Ecological environment dynamic monitoring method based on remote sensing and geographic information system

Abstract

The invention discloses an ecological environment dynamic monitoring method based on a remote sensing and geographic information system. The method comprises the following steps: establishing an evaluation system of the ecological environment dynamic monitoring method; determining indexes of ecological environment influence factors; acquiring remote sensing satellite data of a measurement area; calculating the coverage rate of vegetation in the measurement area; calculating the water content of soil in the measurement area; calculating the salinity of the land in the measurement area; comprehensively analyzing a calculation result by utilizing a mathematical model; and recording the calculation and analysis result. According to the method, data can be conveniently and quickly acquired by using remote sensing and geographic information systems, the judgment efficiency of a worker on the land salinization degree can be conveniently and effectively improved, meanwhile, errors of measurement results can be reduced through accurate measurement results of remote sensing satellite data, and the accuracy of the measurement results is improved. The method is helpful for workers to accurately judge the degree of land salinization, so that proper improvement schemes can be made according to the actual conditions of different regions.

Description

Technical Field

[0001] The invention relates to the cross-field of computer mathematical model processing and ecological synthesis, and in particular to a method for dynamic monitoring of ecological environment based on remote sensing and geographic information system. Background Art

[0002] With the acceleration of industrialization and urbanization, the impact of human activities on the natural environment has become increasingly significant, and ecological and environmental issues have become the focus of global attention. In order to fully, accurately and timely understand the status of the ecological environment and its changing trends, ecological and environmental monitoring has emerged. Through ecological and environmental monitoring, the status of the ecosystem can be effectively evaluated: the ecological status monitoring aims to grasp the temporal and spatial pattern of the quantity, quality, structure and service functions of the ecosystem and its changing trends, covering all typical ecosystems such as forests, grasslands, wetlands, deserts, water bodies, farmlands, cities, and oceans, which helps to better understand the operating laws of the ecosystem and provide strong support for ecological protection. At the same time, the results of ecological and environmental monitoring can provide a scientific basis for the formulation of environmental protection policies. Through the analysis and evaluation of monitoring data, environmental protection policies can be formulated more accurately to improve the effectiveness and pertinence of policies.

[0003] Land salinization refers to the process in which salt in the bottom soil or groundwater rises to the surface with capillary water, and after the water evaporates, the salt accumulates in the surface soil. Land salinization will destroy the soil structure, reduce crop yields, and affect the daily life of residents. The subsequent treatment of land salinization often requires a lot of manpower, material and financial resources. Therefore, it is very necessary to predict and prevent land salinization in the region.

[0004] Chinese invention patent CN 113869689A2 discloses a method for dynamic monitoring of the ecological environment based on remote sensing and geographic information systems, including: completing the construction of an ecological environment indicator system and data processing; building a hydrodynamic model and debugging it; implementing the construction and analysis of an ecological environment quality evaluation model; debugging the ecological environment quality evaluation model, calibrating and verifying the results; analyzing the obstacle degree of the ecological environment quality and formulating an ecological restoration strategy. This invention simply realizes the production of precision stamping dies, and does not conduct quality inspections on the products produced. This invention can derive the degree of threat to the reservoir area under specific working conditions through the constructed hydrodynamic-water quality model, providing a reference for monitoring and early warning. However, it cannot judge and improve the degree of salinization of the land from multiple angles. Summary of the invention

[0005] The present invention provides a method for dynamic monitoring of the ecological environment based on remote sensing and geographic information systems. The use of remote sensing and geographic information systems can collect data conveniently and quickly, and can conveniently and effectively improve the efficiency of staff in judging the degree of land salinization. At the same time, through the precise measurement results of remote sensing satellite data, the error of the measurement results can be reduced, which helps staff to accurately judge the degree of land salinization, so as to formulate appropriate improvement plans according to the actual conditions in different regions.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] The present invention provides a method for dynamic monitoring of ecological environment based on remote sensing and geographic information system, comprising:

[0008] S1 Establish an evaluation system for dynamic ecological environment monitoring methods;

[0009] S2 Establish indicators of factors affecting the ecological environment;

[0010] S3 obtains remote sensing satellite data of the survey area;

[0011] S4 calculates the vegetation coverage in the measurement area;

[0012] S5 calculates the water content of the soil in the measurement area;

[0013] S6 calculates the salinity of the land in the measurement area;

[0014] S7 uses mathematical models to comprehensively analyze the calculation results;

[0015] S8 records the results of this calculation and analysis.

[0016] The beneficial effects brought about by the technical solution provided by the present invention include at least:

[0017] The present invention uses an evaluation system for establishing a dynamic monitoring method for the ecological environment; establishes indicators of factors affecting the ecological environment; obtains remote sensing satellite data of the measurement area; calculates the coverage of vegetation in the measurement area; calculates the water content of the soil in the measurement area; calculates the salinity of the land in the measurement area; uses a mathematical model to comprehensively analyze the calculation results; and records the results of this calculation and analysis. The method of the present invention can measure the degree of land salinization in different periods through satellite data, and accurately detect the measurement conditions, thereby helping and facilitating the staff to accurately determine the cause of land salinization in the measurement area, so as to formulate appropriate improvement plans according to the actual conditions of different regions and reduce the cost of land salinization improvement. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 is a flow chart of a method for dynamic monitoring of ecological environment based on remote sensing and geographic information system provided by an embodiment of the present invention;

[0020] Figure 2 A schematic diagram of a soil moisture detection implementation technique provided by an embodiment of the present invention;

[0021] Figure 3 A schematic diagram of the training of the adaptive enhancement algorithm model provided by an embodiment of the present invention;

[0022] Figure 4 A schematic diagram of the land salinization degree analysis process provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0023] In order to make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0024] Example

[0025] A dynamic monitoring method of ecological environment based on remote sensing and geographic information system.

[0026] Please refer to Figure 1 It is a flow chart of a method for dynamic monitoring of ecological environment based on remote sensing and geographic information system provided by an embodiment of the present invention.

[0027] S1 Establish an evaluation system for dynamic ecological environment monitoring methods;

[0028] S101, the evaluation system of the ecological environment monitoring method shall refer to "HJ 1320-2023 Technical Guidelines for Ground Observation and Verification of Ecological Remote Sensing";

[0029] It should be noted that the actual testing process is not limited to this, and other relevant standard documents can be introduced as reference and basis according to the testing requirements.

[0030] S102, select the surface radiation characteristics and surface ecosystem characteristics in the technical guidelines as observation parameters;

[0031] S103, the surface radiation characteristics include surface reflectivity, surface albedo, and surface temperature;

[0032] S104, the surface ecosystem characteristics include leaf area index, vegetation coverage, photosynthetically active radiation absorption ratio, and soil moisture content.

[0033] It should be noted that only the main test parameters in the technical guidelines are selected here. In the actual test process, other parameters in the guidelines can also be taken as a reference to improve the accuracy of the test data.

[0034] S2 Establish indicators of factors affecting the ecological environment;

[0035] S201, the index of the influencing factor selects the index factor in ERSEI and combines it with the parameters in the technical guidelines as the main detection conditions;

[0036] It should be noted that the ERSEI improved remote sensing ecological index also includes dryness factor, heat factor, and water network density factor. In the actual detection process, the ecological index factor can be increased or decreased according to the temperature, climate, altitude, and geographical characteristics of the measurement area.

[0037] S202, the indicators of the influencing factors of the ecological environment include vegetation greenness, soil moisture, and salt content in the land.

[0038] S3 obtains remote sensing satellite data of the area to be measured;

[0039] S301, the remote sensing satellite data may be MODIS remote sensing image data, Google Earth cloud platform, or geospatial data cloud as a source;

[0040] It should be noted that the remote sensing satellite data is not limited thereto, and any satellite remote sensing data that meets the standards can be used as a reference.

[0041] S302, the satellite data needs to select a characteristic time period and an average time period of the measurement area respectively;

[0042] S303: The characteristic time period of the measurement area includes a flood period and a drought period.

[0043] It should be noted that the characteristic period refers to satellite remote sensing data in a short period of time, such as one to three months, and the average period refers to satellite remote sensing data in a long period of time, such as half a year or one year. By comparing the detection results of the characteristic period with the detection results of the average period, the changing trend of land salinization in the measured area in different periods can be obtained.

[0044] The S4 calculates the coverage rate of vegetation in the measurement area;

[0045] S401, the vegetation coverage rate is calculated by using a threshold method on the collected satellite data;

[0046] It should be noted that the threshold value of the threshold method needs to refer to the environment of the measurement area, such as plains, mountains, and plateaus. The threshold value needs to be appropriately increased or decreased according to the vegetation types in different regions so that the detection results meet the local ecological conditions.

[0047] S402, the threshold method uses the RGB vegetation index of the measurement area to screen and select qualified vegetation index as reference data, as shown in formulas (S4-1 to S4-5);

[0048]

[0049] EXG=2G-RB S4-2

[0050]

[0051] Wherein, RGRI is the red-green ratio index; EXG is the overgreen index; VDVI is the visible light band difference vegetation index; R, G, and B are the pixel values ​​of the red, green, and blue bands, respectively.

[0052] S403, normalizing the collected pixel values, and obtaining the vegetation coverage rate based on the normalized result comparison, as shown in formulas (S4-4 to S4-5);

[0053]

[0054] Where NGRDI is the normalized green-red difference index; NGBDI is the normalized green-blue difference index; r, g, and b are the pixel values ​​of the red, green, and blue bands after normalization, respectively.

[0055] S5 calculates the water content of the soil in the measurement area;

[0056] Please refer to Figure 2 It is a schematic diagram of the technical flow of implementing soil moisture detection provided by an embodiment of the present invention.

[0057] It should be noted that the moisture content of the soil needs to focus on the characteristic period of the sample area as the main reference, and be judged from multiple angles in combination with the local precipitation and groundwater content.

[0058] S501, the soil moisture content is calculated using the GNSS-IR global satellite navigation system interferometry method to obtain a SRN signal-to-noise ratio data value, as shown in formula (S5-1);

[0059]

[0060] D=2HsinθS5-2

[0061]

[0062] In the formula, A d and A m are the amplitudes of the reflected signal and the direct signal respectively; ψ is the phase difference; D is the optical path difference; θ is the satellite altitude angle; H is the distance from the phase center to the reflecting surface; λ is the carrier wavelength.

[0063] S502, calculating the multipath signal-to-noise ratio interference phase according to the SRN, and obtaining the correlation between the soils according to the interference phase, as shown in formulas (S5-2 to S5-3);

[0064]

[0065] In the formula, is the interference phase of the reflected component; A MP is the multipath signal-to-noise ratio oscillation amplitude; is the multipath signal-to-noise ratio interferometric phase.

[0066] S6 calculates the salinity of the land in the measurement area;

[0067] It should be noted that the salinity of the land needs to be combined with the vegetation types in the reference measurement area, such as the distribution of agriculture and forestry.

[0068] S601, extracting the distribution of vegetation using a random forest algorithm, and calculating the salt content of the land according to the distribution of vegetation;

[0069] S602, using the Adaboost adaptive boosting algorithm to build an inversion model of soil salinity, and updating the weights of the training samples by finding the weights of the weak learning machine, as shown in the formula;

[0070] E k =max|y i -G k (x i )| S6-1

[0071]

[0072]

[0073] In the formula, i is the i-th sample; m is the number of samples; x i is the feature of the i-th sample; y i is the true value of soil salt content in the i-th sample; G k is the kth weak learner; G k (x i ) is the predicted value of the weak learner based on the sample; w ki is the weight distribution of the current training data.

[0074] See also Figure 3 Schematic diagram of adaptive enhancement algorithm model training provided by an embodiment of the present invention

[0075] The model uses decision trees as weak learners of the Adaboost algorithm and constructs an AB-DT model to invert soil salinity;

[0076] The results of the AB-DT prediction model can be evaluated using three consistency metrics: determination coefficient, root mean square error, and mean absolute error.

[0077] S7 uses mathematical models to comprehensively analyze the calculation results;

[0078] Please refer to Figure 4 It is a schematic diagram of the technical process of analyzing the degree of land salinization provided by an embodiment of the present invention.

[0079] S701, the mathematical model constructs a BP neural network model and substitutes the calculated results into the model, and analyzes the relationship between the degree of land salinization and the vegetation coverage and the water content of the soil to obtain the cause of land salinization in the measured area, as shown in formula (S7-1);

[0080]

[0081] In the formula, xp is the standardized variable value; xp max and xp min are the maximum and minimum values ​​of the standardized variables respectively; x is the measured variable value; x max and x min are the minimum and maximum values ​​of the measured variables, respectively.

[0082] S702, using the Bayesian algorithm to optimize the analysis results, by setting the weight parameters as random variables, and determining the optimal weight function according to the probability density of the weights, as shown in formula (S7-2);

[0083] f(w)=αE w +βE d S7-2

[0084] Where f(w) is the corrected performance function; E w is the mean square error of all network values; E d is the mean square error of the network output; α and β are regularization parameters.

[0085] S8 records the results of this calculation and analysis, including:

[0086] S801, the calculation and analysis results are stored in a cloud database, and the relationship between the degree of land salinization and the vegetation coverage and soil moisture content is recorded to facilitate subsequent improvement of the degree of salinization in the measurement area;

[0087] S802, the cloud database is used to compare and measure the actual effects of the improvement plan for the degree of salinization in the area, and to predict the results of the improvement plan by establishing a multivariate regression linear model.

[0088] It should be noted that the effectiveness of the improvement plan can be comprehensively judged by comparing the comparison results within a fixed sampling period with the monitoring results within a random period.

[0089] In addition, it should be noted that the present invention can be provided as a method, an apparatus or a computer program product. Therefore, the embodiments of the present invention can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0090] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0091] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, so that a series of operation steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable terminal device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1The steps for the functions specified in one or more boxes.

[0092] It should also be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0093] Finally, it should be noted that the above is a preferred embodiment of the present invention. It should be pointed out that although the preferred embodiment of the present invention has been described, for those skilled in the art, once the basic creative concept of the present invention is known, several improvements and modifications can be made without departing from the principles of the present invention, and these improvements and modifications should also be regarded as the protection scope of the present invention. Therefore, the attached claims are intended to be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the embodiments of the present invention.

Claims

1. A method for dynamic monitoring of ecological environment based on remote sensing and geographic information system, characterized in that: include: S1 Establish an evaluation system for dynamic ecological environment monitoring methods; S2 Establish indicators of factors affecting the ecological environment; S3 obtains remote sensing satellite data of the survey area; S4 calculates the vegetation coverage in the measurement area; S5 calculates the water content of the soil in the measurement area; S6 calculates the salinity of the land in the measurement area; S7 uses mathematical models to comprehensively analyze the calculation results; S8 records the results of this calculation and analysis.

2. The method for dynamic monitoring of ecological environment based on remote sensing and geographic information system according to claim 1, characterized in that: S1 establishes an evaluation system for dynamic monitoring methods of the ecological environment, including: S101, the evaluation system of the ecological environment monitoring method shall refer to "HJ 1320-2023 Technical Guidelines for Ground Observation and Verification of Ecological Remote Sensing"; S102, select the surface radiation characteristics and surface ecosystem characteristics in the technical guidelines as observation parameters; S103, the surface radiation characteristics include surface reflectivity, surface albedo, and surface temperature; S104, the surface ecosystem characteristics include leaf area index, vegetation coverage, photosynthetically active radiation absorption ratio, and soil moisture content.

3. The method for dynamic monitoring of ecological environment based on remote sensing and geographic information system according to claim 1, characterized in that: S2 establishes indicators of factors affecting the ecological environment, including: S201, the index of the influencing factor selects the index factor in ERSEI and combines it with the parameters in the technical guidelines as the main detection conditions; S202, the indicators of the influencing factors of the ecological environment include vegetation greenness, soil moisture, and salt content in the land.

4. The method for dynamic monitoring of ecological environment based on remote sensing and geographic information system according to claim 1, characterized in that: S3 obtains remote sensing satellite data of the area to be measured, wherein: S301, the remote sensing satellite data may be MODIS remote sensing image data, Google Earth cloud platform, or geospatial data cloud as a source; S302, the satellite data needs to select a characteristic time period and an average time period of the measurement area respectively; S303: The characteristic time period of the measurement area includes a flood period and a drought period.

5. The method for dynamic monitoring of ecological environment based on remote sensing and geographic information system according to claim 1, characterized in that: The S4 calculates the coverage of vegetation in the measurement area, where: S401, the vegetation coverage rate is calculated by using a threshold method on the collected satellite data; S402, the threshold method uses the RGB vegetation index of the measurement area to screen and select qualified vegetation index as reference data, as shown in formulas (S4-1 to S4-5); EXG=2G-RB S4-2 Wherein, RGRI is the red-green ratio index; EXG is the overgreen index; VDVI is the visible light band difference vegetation index; R, G, and B are the pixel values ​​of the red, green, and blue bands, respectively. S403, normalizing the collected pixel values, and obtaining the vegetation coverage rate based on the normalized result comparison, as shown in formulas (S4-4 to S4-5); Where NGRDI is the normalized green-red difference index; NGBDI is the normalized green-blue difference index; r, g, and b are the pixel values ​​of the red, green, and blue bands after normalization, respectively.

6. The method for dynamic monitoring of ecological environment based on remote sensing and geographic information system according to claim 1, characterized in that: The S5 calculates the water content of the soil in the measurement area, where: S501, the soil moisture content is calculated using the GNSS-IR global satellite navigation system interferometry method to obtain a SRN signal-to-noise ratio data value, as shown in formula (S5-1); D=2Hsinθ S5-2 In the formula, A d and A m are the amplitudes of the reflected signal and the direct signal respectively; ψ is the phase difference; D is the optical path difference; θ is the satellite altitude angle; H is the distance from the phase center to the reflecting surface; λ is the carrier wavelength. S502, calculating the multipath signal-to-noise ratio interference phase according to the SRN, and obtaining the correlation between the soils according to the interference phase, as shown in formulas (S5-2 to S5-3); In the formula, is the interference phase of the reflected component; A MP is the multipath signal-to-noise ratio oscillation amplitude; is the multipath signal-to-noise ratio interferometric phase.

7. The method for dynamic monitoring of ecological environment based on remote sensing and geographic information system according to claim 1, characterized in that: The S6 calculates the salinity of the land in the measurement area, wherein: S601, extracting the distribution of vegetation using a random forest algorithm, and calculating the salt content of the land according to the distribution of vegetation; S602, using the Adaboost adaptive boosting algorithm to build an inversion model of soil salinity, and updating the weights of the training samples by finding the weights of the weak learning machine, as shown in the formula; E k =max|y i -G k (x i )| S6-1 In the formula, i is the i-th sample; m is the number of samples; x i is the feature of the i-th sample; y i is the true value of soil salt content in the i-th sample; G k is the kth weak learner; G k (x i ) is the predicted value of the weak learner based on the sample; w ki is the weight distribution of the current training data.

8. The method of constructing the soil salinity inversion model using the Adaboost adaptive boosting algorithm as claimed in claim 7, wherein the weights of the training samples are updated by finding the weights of the weak learning machine, characterized in that: The model uses decision trees as weak learners of the Adaboost algorithm and constructs an AB-DT model to invert soil salinity; The results of the AB-DT prediction model can be evaluated using three consistency metrics: determination coefficient, root mean square error, and mean absolute error.

9. The method for dynamic monitoring of ecological environment based on remote sensing and geographic information system according to claim 1, characterized in that: S7 uses a mathematical model to comprehensively analyze the calculation results, wherein: S701, the mathematical model constructs a BP neural network model and substitutes the calculated results into the model, and analyzes the relationship between the degree of land salinization and the vegetation coverage and the water content of the soil to obtain the cause of land salinization in the measured area, as shown in formula (S7-1); In the formula, xp is the standardized variable value; xp max and xp min are the maximum and minimum values ​​of the standardized variables respectively; x is the measured variable value; x max and x min are the minimum and maximum values ​​of the measured variables, respectively. S702, using the Bayesian algorithm to optimize the analysis results, by setting the weight parameters as random variables, and determining the optimal weight function according to the probability density of the weights, as shown in formula (S7-2); f(w)=αE w +βE d S7-2 Where f(w) is the corrected performance function; E w is the mean square error of all network values; E d is the mean square error of the network output; α and β are regularization parameters.

10. The method for dynamic monitoring of ecological environment based on remote sensing and geographic information system according to claim 1, characterized in that: S8 records the results of this calculation and analysis, where: S801, the calculation and analysis results are stored in a cloud database, and the relationship between the degree of land salinization and the vegetation coverage and soil moisture content is recorded to facilitate subsequent improvement of the degree of salinization in the measurement area; S802, the cloud database is used to compare and measure the actual effects of the improvement plan for the degree of salinization in the area, and to predict the results of the improvement plan by establishing a multivariate regression linear model.

Images