample data of the sample-missing area, a set of sample-missing feature information is collected, and a set of sample ecological impact parameters is collected to train an ecological impact analyzer; Based on the ecological impact analyzer, an ecological impact analysis is performed on the missing feature information to obtain ecological impact parameters, wherein the ecological impact parameters include a regional ecological impact coefficient and multiple range ecological impact coefficients within multiple distance ranges.

4. The method according to claim 3, characterized in that Based on the multiple range ecological monitoring data sets, an ecological impact analysis of the missing area on the normal area is performed, including: Calculating multiple ecological change coefficient sets based on the multiple range ecological monitoring data sets, and performing weighted calculation to obtain multiple ecological change coefficients; Calculate multiple accuracy coefficients based on the multiple range ecological impact coefficients and the multiple ecological change coefficients, and perform weighted calculation to obtain a total accuracy coefficient; According to the total accuracy coefficient, the regional ecological impact coefficient within the ecological impact parameter is corrected and calculated to obtain a corrected regional ecological impact coefficient.

5. The method according to claim 4, characterized in that According to the revised ecological impact parameters combined with the supplementary ecological monitoring data, the missing ecological monitoring data are analyzed and generated, including: According to the revised regional ecological impact coefficient, combined with the supplementary ecological monitoring data, the missing ecological monitoring data are analyzed and generated; Based on the missing ecological monitoring data and basic ecological monitoring data, the current ecological monitoring data of the target area is generated, and an ecological restoration effectiveness analysis is conducted to obtain ecological restoration effectiveness monitoring results.

6. An ecological restoration effectiveness monitoring system based on big data analysis, characterized in that: The system comprises: The missing area identification module is used to identify and mark the missing areas of the target areas for ecological restoration effectiveness monitoring, and collect ecological monitoring data of normal areas outside the missing areas to obtain basic ecological monitoring data; An ecological data supplementation module, used to supplement the ecological monitoring data of the missing area according to the basic ecological monitoring data to obtain supplementary ecological monitoring data, wherein the supplementary processing includes basic supplementary processing and historical supplementary processing; An ecological impact analysis module, for collecting missing feature information of the missing area based on big data, performing ecological impact analysis, and obtaining ecological impact parameters, wherein the ecological impact parameters include multiple range ecological impact coefficients within multiple distance ranges; A neighboring data indexing module is used to divide and obtain multiple neighboring areas in the target area according to the location information of the missing area, index and obtain multiple neighboring ecological monitoring data of the multiple neighboring areas, and divide them into multiple range ecological monitoring data sets according to the distance from the missing area; An ecological impact correction module, used to analyze the ecological impact of the missing area on the normal area according to the multiple range ecological monitoring data sets, and correct the ecological impact parameters; The ecological restoration analysis module is used to analyze and generate missing ecological monitoring data based on the revised ecological impact parameters in combination with the supplementary ecological monitoring data, generate the current ecological monitoring data of the target area in combination with the basic ecological monitoring data, and analyze and obtain the ecological restoration effectiveness monitoring results; Among them, according to the basic ecological monitoring data, the ecological monitoring data of the missing area is supplemented and processed to obtain supplementary ecological monitoring data, including: Collecting regional characteristic information of the missing area and indexing to obtain multiple homologous areas; Collect sample ecological monitoring data in historical time in multiple homogeneous regions. The collected data reflects the ecological data status of homogeneous regions in different time periods, and obtain a sample ecological monitoring data series set. Collect ecological monitoring data at current time nodes in multiple homogeneous regions as sample data for predicting and supplementing current ecological monitoring data, and obtain a sample historical supplementary ecological monitoring data set. The sample ecological monitoring data sequence set and the sample historical supplementary ecological monitoring data set are used to train the historical ecological data compensation branch, wherein the training basic ecological data compensation branch is obtained by using the sample ecological monitoring data sequence set as the model input, using the sample historical supplementary ecological monitoring data set as the model output and supervision, and adjusting the model parameters through gradient descent for supervised training; According to the historical ecological monitoring data of the target area, the missing ecological monitoring data sequence of the missing area is collected and input into the historical ecological data compensation branch, and the historical supplementary ecological monitoring data is obtained through supplementary analysis; Performing basic supplementary processing on the ecological monitoring data of the missing area to obtain basic supplementary ecological monitoring data, and combining the historical supplementary ecological monitoring data to calculate and obtain supplementary ecological monitoring data; Basic supplementary processing of ecological monitoring data of the missing areas is carried out, including: According to the location information of the missing area, multiple boundary areas farthest from the missing area are indexed in the target area, and multiple boundary ecological monitoring data are indexed in the basic ecological monitoring data; According to the historical ecological monitoring data of the target area, collect the previous historical ecological monitoring data of multiple border areas and the previous historical ecological monitoring data of the missing areas. In the collection process, ensure that the preset time span and frequency are covered, and obtain multiple sample border ecological monitoring data sets of multiple border areas and sample basic supplementary ecological monitoring data sets of the missing areas; The multiple sample boundary ecological monitoring data sets and the sample basic supplementary ecological monitoring data sets are used to train and obtain a basic ecological data compensation branch, wherein the training of the basic ecological data compensation branch is obtained by using the multiple sample boundary ecological monitoring data sets as model inputs, using the sample basic supplementary ecological monitoring data sets as model outputs and supervision, and adjusting model parameters through gradient descent for supervised training; Based on the basic ecological data compensation branch, basic supplementary processing is performed according to the multiple boundary ecological monitoring data to obtain basic supplementary ecological monitoring data.

7. A computer device, characterized in that: The computer device comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images