A water ecological monitoring method, device, equipment and storage medium

Abstract

The application discloses a kind of water area ecology monitoring method, device, equipment and storage medium.Firstly, the ecological hydrological data of target water area is collected by real-time remote sensing technology, including water table color, suspended solids concentration and surrounding vegetation coverage image, radiation calibration processing is carried out on vegetation coverage image to obtain radiation brightness value and apparent reflectivity, and regional growth algorithm is used to identify vegetation area image.Combined with apparent reflectivity, atmospheric correction is carried out to obtain water surface temperature.At the same time, the predicted water level height is obtained by inputting suspended solids concentration into water level prediction model.If real-time data (such as predicted water level height, real-time water table color, real-time suspended solids concentration, vegetation color or vegetation density) is inconsistent with target data, ecological early warning is triggered.The application automatically collects and processes real-time remote sensing data of target water area, efficiently extracts key ecological indicators using algorithms and integrates multi-dimensional data, improves monitoring efficiency and accuracy, and optimizes ecological early warning effect.

Description

Technical Field

[0001] This application relates to the field of ecological monitoring technology, specifically to a method, device, equipment, and storage medium for monitoring aquatic ecology. Background Technology

[0002] Certain important river basins (such as the Yellow River) serve as major water suppliers, playing a vital role not only in the local ecological environment and biodiversity but also in providing essential water sources for downstream areas. However, with the continuous expansion of human activities and changes in natural factors, these important river basins face severe challenges, such as soil erosion, increased pollution, and serious degradation of the ecological environment. These problems not only threaten the stability of local ecosystems but may also pose potential risks to water security in downstream and wider areas.

[0003] Traditional monitoring methods rely on manual methods to monitor the hydrology and ecology of these important river basins. While manual monitoring can provide some field data, its high cost, long processing time, and inability to comprehensively cover a wide area make it inefficient when facing large-scale monitoring needs. Especially along some rivers and in their surrounding areas, manual monitoring struggles to achieve timely updates and comprehensive understanding of key data such as vegetation changes and water quality.

[0004] With the development of remote sensing technology, especially the widespread application of drones and satellite remote sensing, more efficient and wide-area solutions have been provided for hydrological monitoring. Drones provide high-resolution imagery data, enabling precise capture of changes in local areas; while satellite remote sensing can cover large areas and quickly acquire ground information. The combination of the two provides richer data support for monitoring. However, despite significant progress in the application of remote sensing technology, the processing of data acquired through remote sensing still relies on manual analysis, which makes it difficult to effectively improve processing speed, efficiency, and accuracy. This situation increases the workload, thereby increasing the possibility of false warnings and affecting the ability to respond promptly to hydrological and ecological changes.

[0005] Therefore, how to improve the automation and intelligence of remote sensing data processing to enhance the response speed, accuracy and efficiency of early warning systems and respond to hydrological and ecological changes in a timely manner is a technical problem that urgently needs to be solved by those skilled in the art. Summary of the Invention

[0006] To address the aforementioned issues, this application provides a method, apparatus, equipment, and storage medium for monitoring aquatic ecosystems, which can enhance the automation and intelligence of remote sensing data processing, thereby improving the response speed, accuracy, and efficiency of early warning systems and enabling timely responses to hydrological and ecological changes.

[0007] The embodiments of this application disclose the following technical solutions:

[0008] A method for monitoring aquatic ecology, the method comprising:

[0009] Collect real-time remote sensing eco-hydrological data of the target water area; the real-time remote sensing eco-hydrological data includes the real-time water surface color of the target water area, the real-time suspended solids concentration of the target water area, and the real-time vegetation cover image of the surrounding area of ​​the target water area.

[0010] The real-time vegetation cover image is radiometrically calibrated to obtain radiance values ​​and apparent reflectance, and a region growing algorithm is used to identify vegetation regions in the real-time vegetation cover image.

[0011] The water surface temperature is obtained by atmospheric correction of the radiance value based on the apparent reflectance.

[0012] The real-time suspended solids concentration is input into a pre-built water level prediction model to obtain the predicted water level height;

[0013] If any one or more of the following conditions are met: the predicted water level does not match the target water level, the real-time water meter color does not match the target water meter color, the real-time suspended solids concentration does not match the target suspended solids concentration, the vegetation color in the vegetation area image does not match the target color, or the vegetation density in the vegetation area image does not match the target density, then an ecological warning for the target water area will be issued.

[0014] In one possible implementation, the radiometric calibration of the real-time vegetation cover image to obtain radiance values ​​and apparent reflectance includes:

[0015] The digital quantization values ​​of the vegetation cover image are converted into the radiance values ​​respectively;

[0016] The apparent reflectance is calculated based on the radiance value.

[0017] In one possible implementation, the step of atmospherically correcting the radiance value based on the apparent reflectance to obtain the water surface temperature includes:

[0018] The apparent reflectance was atmospherically corrected using the 6S atmospheric correction model to obtain the corrected apparent reflectance.

[0019] Based on the corrected apparent reflectance, the radiance value is converted into surface luminance temperature using the 6S atmospheric correction model.

[0020] The Earth's surface brightness temperature is converted into water surface temperature using the blackbody radiation law.

[0021] In one possible implementation, the construction process of the pre-built water level prediction model includes:

[0022] Obtain multiple historical water level heights and multiple historical suspended solids concentrations that have a one-to-one correspondence with the historical water level heights;

[0023] The water level prediction model is obtained by inputting multiple historical water level heights, multiple historical suspended solids concentrations, and the one-to-one correspondence between historical water level heights and historical suspended solids concentrations into a random forest regression model for model training.

[0024] In one possible implementation, the water quality parameters are collected via a ground-based sensor network, and the vegetation cover images are collected via remote sensing satellites and / or drones.

[0025] A monitoring device for aquatic ecology, the device comprising:

[0026] The data acquisition unit is used to acquire real-time remote sensing eco-hydrological data of the target water area; the real-time remote sensing eco-hydrological data includes the real-time water surface color of the target water area, the real-time suspended solids concentration of the target water area, and the real-time vegetation cover image of the surrounding area of ​​the target water area.

[0027] The data processing unit is used to perform radiometric calibration on the real-time vegetation cover image to obtain radiance values ​​and apparent reflectance.

[0028] A vegetation image recognition unit is used to identify vegetation region images in the real-time vegetation cover image using a region growing algorithm.

[0029] A water surface temperature acquisition unit is used to perform atmospheric correction on the radiance value based on the apparent reflectance to obtain the water surface temperature.

[0030] The water level prediction unit is used to input the real-time suspended solids concentration into a pre-built water level prediction model to obtain the predicted water level height.

[0031] The early warning unit issues an ecological early warning for the target water area if any one or more of the following conditions are met: the predicted water level does not match the target water level; the real-time water meter color does not match the target water meter color; the real-time suspended solids concentration does not match the target suspended solids concentration; the vegetation color in the vegetation area image does not match the target color; or the vegetation density in the vegetation area image does not match the target density.

[0032] In one possible implementation, the data processing unit specifically includes:

[0033] The first conversion unit is used to convert the digital quantization values ​​of the vegetation cover image into the radiance values ​​respectively.

[0034] A calculation unit is used to calculate the apparent reflectance based on the radiance value.

[0035] In one possible implementation, the water meter temperature acquisition unit specifically includes:

[0036] The correction unit is used to perform atmospheric correction on the apparent reflectance using the 6S atmospheric correction model to obtain the corrected apparent reflectance.

[0037] The second conversion unit is used to convert the radiance value into surface radiance temperature based on the corrected apparent reflectance using the 6S atmospheric correction model.

[0038] The third conversion unit is used to convert the surface brightness temperature into water surface temperature using the blackbody radiation law.

[0039] A device for monitoring aquatic ecology includes: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the aquatic ecology monitoring method as described above.

[0040] A computer-readable storage medium storing instructions that, when executed on a terminal device, cause the terminal device to perform the aquatic ecology monitoring method as described above.

[0041] Compared with the prior art, this application has the following advantages:

[0042] This application provides a method, apparatus, device, and storage medium for monitoring aquatic ecology. Specifically, when implementing the aquatic ecology monitoring method provided in this application, real-time remote sensing eco-hydrological data of the target water area can first be collected, including real-time water surface color, suspended solids concentration, and surrounding vegetation cover images. By performing radiometric calibration on the vegetation cover images, radiance values ​​and apparent reflectance are obtained, and a region growing algorithm is used to identify the vegetation area image. Atmospheric correction is performed on the radiance values ​​based on the apparent reflectance to obtain the water surface temperature. The real-time suspended solids concentration is input into a pre-constructed water level prediction model to obtain the predicted water level height. If any one or more of the predicted water level height, real-time water surface color, real-time suspended solids concentration, vegetation color, or vegetation density do not meet the preset target, an ecological warning is automatically issued, achieving efficient and accurate aquatic ecology monitoring and early warning.

[0043] This application enables the automatic acquisition and processing of real-time remote sensing data of target water areas, and efficiently extracts key ecological indicators such as water surface color, suspended solids concentration, and vegetation cover through a series of algorithms (such as regional growth algorithm and atmospheric correction). This automated data processing workflow significantly improves monitoring efficiency, reduces errors caused by human operation, and enhances processing accuracy and efficiency. Simultaneously, this application enhances the monitoring capability of aquatic ecological changes by integrating multi-dimensional data (such as water surface color, suspended solids concentration, and vegetation cover) for comprehensive analysis. By establishing predictive models and conducting dynamic comparisons, ecological warnings can be issued promptly if abnormal changes in ecological indicators of the target water area are detected. This timely warning mechanism provides higher response speed and accuracy for aquatic ecological protection, thereby improving the overall capability of ecological monitoring and effectively responding to aquatic ecological changes without missing critical intervention opportunities. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in this embodiment or the prior art, the drawings used in the description of the embodiment or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 A flowchart illustrating a method for monitoring aquatic ecology provided in this application embodiment;

[0046] Figure 2 A flowchart illustrating a method for obtaining water surface temperature according to an embodiment of this application;

[0047] Figure 3 A flowchart illustrating a method for predicting water level height provided in this application embodiment;

[0048] Figure 4 This is a schematic diagram of the structure of a water ecology monitoring device provided in an embodiment of this application. Detailed Implementation

[0049] To facilitate understanding of the technical solutions provided in the embodiments of this application, the background technology involved in the embodiments of this application will be described below.

[0050] Some important river basins (such as the Yellow River) are key water resource suppliers, playing vital ecological functions and providing water to downstream areas. However, with human activities and natural changes, these basins face challenges such as soil erosion, increased pollution, and ecological degradation, threatening ecological stability and water resource security. Traditional manual monitoring, while providing some data, is costly, inefficient, and lacks comprehensive coverage. Remote sensing technology, especially the application of drones and satellite remote sensing, offers more efficient and extensive monitoring solutions; however, data acquired through remote sensing still relies on manual processing, affecting processing speed, efficiency, and accuracy, and increasing the risk of false alarms.

[0051] To address this issue, this application provides a method, apparatus, device, and storage medium for monitoring aquatic ecosystems. First, real-time remote sensing technology is used to collect eco-hydrological data of the target water area, including water surface color, suspended solids concentration, and surrounding vegetation cover images. The vegetation images are then processed using radiometric calibration and a region growing algorithm to identify vegetation areas and obtain apparent reflectance. Combined with atmospherically corrected radiance values, the water surface temperature is calculated, and the suspended solids concentration is input into a water level prediction model for water level prediction. If any one or more of the predicted water level, real-time water surface color, real-time suspended solids concentration, vegetation color of the vegetation area, or vegetation density of the vegetation area deviates from the target data, an ecological warning is triggered. This application utilizes an automated process to collect and process remote sensing data of the target water area in real time, and combines algorithms such as region growing algorithms and atmospheric correction to accurately extract key ecological indicators, significantly improving monitoring efficiency, reducing errors, and enhancing processing accuracy. By comprehensively analyzing multidimensional data and establishing predictive models, abnormal changes can be quickly detected and ecological warnings can be issued, thereby providing a higher response speed and accuracy for aquatic ecological protection, comprehensively improving ecological monitoring capabilities, and effectively intervening in aquatic ecological changes.

[0052] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0053] See Figure 1 The figure is a flowchart of a method for monitoring aquatic ecology provided in an embodiment of this application, as shown below. Figure 1 As shown, the method for monitoring the aquatic ecosystem may include steps S101-S105:

[0054] S101: Collect real-time remote sensing eco-hydrological data of the target water area.

[0055] "Collecting real-time remote sensing eco-hydrological data of target water areas" refers to acquiring relevant ecological and hydrological data of target water areas (such as lakes and rivers) in real time through remote sensing technology. This data mainly includes the color of the water surface, the concentration of suspended solids, and the vegetation cover around the water area.

[0056] It should be noted that water surface color refers to the color of the water surface. Remote sensing imagery can reflect different characteristics of water bodies, such as water quality and pollutant levels. Suspended solids concentration refers to the concentration of solid particles floating in the water. These suspended solids can affect water transparency and water quality, so monitoring their concentration is crucial for assessing the health of water bodies. Vegetation cover images, collected using remote sensing technology, show the distribution of vegetation around water areas. They reflect the health of the ecological environment in that area, as vegetation cover is usually closely related to the stability of aquatic ecosystems and their pollutant adsorption capacity.

[0057] In one possible implementation, the water quality parameters are collected via a ground-based sensor network, and the vegetation cover images are collected via remote sensing satellites and / or drones.

[0058] Ground-based sensor networks: These networks collect water quality data, such as water temperature, pH, dissolved oxygen, and turbidity, through sensors deployed at specific locations. Ground-based data provides more accurate real-time water quality information and is often used in conjunction with remote sensing data to help assess the health of water bodies and their relationship with surrounding vegetation. Ground-based sensor networks include water level gauges, rain gauges, color sensors, and turbidity sensors. Water level gauges monitor water level, rain gauges monitor rainfall, color sensors monitor water color, and turbidity sensors monitor suspended solids concentration.

[0059] Remote sensing satellite / UAV imagery: Remote sensing satellites provide large-scale, continuous ground information, suitable for monitoring vegetation cover on a large scale. UAVs, on the other hand, provide high-resolution data, particularly suitable for monitoring fine-scale areas. By analyzing these images, vegetation cover, greening index, and other vegetation-related ecological characteristics can be assessed.

[0060] This step aims to obtain the current eco-hydrological status of the target water body, facilitating real-time monitoring of the water environment and providing data support for decision-making and early warning. This data can be used not only for ecological environmental protection but also to aid in water quality management, resource planning, and other analyses.

[0061] S102: Perform radiometric calibration on the real-time vegetation cover image to obtain radiance values ​​and apparent reflectance, and use a region growing algorithm to identify vegetation regions in the real-time vegetation cover image.

[0062] After acquiring real-time remote sensing eco-hydrological data of the target water area, the first step is to perform radiometric calibration on the acquired vegetation cover images. The purpose of radiometric calibration is to convert the digital quantized values ​​(i.e., pixel values) in the image into actual physical quantities (such as radiance values). Radiance values ​​represent the radiant intensity corresponding to each pixel in the image and are a representation of the original spectral information in the remote sensing data. This process can eliminate noise in the image data or errors caused by different shooting conditions (such as weather, season, etc.), thereby improving the accuracy of the data.

[0063] After obtaining the radiance value, it is necessary to further calculate the apparent reflectance based on the radiance value. Apparent reflectance refers to the intensity of light reflected by an object's surface; it is an indicator of the reflective properties of a ground object's surface. In remote sensing imagery, calculating the apparent reflectance can better reflect the true characteristics of ground objects and avoid the influence of factors such as the sensor's observation angle on image quality.

[0064] After completing radiometric calibration and obtaining radiance and apparent reflectance values, the next step is to identify vegetated areas using a region growing algorithm. Region growing is a common image segmentation method that starts from a seed point and adds neighboring pixels to an existing region according to certain rules (such as color, texture, or similarity), gradually expanding and forming a complete region. In this context, the algorithm identifies regions in the image whose reflectance characteristics match vegetation, thus separating the vegetated areas. This step helps analysts identify which areas in the image are covered by vegetation, enabling further environmental monitoring or land use analysis.

[0065] It should be noted that the formula for calculating the radiance value is: L λ =G*DN+B;

[0066] Among them, L λ G is the apparent radiance value, DN is the calibration slope, B is the absolute calibration coefficient offset, and D = 1 + 0.0167sin[2π(J-93.5) / 360], where J is the annual day and π is pi.

[0067] The formula for calculating apparent reflectance is:

[0068]

[0069] Where, ρ T Where D is the apparent reflectance, E is the astronomical distance between the Earth and the Sun, and D is the apparent reflectance. λ θ represents the spectral irradiance of the top of the atmosphere in each band, and θ is the solar zenith angle.

[0070] In summary, step S102 aims to accurately identify vegetation areas by processing the radiation information in remote sensing images and using a region growing algorithm, thereby enabling subsequent analysis and research.

[0071] S103: The water surface temperature is obtained by atmospheric correction of the radiance value based on the apparent reflectance.

[0072] Apparent reflectance refers to the ratio of reflected radiation received by remote sensing satellites or sensors from a water surface or other land surface to the incident solar radiation. This reflectance is affected by the atmosphere, the ground surface, and other environmental factors, and does not represent the actual state of the ground or water surface. Therefore, the radiance value obtained directly from remote sensing data cannot accurately reflect the temperature of the ground or water surface.

[0073] Atmospheric correction aims to remove these atmospheric influencing factors, making the radiance values ​​obtained from remote sensing data more accurately reflect the actual surface conditions. By applying atmospheric correction to radiance, a more realistic surface temperature can be obtained.

[0074] Therefore, by combining apparent reflectance with atmospheric correction of radiance, the actual temperature of the water surface or other land surfaces can be obtained.

[0075] See Figure 2 , Figure 2 This application provides a flowchart of a method for obtaining water surface temperature. Accordingly, step S103, which combines the apparent reflectance with atmospheric correction of the radiance value to obtain the water surface temperature, can be specifically implemented through steps A1-A3:

[0076] A1: The apparent reflectance is atmospherically corrected using the 6S atmospheric correction model to obtain the corrected apparent reflectance.

[0077] First, the acquired apparent reflectance was processed using the 6S (Second Simulation of the Satellite Signal in the Solar Spectrum) atmospheric correction model. This model can take into account the scattering and absorption effects in the atmosphere. By inputting specific atmospheric parameters (such as aerosol optical thickness, water vapor content, etc.), the apparent reflectance is corrected to eliminate the influence of the atmosphere, thus obtaining the corrected apparent reflectance.

[0078] It should be noted that the 6S atmospheric correction model (Second Simulation of the Satellite Signal in the Solar Spectrum, 6S) is a tool for atmospheric correction of remote sensing images. It is mainly used to eliminate the influence of the atmosphere on the ground reflectance spectrum, thereby improving the accuracy and comparability of remote sensing data.

[0079] A2: Based on the corrected apparent reflectance, the radiance value is converted into surface luminance temperature using the 6S atmospheric correction model.

[0080] Next, using the corrected apparent reflectance as a reference, the 6S atmospheric correction model is applied again to correct the radiance values ​​received by the sensor. This process converts the original radiance values ​​into surface brightness temperature unaffected by atmospheric interference. Surface brightness temperature reflects the radiation of the Earth's surface in a specific wavelength band, providing temperature information unaffected by atmospheric influence.

[0081] A3: The Earth's surface brightness temperature is converted into water surface temperature using the blackbody radiation law.

[0082] Finally, based on the surface brightness temperature, the blackbody radiation law is applied to calculate and convert the surface brightness temperature into the actual water surface temperature. The blackbody radiation law describes the relationship between the radiated energy of an object and its temperature; through this conversion, the actual water surface temperature of the target body of water can be accurately determined.

[0083] By following steps A1-A3 above, the influence of the atmosphere on remote sensing data can be effectively eliminated, ensuring that the final water surface temperature data is more accurate and reliable, and providing a solid data foundation for subsequent water quality monitoring and ecological environment assessment.

[0084] S104: Input the real-time suspended solids concentration into the pre-built water level prediction model to obtain the predicted water level height.

[0085] By inputting real-time suspended solids concentration into a pre-built water level prediction model, the future water level can be estimated using the model's algorithm and correlation parameters. This process leverages the potential correlation between suspended solids concentration and water level to predict water level based on real-time monitored suspended solids concentration data.

[0086] See Figure 3 , Figure 3 This application provides a flowchart of a method for predicting water level height, specifically, the construction process of a pre-built water level prediction model can be implemented through steps B1-B2:

[0087] B1: Obtain multiple historical water level heights and multiple historical suspended solids concentrations that have a one-to-one correspondence with the historical water level heights.

[0088] First, we collect multiple historical water level data points and corresponding historical suspended solids concentration data. This data will serve as the input and target output for training the model.

[0089] B2: Input multiple historical water level heights, multiple historical suspended solids concentrations, and the one-to-one correspondence between historical water level heights and historical suspended solids concentrations into a random forest regression model for model training to obtain the water level prediction model.

[0090] Next, historical water level heights, historical suspended solids concentrations, and their corresponding relationships are input into a random forest regression model for training. Through the learning and fitting process of the random forest regression model, a water level prediction model can be constructed, which can predict future water level heights based on historical water level and suspended solids concentration data.

[0091] This modeling approach combines historical data and machine learning techniques, which helps to capture the complex relationship between water level and suspended solids concentration, providing an effective method for predicting water levels.

[0092] S105: If any one or more of the following conditions are met: the predicted water level does not match the target water level, the real-time water meter color does not match the target water meter color, the real-time suspended solids concentration does not match the target suspended solids concentration, the vegetation color in the vegetation area image does not match the target color, or the vegetation density in the vegetation area image does not match the target density, then an ecological warning for the target water area is issued.

[0093] An ecological early warning system for a target water area can be triggered if any one or more of the predicted water level, real-time water surface color, real-time suspended solids concentration, or vegetation color and density in the vegetation area image do not meet the target requirements. This means the system monitors and detects inconsistencies with expected environmental conditions, thus indicating potential ecosystem problems or changes. Through this early warning mechanism, relevant personnel can take timely and necessary measures to adjust, monitor, or resolve emerging issues to maintain the ecological balance and environmental health of the target water area. The implementation of an ecological early warning system can effectively protect aquatic ecosystems and improve the ability to respond to changes in the ecological environment.

[0094] Specifically, this judgment process can be described in the following steps:

[0095] Predicted water level: This needs to be compared with the target water level. If the current water level does not meet the expected target, measures may need to be taken to adjust the water level.

[0096] Real-time water meter color: The color of water can often reflect changes in water quality. If the real-time water meter color does not match the target color, it may mean that the water quality has changed (e.g., an increase in pollutants).

[0097] Real-time suspended solids concentration: The concentration of suspended solids is an important indicator of water cleanliness. If the concentration exceeds or falls below the target concentration, it may affect the normal state of water quality.

[0098] Vegetation color in vegetated area images: Image analysis is used to compare whether the vegetation colors match the target colors. Color discrepancies may indicate that vegetation growth has been affected, or that there may be problems with the aquatic ecosystem.

[0099] Vegetation density in vegetated areas: Vegetation density is also an important indicator of aquatic health. Sparse or excessive vegetation may indicate an ecological imbalance.

[0100] When any one or more of the above conditions fail to meet the target standards, an ecological warning should be triggered, indicating the need to take measures to protect the aquatic ecological environment and prevent further deterioration.

[0101] It should be noted that this application does not impose specific restrictions on the numerical values ​​of target water level height, target water meter color, target suspended solids concentration, target color, and target density. Users can adjust the values ​​according to the actual situation.

[0102] Based on the content of S101-S105, real-time remote sensing eco-hydrological data of the target water area is collected, including real-time water surface color, suspended solids concentration, and surrounding vegetation cover images. First, the vegetation cover image undergoes radiometric calibration to obtain radiance values ​​and apparent reflectance, and a region growing algorithm is used to identify vegetation areas within it. Then, atmospheric correction is applied to the radiance values ​​based on apparent reflectance to obtain the water surface temperature. Next, the real-time suspended solids concentration is input into a pre-constructed water level prediction model to obtain the predicted water level height. If any one or more of the predicted water level height, real-time water surface color, real-time suspended solids concentration, vegetation color in the vegetation area image, or vegetation density in the vegetation area image do not meet the preset targets, an ecological warning is automatically issued. This application, through automated collection and processing of real-time remote sensing data of the target water area, combined with techniques such as region growing algorithms and atmospheric correction, accurately extracts ecological indicators such as water surface color, suspended solids concentration, and vegetation cover, improving monitoring efficiency and processing accuracy while reducing human error. Meanwhile, by integrating and analyzing various data sources and establishing predictive models, ecological anomalies can be detected and early warnings issued in a timely manner, enhancing the monitoring capabilities for changes in aquatic ecosystems. This early warning mechanism provides a faster and more accurate response, facilitating timely intervention and improving the overall effectiveness of ecological monitoring.

[0103] See Figure 4 , Figure 4 This is a schematic diagram of the structure of a monitoring device for aquatic ecology provided in an embodiment of this application. Figure 4 As shown, the monitoring device for the aquatic ecosystem includes:

[0104] The data acquisition unit 401 is used to acquire real-time remote sensing eco-hydrological data of the target water area; the real-time remote sensing eco-hydrological data includes the real-time water surface color of the target water area, the real-time suspended solids concentration of the target water area, and the real-time vegetation cover image of the surrounding area of ​​the target water area.

[0105] Data processing unit 402 is used to perform radiometric calibration processing on the real-time vegetation cover image to obtain radiance value and apparent reflectance;

[0106] Vegetation image recognition unit 403 is used to recognize vegetation region images in the real-time vegetation cover image using a region growing algorithm;

[0107] The water surface temperature acquisition unit 404 is used to perform atmospheric correction on the radiance value in conjunction with the apparent reflectance to obtain the water surface temperature.

[0108] The water level prediction unit 405 is used to input the real-time suspended solids concentration into a pre-built water level prediction model to obtain the predicted water level height.

[0109] The early warning unit 406 is used to issue an ecological early warning for the target water area if any one or more of the following conditions are met: the predicted water level does not match the target water level, the real-time water meter color does not match the target water meter color, the real-time suspended solids concentration does not match the target suspended solids concentration, the vegetation color in the vegetation area image does not match the target color, or the vegetation density in the vegetation area image does not match the target density.

[0110] In one possible implementation, the data processing unit 402 specifically includes:

[0111] The first conversion unit is used to convert the digital quantization values ​​of the vegetation cover image into the radiance values ​​respectively.

[0112] A calculation unit is used to calculate the apparent reflectance based on the radiance value.

[0113] In one possible implementation, the water meter temperature acquisition unit 404 specifically includes:

[0114] The correction unit is used to perform atmospheric correction on the apparent reflectance using the 6S atmospheric correction model to obtain the corrected apparent reflectance.

[0115] The second conversion unit is used to convert the radiance value into surface radiance temperature based on the corrected apparent reflectance using the 6S atmospheric correction model.

[0116] The third conversion unit is used to convert the surface brightness temperature into water surface temperature using the blackbody radiation law.

[0117] In one possible implementation, the device further includes:

[0118] The historical data acquisition unit is used to acquire multiple historical water level heights and multiple historical suspended solids concentrations that have a one-to-one correspondence with the historical water level heights.

[0119] The model training unit is used to input multiple historical water level heights, multiple historical suspended solids concentrations, and the one-to-one correspondence between historical water level heights and historical suspended solids concentrations into the random forest regression model for model training to obtain the water level prediction model.

[0120] In one possible implementation, the water quality parameters are collected via a ground-based sensor network, and the vegetation cover images are collected via remote sensing satellites and / or drones.

[0121] In addition, this application embodiment also provides a monitoring device for aquatic ecology, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the aquatic ecology monitoring method as described above.

[0122] In addition, this application embodiment also provides a computer-readable storage medium storing instructions that, when executed on a terminal device, cause the terminal device to perform the aquatic ecology monitoring method as described above.

[0123] This application provides a monitoring device for aquatic ecology. First, a data acquisition unit 401 acquires real-time water surface color, real-time suspended solids concentration, and real-time vegetation cover images of the target water area. A data processing unit 402 performs radiometric calibration on the real-time vegetation cover images to obtain radiance values ​​and apparent reflectance. A vegetation image recognition unit 403 uses a region growing algorithm to identify vegetation areas in the real-time vegetation cover images, allowing the water surface temperature acquisition unit to perform atmospheric correction on the radiance values ​​based on apparent reflectance to obtain the water surface temperature. Then, a water level prediction unit 405 obtains a predicted water level height by inputting the real-time suspended solids concentration into a pre-built water level prediction model. This allows an early warning unit 406 to issue an ecological early warning for the target water area when any one or more of the following conditions are met: the predicted water level height does not match the target water level height; the real-time water surface color does not match the target water surface color; the real-time suspended solids concentration does not match the target suspended solids concentration; the vegetation color in the vegetation area image does not match the target color; or the vegetation density in the vegetation area image does not match the target density. This application enables the automatic acquisition and processing of real-time remote sensing data of target water areas. Through a series of algorithms (such as regional growth algorithms and atmospheric correction), it efficiently extracts key ecological indicators such as water surface color, suspended solids concentration, and vegetation cover. This automated data processing workflow significantly improves monitoring efficiency, reduces errors caused by human operation, and enhances processing accuracy and efficiency. Simultaneously, by integrating multi-dimensional data for comprehensive analysis, it strengthens the monitoring capability of aquatic ecological changes. By establishing predictive models and conducting dynamic comparisons, it can promptly issue ecological warnings once abnormal changes in ecological indicators of the target water area are detected, providing higher response speed and accuracy, thereby effectively addressing aquatic ecological changes and ensuring that critical intervention opportunities are not missed.

[0124] The foregoing has provided a detailed description of a method, apparatus, device, and storage medium for monitoring aquatic ecology provided in this application. The various embodiments in the specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section. It should be noted that those skilled in the art can make several improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of the claims of this application.

[0125] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0126] It should also be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

Claims

1. A method for monitoring aquatic ecology, characterized in that, The method includes: Collect real-time remote sensing eco-hydrological data of the target water area; the real-time remote sensing eco-hydrological data includes the real-time water surface color of the target water area, the real-time suspended solids concentration of the target water area, and the real-time vegetation cover image of the surrounding area of ​​the target water area. The real-time vegetation cover image is radiometrically calibrated to obtain radiance values ​​and apparent reflectance, and a region growing algorithm is used to identify vegetation regions in the real-time vegetation cover image. The water surface temperature is obtained by atmospheric correction of the radiance value based on the apparent reflectance. The real-time suspended solids concentration is input into a pre-built water level prediction model to obtain the predicted water level height; If any one or more of the following conditions are met: the predicted water level does not match the target water level, the real-time water meter color does not match the target water meter color, the real-time suspended solids concentration does not match the target suspended solids concentration, the vegetation color in the vegetation area image does not match the target color, or the vegetation density in the vegetation area image does not match the target density, then an ecological warning for the target water area will be issued.

2. The method according to claim 1, characterized in that, The step of performing radiometric calibration on the real-time vegetation cover image to obtain radiance values ​​and apparent reflectance includes: The digital quantization values ​​of the vegetation cover image are converted into the radiance values ​​respectively; The apparent reflectance is calculated based on the radiance value.

3. The method according to claim 1, characterized in that, The process of obtaining the water surface temperature by atmospheric correction of the radiance value based on the apparent reflectance includes: The apparent reflectance was atmospherically corrected using the 6S atmospheric correction model to obtain the corrected apparent reflectance. Based on the corrected apparent reflectance, the radiance value is converted into surface luminance temperature using the 6S atmospheric correction model. The Earth's surface brightness temperature is converted into water surface temperature using the blackbody radiation law.

4. The method according to claim 1, characterized in that, The construction process of the pre-built water level prediction model includes: Obtain multiple historical water level heights and multiple historical suspended solids concentrations that have a one-to-one correspondence with the historical water level heights; The water level prediction model is obtained by inputting multiple historical water level heights, multiple historical suspended solids concentrations, and the one-to-one correspondence between historical water level heights and historical suspended solids concentrations into a random forest regression model for model training.

5. The method according to claim 1, characterized in that, The water quality parameters are collected through a ground sensor network, and the vegetation cover images are collected through remote sensing satellites and / or drones.

6. A monitoring device for aquatic ecology, characterized in that, The device includes: The data acquisition unit is used to acquire real-time remote sensing eco-hydrological data of the target water area; the real-time remote sensing eco-hydrological data includes the real-time water surface color of the target water area, the real-time suspended solids concentration of the target water area, and the real-time vegetation cover image of the surrounding area of ​​the target water area. The data processing unit is used to perform radiometric calibration on the real-time vegetation cover image to obtain radiance values ​​and apparent reflectance. A vegetation image recognition unit is used to identify vegetation region images in the real-time vegetation cover image using a region growing algorithm. A water surface temperature acquisition unit is used to perform atmospheric correction on the radiance value based on the apparent reflectance to obtain the water surface temperature. The water level prediction unit is used to input the real-time suspended solids concentration into a pre-built water level prediction model to obtain the predicted water level height. The early warning unit issues an ecological early warning for the target water area if any one or more of the following conditions are met: the predicted water level does not match the target water level; the real-time water meter color does not match the target water meter color; the real-time suspended solids concentration does not match the target suspended solids concentration; the vegetation color in the vegetation area image does not match the target color; or the vegetation density in the vegetation area image does not match the target density.

7. The apparatus according to claim 6, characterized in that, The data processing unit specifically includes: The first conversion unit is used to convert the digital quantization values ​​of the vegetation cover image into the radiance values ​​respectively. A calculation unit is used to calculate the apparent reflectance based on the radiance value.

8. The apparatus according to claim 6, characterized in that, The water meter temperature acquisition unit specifically includes: The correction unit is used to perform atmospheric correction on the apparent reflectance using the 6S atmospheric correction model to obtain the corrected apparent reflectance. The second conversion unit is used to convert the radiance value into surface radiance temperature based on the corrected apparent reflectance using the 6S atmospheric correction model. The third conversion unit is used to convert the surface brightness temperature into water surface temperature using the blackbody radiation law.

9. A monitoring device for aquatic ecology, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method for monitoring aquatic ecology as described in any one of claims 1-5.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed on a terminal device, cause the terminal device to perform the aquatic ecology monitoring method as described in any one of claims 1-5.

Images