Method and device for predicting development trend of water bloom, electronic equipment and medium

Abstract

This application relates to the field of algal bloom development trend prediction technology, and discloses a method, device, electronic device, and medium for algal bloom development trend prediction. The method includes: acquiring the current algal bloom area and current environmental influencing factors of a target water area; acquiring historical time-series data of the target water area; the historical time-series data includes historical algal bloom areas and historical environmental influencing factors within a historical time period; determining a first prediction function for the algal bloom area based on the historical time-series data; adjusting the first prediction function according to the current environmental influencing factors to obtain a second prediction function; and inputting the current algal bloom area into the second prediction function to obtain a prediction result for the algal bloom area in a future preset time period. This application can obtain a relatively accurate prediction result for the algal bloom area in a future preset time period, achieving quantitative prediction of algal bloom development trends.

Description

Technical Field

[0001] This application relates to the field of algal bloom development trend prediction technology, specifically to algal bloom development trend prediction methods, devices, electronic equipment and media. Background Technology

[0002] Algal blooms can severely disrupt the ecological balance of aquatic areas, affect water resource utilization and aquatic ecological security, and cause significant harm to watershed ecological protection and daily life. Therefore, accurate prediction of the development trend of algal bloom area has become a key requirement for aquatic ecological environment governance. Among related technologies, most prediction methods focus on qualitative judgments of the probability of algal blooms, i.e., determining whether an algal bloom will occur, but they cannot predict the development trend after the bloom occurs. Summary of the Invention

[0003] This application provides a method, apparatus, electronic device, and medium for predicting the development trend of algal blooms, in order to solve the problem that traditional solutions are difficult to accurately assess the development trend after an algal bloom occurs.

[0004] Firstly, this application provides a method for predicting the development trend of algal blooms, the method comprising: Obtain the current area of ​​algal blooms and current environmental influencing factors in the target water area; Acquire historical time-series data of the target water area; the historical time-series data includes the historical algal bloom area and historical environmental influencing factors within the historical time period; A first prediction function for the area of ​​algal blooms is determined based on the historical time series data; The first prediction function is adjusted based on the current environmental influencing factors to obtain the second prediction function; The current algal bloom area is input into the second prediction function to obtain the prediction result of the algal bloom area in the future preset time period.

[0005] The method provided in this application obtains the current algal bloom area, current environmental influencing factors, and historical time-series data of the target water area. Based on the historical time-series data, a first prediction function is constructed, and a second prediction function is obtained by adjusting it in conjunction with the current environmental influencing factors. The current algal bloom area is then input into the second prediction function to obtain a prediction result for the algal bloom area over a preset future time period. Compared to related technologies that only qualitatively judge the probability of algal bloom occurrence, this embodiment can accurately obtain a quantitative prediction value for the future algal bloom area, effectively solving the problem that traditional schemes are difficult to assess the area expansion trend after algal blooms occur. This improves the accuracy and practicality of algal bloom prediction and provides reliable data support for subsequent algal bloom management and ecological scheduling. Adjusting the first prediction function according to the current environmental influencing factors allows the prediction function to be adapted to the current actual environmental conditions of the target water area, effectively eliminating prediction bias caused by differences between historical time-series data and the current environment, and improving the real-time performance and applicability of the prediction function.

[0006] In one possible implementation, obtaining the current algal bloom area of ​​the target water area includes: Acquire remote sensing image data of the target water area and determine the atmospheric bottom reflectance data corresponding to each pixel in the remote sensing image data; The difference value of water bloom characteristics for each pixel is determined based on the atmospheric reflectance data corresponding to each pixel; the difference value of water bloom characteristics is used to indicate the degree of significance of the presence of water bloom at the corresponding pixel. The pixels containing algal blooms are determined based on the difference values ​​of the algal bloom characteristics; The current algal bloom area is obtained based on the water area corresponding to the pixel where the algal bloom exists.

[0007] The method provided in this application determines the difference values ​​of algal bloom characteristics for each pixel based on remote sensing image data and atmospheric bottom reflectance data. It identifies pixels with algal blooms based on these difference values ​​and calculates the current algal bloom area, enabling automated and high-precision quantitative extraction of algal bloom area in target water bodies. This embodiment uses atmospheric bottom reflectance data as the basis for judgment, avoiding subjective errors caused by manual judgment. The difference values ​​accurately characterize the significance of algal bloom presence at pixel locations, improving the reliability of algal bloom area identification. It achieves quantitative calculation of algal bloom area from remote sensing image data, providing accurate and stable current algal bloom area for subsequent algal bloom trend prediction, ensuring data accuracy in the prediction process.

[0008] In one possible implementation, determining the atmospheric subsurface reflectance data corresponding to each pixel in the remote sensing image data includes: Atmospheric correction processing is performed on the remote sensing image data to obtain atmospheric reflectance data corresponding to each pixel; the atmospheric correction processing is used to eliminate the interference of the atmosphere on the remote sensing image data; the atmospheric reflectance data includes reflectance corresponding to the blue-green light band, red light band, green light band and near-infrared band respectively.

[0009] The method provided in this application performs atmospheric correction processing on remote sensing image data to eliminate interference from atmospheric scattering and absorption, obtaining reflectance values ​​for blue-green, red, green, and near-infrared bands. This significantly improves the authenticity and accuracy of remote sensing image reflectance information. Multi-band reflectance data comprehensively reflects the spectral characteristics of water bodies, providing reliable foundational data for subsequent calculations of algal bloom characteristic differences. This avoids reflectance distortion caused by atmospheric interference, improves the accuracy of algal bloom feature identification and algal bloom area calculation, and makes algal bloom monitoring and prediction based on remote sensing data more closely reflect the actual state of the target water area.

[0010] In one possible implementation, determining the difference value of algal bloom characteristics for each pixel based on the atmospheric sub-layer reflectance data corresponding to each pixel includes: Calculate the first difference between the reflectance of the blue-green band and the reflectance of the red band, and the second difference between the reflectance of the near-infrared band and the reflectance of the red band; Calculate the product of the near-infrared band reflectance and the first difference, and calculate the ratio of the product to the second difference; Calculate the first difference and the third difference between the reflectivity of the green light band; Calculate the fourth difference between the third difference and the ratio; The fourth difference is taken as the characteristic difference value of the algal bloom.

[0011] The method provided in this application calculates the difference values ​​of algal bloom characteristics using multi-band reflectance data, enabling the construction of a quantitative discrimination index specifically for algal bloom identification, accurately distinguishing algal bloom pixels from non-algal bloom pixels. This calculation method fully utilizes the spectral differences in blue-green, red, green, and near-infrared bands, enhancing the spectral response characteristics of algal bloom regions, reducing the influence of interference factors such as water background, sediment, and suspended matter, improving the discriminative power and stability of algal bloom characteristic difference values, ensuring accurate and reliable algal bloom pixel determination results, and providing a core basis for the precise calculation of algal bloom area.

[0012] In one possible implementation, before performing atmospheric correction processing on the remote sensing image data, the method further includes: The remote sensing image data is projected and converted according to the preset latitude and longitude data to obtain the first remote sensing image data. The first remote sensing image data is cropped based on the target predicted area in the target water area to obtain the second remote sensing image data. The second remote sensing image data is subjected to geometric fine correction processing to obtain the third remote sensing image data; After obtaining the third remote sensing image data, an atmospheric correction process is performed on the third remote sensing image data.

[0013] The method provided in this application sequentially performs projection transformation, cropping, and geometric correction on remote sensing image data. This unifies the coordinate reference of multi-source remote sensing images, eliminates redundant regional information, and corrects geographical deviations caused by sensor attitude and Earth's rotation. This ensures that the preprocessed third-party remote sensing image data possesses a unified coordinate system, accurate geographic positioning, and complete and valid information. It improves the spatial consistency and geometric accuracy of remote sensing images, avoiding the adverse effects of coordinate inconsistencies, regional redundancy, and geometric deviations on subsequent atmospheric correction and algal bloom identification, thus ensuring the stability and accuracy of the entire algal bloom monitoring and prediction process.

[0014] In one possible implementation, adjusting the first prediction function based on the current environmental influencing factors to obtain the second prediction function includes: Extract the algal bloom growth driving term from the first prediction function; the algal bloom growth driving term is used to represent the driving effect of environmental factors on the algal bloom area growth process; The second prediction function is obtained by adjusting the algal bloom growth driving term based on the current environmental influencing factors.

[0015] The method provided in this application extracts the algal bloom growth driving term from the first prediction function and adjusts it based on current environmental influencing factors. This makes the prediction function more closely match the current real environmental conditions of the target water area, improving its adaptability and timeliness. The algal bloom growth driving term accurately characterizes the driving effect of environmental influencing factors on the growth of algal bloom area. Dynamically adjusting this driving term based on real-time environmental data can weaken the prediction bias caused by the difference between historical time-series data and current environmental influencing factors, making the second prediction function more consistent with the real-time growth pattern of algal blooms and significantly improving the accuracy of algal bloom area prediction results for a future preset time period.

[0016] In one possible implementation, the method further includes: The current algal bloom area and the current environmental influencing factors are added as new data; The first prediction function is adjusted based on the new data to obtain the adjusted first prediction function. The adjusted first prediction function is then applied to the next algal bloom development trend prediction process.

[0017] The method provided in this application uses the current algal bloom area and current environmental influencing factors as new data, dynamically adjusts the first prediction function, and applies the adjusted prediction function to the next prediction process, enabling rolling updates and iterative optimization of the prediction function. This embodiment continuously introduces the latest data to correct the prediction function, constantly narrowing the deviation between the prediction function and the actual algal bloom development pattern, improving the prediction function's adaptability to environmental changes and the dynamic development of algal blooms, and continuously optimizing the subsequent algal bloom development trend prediction results, achieving long-term stable and high-precision algal bloom area prediction.

[0018] Secondly, this application provides an algal bloom development trend prediction device, the device comprising: The first processing module is used to obtain the current algal bloom area and current environmental influencing factors of the target water area; The second processing module is used to acquire historical time-series data of the target water area; the historical time-series data includes the historical algal bloom area and historical environmental influencing factors within a historical time period. The third processing module is used to determine a first prediction function for the area of ​​algal blooms based on the historical time series data. The fourth processing module is used to adjust the first prediction function according to the current environmental influencing factors to obtain the second prediction function; The fifth processing module is used to input the current algal bloom area into the second prediction function to obtain the prediction result of the algal bloom area in the future preset time period.

[0019] Thirdly, this application provides an electronic device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the algal bloom development trend prediction method described in the first aspect or any corresponding embodiment.

[0020] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer instructions, which are used to cause a computer to execute the algal bloom development trend prediction method described in the first aspect or any of its corresponding optional embodiments.

[0021] Fifthly, this application provides a computer program product, including computer instructions for causing a computer to execute the algal bloom development trend prediction method of the first aspect or any of its corresponding optional embodiments. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0023] Figure 1 This is a schematic diagram illustrating an application scenario according to an embodiment of this application; Figure 2 This is a flowchart of the algal bloom development trend prediction method according to an embodiment of this application; Figure 3 This is a structural block diagram of an algal bloom development trend prediction device according to an embodiment of this application; Figure 4 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0025] It is understood that before using the technical solutions disclosed in the various embodiments of this application, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this application in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0026] As one optional application scenario in the embodiments of this application, such as Figure 1 As shown, the algal bloom development trend prediction system may include at least one terminal device and at least one server. Figure 1 The system is illustrated in the example, which includes a computer 101, a mobile terminal 102, and a server 103, and the terminal devices such as the computer 101 and the mobile terminal 102 are connected to the server 103 through a network 110.

[0027] The terminal device can be a smartphone, tablet, laptop, PDA, or desktop computer. Server 103 can be a standalone physical server, a server cluster, a distributed system, or a cloud server providing cloud services. Network 110 can be a wired or wireless network, examples of which include, but are not limited to, the Internet, corporate intranets, local area networks, wide area networks, mobile communication networks, and combinations thereof.

[0028] According to an embodiment of this application, an embodiment of a method for predicting the development trend of algal blooms is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0029] This embodiment provides a method for predicting the development trend of algal blooms. Figure 2 This is a flowchart of the algal bloom development trend prediction method according to an embodiment of this application, such as... Figure 2 As shown, the process includes the following steps: S201: Obtain the current algal bloom area and current environmental influencing factors of the target water area.

[0030] In this embodiment of the application, the target water area is the reservoir, lake, or other water area to be monitored and predicted, which is the object of prediction of the development trend of algal blooms.

[0031] In this embodiment, the current algal bloom area refers to the total area of ​​the target water body where algal blooms actually exist at the current moment. The current algal bloom area can be determined by acquiring remote sensing image data of the target water body, determining whether algal blooms have occurred in each pixel of the remote sensing image data, and then calculating the area corresponding to the pixels where algal blooms have occurred. A pixel refers to the smallest imaging unit of a remote sensing image, and is the basic unit for identifying whether algal blooms have occurred and for calculating the area.

[0032] In this embodiment of the application, the current environmental influencing factors include at least water quality data, and may also include meteorological data. Water quality data includes: surface water temperature, pH value (acidity / alkalinity of the water body), total nitrogen content, total phosphorus content, etc. As an example, water quality data can be obtained through on-site water sampling and actual measurement using online water quality monitoring equipment.

[0033] In this embodiment, meteorological data includes: temperature, sunshine duration, precipitation, wind speed, relative humidity, etc. As an example, meteorological data can be collected by automatic weather stations within the target water area and precisely matched with the transit time of remote sensing images, then resampled to the remote sensing pixel scale to obtain meteorological data corresponding to each pixel.

[0034] S202: Obtain historical time-series data of the target water area.

[0035] In this embodiment of the application, historical time-series data includes historical algal bloom area and historical environmental influencing factors within a historical time period.

[0036] In this embodiment, the historical time period refers to a preset time period within the previous algal bloom cycle of the target water area. For example, it could be the complete period from the initial discovery of the algal bloom in the target predicted area of ​​the target water area to the peak area of ​​the algal bloom and its subsequent decline after treatment. As an example, historical time series data could include the algal bloom area and corresponding environmental impact factors at each time point, starting from the day the most recent algal bloom was first detected, categorized by multiple time nodes, such as day 1, day 4, day 10, day 15, until the area reaches its maximum and treatment is completed. The algal bloom cycle refers to the complete time process from the first appearance of the algal bloom, its continuous expansion, reaching its peak, and then its complete decline after natural decay or artificial treatment.

[0037] S203: Determine the first prediction function for the area of ​​algal blooms based on historical time series data.

[0038] In this embodiment of the application, as an example, the prediction function can also be a nonlinear dynamic prediction model for algal bloom area.

[0039] In this embodiment, the prediction function includes a first prediction function directly determined based on historical time-series data and a second prediction function adjusted based on current environmental influencing factors. The prediction function represents the fundamental pattern of algal bloom area changes with environmental influencing factors and time.

[0040] As an example, the first prediction function can be a specific nonlinear dynamic formula: .

[0041] .

[0042] .

[0043] in, Represents the distance from the initial time. The algal bloom area corresponding to the time length, i.e., the predicted algal bloom area based on the first prediction function. This represents the time elapsed since the initial time. This indicates the pre-set prediction time interval, which can be the same as the time interval for collecting historical time-series data, such as 3 days or 6 days. Indicates the current area of ​​algal bloom. Indicates the driving factor for algal bloom growth. Indicates environmental influencing factors, This represents the random error term, which is optional and can be omitted. It follows a normal distribution. , The standard deviation of the error is used. The algal bloom growth driving term is used to represent the driving effect of environmental factors on the algal bloom area growth process. For example, the initial time is the day when the most recent algal bloom was first detected (the first day). Preset prediction time interval The fixed value is 3 days.

[0044] Indicates the area of ​​algal bloom on the first day, Indicates the area of ​​algal bloom on the fourth day. This represents the area of ​​the algal bloom on the seventh day. When predicting the algal bloom area on the fourth day using historical time-series data from the first day, the algal bloom area on the first day is used as the current algal bloom area. The predicted algal bloom area on the fourth day is the predicted algal bloom area. Furthermore, the area of ​​the algal bloom on the seventh day can be predicted using historical time-series data from the fourth day, with the algal bloom area on the fourth day being the current algal bloom area. The predicted algal bloom area on the fourth day is the predicted algal bloom area. .

[0045] , , , , , represent basic parameters, which are calibrated by using historical time-series data through the non-linear least squares method, and respectively represent the basic growth coefficient, water temperature exponential term coefficient, pH deviation term coefficient, total nitrogen influence coefficient, total phosphorus influence coefficient, and time accumulation term coefficient. The time accumulation term coefficient is optional and can be not set. represents the water temperature exponential growth coefficient, which characterizes the non-linear amplification / suppression degree of the water bloom growth rate when the water temperature deviates from the optimal growth temperature, and is calibrated by historical time-series data. represents the water temperature at the water surface layer, with the unit of °C. represents the optimal growth water temperature of the water bloom, which is an empirical constant and usually takes a value of 25 - 30 °C. represents the water body acidity and alkalinity, represents the optimal growth pH value of the water bloom, which is an empirical constant and usually takes a value of 8.0 - 9.0. represents the total nitrogen content, with the unit of mg / L represents the total phosphorus content, with the unit of mg / L. represents the pixel-level meteorological driving term. , , , , represents the pixel meteorological influence coefficient, which is calibrated by historical time-series data, and respectively represents the contribution weights of air temperature, sunshine duration, precipitation, wind speed, and relative humidity to the growth of the water bloom. represents the air temperature corresponding to the pixel (i, j), represents the sunshine duration corresponding to the pixel (i, j), represents the precipitation corresponding to the pixel (i, j), represents the wind speed corresponding to the pixel (i, j), represents the relative humidity corresponding to the pixel (i, j).

[0046] (i, j) represents a plane rectangular coordinate system established with the upper left corner of the remote sensing image of the target water area as the coordinate origin (0, 0), where the row direction is the i-axis and the column direction is the j-axis, and is used to uniquely identify the spatial position of each minimum imaging unit in the remote sensing image. i: row index, with the value range of 0 ≤ i < H, representing the longitudinal position of the pixel in the image, where H is the total number of rows of the remote sensing image. j: column index, with the value range of 0 ≤ j < W, representing the horizontal position of the pixel in the image, where W is the total number of columns of the remote sensing image. For the remote sensing image with a size of 1024×1024 pixels in the embodiment of the present application, H = W = 1024, that is, the image includes a total of 1024×1024 = 1,048,576 pixels, and each pixel corresponds to an actual water area of 2 meters × 2 meters.

[0047] S204: Adjust the first prediction function according to the current environmental influencing factors to obtain the second prediction function.

[0048] In this embodiment, the second prediction function incorporates real-time corrections based on current environmental influencing factors. Compared to the first prediction function, the second prediction function is better suited to the current environmental conditions of the target water area, exhibiting smaller prediction bias and stronger timeliness. The second prediction function is adjusted based on current environmental influencing factors, making it compatible with the real-time environment and significantly improving its fit to the current algal bloom growth state, thereby enhancing prediction accuracy.

[0049] S205: Input the current algal bloom area into the second prediction function to obtain the prediction result of the algal bloom area in the future preset time period.

[0050] In this embodiment, the confidence interval / range corresponding to the predicted algal bloom area can also be calculated. The preset future time period includes at least one future time period. Based on historical time series data, the predicted algal bloom area corresponding to the actual algal bloom area is calculated using a first prediction function, and the residual between the actual algal bloom area and the predicted algal bloom area is calculated. Statistical calculations are performed on all residuals to obtain the standard deviation of the residuals, which is used to characterize the overall error level of the first prediction function. A corresponding preset confidence coefficient is selected according to a preset confidence level, commonly the confidence coefficient corresponding to 95% confidence level. The lower limit of the confidence interval is obtained by subtracting the confidence coefficient from the predicted algal bloom area and multiplying it by the standard deviation of the residuals. The upper limit of the confidence interval is obtained by adding the confidence coefficient to the predicted algal bloom area and multiplying it by the standard deviation of the residuals. The lower limit and the upper limit together constitute the confidence interval / range corresponding to the predicted algal bloom area.

[0051] In this embodiment, the predicted area of ​​algal bloom over a predetermined time period is used to represent the development trend of algal bloom. The relative growth rate of algal bloom area per unit time can also be calculated, i.e. The development trend of algal blooms is represented by the relative growth rate.

[0052] The method provided in this application obtains the current algal bloom area, current environmental influencing factors, and historical time-series data of the target water area. Based on the historical time-series data, a first prediction function is constructed, and a second prediction function is obtained by adjusting it in conjunction with the current environmental influencing factors. The current algal bloom area is then input into the second prediction function to obtain a prediction result for the algal bloom area over a preset future time period. Compared to related technologies that only qualitatively judge the probability of algal bloom occurrence, this embodiment can accurately obtain a quantitative prediction value for the future algal bloom area, effectively solving the problem that traditional schemes are difficult to assess the area expansion trend after algal blooms occur. This improves the accuracy and practicality of algal bloom prediction and provides reliable data support for subsequent algal bloom management and ecological scheduling. Adjusting the first prediction function according to the current environmental influencing factors allows the prediction function to be adapted to the current actual environmental conditions of the target water area, effectively eliminating prediction bias caused by differences between historical time-series data and the current environment, and improving the real-time performance and applicability of the prediction function.

[0053] In one possible implementation, S201 obtains the current algal bloom area of ​​the target water area, including Sa1 to Sa4.

[0054] Sa1: Acquire remote sensing image data of the target water area and determine the atmospheric reflectance data corresponding to each pixel in the remote sensing image data.

[0055] In this embodiment of the application, acquiring remote sensing image data of the target water area specifically includes: acquiring panchromatic remote sensing images of the target water area using a geostationary orbit microsatellite equipped with a multispectral remote sensing sensor. The image size is 1024×1024 pixels, and the spatial resolution is 2 meters, achieving high-resolution full-coverage acquisition.

[0056] In this embodiment of the application, determining the atmospheric subsurface reflectance data corresponding to each pixel in the remote sensing image data includes: Atmospheric correction is performed on remote sensing image data to obtain the atmospheric reflectance data for each pixel. Atmospheric correction is used to eliminate the interference of the atmosphere on the remote sensing image data. The atmospheric reflectance data includes the reflectance corresponding to the blue-green, red, green, and near-infrared bands, respectively.

[0057] In this embodiment of the application, atmospheric correction processing is performed on remote sensing image data to obtain atmospheric reflectance data corresponding to each pixel. Specifically, this includes using a dark object correction model and a seven-stage atmospheric correction model to sequentially correct solar light source, surface reflection, atmospheric scattering, gas absorption, water vapor absorption, oxidant absorption, and annular scattering interference, and outputting accurate reflectance data.

[0058] This application embodiment uses high-resolution remote sensing acquisition combined with refined atmospheric correction to eliminate atmospheric interference, obtain real and reliable multi-band reflectivity data, and improve the basic accuracy of algal bloom identification.

[0059] Sa2: Determine the difference value of algal bloom characteristics for each pixel based on the atmospheric bottom reflectance data corresponding to each pixel.

[0060] In the embodiments of this application, the algal bloom feature difference value is used to indicate the degree of significance of the presence of algal bloom at the corresponding pixel.

[0061] In this embodiment of the application, Sa2 determines the difference value of algal bloom characteristics for each pixel based on the atmospheric subsurface reflectance data corresponding to each pixel, specifically including: Calculate the first difference between the reflectance of the blue-green band and the reflectance of the red band, and the second difference between the reflectance of the near-infrared band and the reflectance of the red band.

[0062] Calculate the product of the near-infrared band reflectance and the first difference, and then calculate the ratio of the product to the second difference.

[0063] Calculate the first difference and the third difference between the reflectance of the green light band.

[0064] Calculate the fourth difference between the third difference and the ratio.

[0065] The fourth difference is used as the characteristic difference value of algal bloom.

[0066] In this embodiment of the application, the formula for calculating the difference value of algal bloom characteristics of each pixel based on the atmospheric subsurface reflectance data corresponding to each pixel is as follows: P=BG-RED-G-NIR×(BG-RED) / (NIR-RED).

[0067] Where P represents the characteristic difference value of algal bloom, BG is the reflectance in the blue-green light band, RED is the reflectance in the red light band, G is the reflectance in the green light band, and NIR is the reflectance in the near-infrared band. This calculation method fully amplifies the spectral differences between algal blooms and ordinary water bodies, suppresses background interference such as sediment and suspended matter, and improves the sensitivity of algal bloom identification. By calculating the characteristic difference value of algal bloom through multi-band reflectance combination, the spectral characteristics of algal blooms are enhanced, background interference is reduced, and pixel-level accurate identification of algal blooms is achieved.

[0068] Sa3: Pixels with algal blooms are determined based on the difference values ​​of algal bloom characteristics.

[0069] In this embodiment of the application, determining the pixels containing algal blooms based on algal bloom characteristic difference values ​​specifically includes: The difference value P of the algal bloom feature is compared with a preset threshold (e.g., 0.08). Pixels with P greater than 0.08 are marked as algal bloom pixels (assigned a value of 1), and pixels with P less than or equal to 0.08 are marked as non-algal bloom pixels (assigned a value of 0), generating a binary image of algal blooms. By using a fixed threshold for determination, the automatic and standardized differentiation of algal bloom pixels is achieved, improving the efficiency and consistency of area calculation.

[0070] Sa4: The current area of ​​algal bloom is obtained based on the water area corresponding to the pixel where algal bloom exists.

[0071] In this embodiment, obtaining the current algal bloom area based on the water area corresponding to the pixel containing the algal bloom specifically includes: counting the total number of algal bloom pixels in the binary algal bloom map, combining this with the 2-meter spatial resolution of the remote sensing image, calculating the water area corresponding to a single pixel, and multiplying the total number of algal bloom pixels by the water area corresponding to a single pixel to obtain the actual current algal bloom area. Based on high-resolution pixel-based area calculation, the results are accurate and detailed, providing reliable current area data for trend prediction.

[0072] The method provided in this application determines the difference values ​​of algal bloom characteristics for each pixel based on remote sensing image data and atmospheric bottom reflectance data. It identifies pixels with algal blooms based on these difference values ​​and calculates the current algal bloom area, enabling automated and high-precision quantitative extraction of algal bloom area in target water bodies. This embodiment uses atmospheric bottom reflectance data as the basis for judgment, avoiding subjective errors caused by manual judgment. The difference values ​​accurately characterize the significance of algal bloom presence at pixel locations, improving the reliability of algal bloom area identification. It achieves quantitative calculation of algal bloom area from remote sensing image data, providing accurate and stable current algal bloom area for subsequent algal bloom trend prediction, ensuring data accuracy in the prediction process.

[0073] In one possible implementation, the method for predicting the development trend of algal blooms further includes, before performing atmospheric correction processing on the remote sensing image data: The remote sensing image data is projected and converted based on the preset latitude and longitude data to obtain the first remote sensing image data.

[0074] In this embodiment of the application, as an example, the specific implementation method of projection transformation processing of remote sensing image data based on preset latitude and longitude data is as follows: using the WGS84 geographic coordinate system as the reference, the projection coordinate system of the original remote sensing image is converted into the UTM projection coordinate system, a one-to-one mapping relationship between latitude and longitude coordinates and plane rectangular coordinates is established, the spatial offset caused by the projection difference of different data sources is eliminated, and the first remote sensing image data with unified coordinate reference is obtained.

[0075] The first remote sensing image data is cropped based on the target predicted area in the target water area to obtain the second remote sensing image data.

[0076] In this embodiment of the application, as an example, the specific implementation of cropping the first remote sensing image data based on the target prediction area in the target water area is as follows: based on the vector boundary range of the target prediction area, the first remote sensing image data is spatially masked and cropped, retaining the effective image data within the target prediction area, and removing redundant image information of irrelevant areas to obtain the second remote sensing image data that only includes the target prediction area.

[0077] The second remote sensing image data is subjected to geometric fine correction to obtain the third remote sensing image data.

[0078] In this embodiment of the application, as an example, the specific implementation method for geometric fine correction processing of the second remote sensing image data is as follows: select ground control points evenly distributed in the target water area, use a quadratic polynomial model and least squares method to fit the correction equation, correct the geometric distortion caused by sensor attitude, terrain undulation and Earth rotation, so that the image pixel position is accurately matched with the real geographic coordinates, and obtain the third remote sensing image data after the geometric accuracy meets the standard.

[0079] After obtaining the third remote sensing image data, an atmospheric correction process is performed on the third remote sensing image data.

[0080] The method provided in this application sequentially performs projection transformation, cropping, and geometric correction on remote sensing image data. This unifies the coordinate reference of multi-source remote sensing images, eliminates redundant regional information, and corrects geographical deviations caused by sensor attitude and Earth's rotation. This ensures that the preprocessed third-party remote sensing image data possesses a unified coordinate system, accurate geographic positioning, and complete and valid information. It improves the spatial consistency and geometric accuracy of remote sensing images, avoiding the adverse effects of coordinate inconsistencies, regional redundancy, and geometric deviations on subsequent atmospheric correction and algal bloom identification, thus ensuring the stability and accuracy of the entire algal bloom monitoring and prediction process.

[0081] In one possible implementation, S204 adjusts the first prediction function according to the current environmental influencing factors to obtain a second prediction function, including Sb1 to Sb4.

[0082] Sb1: Extract the algal bloom growth driving term from the first prediction function.

[0083] In the embodiments of this application, the algal bloom growth driving term is used to represent the driving effect of environmental influencing factors on the algal bloom area growth process.

[0084] Sb2: Adjust the algal bloom growth driving term according to the current environmental influencing factors to obtain the second prediction function.

[0085] In this embodiment, adjusting the algal bloom growth driving term based on current environmental influencing factors to obtain the second prediction function specifically includes: substituting the current environmental influencing factors into the algal bloom growth driving term, and correcting the parameters in the first prediction function based on the current environmental influencing factors. As an example, the current water temperature can be calculated. Deviation from optimal temperature Degree: If ΔT > 2℃, then the water temperature exponential growth coefficient should be corrected. , This represents the corrected growth coefficient of the water temperature index (new indicates the corrected value). This represents the water temperature index growth factor before correction (old indicates before correction), and also includes the corrected water temperature index term coefficient: If ΔT≤2℃, then it remains unchanged.

[0086] It can calculate the degree to which the current pH deviates from the optimum value: like Then correct the pH deviation term coefficient If ΔpH≤0.5, then the pH deviation term coefficient remains unchanged.

[0087] It can calculate the degree to which each meteorological factor deviates from its historical mean:

[0088] The degree to which a meteorological factor deviates from its historical mean is defined as the difference between the current meteorological data and the corresponding historical mean, and the ratio of this difference to the historical standard deviation of the meteorological factor. For example, This indicates the degree to which the meteorological factor of temperature deviates from the historical average. Indicates the current temperature. This represents the historical average temperature. This represents the historical standard deviation of temperature. For the explanation of the other parameters, please refer to the example of meteorological factors as temperature mentioned above, which will not be explained in detail here.

[0089] Corrected pixel meteorological influence coefficient:

[0090] If a meteorological factor, such as precipitation, is equal to the historical average and has not been updated, then the corresponding coefficient remains unchanged.

[0091] The method provided in this application extracts the algal bloom growth driving term from the first prediction function and adjusts it based on current environmental influencing factors. This makes the prediction function more closely match the current real environmental conditions of the target water area, improving its adaptability and timeliness. The algal bloom growth driving term accurately characterizes the driving effect of environmental influencing factors on the growth of algal bloom area. Dynamically adjusting this driving term based on real-time environmental data can weaken the prediction bias caused by the difference between historical time-series data and current environmental influencing factors, making the second prediction function more consistent with the real-time growth pattern of algal blooms and significantly improving the accuracy of algal bloom area prediction results for a future preset time period.

[0092] In one possible implementation, this method for predicting algal bloom trends also includes: The current area of ​​algal blooms and current environmental impact factors will be added as new data.

[0093] The first prediction function is adjusted based on the new data to obtain the adjusted first prediction function.

[0094] The adjusted first prediction function will be applied to the next algal bloom development trend prediction process.

[0095] As an example, the current algal bloom area and current environmental influencing factors can be added to the historical time-series data to form updated historical time-series data. Using this updated historical time-series data, the function parameters are refitted using the nonlinear least squares method. The newly calibrated function parameters replace the original function parameters, resulting in a first prediction function adapted to the latest patterns, which is used in the next prediction process. Each prediction cycle involves updating the historical time-series data, refitting the function parameters, and updating the function, achieving continuous self-optimization and rolling optimization of the prediction function to obtain more accurate prediction results. As the amount of historical time-series data increases, the prediction results of the prediction function will also become more accurate.

[0096] The method provided in this application uses the current algal bloom area and current environmental influencing factors as new data, dynamically adjusts the first prediction function, and applies the adjusted prediction function to the next prediction process, enabling rolling updates and iterative optimization of the prediction function. This embodiment continuously introduces the latest data to correct the prediction function, constantly narrowing the deviation between the prediction function and the actual algal bloom development pattern, improving the prediction function's adaptability to environmental changes and the dynamic development of algal blooms, and continuously optimizing the subsequent algal bloom development trend prediction results, achieving long-term stable and high-precision algal bloom area prediction.

[0097] This application also provides an algal bloom development trend prediction device, which is used to implement the above embodiments and preferred embodiments, and will not be repeated as already described. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0098] This application provides a device for predicting the development trend of algal blooms. Figure 3 This is a structural block diagram of an algal bloom development trend prediction device according to an embodiment of this application, such as... Figure 3 As shown, it includes: The first processing module 301 is used to obtain the current algal bloom area and current environmental influencing factors of the target water area.

[0099] The second processing module 302 is used to acquire historical time-series data of the target water area. The historical time-series data includes the historical algal bloom area and historical environmental influencing factors within the historical time period.

[0100] The third processing module 303 is used to determine the first prediction function for the area of ​​algal blooms based on historical time series data.

[0101] The fourth processing module 304 is used to adjust the first prediction function according to the current environmental influencing factors to obtain the second prediction function.

[0102] The fifth processing module 305 is used to input the current algal bloom area into the second prediction function to obtain the prediction result of the algal bloom area in the future preset time period.

[0103] In one possible implementation, the first processing module 301 includes: The first processing unit is used to acquire remote sensing image data of the target water area and determine the atmospheric bottom reflectance data corresponding to each pixel in the remote sensing image data.

[0104] The second processing unit is used to determine the algal bloom characteristic difference value of each pixel based on the atmospheric sub-layer reflectance data corresponding to each pixel. The algal bloom characteristic difference value is used to indicate the significance of the presence of algal bloom at the corresponding pixel.

[0105] The third processing unit is used to determine the pixels where algal blooms exist based on the difference values ​​of algal bloom characteristics.

[0106] The fourth processing unit is used to obtain the current algal bloom area based on the water area corresponding to the pixel where the algal bloom exists.

[0107] In one possible implementation, the first processing unit is specifically used to perform atmospheric correction processing on the remote sensing image data to obtain the atmospheric bottom reflectance data corresponding to each pixel. Atmospheric correction processing is used to eliminate the interference of the atmosphere on the remote sensing image data. The atmospheric bottom reflectance data includes the reflectance corresponding to the blue-green band, red band, green band, and near-infrared band, respectively.

[0108] In one possible implementation, the second processing unit is specifically used to calculate a first difference between the reflectance of the blue-green band and the reflectance of the red band, and a second difference between the reflectance of the near-infrared band and the reflectance of the red band.

[0109] Calculate the product of the near-infrared band reflectance and the first difference, and then calculate the ratio of the product to the second difference.

[0110] Calculate the first difference and the third difference between the reflectance of the green light band.

[0111] Calculate the fourth difference between the third difference and the ratio.

[0112] The fourth difference is used as the characteristic difference value of algal bloom.

[0113] In one possible implementation, the algal bloom development trend prediction device further includes: a sixth processing module, used to perform projection conversion processing on the remote sensing image data according to preset latitude and longitude data before performing atmospheric correction processing on the remote sensing image data, to obtain the first remote sensing image data.

[0114] The first remote sensing image data is cropped based on the target predicted area in the target water area to obtain the second remote sensing image data.

[0115] The second remote sensing image data is subjected to geometric fine correction to obtain the third remote sensing image data.

[0116] After obtaining the third remote sensing image data, an atmospheric correction process is performed on the third remote sensing image data.

[0117] In one possible implementation, the fourth processing module 304 is specifically used to extract the algal bloom growth driving term from the first prediction function. The algal bloom growth driving term is used to represent the driving effect of environmental influencing factors on the algal bloom area growth process.

[0118] The second prediction function is obtained by adjusting the algal bloom growth driving term based on the current environmental influencing factors.

[0119] In one possible implementation, the algal bloom development trend prediction device further includes a seventh processing module for adding the current algal bloom area and current environmental impact factors as new data.

[0120] The first prediction function is adjusted based on the new data to obtain the adjusted first prediction function.

[0121] The adjusted first prediction function will be applied to the next algal bloom development trend prediction process.

[0122] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0123] The following is a detailed reference. Figure 4 The diagram illustrates a structural schematic suitable for implementing the electronic device described in the embodiments of this application. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 501, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 502 or a program loaded from memory 508 into random access memory (RAM) 503. The RAM 503 also stores various programs and data required for the operation of the electronic device. The processor 501, ROM 502, and RAM 503 are interconnected via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0124] Typically, the following devices can be connected to I / O interface 505: input devices 506 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 507 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 508 including, for example, magnetic tapes, hard disks, etc.; and communication devices 509. Communication device 509 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although... Figure 4 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0125] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program including program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 509, or installed from a memory 508, or installed from a ROM 502. When the computer program is executed by the processor 501, it performs the functions defined in the algal bloom development trend prediction method of embodiments of this application.

[0126] Figure 4 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0127] This application also provides a computer-readable storage medium. The methods described in this application can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc. Further, the storage medium may also include combinations of the above types of memory. It is understood that computers, processors, microprocessors, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the algal bloom development trend prediction method shown in the above embodiments is implemented.

[0128] A portion of this application can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to this application through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0129] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and all such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A method for predicting the development trend of algal blooms, characterized in that, The method includes: Obtain the current area of ​​algal blooms and current environmental influencing factors in the target water area; Acquire historical time-series data of the target water area; the historical time-series data includes the historical algal bloom area and historical environmental influencing factors within the historical time period; A first prediction function for the area of ​​algal blooms is determined based on the historical time series data; The first prediction function is adjusted based on the current environmental influencing factors to obtain the second prediction function; The current algal bloom area is input into the second prediction function to obtain the prediction result of the algal bloom area in the future preset time period.

2. The method according to claim 1, characterized in that, The acquisition of the current algal bloom area of ​​the target water area includes: Acquire remote sensing image data of the target water area and determine the atmospheric bottom reflectance data corresponding to each pixel in the remote sensing image data; The difference value of water bloom characteristics for each pixel is determined based on the atmospheric reflectance data corresponding to each pixel; the difference value of water bloom characteristics is used to indicate the degree of significance of the presence of water bloom at the corresponding pixel. The pixels containing algal blooms are determined based on the difference values ​​of the algal bloom characteristics; The current algal bloom area is obtained based on the water area corresponding to the pixel where the algal bloom exists.

3. The method according to claim 2, characterized in that, Determining the atmospheric reflectance data corresponding to each pixel in the remote sensing image data includes: Atmospheric correction processing is performed on the remote sensing image data to obtain atmospheric reflectance data corresponding to each pixel; the atmospheric correction processing is used to eliminate the interference of the atmosphere on the remote sensing image data; the atmospheric reflectance data includes reflectance corresponding to the blue-green light band, red light band, green light band and near-infrared band respectively.

4. The method according to claim 3, characterized in that, The step of determining the difference value of algal bloom characteristics for each pixel based on the atmospheric subsurface reflectance data corresponding to each pixel includes: Calculate the first difference between the reflectance of the blue-green band and the reflectance of the red band, and the second difference between the reflectance of the near-infrared band and the reflectance of the red band; Calculate the product of the near-infrared band reflectance and the first difference, and calculate the ratio of the product to the second difference; Calculate the first difference and the third difference between the reflectivity of the green light band; Calculate the fourth difference between the third difference and the ratio; The fourth difference is taken as the characteristic difference value of the algal bloom.

5. The method according to claim 3, characterized in that, Before performing atmospheric correction processing on the remote sensing image data, the method further includes: The remote sensing image data is projected and converted according to the preset latitude and longitude data to obtain the first remote sensing image data. The first remote sensing image data is cropped based on the target predicted area in the target water area to obtain the second remote sensing image data. The second remote sensing image data is subjected to geometric fine correction processing to obtain the third remote sensing image data; After obtaining the third remote sensing image data, an atmospheric correction process is performed on the third remote sensing image data.

6. The method according to claim 1, characterized in that, The step of adjusting the first prediction function according to the current environmental influencing factors to obtain the second prediction function includes: Extract the algal bloom growth driving term from the first prediction function; the algal bloom growth driving term is used to represent the driving effect of environmental factors on the algal bloom area growth process; The second prediction function is obtained by adjusting the algal bloom growth driving term based on the current environmental influencing factors.

7. The method according to claim 1, characterized in that, The method further includes: The current algal bloom area and the current environmental influencing factors are added as new data; The first prediction function is adjusted based on the new data to obtain the adjusted first prediction function. The adjusted first prediction function is then applied to the next algal bloom development trend prediction process.

8. A device for predicting the development trend of algal blooms, characterized in that, The device includes: The first processing module is used to obtain the current algal bloom area and current environmental influencing factors of the target water area; The second processing module is used to acquire historical time-series data of the target water area; the historical time-series data includes the historical algal bloom area and historical environmental influencing factors within a historical time period. The third processing module is used to determine a first prediction function for the area of ​​algal blooms based on the historical time series data. The fourth processing module is used to adjust the first prediction function according to the current environmental influencing factors to obtain the second prediction function; The fifth processing module is used to input the current algal bloom area into the second prediction function to obtain the prediction result of the algal bloom area in the future preset time period.

9. An electronic device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the algal bloom development trend prediction method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the method of any one of claims 1 to 7.

Images