Dynamic monitoring and early warning method and system for water ecological health

Abstract

The invention relates to the technical field of water ecology monitoring, in particular to a dynamic monitoring and early warning method and system for water ecology health. According to the method, the remote sensing image data is acquired and equally divided into a plurality of grids, so that high-precision and high-efficiency data acquisition is facilitated, the condition of each region is more refined, monitoring data with higher spatial resolution can be acquired, and the monitoring accuracy is improved. The calculation of the local heterogeneity index is beneficial to revealing the difference of different areas of the water body in the aspect of ecological health, and the health conditions of different water body areas can be accurately identified. The problem that in the prior art, ecological health assessment is inaccurate due to spatial resolution limitation and an unreasonable data acquisition mode is solved, a more scientific and accurate assessment means is provided for water health through real-time and dynamic water monitoring, accurate region division and health index calculation, and the ecological health assessment method is more accurate. And early warning and timely response based on data driving are realized.

Description

Technical Field

[0001] This invention relates to the field of water ecological monitoring technology, and in particular to a method and system for dynamic monitoring and early warning of water ecological health. Background Technology

[0002] Dynamic monitoring and early warning of water ecological health refers to assessing the health status of aquatic ecosystems through real-time monitoring and data analysis of water bodies and their surrounding ecological environment, and providing early warnings of potential ecological risks or pollution events. The aim is to protect the sustainable use of water resources, improve the resilience and stress resistance of aquatic ecosystems, and ensure the ecological balance of aquatic areas.

[0003] Current technologies for dynamic monitoring and early warning of aquatic ecological health assess the health status of water bodies by monitoring various indicators and analyzing the data using mathematical models. However, existing aquatic ecological health monitoring technologies suffer from limitations in spatial resolution and the inability to effectively integrate multiple data types collected by different monitoring methods, resulting in low accuracy in assessing the health of aquatic ecosystems. Summary of the Invention

[0004] The main objective of this invention is to provide a method for dynamic monitoring and early warning of water ecological health, aiming to solve the technical problems in the prior art.

[0005] This invention proposes a method for dynamic monitoring and early warning of aquatic ecological health, comprising:

[0006] Acquire remote sensing image data of the target water body area, and divide the remote sensing image data into multiple equal-level grids;

[0007] Obtain the water reflectance of each pixel within each of the sibling grids, and obtain the local heterogeneity index of each sibling grid based on multiple water reflectances;

[0008] Based on the local heterogeneity index, the target water body area is divided into multiple highly heterogeneous water body areas and low heterogeneous water body areas;

[0009] Acquire the first real-time monitoring data for each highly heterogeneous water body area and the second real-time monitoring data for each low-heterogeneous water body area;

[0010] The first dynamic sampling frequency of the highly heterogeneous water body area is obtained based on multiple first real-time monitoring data, and sampling is performed based on the first dynamic sampling frequency to obtain the first comprehensive health index of the highly heterogeneous water body area.

[0011] The second dynamic sampling frequency of each low heterogeneous water body area is obtained based on multiple second real-time monitoring data, and the second comprehensive health index of the low heterogeneous water body area is obtained based on the second dynamic sampling frequency.

[0012] The total health index is obtained based on the second comprehensive health index and the first comprehensive health index, and an early warning is issued for the target water area based on the total health index.

[0013] Preferably, the step of obtaining the local heterogeneity index of each grid at the same level based on the reflectance of the multiple water bodies includes:

[0014] The mean reflectance of each grid at the same level is obtained based on the reflectance of multiple water bodies, and the standard deviation of reflectance of each grid at the same level is obtained based on the mean reflectance and the reflectance of multiple water bodies.

[0015] The standard deviation ratio is obtained based on the standard deviation of reflectance and the mean reflectance.

[0016] Obtain the water gradient and vertical gradient of each grid at the same level, and obtain the corresponding gradient magnitude based on each water gradient and vertical gradient;

[0017] Obtain the information entropy of each peer grid, and obtain the local heterogeneity index of each peer grid based on the information entropy, gradient magnitude, and standard deviation ratio.

[0018] Preferably, the step of dividing the target water body region into multiple highly heterogeneous water body regions and low heterogeneous water body regions based on the local heterogeneity index includes:

[0019] Multiple grids of the same level are sorted according to the magnitude of their corresponding local heterogeneity indices to obtain a grid sorting table;

[0020] A preset segmentation threshold is set, and the grid sorting table is divided into a high heterogeneous grid sorting table and a low heterogeneous grid sorting table according to the preset segmentation threshold.

[0021] Obtain the local water area corresponding to each grid at the same level in the target water area, and mark the local water area corresponding to each grid at the same level in the high heterogeneous grid sorting table as a high heterogeneous water area;

[0022] The local water body region corresponding to each grid of the same level in the low heterogeneous grid sorting table is marked as a low heterogeneous water body region.

[0023] Preferably, the step of obtaining the first dynamic sampling frequency of the highly heterogeneous water body area based on multiple first real-time monitoring data includes:

[0024] Based on each of the first real-time monitoring data, multiple water quality monitoring data for each highly heterogeneous water body area within a preset time period are obtained, and the average water quality monitoring value is obtained based on the multiple water quality monitoring data.

[0025] The water quality monitoring standard deviation is obtained based on the water quality monitoring mean and multiple water quality monitoring data, and the local dynamic fluctuation coefficient of each highly heterogeneous water body area is obtained based on the water quality monitoring standard deviation and the water quality monitoring mean.

[0026] The first dynamic fluctuation coefficient is obtained based on the multiple local dynamic fluctuation coefficients;

[0027] Obtain the reference sampling frequency and reference fluctuation coefficient of the highly heterogeneous water body area, and obtain the dynamic fluctuation ratio based on the reference fluctuation coefficient and the first dynamic fluctuation coefficient;

[0028] The first dynamic sampling frequency is obtained based on the dynamic fluctuation ratio and the reference sampling frequency.

[0029] Preferably, the step of obtaining a first comprehensive health index for a highly heterogeneous water body area based on the first dynamic sampling frequency includes:

[0030] Obtain the water flow rate in the target water body area, and determine the sampling time interval based on the water flow rate;

[0031] The first real-time biological indicator data and the first real-time water quality parameter data of each highly heterogeneous water body area are collected in real time according to the sampling time interval and dynamic sampling frequency.

[0032] The total number of biological species and the number of individuals of each species are obtained based on each of the first real-time biological indicator data, and the corresponding species richness is obtained based on the number of individuals of each species and the total number of biological species.

[0033] The species diversity index of each highly heterogeneous water body area was obtained based on multiple species richness and total number of biological species;

[0034] Water quality physical parameters and water quality chemical parameters are obtained based on each of the first real-time water quality parameter data, and water quality physical pollution index is obtained based on the water quality physical parameters;

[0035] The water quality chemical pollution index is obtained based on the water quality chemical parameters, and the total water quality pollution index is obtained based on the water quality chemical pollution index and the water quality physical pollution index.

[0036] The first comprehensive health index is obtained based on each total water pollution index and species diversity index.

[0037] Preferably, the step of obtaining a total health index based on the second comprehensive health index and the first comprehensive health index, and issuing an early warning for the target water area based on the total health index, includes:

[0038] Obtain the total area of ​​the target water body region and the first actual area of ​​each highly heterogeneous water body region, and obtain the first total proportion weight coefficient of all highly heterogeneous water body regions based on multiple first actual areas and total areas;

[0039] Obtain the second actual area of ​​each low heterogeneous water body area, and obtain the second total proportion weighting coefficient of the low heterogeneous water body area based on multiple second actual areas and the total area;

[0040] The total health index is obtained based on the first total weighting coefficient, the first comprehensive health index, the second total weighting coefficient, and the second comprehensive health index.

[0041] Determine whether the total health index is greater than a preset threshold range;

[0042] If the total health index is greater than a preset threshold, the target water body area is determined to be severely polluted, triggering an early warning.

[0043] If the total health index is not greater than the preset threshold, the target water body area is determined to be lightly polluted and no warning is triggered.

[0044] This application also provides a dynamic monitoring and early warning system for water ecological health, including:

[0045] The first partitioning module is used to acquire remote sensing image data of the target water body area and divide the remote sensing image data into multiple grids of the same level.

[0046] The first acquisition module is used to acquire the water reflectance of each pixel in each of the same level grids, and to acquire the local heterogeneity index of each same level grid based on multiple water reflectances;

[0047] The second partitioning module is used to divide the target water body region into multiple highly heterogeneous water body regions and low heterogeneous water body regions according to the local heterogeneity index.

[0048] The second acquisition module is used to acquire the first real-time monitoring data of each highly heterogeneous water body area and the second real-time monitoring data of each low heterogeneous water body area.

[0049] The third acquisition module is used to acquire the first dynamic sampling frequency of the high heterogeneous water body area based on multiple first real-time monitoring data, and to sample based on the first dynamic sampling frequency to acquire the first comprehensive health index of the high heterogeneous water body area.

[0050] The fourth acquisition module is used to acquire the second dynamic sampling frequency of each low heterogeneous water body area based on multiple second real-time monitoring data, and to acquire the second comprehensive health index of the low heterogeneous water body area based on the second dynamic sampling frequency.

[0051] The early warning module is used to obtain the total health index based on the second comprehensive health index and the first comprehensive health index, and to issue an early warning for the target water area based on the total health index.

[0052] Preferably, the third acquisition module includes:

[0053] The first acquisition unit is used to acquire multiple water quality monitoring data for each highly heterogeneous water body area within a preset time period based on each of the first real-time monitoring data, and to acquire the average water quality monitoring value based on the multiple water quality monitoring data.

[0054] The second acquisition unit is used to acquire the water quality monitoring standard deviation based on the water quality monitoring mean and multiple water quality monitoring data, and to acquire the local dynamic fluctuation coefficient of each highly heterogeneous water body area based on the water quality monitoring standard deviation and the water quality monitoring mean.

[0055] The third acquisition unit is used to acquire the first dynamic fluctuation coefficient based on the plurality of local dynamic fluctuation coefficients;

[0056] The fourth acquisition unit is used to acquire the reference sampling frequency and reference fluctuation coefficient of the highly heterogeneous water body area, and to acquire the dynamic fluctuation ratio based on the reference fluctuation coefficient and the first dynamic fluctuation coefficient.

[0057] The fifth acquisition unit is used to acquire the first dynamic sampling frequency based on the dynamic fluctuation ratio and the reference sampling frequency.

[0058] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described method for dynamic monitoring and early warning of water ecological health.

[0059] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the above-described method for dynamic monitoring and early warning of water ecological health.

[0060] The beneficial effects of this invention are as follows: By acquiring remote sensing image data and dividing it into multiple grids equally, this invention helps to achieve high-precision and efficient data acquisition, making the situation of each region more detailed and enabling the acquisition of monitoring data with higher spatial resolution. The calculation of the local heterogeneity index helps to reveal the differences in ecological health among different areas of the water body, accurately identifying the health status of different water body areas. The division into highly heterogeneous and low-heterogeneous water body areas makes subsequent monitoring and early warning more targeted, enabling more accurate capture of changes in water health problems and timely adjustments. By dynamically adjusting the sampling frequency through real-time monitoring data, sampling can be increased in highly heterogeneous water body areas. By using sampling frequencies to capture water body changes more precisely, this dynamic adjustment mechanism improves monitoring responsiveness. By integrating the health indices of two water body regions with high and low heterogeneity, a comprehensive and accurate overall water body health assessment result can be obtained. This invention effectively solves the problem of inaccurate ecological health assessment caused by spatial resolution limitations and unreasonable data collection methods in existing technologies through multi-level and refined dynamic monitoring and data processing methods. Through real-time and dynamic water body monitoring, precise regional division, and health index calculation, it provides a more scientific and accurate assessment method for water body health and realizes data-driven early warning and timely response. Attached Figure Description

[0061] Figure 1 This is a schematic diagram of a method flow according to an embodiment of the present invention.

[0062] Figure 2 This is a schematic diagram of the system structure according to an embodiment of the present invention.

[0063] Figure 3 This is a schematic diagram of the internal structure of a computer device according to an embodiment of this application.

[0064] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0065] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0066] like Figure 1 As shown, this application provides a method for dynamic monitoring and early warning of aquatic ecological health, including:

[0067] S1. Acquire remote sensing image data of the target water body area, and divide the remote sensing image data into multiple grids of the same level;

[0068] S2. Obtain the water reflectance of each pixel in each of the same level grids, and obtain the local heterogeneity index of each same level grid based on multiple water reflectances;

[0069] S3. Based on the local heterogeneity index, the target water body area is divided into multiple highly heterogeneous water body areas and low heterogeneous water body areas.

[0070] S4. Obtain the first real-time monitoring data for each highly heterogeneous water body area and the second real-time monitoring data for each low heterogeneous water body area;

[0071] S5. Obtain the first dynamic sampling frequency of the highly heterogeneous water body area based on multiple first real-time monitoring data, and sample based on the first dynamic sampling frequency to obtain the first comprehensive health index of the highly heterogeneous water body area.

[0072] S6. Obtain the second dynamic sampling frequency for each low heterogeneous water body area based on multiple second real-time monitoring data, and obtain the second comprehensive health index of the low heterogeneous water body area based on the second dynamic sampling frequency;

[0073] S7. Obtain the total health index based on the second comprehensive health index and the first comprehensive health index, and issue an early warning for the target water area based on the total health index.

[0074] As described in steps S1-S7 above, both the first and second real-time monitoring data include temperature, dissolved oxygen, pH value, and conductivity. The acquisition method for the second comprehensive health index in low-heterogeneity water bodies is the same as that for the first comprehensive health index in high-heterogeneity water bodies. This invention acquires remote sensing image data of the target water body area and divides the remote sensing image data into multiple equal-level grids. This acquisition and equal division of remote sensing image data into multiple grids helps achieve high-precision and efficient data acquisition. The data volume of each grid is relatively small, avoiding the computational burden of traditional large-scale remote sensing image processing. Furthermore, gridding allows for more detailed analysis of each region, enabling higher spatial resolution. Monitoring data, after being processed into a grid, provides local data for subsequent analysis, enabling a more detailed analysis of the heterogeneity of water bodies and improving the accuracy of water body region delineation. By acquiring the water reflectance of each pixel within each grid and calculating the local heterogeneity index for each grid based on multiple water reflectance values, the dynamic changes of water bodies, especially changes in water quality and ecological health, can be captured more precisely through the water reflectance data of each pixel. This high-resolution remote sensing data helps to analyze the state of water bodies more accurately, and the calculation of the local heterogeneity index helps to reveal the differences in ecological health among different areas of the water body, accurately identifying the health status of different water body areas. This is of great significance for subsequent monitoring and early warning. By using a local heterogeneity index, the target water body area is divided into multiple highly heterogeneous and low-heterogeneous water body zones. This subdivision of the water body area into different health status zones helps to clarify the focus of attention in different areas, avoiding a one-size-fits-all approach. This differentiation facilitates the development of personalized water quality management and health monitoring plans for each area. The division into highly heterogeneous and low-heterogeneous water body zones makes subsequent monitoring and early warning more targeted, enabling more accurate detection of changes in water health issues and timely adjustments. By acquiring first real-time monitoring data for each highly heterogeneous water body zone and second real-time monitoring data for each low-heterogeneous water body zone, the high-heterogeneity index can be obtained through multiple first real-time monitoring data. The first dynamic sampling frequency for water bodies, by acquiring real-time water monitoring data, can promptly reflect changes in the water body, avoiding the delay problems existing in traditional methods. This real-time monitoring data can more accurately provide information on the health status of the water body. Acquiring water monitoring data from different areas (highly heterogeneous and lowly heterogeneous) further enhances the multi-dimensional fusion of data, ensuring the comprehensiveness and accuracy of monitoring results. By dynamically adjusting the sampling frequency based on real-time monitoring data, the sampling frequency can be increased in rapidly changing water body areas (such as highly heterogeneous areas), thereby capturing water changes more precisely. This dynamic adjustment mechanism improves the responsiveness of monitoring, ensuring that valuable data can be acquired in a timely manner at critical moments.This approach avoids unnecessary oversampling or excessively long sampling intervals, optimizes the use of monitoring resources, and obtains a first comprehensive health index for high-heterogeneity water bodies based on a first dynamic sampling frequency. A second dynamic sampling frequency is obtained for each low-heterogeneity water body area through multiple second real-time monitoring data points, and a second comprehensive health index is obtained based on this second dynamic sampling frequency. For low-heterogeneity water bodies, the dynamic adjustment of the sampling frequency can be adjusted according to changes in the water body, ensuring that excessive monitoring resources are not wasted in low-risk areas while allowing for more monitoring when necessary. The dynamic sampling frequency setting makes monitoring efficiency higher for low-heterogeneity water bodies, avoiding the problems of too much or too little monitoring data and ensuring the rational allocation of resources. The comprehensive health index comprehensively reflects the ecological health status of high-heterogeneity water bodies. This comprehensive index, obtained through high-precision data from dynamic sampling frequencies, provides a more accurate and real-time assessment of water body ecological health. This health index not only provides timely feedback on the health status of water bodies but also provides data support for subsequent water body management and protection, enabling managers to make more scientific decisions. The second comprehensive health index... This invention obtains a total health index from the first comprehensive health index and uses this index to issue early warnings for target water bodies. By integrating the health indices of two water body regions—one with high heterogeneity and the other with low heterogeneity—a comprehensive and accurate overall water health assessment can be obtained. This total health index reflects the overall ecological health status of the entire target water body region, providing decision-makers with a global perspective. Combined analysis of the total health index helps eliminate local data biases, achieving more precise ecological monitoring and water protection. Real-time early warnings based on the total health index can promptly identify potential water ecological problems, allowing for early and effective measures to prevent ecological disasters. This improves the predictability and foresight of monitoring, avoiding serious impacts of sudden environmental pollution on water ecological health. This invention effectively solves the problem of inaccurate ecological health assessments caused by spatial resolution limitations and unreasonable data collection methods in existing technologies through multi-level, refined dynamic monitoring and data processing methods. Through real-time, dynamic water body monitoring, precise regional division, and health index calculation, it provides a more scientific and accurate assessment method for water health and achieves data-driven early warning and timely response.

[0075] In one embodiment, step S2, which involves obtaining the local heterogeneity index of each peer grid based on the reflectance of the plurality of water bodies, includes:

[0076] S21. Obtain the mean reflectance of each grid at the same level based on the multiple water body reflectances, and obtain the standard deviation of the reflectance of each grid at the same level based on the mean reflectance and the multiple water body reflectances;

[0077] S22. Obtain the standard deviation ratio based on the ratio of the standard deviation of reflectance to the mean of reflectance;

[0078] S23. Obtain the water gradient and vertical gradient of each grid at the same level, and obtain the corresponding gradient magnitude based on each water gradient and vertical gradient;

[0079] S24. Obtain the information entropy of each peer grid, and obtain the local heterogeneity index of each peer grid based on the sum of the product of the information entropy and its weight coefficient, the product of the gradient magnitude and its weight coefficient, and the product of the standard deviation ratio and its weight coefficient.

[0080] As described in steps S21-S24 above, information entropy is used to quantify the texture complexity within a grid block. Higher entropy values ​​indicate more complex textures. This invention obtains the average reflectance of each grid at the same level using multiple water body reflectance values, and calculates the standard deviation of the reflectance for each grid at the same level based on the average reflectance and the multiple water body reflectance values. The standard deviation ratio is obtained by comparing the standard deviation and the average reflectance. By obtaining the average reflectance of multiple water bodies, reflectance information from different regions can be effectively integrated, thereby reducing local noise from single water body data and improving the reliability of overall water health assessment. The standard deviation of reflectance reflects the amplitude and fluctuation of water body reflectance changes. By calculating the standard deviation, the reflectance differences between different regions can be quantified, thereby identifying potential hazards. In the context of water quality changes or imbalances in aquatic ecosystems, the standard deviation ratio can provide the relative level of reflectance fluctuations, further illustrating the stability and trends of water bodies. A higher standard deviation ratio may indicate significant reflectance fluctuations in certain areas, which may be related to water quality changes, pollution sources, or ecological heterogeneity. This helps to more accurately assess the dynamic changes in water health, overcoming the dependence on single data points in traditional methods. By acquiring the water gradient and vertical gradient of each grid at the same level, and obtaining the corresponding gradient amplitude based on each gradient, and by acquiring the information entropy of each grid at the same level, and obtaining the local heterogeneity index of each grid at the same level based on the information entropy, gradient amplitude, and standard deviation ratio, the water gradient and vertical gradient can reveal the water's... The characteristics of water flow and material distribution within a body reflect its hierarchical structure and energy transformation. This information can reveal whether there are significant health differences between different levels of the water body, providing a more comprehensive perspective on aquatic ecological health. This is particularly important for aquatic ecosystems influenced by multiple factors, offering a more complete health assessment. Gradient amplitude is a crucial indicator in water health assessment, reflecting changes in the material and energy gradients between different levels of the water body. By calculating gradient amplitude, the magnitude of change in various regions of the water body can be quantified, helping to identify potential sources of water stress. A high gradient amplitude may indicate significant ecological stress or pollution sources, providing strong support for accurately assessing the health status of water bodies. Entropy reflects the complexity and disorder of data. Higher information entropy in water bodies indicates greater complexity and diversity of the aquatic ecosystem. In aquatic health monitoring, calculating information entropy helps determine whether a water body is in ecological balance and helps identify potential problems in the ecosystem. Lower information entropy may indicate poor water health or water pollution. The local heterogeneity index integrates information entropy, gradient amplitude, and standard deviation ratio to provide a comprehensive assessment indicator of water health. By calculating this index, the ecological differences between various grids within a water body can be fully reflected, and healthy areas and potentially problematic areas can be effectively distinguished. The local heterogeneity index provides a reliable basis for dynamic monitoring and early warning, enabling timely detection of trends in water health changes.Therefore, effective intervention measures can be taken.

[0081] In one embodiment, step S3, which divides the target water body region into multiple highly heterogeneous water body regions and low heterogeneous water body regions based on the local heterogeneity index, includes:

[0082] S31. Sort multiple grids of the same level according to the magnitude of their corresponding local heterogeneity indices to obtain a grid sorting table;

[0083] S32. Set a preset segmentation threshold, and divide the grid sorting table into a high heterogeneous grid sorting table and a low heterogeneous grid sorting table according to the preset segmentation threshold.

[0084] S33. Obtain the local water area corresponding to each grid of the same level in the target water area, and mark the local water area corresponding to each grid of the same level in the high heterogeneous grid sorting table as a high heterogeneous water area.

[0085] S34. Mark the local water body area corresponding to each grid of the same level in the low heterogeneous grid sorting table as a low heterogeneous water body area.

[0086] As described in steps S31-S34 above, this invention obtains a grid sorting table by sorting multiple grids of the same level according to the magnitude of their corresponding local heterogeneity indices. A preset segmentation threshold is established, and the grid sorting table is divided into a high-heterogeneity grid sorting table and a low-heterogeneity grid sorting table based on this threshold. The local water area corresponding to each grid of the same level in the target water body region is obtained, and the local water area corresponding to each grid of the high-heterogeneity grid sorting table is marked as a high-heterogeneity water area. Similarly, the local water area corresponding to each grid of the low-heterogeneity grid sorting table is marked as a low-heterogeneity water area. By sorting the heterogeneity indices of the grids, the spatial resolution of different regions can be effectively improved, and the division between high-heterogeneity and low-heterogeneity regions becomes clearer, thus providing a more accurate water health assessment. By setting a threshold segmentation, grids can be effectively distinguished according to their heterogeneity, ensuring accurate monitoring of high-heterogeneity regions. The challenges of diverse data sources and heterogeneous data types faced by traditional technologies can be overcome by setting reasonable thresholds and segmenting, allowing different types of... The effective fusion of data from different regions avoids analytical errors caused by data contamination. This segmentation process ensures that data from highly heterogeneous and low-heterogeneous areas do not interfere with each other, thus contributing to more accurate health assessments. Marking highly heterogeneous areas as highly heterogeneous water bodies ensures precise assessment of the areas of greatest concern in the water body. This not only improves the focus of monitoring but also strengthens the dynamic monitoring of these high-risk areas, helping to detect changes in the ecological health of the water body in a timely manner. Highly heterogeneous areas are often important indicators of water health. By specifically marking these areas, resources can be concentrated for in-depth analysis and assessment, ensuring optimal resource allocation and improving monitoring efficiency and effectiveness. Effectively marking low-heterogeneous areas helps optimize the allocation of monitoring resources, ensuring that highly heterogeneous areas receive more attention while avoiding excessive intervention in low-heterogeneous areas, saving monitoring costs and time. Clear marking of low-heterogeneous water bodies helps improve the response speed and sensitivity of the overall water body ecological assessment system, significantly promoting the accuracy of long-term monitoring and health early warning.

[0087] In one embodiment, step S5, which involves obtaining the first dynamic sampling frequency of the highly heterogeneous water body area based on multiple sets of first real-time monitoring data, includes:

[0088] S51. Based on each of the first real-time monitoring data, obtain multiple water quality monitoring data for each highly heterogeneous water body area within a preset time period, and obtain the average water quality monitoring value based on the multiple water quality monitoring data.

[0089] S52. Obtain the water quality monitoring standard deviation based on the water quality monitoring mean and multiple water quality monitoring data, and obtain the local dynamic fluctuation coefficient of each highly heterogeneous water body area based on the water quality monitoring standard deviation and the water quality monitoring mean.

[0090] S53. Obtain the first dynamic fluctuation coefficient by adding up the multiple local dynamic fluctuation coefficients;

[0091] S54. Obtain the reference sampling frequency and reference fluctuation coefficient of the highly heterogeneous water body area, and obtain the dynamic fluctuation ratio based on the ratio of the reference fluctuation coefficient to the first dynamic fluctuation coefficient.

[0092] S55. Obtain the first dynamic sampling frequency based on the product of the dynamic fluctuation ratio and the reference sampling frequency.

[0093] As described in steps S51-S55 above, this invention acquires multiple water quality monitoring data for each highly heterogeneous water body area within a preset time period using each of the first real-time monitoring data. It then obtains the water quality monitoring mean based on these multiple data points, and calculates the water quality monitoring standard deviation using the mean and multiple data points. By calculating the mean of these multiple data points, the basic trend and overall level of water quality can be obtained. The mean, as a reflection of central tendency, helps identify changes in the health status of the water body and provides a standardized benchmark for subsequent volatility analysis. The standard deviation, as a measure of water quality volatility, can reveal the stability of the water body over a time span. By calculating the standard deviation, fluctuations in water quality indicators within the water body can be effectively identified. This method determines whether there are unstable factors in the health status of water bodies and obtains the local dynamic fluctuation coefficient for each highly heterogeneous water body area based on the water quality monitoring standard deviation and mean. The local dynamic fluctuation coefficient combines the water quality mean and standard deviation, enabling a more accurate assessment of the dynamic changes in each highly heterogeneous water body area. For highly heterogeneous water body areas, the mean or standard deviation alone cannot fully reflect the complexity and dynamic characteristics of the water quality. The fluctuation coefficient comprehensively considers the degree of fluctuation of the water body under different conditions, thus providing support for more refined water quality monitoring and assessment. A first dynamic fluctuation coefficient is obtained by obtaining multiple local dynamic fluctuation coefficients, and a global first dynamic fluctuation coefficient is generated by summing these multiple local dynamic fluctuation coefficients, which can provide a... The measurement of overall water body health fluctuations, with the first dynamic fluctuation coefficient as a core indicator for overall assessment, enables the technical solution to further determine the dynamic change state of the water body based on the overall trend of regional fluctuations. This facilitates horizontal comparisons between multiple water body areas, ensuring more comprehensive water quality monitoring and more objective assessments. By obtaining the benchmark sampling frequency and benchmark fluctuation coefficient for highly heterogeneous water body areas, a reference standard matching the water body's health status is provided for obtaining the benchmark sampling frequency and benchmark fluctuation coefficient. This helps to establish a reasonable reference framework for dynamic water quality monitoring, making subsequent dynamic change assessments more targeted and accurate. It also enhances the system's flexibility, adapting to the specific needs of different water body areas, and based on the benchmark fluctuation coefficient and the first dynamic fluctuation coefficient... The fluctuation coefficient yields the dynamic fluctuation ratio. The first dynamic sampling frequency is obtained by comparing the dynamic fluctuation ratio with the benchmark sampling frequency. The dynamic fluctuation ratio, by comparing the first dynamic fluctuation coefficient with the benchmark fluctuation coefficient, reveals the degree of dynamic change in the water body. A high ratio indicates that the water body's fluctuations exceed the expected range, potentially indicating ecological health problems. Conversely, a low ratio indicates smaller fluctuations and a relatively stable health status. Calculating this ratio allows for further optimization of the water quality monitoring early warning mechanism, timely detection of potential risks, and improvement of the system's response capability and sensitivity. The goal of obtaining the first dynamic sampling frequency is to dynamically adjust the water quality monitoring sampling frequency based on the dynamic fluctuation ratio, enabling real-time adjustments to the sampling strategy according to actual water quality fluctuations.Ensuring sufficient density of water quality data collection at critical moments improves the accuracy of water body health monitoring. Flexible adjustment of sampling frequency better addresses changes caused by water quality fluctuations, improving monitoring efficiency and reducing resource waste. Combining different data types using statistical methods such as standard deviation, mean, and fluctuation coefficient effectively integrates data and provides more accurate dynamic water quality assessments. Multi-level, multi-dimensional water quality monitoring data analysis makes water body health assessments more comprehensive, reflecting the individual fluctuation characteristics of different water areas and enhancing the system's adaptability to complex environments. Dynamic sampling frequency adjustment allows for real-time adjustments to the monitoring frequency based on the dynamic characteristics of water quality changes, making the system's response to emergencies and long-term trends more timely and sensitive, providing more effective early warning capabilities.

[0094] In one embodiment, step S5, which involves sampling based on the first dynamic sampling frequency to obtain a first comprehensive health index for a highly heterogeneous water body area, includes:

[0095] S56. Obtain the water flow rate of the target water body area, and obtain the sampling time interval based on the reciprocal of the water flow rate;

[0096] S57. Collect the first real-time biological indicator data and the first real-time water quality parameter data of each highly heterogeneous water body area in real time according to the sampling time interval and dynamic sampling frequency;

[0097] S58. Obtain the total number of biological species and the number of individuals of each species based on each of the first real-time biological indicator data, and obtain the corresponding species richness based on the ratio of the number of individuals of each species to the total number of biological species.

[0098] S59. Calculate the species diversity index for each highly heterogeneous water body zone based on the aforementioned species richness and total biological species, wherein the calculation formula is:

[0099]

[0100] Where W(DY) represents the species diversity index, N represents the total number of biological species, n represents the species richness index, and W(FD) represents the species richness index. n This represents the species richness of the nth species;

[0101] S510. Obtain water quality physical parameters and water quality chemical parameters based on each of the first real-time water quality parameter data, and obtain the water quality physical pollution index based on the water quality physical parameters;

[0102] S511. Obtain the water quality chemical pollution index based on the water quality chemical parameters, and obtain the total water quality pollution index based on the sum of the water quality chemical pollution index and the water quality physical pollution index.

[0103] S512. Obtain the ecological health index of the corresponding highly heterogeneous water body area based on the sum of each of the total water pollution index and species diversity index, and obtain the first comprehensive health index by summing multiple ecological health indices.

[0104] As described in steps S56-S512 above, this invention acquires the water flow rate of the target water body area and obtains the sampling time interval based on the water flow rate. The water flow rate is an important indicator of the dynamic changes in water bodies, directly affecting the flow patterns and physical and chemical properties of the water. By acquiring the water flow rate in real time, the sampling frequency can be adjusted according to changes in water flow, avoiding data deviations caused by inappropriate sampling times. Dynamically adjusting the sampling time interval based on the water flow rate helps to increase the sampling frequency when water flow changes significantly, improving the timeliness and representativeness of monitoring data, and ensuring a comprehensive assessment of the ecological state of the water body. The first real-time biological indicator data and the first real-time water quality parameters of each highly heterogeneous water body area are collected in real time through the sampling time interval and dynamic sampling frequency. By optimizing sampling frequency and time intervals, real-time acquisition of water quality and biological indicator data in different regions is achieved, particularly for highly heterogeneous water bodies. These areas often experience significant water quality fluctuations due to factors such as water flow and topography. Dynamic sampling frequency ensures timely capture of effective data during rapid water quality changes, improving monitoring accuracy. Real-time data acquisition reduces the time delay in water health assessment compared to traditional static sampling, increasing the response speed to water health issues. The total number of biological species and the number of individuals for each species are obtained through each real-time biological indicator data point. These total number of species and individuals are crucial parameters reflecting the ecological health of aquatic bodies. By acquiring biological indicator data in real-time and accurately calculating these data, a more direct reflection of water quality can be achieved. Changes in biodiversity within a region can be precisely identified by real-time calculations of the number of individuals for each species. This is particularly helpful in detecting early signs of ecological imbalance, especially when the populations of specific species change. Species richness can be obtained based on the number of individuals and the total number of species for each species. Species richness is a crucial indicator of ecological health, effectively reflecting the diversity of aquatic biological communities. By obtaining real-time data on the number of individuals and the total number of species, the species richness of each highly heterogeneous water body can be accurately calculated. Changes in richness can reveal changes in the ecosystem; for example, a significant decrease in the number of individuals of a particular species may indicate a drastic change in the ecological environment. Calculating the species richness of each highly heterogeneous water body using multiple species richness and total number of species can reveal changes in the ecosystem. The species diversity index of aquatic areas is a core indicator of ecological health assessment. It comprehensively considers both species diversity and abundance. By combining multiple species richness and total abundance data, it can comprehensively assess the relationships and distribution among different species within the water body, further enhancing the scientific rigor of ecological health assessment and improving the understanding of the ecological roles of different species. This allows water health monitoring to move beyond relying on a single indicator and improve accuracy through multi-dimensional data analysis. It obtains physical and chemical parameters of water quality from each real-time water quality parameter data point. The physical parameters yield the physical pollution index, and the chemical parameters yield the chemical pollution index. These physical and chemical parameters are key factors in determining the pollution status of water bodies.Real-time monitoring of water quality parameters allows for faster reflection of changes in water pollutants, timely detection of pollution sources, and prompt implementation of corresponding measures to reduce the risk of water quality deterioration. This provides more comprehensive data support for refined physical and chemical water quality monitoring, effectively addressing the shortcomings of existing monitoring methods that focus insufficiently on single water quality indicators. The physical pollution index, through quantitative indicators such as suspended solids content and turbidity, reflects the degree of physical pollution in water bodies. This index helps to quickly assess the physical pollution of water bodies and provides a basis for developing remediation plans. The chemical pollution index, through chemical parameters such as dissolved oxygen, pH, and heavy metals, reflects the degree of pollution from harmful chemicals in water bodies. Complementing the physical pollution index, this index provides a more comprehensive assessment of water pollution, enabling timely detection of the sources and trends of chemical pollution and providing scientific guidance for water quality restoration, ensuring water safety. The total water pollution index is obtained by combining the physical and chemical pollution indices. This study yielded a comprehensive water pollution index, capable of considering multiple factors contributing to water pollution. It serves as a more precise pollution assessment tool. The introduction of the comprehensive water pollution index enhances the overall capabilities of existing monitoring systems, moving beyond reliance on a single indicator to integrate multi-dimensional evaluations, thus improving the overall accuracy of water quality assessments. By using each comprehensive water pollution index and species diversity index, an ecological health index is obtained for corresponding highly heterogeneous water bodies. A first comprehensive health index is derived from multiple ecological health indices. This ecological health index is a key indicator for comprehensively assessing the health status of aquatic ecosystems, integrating both water pollution and biodiversity aspects. It provides a more comprehensive reflection of the ecological health status of water bodies. The comprehensive health index offers a high-level water health assessment result. Combined with ecological health data from multiple regions and time periods, it provides water ecological management departments with a global and long-term assessment basis, effectively eliminating the interference of local data fluctuations on the overall assessment and enhancing the reliability and accuracy of the monitoring system.

[0105] In one embodiment, step S7, which involves obtaining a total health index based on the second comprehensive health index and the first comprehensive health index, and issuing an early warning for the target water area based on the total health index, includes:

[0106] S71. Obtain the total area of ​​the target water body region and the first actual area of ​​each highly heterogeneous water body region, and obtain the first total proportion weight coefficient of all highly heterogeneous water body regions based on the ratio of multiple first actual areas to the total area.

[0107] S72. Obtain the second actual area of ​​each low heterogeneous water body area, and obtain the second total proportion weight coefficient of the low heterogeneous water body area based on the ratio of multiple second actual areas to the total area.

[0108] S73. Calculate the total health index based on the first total weighting coefficient, the first comprehensive health index, the second total weighting coefficient, and the second comprehensive health index, wherein the calculation formula is:

[0109] Z(JZ)=α*D(J1)+β*D(J2);

[0110] Where Z(JZ) represents the total health index, α represents the first total weight coefficient, D(J1) represents the first comprehensive health index, β represents the second total weight coefficient, and D(J2) represents the second comprehensive health index.

[0111] S74. Determine whether the total health index is greater than a preset threshold range;

[0112] If the total health index is greater than a preset threshold, the target water body area is determined to be severely polluted, triggering an early warning.

[0113] If the total health index is not greater than the preset threshold, the target water body area is determined to be lightly polluted and no warning is triggered.

[0114] As described in steps S71-S74 above, this invention obtains the total area of ​​the target water body region and the first actual area of ​​each highly heterogeneous water body region. Based on multiple first actual areas and the total area, it obtains the first total proportion weighting coefficient for all highly heterogeneous water body regions. By calculating the proportion weighting coefficient of highly heterogeneous water body regions, the relative importance of different water body regions in the total water body can be fully considered. This differs from the traditional method of directly calculating water health indicators, and can more precisely reflect the impact of highly heterogeneous water body regions on the ecological health of the water body. This method of calculating weighting coefficients avoids the shortcomings of simply weighting data from different water body regions, and improves the efficiency of water quality assessment through a more scientific proportional allocation. The accuracy of the overall health assessment is improved by obtaining the second actual area of ​​each low-heterogeneity water body zone and calculating the second total proportion weighting coefficient of the low-heterogeneity water body zone based on multiple second actual areas and the total area. This ensures that the data of low-heterogeneity water body zones are processed with the same precision as the data of high-heterogeneity water body zones, making the subsequent health assessment more comprehensive. By calculating the weighting coefficient of low-heterogeneity water body zones, the influence of low-heterogeneity areas on the overall health assessment is avoided, thus making the overall assessment more comprehensive and able to reflect the actual proportion of low-heterogeneity water body zones in the total water body. This allows for a more objective assessment of the contribution of different types of water body zones to the overall water health. The second total proportion weighting coefficient is used to further refine the assessment. The overall health index is calculated using a comprehensive health index, a second overall weighting coefficient, and a second comprehensive health index. It is formed by combining the weighting coefficients of highly heterogeneous and low-heterogeneous water body areas with their respective aquatic ecological health indices. This multi-dimensional comprehensive assessment method can more accurately reflect the overall health status of water bodies, rather than relying on a single indicator, thus avoiding the one-sidedness of traditional methods. This calculation method provides dynamic adjustment capabilities, reflecting the health status of water bodies in real time based on changes in different areas, providing a scientific basis for ecological protection and governance. The overall health index is determined by whether it exceeds a preset threshold range; if the overall health index exceeds the preset threshold, then... The target water body is severely polluted, triggering an early warning. If the total health index is not greater than a preset threshold, the target water body is considered to be lightly polluted, and no early warning is triggered. By setting a preset threshold range and comparing it with the total health index, an early warning can be triggered in a timely manner when the pollution level is high, ensuring the timeliness of water body ecological health monitoring. This mechanism avoids the problems of missed or misjudgment caused by lag or unclear judgment criteria in traditional methods. By accurately judging the health status of the water body and comparing it with the threshold range, this invention provides strong technical support for water pollution control through a real-time monitoring and early warning system, and provides a scientific basis for environmental protection and ecological restoration.

[0115] like Figure 2 As shown, this application also provides a dynamic monitoring and early warning system for water ecological health, comprising:

[0116] The first partitioning module is used to acquire remote sensing image data of the target water body area and divide the remote sensing image data into multiple grids of the same level.

[0117] The first acquisition module is used to acquire the water reflectance of each pixel in each of the same level grids, and to acquire the local heterogeneity index of each same level grid based on multiple water reflectances;

[0118] The second partitioning module is used to divide the target water body region into multiple highly heterogeneous water body regions and low heterogeneous water body regions according to the local heterogeneity index.

[0119] The second acquisition module is used to acquire the first real-time monitoring data of each highly heterogeneous water body area and the second real-time monitoring data of each low heterogeneous water body area.

[0120] The third acquisition module is used to acquire the first dynamic sampling frequency of the high heterogeneous water body area based on multiple first real-time monitoring data, and to sample based on the first dynamic sampling frequency to acquire the first comprehensive health index of the high heterogeneous water body area.

[0121] The fourth acquisition module is used to acquire the second dynamic sampling frequency of each low heterogeneous water body area based on multiple second real-time monitoring data, and to acquire the second comprehensive health index of the low heterogeneous water body area based on the second dynamic sampling frequency.

[0122] The early warning module is used to obtain the total health index based on the second comprehensive health index and the first comprehensive health index, and to issue an early warning for the target water area based on the total health index.

[0123] In one embodiment, the third acquisition module includes:

[0124] The first acquisition unit is used to acquire multiple water quality monitoring data for each highly heterogeneous water body area within a preset time period based on each of the first real-time monitoring data, and to acquire the average water quality monitoring value based on the multiple water quality monitoring data.

[0125] The second acquisition unit is used to acquire the water quality monitoring standard deviation based on the water quality monitoring mean and multiple water quality monitoring data, and to acquire the local dynamic fluctuation coefficient of each highly heterogeneous water body area based on the water quality monitoring standard deviation and the water quality monitoring mean.

[0126] The third acquisition unit is used to acquire the first dynamic fluctuation coefficient based on the plurality of local dynamic fluctuation coefficients;

[0127] The fourth acquisition unit is used to acquire the reference sampling frequency and reference fluctuation coefficient of the highly heterogeneous water body area, and to acquire the dynamic fluctuation ratio based on the reference fluctuation coefficient and the first dynamic fluctuation coefficient.

[0128] The fifth acquisition unit is used to acquire the first dynamic sampling frequency based on the dynamic fluctuation ratio and the reference sampling frequency.

[0129] It should be noted that each module and unit in the dynamic monitoring and early warning system for water ecological health corresponds one-to-one with the steps in the dynamic monitoring and early warning method for water ecological health.

[0130] like Figure 3 As shown, this application also provides a computer device, which can be a server, and its internal structure can be as follows: Figure 3 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores all data required for the process of the dynamic monitoring and early warning method for water ecological health. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements the dynamic monitoring and early warning method for water ecological health.

[0131] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer equipment on which the present application is applied.

[0132] An embodiment of this application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements any one of the above-described methods for dynamic monitoring and early warning of water ecological health.

[0133] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media provided in this application and in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual-speed SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0134] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, apparatus, article, or method. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0135] The above description is merely a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A method for dynamic monitoring and early warning of aquatic ecological health, characterized in that, include: Acquire remote sensing image data of the target water body area, and divide the remote sensing image data into multiple equal-level grids; Obtain the water reflectance of each pixel within each of the sibling grids, and obtain the local heterogeneity index of each sibling grid based on multiple water reflectances; Based on the local heterogeneity index, the target water body area is divided into multiple highly heterogeneous water body areas and low heterogeneous water body areas; Acquire the first real-time monitoring data for each highly heterogeneous water body area and the second real-time monitoring data for each low-heterogeneous water body area; A first dynamic sampling frequency is obtained based on multiple first real-time monitoring data, and sampling is performed based on the first dynamic sampling frequency to obtain a first comprehensive health index for the highly heterogeneous water body area. A second dynamic sampling frequency is obtained based on multiple second real-time monitoring data, and sampling is performed based on the second dynamic sampling frequency to obtain a second comprehensive health index for the low heterogeneous water body area; The total health index is obtained based on the second comprehensive health index and the first comprehensive health index, and an early warning is issued for the target water area based on the total health index.

2. The method for dynamic monitoring and early warning of water ecological health according to claim 1, characterized in that, The step of obtaining the local heterogeneity index of each same-level grid based on the reflectivity of multiple water bodies includes: The mean reflectance of each grid at the same level is obtained based on the reflectance of multiple water bodies, and the standard deviation of reflectance of each grid at the same level is obtained based on the mean reflectance and the reflectance of multiple water bodies. The standard deviation ratio is obtained based on the standard deviation of reflectance and the mean reflectance. Obtain the water gradient and vertical gradient of each grid at the same level, and obtain the corresponding gradient magnitude based on each water gradient and vertical gradient; Obtain the information entropy of each peer grid, and obtain the local heterogeneity index of each peer grid based on the information entropy, gradient magnitude, and standard deviation ratio.

3. The method for dynamic monitoring and early warning of water ecological health according to claim 1, characterized in that, The step of dividing the target water body region into multiple highly heterogeneous water body regions and low heterogeneous water body regions based on the local heterogeneity index includes: Multiple grids of the same level are sorted according to the magnitude of their corresponding local heterogeneity indices to obtain a grid sorting table; A preset segmentation threshold is set, and the grid sorting table is divided into a high heterogeneous grid sorting table and a low heterogeneous grid sorting table according to the preset segmentation threshold. Obtain the local water area corresponding to each grid at the same level in the target water area, and mark the local water area corresponding to each grid at the same level in the high heterogeneous grid sorting table as a high heterogeneous water area; The local water body region corresponding to each grid of the same level in the low heterogeneous grid sorting table is marked as a low heterogeneous water body region.

4. The method for dynamic monitoring and early warning of water ecological health according to claim 1, characterized in that, The step of obtaining the first dynamic sampling frequency based on multiple sets of the first real-time monitoring data includes: Based on each of the first real-time monitoring data, multiple water quality monitoring data for each highly heterogeneous water body area within a preset time period are obtained, and the average water quality monitoring value is obtained based on the multiple water quality monitoring data. The water quality monitoring standard deviation is obtained based on the water quality monitoring mean and multiple water quality monitoring data, and the local dynamic fluctuation coefficient of each highly heterogeneous water body area is obtained based on the water quality monitoring standard deviation and the water quality monitoring mean. The first dynamic fluctuation coefficient is obtained based on the multiple local dynamic fluctuation coefficients; Obtain the reference sampling frequency and reference fluctuation coefficient of the highly heterogeneous water body area, and obtain the dynamic fluctuation ratio based on the reference fluctuation coefficient and the first dynamic fluctuation coefficient; The first dynamic sampling frequency is obtained based on the dynamic fluctuation ratio and the reference sampling frequency.

5. The method for dynamic monitoring and early warning of water ecological health according to claim 1, characterized in that, The step of obtaining a first comprehensive health index for a highly heterogeneous water body area based on the first dynamic sampling frequency includes: Obtain the water flow rate in the target water body area, and determine the sampling time interval based on the water flow rate; The first real-time biological indicator data and the first real-time water quality parameter data of each highly heterogeneous water body area are collected in real time according to the sampling time interval and dynamic sampling frequency. The total number of biological species and the number of individuals of each species are obtained based on each of the first real-time biological indicator data, and the corresponding species richness is obtained based on the number of individuals of each species and the total number of biological species. The species diversity index of each highly heterogeneous water body area was obtained based on multiple species richness and total number of biological species; Water quality physical parameters and water quality chemical parameters are obtained based on each of the first real-time water quality parameter data, and water quality physical pollution index is obtained based on the water quality physical parameters; The water quality chemical pollution index is obtained based on the water quality chemical parameters, and the total water quality pollution index is obtained based on the water quality chemical pollution index and the water quality physical pollution index. The first comprehensive health index is obtained based on each total water pollution index and species diversity index.

6. The method for dynamic monitoring and early warning of water ecological health according to claim 1, characterized in that, The step of obtaining a total health index based on the second comprehensive health index and the first comprehensive health index, and issuing an early warning for the target water area based on the total health index, includes: Obtain the total area of ​​the target water body region and the first actual area of ​​each highly heterogeneous water body region, and obtain the first total proportion weight coefficient of all highly heterogeneous water body regions based on multiple first actual areas and total areas; Obtain the second actual area of ​​each low heterogeneous water body area, and obtain the second total proportion weighting coefficient of the low heterogeneous water body area based on multiple second actual areas and the total area; The total health index is obtained based on the first total weighting coefficient, the first comprehensive health index, the second total weighting coefficient, and the second comprehensive health index. Determine whether the total health index is greater than a preset threshold range; If the total health index is greater than a preset threshold, the target water body area is determined to be severely polluted, triggering an early warning. If the total health index is not greater than the preset threshold, the target water body area is determined to be lightly polluted and no warning is triggered.

7. A dynamic monitoring and early warning system for water ecological health, characterized in that, include: The first partitioning module is used to acquire remote sensing image data of the target water body area and divide the remote sensing image data into multiple grids of the same level. The first acquisition module is used to acquire the water reflectance of each pixel in each of the same level grids, and to acquire the local heterogeneity index of each same level grid based on multiple water reflectances; The second partitioning module is used to divide the target water body region into multiple highly heterogeneous water body regions and low heterogeneous water body regions according to the local heterogeneity index. The second acquisition module is used to acquire the first real-time monitoring data of each highly heterogeneous water body area and the second real-time monitoring data of each low heterogeneous water body area. The third acquisition module is used to acquire the first dynamic sampling frequency of the highly heterogeneous water body area based on multiple first real-time monitoring data, and to sample based on the first dynamic sampling frequency to acquire the first comprehensive health index of the highly heterogeneous water body area. The fourth acquisition module is used to acquire a second dynamic sampling frequency based on multiple second real-time monitoring data, and to acquire a second comprehensive health index of the low heterogeneous water body area based on the second dynamic sampling frequency. The early warning module is used to obtain the total health index based on the second comprehensive health index and the first comprehensive health index, and to issue an early warning for the target water area based on the total health index.

8. The water ecological health dynamic monitoring and early warning system according to claim 7, characterized in that, The third acquisition module includes: The first acquisition unit is used to acquire multiple water quality monitoring data for each highly heterogeneous water body area within a preset time period based on each of the first real-time monitoring data, and to acquire the average water quality monitoring value based on the multiple water quality monitoring data. The second acquisition unit is used to acquire the water quality monitoring standard deviation based on the water quality monitoring mean and multiple water quality monitoring data, and to acquire the local dynamic fluctuation coefficient of each highly heterogeneous water body area based on the water quality monitoring standard deviation and the water quality monitoring mean. The third acquisition unit is used to acquire the first dynamic fluctuation coefficient based on the plurality of local dynamic fluctuation coefficients; The fourth acquisition unit is used to acquire the reference sampling frequency and reference fluctuation coefficient of the highly heterogeneous water body area, and to acquire the dynamic fluctuation ratio based on the reference fluctuation coefficient and the first dynamic fluctuation coefficient. The fifth acquisition unit is used to acquire the first dynamic sampling frequency based on the dynamic fluctuation ratio and the reference sampling frequency.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images