Simulation analysis method and system for the impact of watershed landscape pattern evolution on water quality

Abstract

The present invention discloses a simulation analysis method and system for the impact of the evolution of a watershed landscape pattern on water quality, relating to the technical field of water quality simulation analysis, and comprising the following steps: collecting water quality monitoring data including image data, topographic data, meteorological data and river data; constructing a water quality output model through pre-processed river data in combination with a multiple linear regression algorithm, and thereby obtaining a water quality assessment index; constructing a watershed water quality simulation analysis model based on the obtained water quality assessment index in combination with a neural network algorithm; analyzing the degree of water pollution based on the output results of the watershed water quality simulation analysis model, and thereby generating a watershed water quality simulation analysis report. The multispectral analysis technology, multiple linear regression algorithm, neural network algorithm and simulation analysis technology in the method of the present invention are closely combined with modern information technology, thereby solving the problem that traditional methods are difficult to analyze the dynamic impact of the evolution of a watershed landscape pattern on water quality.

Description

Technical Field

[0001] The present invention relates to the technical field of water quality simulation analysis, and in particular to a simulation analysis method and system for the impact of watershed landscape pattern evolution on water quality. Background Art

[0002] With the rapid development of social economy, changes in landscape pattern have led to changes in surface runoff, which in turn have a negative impact on water quality. Traditional water quality monitoring methods mainly rely on field sampling and laboratory analysis. This method is not only costly and inefficient, but also difficult to fully reflect the dynamic impact of the evolution of the basin landscape pattern on water quality. Therefore, it is of great practical significance to establish a simulation analysis method and system that can comprehensively consider the evolution of the basin landscape pattern and water quality changes. Combining landscape pattern evolution data and water quality models, a simulation analysis model of the impact of basin landscape pattern evolution on water quality is constructed to simulate water quality changes under different landscape pattern scenarios, providing a scientific basis for basin water resources management and protection.

[0003] Although the existing technology has made great progress in the direction of water quality simulation analysis, there are still some problems that need to be optimized. The current water quality monitoring method is single, resulting in inaccurate simulation analysis of water quality changes. Traditional methods only analyze and judge water quality changes based on the properties of the water quality itself, which will lead to low accuracy of simulation analysis of water quality changes. Therefore, how to obtain the correlation between the evolution of the landscape pattern of the water quality monitoring basin and water quality changes through simulation analysis, and realize the simulation and prediction of the process from landscape pattern changes to water quality index changes, is the problem to be solved by the present invention. To this end, a simulation analysis method and system for the impact of basin landscape pattern evolution on water quality are proposed. Summary of the Invention

[0004] The purpose of the present invention is to provide a simulation analysis method and system for the impact of the evolution of watershed landscape pattern on water quality, so as to solve the problems raised in the above background technology.

[0005] To solve the above technical problems, the technical solution adopted by the present invention is as follows: First, a simulation analysis method for the impact of watershed landscape pattern evolution on water quality includes the following steps:

[0006] Step 1: Collect water quality monitoring data including image data, topographic data, meteorological data and river data, and pre-process the collected data to provide a data basis for the implementation of subsequent module functions;

[0007] Step 2: Perform multispectral analysis on the pre-processed image data to distinguish different types of corridor images and obtain corridor pattern evolution data;

[0008] Step 3: Identify landscape patches from different types of corridor images and count the number of landscape patches;

[0009] Step 4: Combine corridor pattern evolution data, landscape patch count, pre-processed topographic and geomorphological data, and meteorological data to analyze corridor flow and landscape fragmentation during landscape pattern evolution.

[0010] Step 5: Using the pre-processed river data and the multiple linear regression algorithm, a water quality output model is constructed to obtain a water quality assessment index.

[0011] Step 6: Based on the obtained water quality assessment index and combined with the neural network algorithm, a watershed water quality simulation analysis model was constructed to analyze the relationship between the landscape pattern evolution of the water quality monitoring basin and water quality changes;

[0012] Step 7: Based on the output results of the watershed water quality simulation analysis model, analyze the degree of water pollution and generate a watershed water quality simulation analysis report.

[0013] A further improvement of the technical solution of the present invention is that in step 1, the process of collecting water quality monitoring data includes:

[0014] Deploy different types of data collection equipment to collect image data, topographic data, meteorological data, and river data for water quality monitoring basins. These data collection equipment include multispectral cameras, total stations, GPS altitude meters, tipping bucket rain gauges, temperature sensors, ultrasonic anemometers, ultrasonic current meters, electromagnetic flow meters, pH meters, dissolved oxygen meters, online chemical oxygen demand monitors, online biochemical oxygen demand monitors, and heavy metal monitors.

[0015] The image data is a real-time remote sensing image of the water quality monitoring basin; the topographic data includes the slope and altitude of the water quality monitoring basin; the meteorological data includes the real-time precipitation, real-time temperature and real-time wind speed of the water quality monitoring basin; the river data includes the real-time river speed, real-time river flow, real-time pH value of the river, real-time dissolved oxygen content, real-time chemical oxygen demand, real-time biochemical oxygen demand and real-time heavy metal element content of the water quality monitoring basin;

[0016] Perform data cleaning and data standardization on the collected topographic data, meteorological data, and river data, perform image enhancement and image denoising on the collected image data, assign timestamps to the image data, topographic data, meteorological data, and river data, adjust the assigned time size, and achieve synchronization of the collection time of the image data, topographic data, meteorological data, and river data;

[0017] The preprocessed river data are integrated to generate a water quality monitoring dataset, which is then divided into a training set and a test set with a ratio of 8:2.

[0018] A further improvement of the technical solution of the present invention is that in step 2, the process of acquiring corridor pattern evolution data includes:

[0019] ENVI is used to extract near-infrared and red band reflectances from image data of the water quality monitoring basin, and then calculate the NDVI value to distinguish different types of corridor images, including vegetation corridors, river corridors, and road corridors. The calculation process of the NDVI value includes:

[0020]

[0021] in, is the reflectivity in the near-infrared band, and R is the reflectivity in the red light band.

[0022] Specifically, when the NDVI value is between 0.2 and 1, it corresponds to a vegetation corridor; when the NDVI value is between -0.1 and 0, it corresponds to a river corridor; and when the NDVI value is between 0 and 0.1, it corresponds to a road corridor.

[0023] Based on the differentiation results of different types of corridor images, GIS software was used to measure the length, width, area, and longitude and latitude coordinates of different types of corridors corresponding to each corridor image to obtain corridor pattern evolution data, which included the length, width, area, and longitude and latitude coordinates of different types of corridors.

[0024] A further improvement of the technical solution of the present invention is that in step 3, the statistical process of the number of landscape patches includes:

[0025] An object-oriented image segmentation method is used to segment each corridor image into different image blocks according to the spectrum, texture and shape of different types of corridor images. The segmentation parameters are adjusted to make the segmented image blocks correspond to the landscape patches.

[0026] GIS software was used to count the landscape patches segmented from each corridor image and to calculate the number of landscape patches in each corridor image.

[0027] A further improvement of the technical solution of the present invention is that in step 4, the analysis process of corridor mobility during the landscape pattern evolution process includes:

[0028] Weights are assigned to corridor pattern evolution data and meteorological data, and the corridor circulation index is calculated by combining the weight summation method. The corridor circulation index is then integrated into the water quality monitoring dataset. The calculation process of the corridor circulation index includes:

[0029]

[0030] in, is the corridor circulation index; , , and are the length, width, area and latitude and longitude coordinate weights of different types of corridors; , and are the weights of real-time precipitation, temperature and wind speed in the water quality monitoring basin respectively; , , and are the length, width, area, and latitude and longitude coordinates of different types of corridors; , and They are the real-time precipitation, air temperature and wind speed in the water quality monitoring basin;

[0031] The first threshold value of corridor circulation and the second threshold value of corridor circulation are set. When the corridor circulation index is lower than the first threshold value of corridor circulation, the corresponding corridor circulation is low; when the corridor circulation index is between the first threshold value of corridor circulation and the second threshold value of corridor circulation, the corresponding corridor circulation is general; when the corridor circulation index is higher than the second threshold value of corridor circulation, the corresponding corridor circulation is high.

[0032] A further improvement of the technical solution of the present invention is that in step 4, the process of analyzing the degree of landscape fragmentation during the evolution of landscape pattern includes:

[0033] The number of landscape patches, topographic data, and meteorological data in each corridor image are weighted and averaged to calculate the landscape fragmentation index. The landscape fragmentation index is then integrated into the water quality monitoring dataset. The calculation process of the landscape fragmentation index includes the following steps:

[0034]

[0035] in, is the landscape fragmentation index; is the weight of the number of landscape patches in each corridor image, and are the weights of slope and elevation of the water quality monitoring basin, respectively; , and are the weights of real-time precipitation, temperature and wind speed in the water quality monitoring basin respectively; is the number of landscape patches in each corridor image; and are the slope and elevation of the water quality monitoring basin, respectively; , and They are the real-time precipitation, air temperature and wind speed in the water quality monitoring basin;

[0036] The first and second thresholds of landscape fragmentation are set. When the landscape fragmentation index is lower than the first threshold, it corresponds to a low degree of landscape fragmentation; when the landscape fragmentation index is between the first and second thresholds, it corresponds to a medium degree of landscape fragmentation; and when the landscape fragmentation index is higher than the second threshold, it corresponds to a high degree of landscape fragmentation.

[0037] A further improvement of the technical solution of the present invention is that in step 5, the analysis process of the water quality assessment index includes:

[0038] Extract river data from the water quality monitoring dataset, use the training set data, combine with the multiple linear regression algorithm, take the river data as input and the water quality assessment index as output, learn the linear relationship between the river data and the water quality assessment index, and train the water quality assessment model;

[0039] Input the test set data into the water quality assessment model, adjust the intercept term and regression coefficient of the water quality assessment model, optimize the water quality assessment model, deploy the optimized water quality assessment model into the system, combine it with the current river data, output the corresponding water quality assessment index, and integrate the water quality assessment index into the water quality monitoring data set;

[0040] The water quality assessment model expression is:

[0041]

[0042] in, is the water quality assessment index; , , , , , and They are the regression coefficients of the real-time river speed, real-time river flow, real-time river pH value, real-time dissolved oxygen, real-time chemical oxygen demand, real-time biochemical oxygen demand and real-time heavy metal element content in the water quality monitoring basin; , , , , , and They are real-time river speed, real-time river flow, real-time pH value, real-time dissolved oxygen, real-time chemical oxygen demand, real-time biochemical oxygen demand and real-time heavy metal element content in the water quality monitoring basin; and are the intercept term and error term of the water quality assessment model, respectively.

[0043] A further improvement of the technical solution of the present invention is that in step 6, the process of constructing the watershed water quality simulation analysis model includes:

[0044] The corridor circulation index, landscape fragmentation index, and water quality assessment index were extracted from the water quality monitoring data set. The training set data was combined with the neural network algorithm. The corridor circulation index and landscape fragmentation index were used as input, and the water quality assessment index was used as output. The nonlinear relationship between the corridor circulation index, landscape fragmentation index, and water quality assessment index was learned to train the watershed water quality simulation analysis model.

[0045] Input the test set data into the watershed water quality simulation analysis model, compare the water quality assessment index output by the watershed water quality simulation analysis model with the actual water quality assessment index, adjust the parameters of the watershed water quality simulation analysis model, optimize the performance of the watershed water quality simulation analysis model, and deploy the optimized watershed water quality simulation analysis model into the system.

[0046] A further improvement of the technical solution of the present invention is that in step seven, the process of generating the watershed water quality simulation analysis report includes:

[0047] Based on the output results of the basin water quality simulation analysis model, the water pollution degree is analyzed. Specifically, when the water quality assessment index is lower than 0.3, it corresponds to a low water pollution degree; when the water quality assessment index is between 0.3 and 0.6, it corresponds to a medium water pollution degree; when the water quality assessment index is higher than 0.6, it corresponds to a high water pollution degree;

[0048] The corridor pattern evolution data, the number of landscape patches in each corridor, the water quality assessment index and the degree of water pollution of each corridor are integrated to generate a watershed water quality simulation analysis report.

[0049] Secondly, a simulation analysis system for the impact of watershed landscape pattern evolution on water quality is used to implement the simulation analysis method for the impact of watershed landscape pattern evolution on water quality described above, including a water quality monitoring data acquisition module, a corridor identification module, a landscape patch identification module, a landscape pattern evolution analysis module, a water quality assessment module, a simulation analysis module, and an execution module, wherein each module is communicatively connected;

[0050] The water quality monitoring data acquisition module collects image data, topographic data, meteorological data and river data of the water quality monitoring basin through different types of acquisition equipment, and pre-processes the collected data to generate a water quality monitoring data set;

[0051] The corridor recognition module performs multispectral analysis on the pre-processed image data to distinguish different types of corridor images and obtain corridor pattern evolution data;

[0052] The landscape patch recognition module combines object-oriented image segmentation methods with GIS software to count the number of landscape patches in each corridor image;

[0053] The landscape pattern evolution analysis module assigns weights to the corridor pattern evolution data and meteorological data, and calculates the corridor circulation index by combining the weighted summation method, thereby analyzing the corridor circulation during the landscape pattern evolution process; assigns weights to the number of landscape patches, topographic data, and meteorological data in each corridor image, and calculates the landscape fragmentation index by using the weighted average method, thereby analyzing the degree of landscape fragmentation during the landscape pattern evolution process;

[0054] The water quality assessment module uses the pre-processed water source data to construct a water quality assessment model through a multiple linear regression algorithm, and then outputs a water quality assessment index;

[0055] The simulation analysis module combines the corridor circulation index, landscape fragmentation index, water quality assessment index and neural network algorithm to learn the nonlinear relationship between the corridor circulation index, landscape fragmentation index and water quality assessment index, and construct a watershed water quality simulation analysis model;

[0056] The execution module analyzes the degree of water pollution based on the output results of the watershed water quality simulation analysis model, and then generates a watershed water quality simulation analysis report.

[0057] The beneficial effects of the present invention are as follows: compared with the traditional simulation analysis method and system for the impact of the evolution of the watershed landscape pattern on water quality, the multispectral analysis technology, multivariate linear regression algorithm, neural network algorithm, simulation analysis technology in the method of the present invention are closely combined with modern information technology. The neural network algorithm is used to obtain the correlation between the evolution of the watershed landscape pattern and the water quality changes in the water quality monitoring basin, thereby achieving real-time and comprehensive monitoring of water quality changes. It solves the problem that the traditional method has a single monitoring mode and is difficult to analyze the dynamic impact of the evolution of the watershed landscape pattern on water quality. It ensures that the method of the present invention can refine the dynamic monitoring standards of the simulation analysis method and system for the impact of the evolution of the watershed landscape pattern on water quality within a more precise range, so that the monitored data becomes a more accurate indicator under the same conditions. The research and development and application of this method significantly enhance the level of intelligence in the simulation analysis process of the impact of the evolution of the watershed landscape pattern on water quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0059] Figure 1 This is a flow chart of the simulation analysis method for the impact of watershed landscape pattern evolution on water quality according to the present invention;

[0060] Figure 2 This is a block diagram of the simulation analysis system for the impact of basin landscape pattern evolution on water quality in the present invention. DETAILED DESCRIPTION

[0061] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0062] Example 1, as Figure 1 As shown, the present invention provides a simulation analysis method for the impact of basin landscape pattern evolution on water quality, comprising the following steps:

[0063] Step 1: Collect water quality monitoring data including image data, topographic data, meteorological data and river data, and pre-process the collected data to provide a data basis for the implementation of subsequent module functions;

[0064] Step 2: Perform multispectral analysis on the pre-processed image data to distinguish different types of corridor images and obtain corridor pattern evolution data;

[0065] Step 3: Identify landscape patches from different types of corridor images and count the number of landscape patches;

[0066] Step 4: Combine corridor pattern evolution data, landscape patch count, pre-processed topographic and geomorphological data, and meteorological data to analyze corridor flow and landscape fragmentation during landscape pattern evolution.

[0067] Step 5: Using the pre-processed river data and the multiple linear regression algorithm, a water quality output model is constructed to obtain a water quality assessment index.

[0068] Step 6: Based on the obtained water quality assessment index and combined with the neural network algorithm, a watershed water quality simulation analysis model was constructed to analyze the relationship between the landscape pattern evolution of the water quality monitoring basin and water quality changes;

[0069] Step 7: Based on the output results of the watershed water quality simulation analysis model, analyze the degree of water pollution and generate a watershed water quality simulation analysis report.

[0070] In step 1, the process of collecting water quality monitoring data includes:

[0071] Deploy different types of data collection equipment to collect image data, topographic data, meteorological data, and river data for water quality monitoring basins. The collection equipment includes multispectral cameras, total stations, GPS altitude meters, tipping bucket rain gauges, temperature sensors, ultrasonic anemometers, ultrasonic current meters, electromagnetic flow meters, pH meters, dissolved oxygen meters, online chemical oxygen demand monitors, online biochemical oxygen demand monitors, and heavy metal monitors.

[0072] The image data is a real-time remote sensing image of the water quality monitoring basin; the topographic data includes the slope and altitude of the water quality monitoring basin; the meteorological data includes the real-time precipitation, real-time temperature and real-time wind speed of the water quality monitoring basin; the river data includes the real-time river speed, real-time river flow, real-time pH value of the river, real-time dissolved oxygen content, real-time chemical oxygen demand, real-time biochemical oxygen demand and real-time heavy metal element content of the water quality monitoring basin;

[0073] Perform data cleaning and data standardization on the collected topographic data, meteorological data, and river data, perform image enhancement and image denoising on the collected image data, assign timestamps to the image data, topographic data, meteorological data, and river data, adjust the assigned time size, and achieve synchronization of the collection time of the image data, topographic data, meteorological data, and river data;

[0074] The preprocessed river data are integrated to generate a water quality monitoring dataset, which is then divided into a training set and a test set with a ratio of 8:2.

[0075] In step 2, the process of obtaining corridor pattern evolution data includes:

[0076] ENVI is used to extract near-infrared and red band reflectances from image data of the water quality monitoring basin, and then calculate the NDVI value to distinguish different types of corridor images. Different types of corridors include vegetation corridors, river corridors, and road corridors. The calculation process of the NDVI value includes:

[0077]

[0078] in, is the reflectivity in the near-infrared band, and R is the reflectivity in the red light band.

[0079] Specifically, when the NDVI value is between 0.2 and 1, it corresponds to a vegetation corridor; when the NDVI value is between -0.1 and 0, it corresponds to a river corridor; and when the NDVI value is between 0 and 0.1, it corresponds to a road corridor.

[0080] Based on the differentiation results of different types of corridor images, GIS software was used to measure the length, width, area, and longitude and latitude coordinates of different types of corridors corresponding to each corridor image to obtain corridor pattern evolution data, which included the length, width, area, and longitude and latitude coordinates of different types of corridors.

[0081] In step 3, the statistical process of the number of landscape patches includes:

[0082] An object-oriented image segmentation method is used to segment each corridor image into different image blocks according to the spectrum, texture and shape of different types of corridor images. The segmentation parameters are adjusted to make the segmented image blocks correspond to the landscape patches.

[0083] GIS software was used to count the landscape patches segmented from each corridor image and to calculate the number of landscape patches in each corridor image.

[0084] In step 4, the analysis process of corridor mobility during landscape pattern evolution includes:

[0085] Weights are assigned to corridor pattern evolution data and meteorological data, and the corridor circulation index is calculated by combining the weight summation method. The corridor circulation index is then integrated into the water quality monitoring dataset. The calculation process of the corridor circulation index includes:

[0086]

[0087] in, is the corridor circulation index; , , and are the length, width, area and latitude and longitude coordinate weights of different types of corridors; , and are the weights of real-time precipitation, temperature and wind speed in the water quality monitoring basin respectively; , , and are the length, width, area, and latitude and longitude coordinates of different types of corridors; , and They are the real-time precipitation, air temperature and wind speed in the water quality monitoring basin;

[0088] The first threshold value of corridor circulation and the second threshold value of corridor circulation are set. When the corridor circulation index is lower than the first threshold value of corridor circulation, the corresponding corridor circulation is low; when the corridor circulation index is between the first threshold value of corridor circulation and the second threshold value of corridor circulation, the corresponding corridor circulation is general; when the corridor circulation index is higher than the second threshold value of corridor circulation, the corresponding corridor circulation is high.

[0089] In step 4, the analysis process of landscape fragmentation during landscape pattern evolution includes:

[0090] The number of landscape patches, topographic data, and meteorological data in each corridor image are weighted and averaged to calculate the landscape fragmentation index. The landscape fragmentation index is then integrated into the water quality monitoring dataset. The calculation process of the landscape fragmentation index includes the following steps:

[0091]

[0092] in, is the landscape fragmentation index; is the weight of the number of landscape patches in each corridor image, and are the weights of slope and elevation of the water quality monitoring basin, respectively; , and are the weights of real-time precipitation, temperature and wind speed in the water quality monitoring basin respectively; is the number of landscape patches in each corridor image; and are the slope and elevation of the water quality monitoring basin, respectively; , and They are the real-time precipitation, air temperature and wind speed in the water quality monitoring basin;

[0093] The first and second thresholds of landscape fragmentation are set. When the landscape fragmentation index is lower than the first threshold, it corresponds to a low degree of landscape fragmentation; when the landscape fragmentation index is between the first and second thresholds, it corresponds to a medium degree of landscape fragmentation; and when the landscape fragmentation index is higher than the second threshold, it corresponds to a high degree of landscape fragmentation.

[0094] In step 5, the analysis process of the water quality assessment index includes:

[0095] Extract river data from the water quality monitoring dataset, use the training set data, combine with the multiple linear regression algorithm, take the river data as input and the water quality assessment index as output, learn the linear relationship between the river data and the water quality assessment index, and train the water quality assessment model;

[0096] Input the test set data into the water quality assessment model, adjust the intercept term and regression coefficient of the water quality assessment model, optimize the water quality assessment model, deploy the optimized water quality assessment model into the system, combine it with the current river data, output the corresponding water quality assessment index, and integrate the water quality assessment index into the water quality monitoring data set;

[0097] The water quality assessment model expression is:

[0098]

[0099] in, is the water quality assessment index; , , , , , and They are the regression coefficients of the real-time river speed, real-time river flow, real-time river pH value, real-time dissolved oxygen, real-time chemical oxygen demand, real-time biochemical oxygen demand and real-time heavy metal element content in the water quality monitoring basin; , , , , , and They are real-time river speed, real-time river flow, real-time pH value, real-time dissolved oxygen, real-time chemical oxygen demand, real-time biochemical oxygen demand and real-time heavy metal element content in the water quality monitoring basin; and are the intercept term and error term of the water quality assessment model, respectively.

[0100] In step 6, the construction process of the watershed water quality simulation analysis model includes:

[0101] The corridor circulation index, landscape fragmentation index, and water quality assessment index were extracted from the water quality monitoring data set. The training set data was combined with the neural network algorithm. The corridor circulation index and landscape fragmentation index were used as input, and the water quality assessment index was used as output. The nonlinear relationship between the corridor circulation index, landscape fragmentation index, and water quality assessment index was learned to train the watershed water quality simulation analysis model.

[0102] Input the test set data into the watershed water quality simulation analysis model, compare the water quality assessment index output by the watershed water quality simulation analysis model with the actual water quality assessment index, adjust the parameters of the watershed water quality simulation analysis model, optimize the performance of the watershed water quality simulation analysis model, and deploy the optimized watershed water quality simulation analysis model into the system.

[0103] In step 7, the process of generating the watershed water quality simulation analysis report includes:

[0104] Based on the output results of the basin water quality simulation analysis model, the water pollution degree is analyzed. Specifically, when the water quality assessment index is lower than 0.3, it corresponds to a low water pollution degree; when the water quality assessment index is between 0.3 and 0.6, it corresponds to a medium water pollution degree; when the water quality assessment index is higher than 0.6, it corresponds to a high water pollution degree;

[0105] The corridor pattern evolution data, the number of landscape patches in each corridor, the water quality assessment index and the degree of water pollution of each corridor are integrated to generate a watershed water quality simulation analysis report.

[0106] Example 2, as Figure 2 As shown, based on Example 1, the present invention provides a technical solution: a simulation analysis system for the impact of watershed landscape pattern evolution on water quality, which is used to implement the simulation analysis method for the impact of watershed landscape pattern evolution on water quality described above, including a water quality monitoring data acquisition module, a corridor identification module, a landscape patch identification module, a landscape pattern evolution analysis module, a water quality assessment module, a simulation analysis module and an execution module, wherein each module is communicatively connected;

[0107] The water quality monitoring data acquisition module collects image data, topographic data, meteorological data and river data of the water quality monitoring basin through different types of acquisition equipment, and pre-processes the collected data to generate a water quality monitoring data set;

[0108] The corridor recognition module performs multispectral analysis on the pre-processed image data to distinguish different types of corridor images and obtain corridor pattern evolution data;

[0109] The landscape patch recognition module combines object-oriented image segmentation methods with GIS software to count the number of landscape patches in each corridor image;

[0110] The landscape pattern evolution analysis module assigns weights to the corridor pattern evolution data and meteorological data, and calculates the corridor circulation index by combining the weighted summation method, thereby analyzing the corridor circulation during the landscape pattern evolution process; assigns weights to the number of landscape patches, topographic data, and meteorological data in each corridor image, and calculates the landscape fragmentation index by using the weighted average method, thereby analyzing the degree of landscape fragmentation during the landscape pattern evolution process;

[0111] The water quality assessment module uses the pre-processed water source data to construct a water quality assessment model through a multiple linear regression algorithm, and then outputs a water quality assessment index;

[0112] The simulation analysis module combines the corridor circulation index, landscape fragmentation index, water quality assessment index and neural network algorithm to learn the nonlinear relationship between the corridor circulation index, landscape fragmentation index and water quality assessment index, and construct a watershed water quality simulation analysis model;

[0113] The execution module analyzes the degree of water pollution based on the output results of the watershed water quality simulation analysis model, and then generates a watershed water quality simulation analysis report.

[0114] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A simulation analysis method for the impact of watershed landscape pattern evolution on water quality, characterized by: The following steps are involved: Step 1: Collect water quality monitoring data including image data, topographic data, meteorological data and river data, and pre-process the collected data; Step 2: Perform multispectral analysis on the pre-processed image data to distinguish different types of corridor images and obtain corridor pattern evolution data; Step 3: Identify landscape patches from different types of corridor images and count the number of landscape patches; Step 4: Combine corridor pattern evolution data, landscape patch count, pre-processed topographic and geomorphological data, and meteorological data to analyze corridor flow and landscape fragmentation during landscape pattern evolution. Step 5: Using the pre-processed river data and the multiple linear regression algorithm, a water quality output model is constructed to obtain a water quality assessment index. Step 6: Based on the obtained water quality assessment index and combined with the neural network algorithm, a watershed water quality simulation analysis model is constructed; Step 7: Based on the output results of the watershed water quality simulation analysis model, analyze the degree of water pollution and generate a watershed water quality simulation analysis report; In step 4, the analysis process of corridor mobility during the landscape pattern evolution process includes: Assign weights to corridor pattern evolution data and meteorological data, calculate the corridor circulation index by combining the weight summation method, and integrate the corridor circulation index into the water quality monitoring dataset; In step 4, the analysis process of the degree of landscape fragmentation during the evolution of landscape pattern includes: Assign weights to the number of landscape patches, topographic and geomorphological data, and meteorological data in each corridor image, use a weighted approach to calculate the landscape fragmentation index, and integrate the landscape fragmentation index into the water quality monitoring dataset; In step 6, the process of constructing the watershed water quality simulation analysis model includes: The corridor circulation index, landscape fragmentation index, and water quality assessment index were extracted from the water quality monitoring data set. The training set data was combined with the neural network algorithm. The corridor circulation index and landscape fragmentation index were used as input, and the water quality assessment index was used as output. The nonlinear relationship between the corridor circulation index, landscape fragmentation index, and water quality assessment index was learned to train the watershed water quality simulation analysis model. Input the test set data into the watershed water quality simulation analysis model, compare the water quality assessment index output by the watershed water quality simulation analysis model with the actual water quality assessment index, adjust the parameters of the watershed water quality simulation analysis model, optimize the performance of the watershed water quality simulation analysis model, and deploy the optimized watershed water quality simulation analysis model into the system.

2. The simulation analysis method for the impact of watershed landscape pattern evolution on water quality according to claim 1 is characterized by: In step 1, the process of collecting water quality monitoring data includes: Deploy different types of data collection equipment to collect image data, topographic data, meteorological data, and river data for water quality monitoring basins. These data collection equipment include multispectral cameras, total stations, GPS altitude meters, tipping bucket rain gauges, temperature sensors, ultrasonic anemometers, ultrasonic current meters, electromagnetic flow meters, pH meters, dissolved oxygen meters, online chemical oxygen demand monitors, online biochemical oxygen demand monitors, and heavy metal monitors. The image data is a real-time remote sensing image of the water quality monitoring basin; the topographic data includes the slope and altitude of the water quality monitoring basin; the meteorological data includes the real-time precipitation, real-time temperature and real-time wind speed of the water quality monitoring basin; the river data includes the real-time river speed, real-time river flow, real-time pH value of the river, real-time dissolved oxygen content, real-time chemical oxygen demand, real-time biochemical oxygen demand and real-time heavy metal element content of the water quality monitoring basin; Perform data cleaning and data standardization on the collected topographic data, meteorological data, and river data, perform image enhancement and image denoising on the collected image data, assign timestamps to the image data, topographic data, meteorological data, and river data, adjust the assigned time size, and achieve synchronization of the collection time of the image data, topographic data, meteorological data, and river data; The preprocessed river data are integrated to generate a water quality monitoring dataset, which is then divided into a training set and a test set.

3. The simulation analysis method for the impact of watershed landscape pattern evolution on water quality according to claim 2 is characterized by: In step 2, the process of obtaining corridor pattern evolution data includes: ENVI was used to extract near-infrared and red band reflectances from image data of the water quality monitoring basin, and then the NDVI values ​​were calculated to distinguish different types of corridor images, including vegetation corridors, river corridors, and road corridors. Based on the differentiation results of different types of corridor images, GIS software was used to measure the length, width, area, and longitude and latitude coordinates of different types of corridors corresponding to each corridor image to obtain corridor pattern evolution data, which included the length, width, area, and longitude and latitude coordinates of different types of corridors.

4. The simulation analysis method for the impact of watershed landscape pattern evolution on water quality according to claim 3 is characterized by: In step 3, the statistical process of the number of landscape patches includes: An object-oriented image segmentation method is used to segment each corridor image into different image blocks according to the spectrum, texture and shape of different types of corridor images. The segmentation parameters are adjusted to make the segmented image blocks correspond to the landscape patches. GIS software was used to count the landscape patches segmented from each corridor image and to calculate the number of landscape patches in each corridor image.

5. The simulation analysis method for the impact of watershed landscape pattern evolution on water quality according to claim 4 is characterized by: The first threshold value of corridor circulation and the second threshold value of corridor circulation are set. When the corridor circulation index is lower than the first threshold value of corridor circulation, the corresponding corridor circulation is low; when the corridor circulation index is between the first threshold value of corridor circulation and the second threshold value of corridor circulation, the corresponding corridor circulation is general; when the corridor circulation index is higher than the second threshold value of corridor circulation, the corresponding corridor circulation is high.

6. The simulation analysis method for the impact of watershed landscape pattern evolution on water quality according to claim 5 is characterized by: The first and second thresholds of landscape fragmentation are set. When the landscape fragmentation index is lower than the first threshold, it corresponds to a low degree of landscape fragmentation; when the landscape fragmentation index is between the first and second thresholds, it corresponds to a medium degree of landscape fragmentation; and when the landscape fragmentation index is higher than the second threshold, it corresponds to a high degree of landscape fragmentation.

7. The simulation analysis method for the impact of watershed landscape pattern evolution on water quality according to claim 6 is characterized by: In step 5, the analysis process of the water quality assessment index includes: Extract river data from the water quality monitoring dataset, use the training set data, combine with the multiple linear regression algorithm, take the river data as input and the water quality assessment index as output, learn the linear relationship between the river data and the water quality assessment index, and train the water quality assessment model; Input the test set data into the water quality assessment model, adjust the intercept term and regression coefficient of the water quality assessment model, optimize the water quality assessment model, deploy the optimized water quality assessment model into the system, combine it with the current river data, output the corresponding water quality assessment index, and integrate the water quality assessment index into the water quality monitoring data set.

8. The simulation analysis method for the impact of watershed landscape pattern evolution on water quality according to claim 7 is characterized by: In step 7, the process of generating the watershed water quality simulation analysis report includes: Based on the output results of the basin water quality simulation analysis model, the degree of water pollution is analyzed, and the corridor pattern evolution data of each corridor, the number of landscape patches in each corridor, the water quality assessment index and the degree of water pollution are integrated to generate a basin water quality simulation analysis report.

9. A simulation analysis system for the impact of watershed landscape pattern evolution on water quality, for implementing the simulation analysis method for the impact of watershed landscape pattern evolution on water quality as described in any one of claims 1 to 8, comprising a water quality monitoring data acquisition module, a corridor identification module, a landscape patch identification module, a landscape pattern evolution analysis module, a water quality assessment module, a simulation analysis module, and an execution module, wherein: The modules are connected in communication, characterized by: The water quality monitoring data acquisition module collects image data, topographic data, meteorological data and river data of the water quality monitoring basin through different types of acquisition equipment, and pre-processes the collected data to generate a water quality monitoring data set; The corridor recognition module performs multispectral analysis on the pre-processed image data to distinguish different types of corridor images and obtain corridor pattern evolution data; The landscape patch recognition module combines object-oriented image segmentation methods with GIS software to count the number of landscape patches in each corridor image; The landscape pattern evolution analysis module assigns weights to the corridor pattern evolution data and meteorological data, and calculates the corridor circulation index by combining the weight summation method, thereby analyzing the corridor circulation during the landscape pattern evolution process; assigns weights to the number of landscape patches, topographic data, and meteorological data in each corridor image, and calculates the landscape fragmentation index by using the weighted method, thereby analyzing the degree of landscape fragmentation during the landscape pattern evolution process; The water quality assessment module uses the pre-processed water source data to construct a water quality assessment model through a multiple linear regression algorithm, and then outputs a water quality assessment index; The simulation analysis module combines the corridor circulation index, landscape fragmentation index, water quality assessment index and neural network algorithm to learn the nonlinear relationship between the corridor circulation index, landscape fragmentation index and water quality assessment index, and construct a watershed water quality simulation analysis model; The execution module analyzes the degree of water pollution based on the output results of the watershed water quality simulation analysis model, and then generates a watershed water quality simulation analysis report.

Images