Water bloom area prediction method, device and equipment based on remote sensing image

Abstract

The present application relates to the field of remote sensing data analysis, in particular to a kind of water bloom area prediction method based on remote sensing image, water quality prediction parameter is obtained by carrying out water quality parameter inversion to remote sensing image, based on water quality prediction parameter, water bloom area extraction is carried out to remote sensing image, and combined with hydrological data, water bloom position prediction is carried out, not only consider the local effect of time and space object, also consider the influence of water quality, hydrology, water temperature and other factors on water bloom, improve water bloom prediction accuracy;Realize the fine, efficient prediction of water bloom.

Description

Technical Field

[0001] This invention relates to the field of remote sensing data analysis, and in particular to a method, apparatus, device, and storage medium for predicting algal bloom areas based on remote sensing images. Background Technology

[0002] Developing precise algal bloom forecasts is of great significance for preventing disasters caused by algal blooms and for formulating reasonable prevention and control measures.

[0003] Currently, research on algal bloom prediction generally relies on satellite remote sensing images to predict the area of ​​algal blooms or indirectly predict their spatial distribution through the probability of bloom outbreaks. However, algal blooms occur rapidly, and the spatial resolution and timeliness of satellite remote sensing are insufficient to meet the needs of algal bloom prediction. Furthermore, the application of satellite remote sensing in cloudy and rainy areas is also limited. In addition, algal blooms are a complex process influenced by multiple factors such as the water environment, water temperature, and climate, making it difficult for a single optical remote sensing method to achieve refined algal bloom prediction. Summary of the Invention

[0004] Based on this, the purpose of this invention is to provide a method, apparatus, device, and storage medium for predicting algal bloom areas based on remote sensing images. This method involves inverting water quality parameters from remote sensing images to obtain water quality prediction parameters, extracting algal bloom areas from the remote sensing images based on these parameters, and combining this with hydrological data to predict algal bloom locations. This approach considers not only the local effects of temporal and spatial objects but also the influence of factors such as water quality, hydrology, and water temperature on algal blooms, thus improving the accuracy of algal bloom prediction and achieving refined and efficient algal bloom prediction.

[0005] In a first aspect, embodiments of this application provide a method for predicting algal bloom areas based on remote sensing images, comprising the following steps:

[0006] Obtain several sample remote sensing images, as well as band reflectance data and hydrological data of each sample remote sensing image within the target time period;

[0007] Based on the band reflectance data and hydrological data of each sample remote sensing image within the target time period, an algal bloom prediction model is constructed, wherein the algal bloom prediction model includes a water quality prediction module, an algal bloom area prediction module, and an algal bloom location prediction module.

[0008] Obtain the band reflectance data, water temperature data, and hydrological data of the remote sensing image to be tested. Input the band reflectance data of the remote sensing image to be tested into the water quality prediction module to obtain the water quality prediction data of the remote sensing image to be tested.

[0009] The water quality prediction data and water temperature data of the remote sensing image to be tested are input into the algal bloom area prediction module. Based on a number of preset prediction windows, the algal bloom prediction area parameters of each prediction window of the remote sensing image to be tested are obtained.

[0010] The algal bloom prediction area parameters and hydrological data of each prediction window of the remote sensing image to be tested are input into the algal bloom location prediction module to obtain the algal bloom prediction coordinate parameters of each prediction window of the remote sensing image to be tested.

[0011] Based on the algal bloom prediction area parameters and algal bloom prediction coordinate parameters of each prediction window of the remote sensing image to be tested, several algal bloom prediction regions of the remote sensing image to be tested are obtained.

[0012] Secondly, embodiments of this application provide a device for predicting algal bloom areas based on remote sensing images, comprising:

[0013] The sample data acquisition module is used to acquire several sample remote sensing images, as well as the band reflectance data and hydrological data of each sample remote sensing image within the target time period.

[0014] The model building module is used to build an algal bloom prediction model based on the band reflectance data and hydrological data of each sample remote sensing image within the target time period. The algal bloom prediction model includes a water quality prediction module, an algal bloom area prediction module, and an algal bloom location prediction module.

[0015] The water quality prediction module is used to obtain the band reflectance data, water temperature data and hydrological data of the remote sensing image to be tested. The band reflectance data of the remote sensing image to be tested is input into the water quality prediction module to obtain the water quality prediction data of the remote sensing image to be tested.

[0016] The algal bloom area prediction module is used to input the water quality prediction data and water temperature data of the remote sensing image to be tested into the algal bloom area prediction module, and obtain the algal bloom prediction area parameters of each prediction window of the remote sensing image to be tested according to a number of preset prediction windows.

[0017] The algal bloom location prediction module is used to input the algal bloom prediction area parameters and hydrological data of each prediction window of the remote sensing image to be measured into the algal bloom location prediction module to obtain the algal bloom prediction coordinate parameters of each prediction window of the remote sensing image to be measured.

[0018] The algal bloom region prediction module is used to obtain several algal bloom prediction regions of the remote sensing image under test based on the algal bloom prediction area parameters and algal bloom prediction coordinate parameters of each prediction window of the remote sensing image under test.

[0019] Thirdly, embodiments of this application provide a computer device, including: a processor, a memory, and a computer program stored in the memory and executable on the processor; when the computer program is executed by the processor, it implements the steps of the algal bloom region prediction method based on remote sensing images as described in the first aspect.

[0020] Fourthly, embodiments of this application provide a storage medium storing a computer program that, when executed by a processor, implements the steps of the algal bloom region prediction method based on remote sensing images as described in the first aspect.

[0021] In this application embodiment, a method, apparatus, device, and storage medium for predicting algal bloom areas based on remote sensing images are provided. Water quality parameters are obtained by inverting water quality parameters from remote sensing images. Based on the water quality prediction parameters, algal bloom area is extracted from the remote sensing images, and the location of algal bloom is predicted by combining hydrological data. This method not only considers the local effects of time and space objects, but also the influence of water quality, hydrology, water temperature, and other factors on algal blooms, thereby improving the accuracy of algal bloom prediction and achieving refined and efficient algal bloom prediction.

[0022] To better understand and implement this invention, the following detailed description is provided in conjunction with the accompanying drawings. Attached Figure Description

[0023] Figure 1 A flowchart illustrating the algal bloom region prediction method based on remote sensing images provided in the first embodiment of this application;

[0024] Figure 2 This is a flowchart illustrating step S2 in the algal bloom region prediction method based on remote sensing images provided in the first embodiment of this application.

[0025] Figure 3 This is a flowchart illustrating step S2 in the algal bloom region prediction method based on remote sensing images provided in the second embodiment of this application.

[0026] Figure 4 This is a flowchart illustrating step S211 of the algal bloom region prediction method based on remote sensing images provided in the second embodiment of this application.

[0027] Figure 5 This is a flowchart illustrating step S214 of the algal bloom region prediction method based on remote sensing images provided in the second embodiment of this application.

[0028] Figure 6 This is a flowchart illustrating step S2 in the algal bloom region prediction method based on remote sensing images provided in the third embodiment of this application.

[0029] Figure 7This is a flowchart illustrating step S6 of the algal bloom region prediction method based on remote sensing images provided in the first embodiment of this application.

[0030] Figure 8 A flowchart illustrating the algal bloom region prediction method based on remote sensing images provided in the fourth embodiment of this application;

[0031] Figure 9 A schematic diagram of the structure of the algal bloom area prediction device based on remote sensing images provided in the fifth embodiment of this application;

[0032] Figure 10 This is a schematic diagram of the structure of a computer device provided in the sixth embodiment of this application. Detailed Implementation

[0033] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0034] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0035] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0036] Please see Figure 1 , Figure 1 The flowchart of the algal bloom region prediction method based on remote sensing images provided in the first embodiment of this application is shown. The method includes the following steps:

[0037] S1: Obtain several sample remote sensing images, as well as band reflectance data and hydrological data of each sample remote sensing image within the target time period.

[0038] The execution entity of the algal bloom area prediction method based on remote sensing images is the prediction device (hereinafter referred to as the prediction device). In an optional embodiment, the prediction device can be a computer device, a server, or a server cluster composed of multiple computer devices.

[0039] In this embodiment, the prediction device can acquire several sample remote sensing images of the sample area via satellite, or it can download several sample remote sensing images of the sample area from a database, along with the band reflectance data and hydrological data of each sample remote sensing image within a target time period. The band reflectance data includes green band reflectance, near-infrared band reflectance, and red band reflectance. The hydrological data includes hydrological parameters corresponding to each time point, including wind speed parameters, wind direction parameters, and water flow velocity parameters.

[0040] S2: Construct an algal bloom prediction model based on the band reflectance data and hydrological data of each sample remote sensing image within the target time period.

[0041] In this embodiment, the prediction device constructs an algal bloom prediction model based on the band reflectance data and hydrological data of each sample remote sensing image within the target time period. The algal bloom prediction model includes a water quality prediction module, an algal bloom area prediction module, and an algal bloom location prediction module.

[0042] Please see Figure 2 , Figure 2 The flowchart of S2 in the algal bloom region prediction method based on remote sensing images provided in the first embodiment of this application is shown below, including steps S201 to S203:

[0043] S201: Obtain the measured water quality data of each of the remote sensing images of the samples within the target time period.

[0044] In this embodiment, the prediction device obtains the measured water quality data of each sample remote sensing image within a target time period, wherein the measured water quality data includes several water quality parameters of several pixels.

[0045] S202: Based on a preset number of sampling points and window size, construct sampling windows corresponding to a number of sampling points of each sample remote sensing image, and obtain the band reflection data and water quality measurement data of each sampling window within the target time period based on the measured water quality data and band reflection data.

[0046] In this embodiment, the prediction device constructs a sampling window corresponding to a number of sampling points of each sample remote sensing image based on a preset number of sampling points and window size, and obtains the band reflection data and water quality measurement data of each sampling window within the target time period based on the measured water quality data and band reflection data.

[0047] S203: Input the band reflection data and water quality measurement data of each sampling window within the target time period into the water quality prediction module for training to obtain the target water quality prediction module.

[0048] The water quality prediction module is a linear regression model with band reflectance data as the independent variable and water quality parameters as the dependent variable. In this embodiment, the prediction device inputs the band reflectance data of each sampling window within the target time period and the measured water quality data into the water quality prediction module for training to obtain the target water quality prediction module. Specifically, the prediction device uses the band reflectance data of each sampling window within the target time period to obtain the water quality prediction data of each sampling window within the target time period. The water quality prediction data is used as the training dataset, and the measured water quality data is used as the validation dataset to train the water quality prediction module to obtain the target water quality prediction module. This avoids noise and image registration errors, improving the accuracy of water quality inversion.

[0049] Please see Figure 3 , Figure 3 The flowchart of S2 in the algal bloom region prediction method based on remote sensing images provided in the second embodiment of this application is shown below. It also includes steps S211 to S214, as follows:

[0050] S211: Based on the band reflection data of each sampling window within the target time period, perform algal bloom pixel extraction on each sampling window to obtain the number of algal bloom pixels corresponding to each time of each sampling window.

[0051] In this embodiment, the prediction device extracts algal bloom pixels for each sampling window based on the band reflection data of each sampling window within the target time period, thereby obtaining the number of algal bloom pixels corresponding to each sampling window at each time.

[0052] Please see Figure 4 , Figure 4 The flowchart of step S211 in the algal bloom region prediction method based on remote sensing images provided in the second embodiment of this application includes steps S2111 to S2112, as follows:

[0053] S2111: Based on the band reflection data and the preset normalized vegetation index calculation algorithm and normalized water index calculation algorithm, obtain the normalized vegetation index and normalized water index corresponding to each pixel at each time.

[0054] In this embodiment, the prediction device obtains the normalized vegetation index (NVI) for each pixel at each time based on the band reflection data and a preset normalized vegetation index (NVI) calculation algorithm. The NVI calculation algorithm is as follows:

[0055]

[0056] In the formula, Normalized Difference Vegetation Index (NDVI) For green band reflectivity, This refers to the reflectivity in the near-infrared band.

[0057] The prediction device obtains the normalized water index corresponding to each pixel at each time based on the band reflection data and a preset normalized water index calculation algorithm, wherein the normalized water index is:

[0058]

[0059] In the formula, The normalized water index, This refers to the reflectivity in the red band.

[0060] S2112: Based on the normalized vegetation index, normalized water index, and preset normalized vegetation index thresholds and normalized water index thresholds corresponding to each pixel at each time, water bloom pixels are extracted from each sampling window to obtain the number of water bloom pixels corresponding to each sampling window at each time.

[0061] In this embodiment, the prediction device extracts algal bloom pixels for each sampling window based on the normalized vegetation index, normalized water index, and preset normalized vegetation index thresholds and normalized water index thresholds corresponding to each pixel at each time, thereby obtaining the number of algal bloom pixels corresponding to each sampling window at each time.

[0062] Specifically, when the value of the normalized vegetation index of a pixel is greater than the first normalized vegetation index threshold and less than the second normalized vegetation index threshold, and the normalized water index is less than the normalized water index threshold, the prediction device uses this pixel as the number of algal bloom pixels to eliminate the influence of vegetation information and water information, thereby improving the accuracy of algal bloom prediction.

[0063] S212: Obtain the spatial resolution of each sampling window, and obtain the bloom area parameters corresponding to each sampling window at each time according to the number of bloom pixels, spatial resolution and preset bloom area parameter calculation algorithm.

[0064] The algorithm for calculating the algal bloom area parameter is as follows:

[0065]

[0066] In the formula, For parameters related to algal bloom area, The number of pixels representing algal bloom. This refers to spatial resolution.

[0067] In this embodiment, the prediction device obtains the spatial resolution of each sampling window, and based on the number of algal bloom pixels, the spatial resolution, and a preset algal bloom area parameter calculation algorithm, obtains the algal bloom area parameters corresponding to each sampling window at each time. By combining the spatial resolution of satellite remote sensing, the accuracy of algal bloom prediction is improved.

[0068] S213: Input the band reflection data of each sampling window within the target time period into the target water quality prediction module to obtain the water quality prediction data corresponding to each time of each sampling window.

[0069] In this embodiment, the prediction device inputs the band reflection data of each sampling window within the target time period to the target water quality prediction module to obtain the water quality prediction data corresponding to each time of each sampling window.

[0070] S214: Obtain the latitude and longitude data of each sampling window, as well as the water temperature parameters corresponding to each time moment. Input the latitude and longitude data of each sampling window, the water temperature parameters corresponding to each time moment, the water quality prediction data, and the algal bloom area parameters into the algal bloom area prediction module. Train the algal bloom area prediction module to obtain the target algal bloom area prediction module.

[0071] In this embodiment, the prediction device obtains the latitude and longitude data of each sampling window and the corresponding water temperature parameters at each time. Latitude and longitude refer to the combined longitude and latitude. The latitude and longitude data include the longitude and latitude of the target area, indicating the location of the sampling window on Earth.

[0072] The prediction device inputs the latitude and longitude data of each sampling window, the water temperature parameters corresponding to each time moment, the water quality prediction data, and the algal bloom area parameters into the algal bloom area prediction module, trains the algal bloom area prediction module, and obtains the target algal bloom area prediction module.

[0073] Please see Figure 5 , Figure 5 The flowchart of S214 in the algal bloom region prediction method based on remote sensing images provided in the second embodiment of this application is shown below, including steps S2141 to S2142:

[0074] S2141: Based on the water quality prediction data corresponding to each time of each sampling window and the preset arithmetic mean calculation algorithm, obtain the arithmetic mean of several water quality prediction parameters corresponding to each time of each sampling window.

[0075] The algorithm for calculating the arithmetic mean is as follows:

[0076]

[0077] In the formula, x This is the arithmetic mean of the water quality prediction parameters. D This represents the total number of pixels in the sampling window. d Indicates the first d One pixel, For the first d The values ​​of water quality prediction parameters for each pixel.

[0078] In this embodiment, the prediction device obtains the arithmetic mean of several water quality prediction parameters corresponding to each time of each sampling window based on the water quality prediction data corresponding to each time of each sampling window and a preset arithmetic mean calculation algorithm.

[0079] S2142: Based on the latitude and longitude data of each sampling window, the water temperature parameters at each time, the algal bloom area parameters, the arithmetic mean of several water quality prediction parameters, and the preset initial algal bloom area parameter prediction algorithm, the algal bloom area prediction module is trained to obtain the target algal bloom area prediction module.

[0080] The algal bloom area prediction module employs a geographically and temporally weighted regression (GTWR) model. In this embodiment, the prediction device trains the algal bloom area prediction module based on the latitude and longitude data of each sampling window, the algal bloom area parameters corresponding to each time moment, the arithmetic mean of several water quality prediction parameters, and a preset initial algal bloom area parameter prediction algorithm. The initial algal bloom area parameter prediction algorithm is as follows:

[0081]

[0082] In the formula, For the first i The sampling window of the first sampling window tThe algal bloom area parameters corresponding to each time point. For the first i The regression constant for each sampling window, For the first i Longitude parameters for each sampling window, For the first i Latitude parameters for each sampling window, For the first i The time parameters corresponding to the times of each sampling window n This represents the total number of types of water quality prediction parameters. k Indicates the first k Various water quality prediction parameters For the first k The first type of water quality prediction parameter affects the... i The regression coefficients for each sampling window, For water quality prediction parameters in the first i The arithmetic mean of the sampling windows. For the algal bloom area prediction module in the first i The residual values ​​of each sampling window. m This represents the total number of sampling windows.

[0083] To better adjust the algal bloom area prediction module In this embodiment, the prediction device uses cross-validation (CV) to determine the bandwidth of the algal bloom area prediction module, calculates the spatial weight matrix using the Gaussian function method, and adjusts the bandwidth based on the spatial weight matrix. The details are as follows:

[0084]

[0085]

[0086]

[0087] In the formula, CV For cross-validation values, a The total number of sampling windows. This represents the average value of the algal bloom area parameter across several sampling windows. For bandwidth, For the first k The first type of water quality prediction parameter affects the... i The weight parameters of each sampling window, For the first k Water quality prediction parameters of various types, the first i Each sampling window is within the bandwidth range Within, the distance from other sampling windows, The symbol represents the conversion between weight parameters and regression coefficients.

[0088] The prediction device will train the algal bloom area prediction module based on the water temperature parameters, algal bloom area parameters, and the arithmetic mean of several water quality prediction parameters corresponding to each time point of each sampling window, to obtain a target algal bloom area prediction module. The expression for the target algal bloom area prediction module is:

[0089]

[0090] In the formula, For the first The corresponding algal bloom area parameters at each time point. For time parameters, TP The total phosphorus content of the water body. TN Total nitrogen content, pH pH level DO Dissolved oxygen content, Q For water temperature parameters, Chla Here, represents the chlorophyll content, and represents the residual value. f ( ) is a nonlinear function.

[0091] The spatiotemporal relationship between historical algal bloom area and water quality parameters was established. The weight of each parameter in the local regression equation was estimated by using the time and location information of the data. The local effects of time and space objects were considered. In addition, the influence of water temperature on algal bloom was considered by combining the water temperature parameters corresponding to each time point, which improved the timeliness and accuracy of algal bloom prediction.

[0092] Please see Figure 6 , Figure 6 The flowchart of S2 in the algal bloom region prediction method based on remote sensing images provided in the third embodiment of this application is shown below. It also includes steps S221 to S222, as follows:

[0093] S221: Obtain the offshore distance data for each of the sampling windows, and the hydrological data for each of the sampling windows within the target time period.

[0094] In this embodiment, the prediction device obtains the offshore distance data of each sampling window and the hydrological data of each sampling window within the target time period. The hydrological data includes hydrological parameters corresponding to each time moment, including wind speed parameters, wind direction parameters, and water flow velocity parameters.

[0095] S222: Train the algal bloom location prediction module with the offshore distance of each sampling window, the hydrological data corresponding to each time moment, the algal bloom area parameters, and the preset initial algal bloom area parameter prediction algorithm to obtain the target algal bloom location prediction module.

[0096] The algorithm for predicting the initial algal bloom area parameters is as follows:

[0097]

[0098]

[0099] In the formula, For the first The x-axis parameter corresponding to the time. For the first The ordinate parameter corresponding to the time. For wind speed parameters, For wind direction parameters, For water flow velocity parameters, l For offshore distance data, The first speed coefficient, The second speed coefficient, This is the third velocity coefficient.

[0100] In this embodiment, the prediction device trains the algal bloom location prediction module with the offshore distance of each sampling window, the hydrological data corresponding to each time moment, the algal bloom area parameters, and the preset initial algal bloom area parameter prediction algorithm to obtain the target algal bloom location prediction module. This takes into account the influence of hydrological data on algal bloom prediction and improves the accuracy of algal bloom prediction.

[0101] S3: Obtain the band reflectance data, water temperature data, and hydrological data of the remote sensing image to be tested, and input the band reflectance data of the remote sensing image to be tested into the water quality prediction module to obtain the water quality prediction data of the remote sensing image to be tested.

[0102] In this embodiment, the prediction device obtains the band reflectance data, water temperature data, and hydrological data of the remote sensing image to be tested, and inputs the band reflectance data of the remote sensing image to be tested into the target water quality prediction module to obtain the water quality prediction data of the remote sensing image to be tested. The water quality prediction data of the remote sensing image to be tested includes several water quality prediction parameters of several pixels.

[0103] S4: Input the water quality prediction data and water temperature data of the remote sensing image to be tested into the algal bloom area prediction module, and obtain the algal bloom prediction area parameters of each prediction window of the remote sensing image to be tested according to a number of preset prediction windows.

[0104] In this embodiment, the prediction device inputs the water quality prediction data and water temperature data of the remote sensing image to be tested into the target algal bloom area prediction module, and obtains the algal bloom prediction area parameters of each prediction window of the remote sensing image to be tested according to a number of preset prediction windows.

[0105] S5: Input the algal bloom prediction area parameters and hydrological data of each prediction window of the remote sensing image to be tested into the algal bloom location prediction module to obtain the algal bloom prediction coordinate parameters of each prediction window of the remote sensing image to be tested.

[0106] In this embodiment, the prediction device inputs the algal bloom prediction area parameters and hydrological data of each prediction window of the remote sensing image to be measured into the target algal bloom location prediction module to obtain the algal bloom prediction coordinate parameters of each prediction window of the remote sensing image to be measured, wherein the algal bloom prediction coordinate parameters include horizontal coordinate parameters and vertical coordinate parameters.

[0107] S6: Based on the algal bloom prediction area parameters and algal bloom prediction coordinate parameters of each prediction window of the remote sensing image to be tested, obtain several algal bloom prediction regions of the remote sensing image to be tested.

[0108] In this embodiment, the prediction device obtains several algal bloom prediction regions of the remote sensing image under test based on the algal bloom prediction area parameters and algal bloom prediction coordinate parameters of each prediction window of the remote sensing image under test.

[0109] Please see Figure 7 , Figure 7 The flowchart of step S6 in the algal bloom region prediction method based on remote sensing images provided in the first embodiment of this application includes steps S61 to S62, as follows:

[0110] S61: Calculate the radius parameter of each prediction window based on the algal bloom prediction area parameter of each prediction window.

[0111] In this embodiment, the prediction device calculates the radius parameter of each prediction window based on the algal bloom prediction area parameter of each prediction window, as follows:

[0112]

[0113] In the formula, This is the radius parameter.

[0114] S62: Based on the radius parameters of each prediction window and the corresponding algal bloom prediction coordinate parameters, construct a circular region for each prediction window as the algal bloom prediction region, and obtain several algal bloom prediction regions for the remote sensing image to be tested.

[0115] In this embodiment, the prediction device constructs a circular region of each prediction window as the center based on the radius parameter of each prediction window and the corresponding algal bloom prediction coordinate parameter, thus obtaining several algal bloom prediction regions of the remote sensing image to be tested.

[0116] In an optional embodiment, the prediction device evaluates the accuracy of the algal bloom prediction results (i.e., several algal bloom prediction regions) of the remote sensing image to be tested. Specifically, the prediction device acquires several real algal bloom regions of the remote sensing image to be tested input by the user. Based on the category of several pixels corresponding to the several algal bloom prediction regions and the type of several pixels corresponding to the several real algal bloom regions, the device obtains the number of pixels correctly predicted as algal bloom, the number of pixels incorrectly predicted as algal bloom, the number of pixels not predicted as algal bloom, and the number of pixels not predicted as algal bloom. The prediction results are evaluated by calculating three indicators: producer accuracy, overall classification accuracy, and misclassification coefficient. Producer accuracy represents the proportion of actual algal bloom among samples predicted as algal bloom; overall classification accuracy represents the probability that the prediction result is consistent with the actual extraction result; the misclassification coefficient is a multivariate analysis method for measuring consistency and is commonly used to evaluate the correctness of remote sensing image classification. The formula is as follows:

[0117]

[0118]

[0119]

[0120]

[0121] In the formula, For the precision of the producer, For overall classification accuracy, This is the error caused by misclassification. These represent the number of pixels correctly predicted for algal blooms and the number of pixels correctly predicted for non-algal blooms, respectively. The number of pixels that were not predicted as non-blossom pixels. The number of pixels that were not predicted as bloom pixels, q This represents the total number of pixels. The misclassification coefficient ranges from -1 to 1; a larger value indicates a more accurate prediction.

[0122] Please see Figure 8 , Figure 8 The flowchart of the algal bloom region prediction method based on remote sensing images provided in the fourth embodiment of this application is shown, and it also includes step S7, as follows:

[0123] S7: In response to the display command, acquire an electronic map, and display and label several algal bloom prediction areas on the electronic map based on several algal bloom prediction areas of the remote sensing image to be tested.

[0124] The display command is issued by the user and received by the prediction device.

[0125] In this embodiment, the prediction device receives and responds to the display command sent by the user, acquires an electronic map, and displays and labels several algal bloom prediction areas on the electronic map based on these areas in the remote sensing image to be measured. By performing visualization processing on the algal bloom prediction areas, refined prediction of the area and spatial distribution of algal blooms can be achieved.

[0126] Please refer to Figure 9 , Figure 9 This is a schematic diagram of the structure of the algal bloom region prediction device based on remote sensing images provided in the fifth embodiment of this application. This device can be implemented in whole or in part through software, hardware, or a combination of both. The device 9 includes:

[0127] The sample data acquisition module 91 is used to acquire several sample remote sensing images, as well as the band reflectance data and hydrological data of each sample remote sensing image within the target time period.

[0128] The model building module 92 is used to build an algal bloom prediction model based on the band reflectance data and hydrological data of each sample remote sensing image within the target time period. The algal bloom prediction model includes a water quality prediction module, an algal bloom area prediction module, and an algal bloom location prediction module.

[0129] The water quality prediction module 93 is used to obtain the band reflectance data, water temperature data and hydrological data of the remote sensing image to be tested, and input the band reflectance data of the remote sensing image to be tested into the water quality prediction module to obtain the water quality prediction data of the remote sensing image to be tested.

[0130] The algal bloom area prediction module 94 is used to input the water quality prediction data and water temperature data of the remote sensing image to be tested into the algal bloom area prediction module, and obtain the algal bloom prediction area parameters of each prediction window of the remote sensing image to be tested according to a number of preset prediction windows.

[0131] The algal bloom location prediction module 95 is used to input the algal bloom prediction area parameters and hydrological data of each prediction window of the remote sensing image to be measured into the algal bloom location prediction module to obtain the algal bloom prediction coordinate parameters of each prediction window of the remote sensing image to be measured.

[0132] The algal bloom region prediction module 96 is used to obtain several algal bloom prediction regions of the remote sensing image under test based on the algal bloom prediction area parameters and algal bloom prediction coordinate parameters of each prediction window of the remote sensing image under test.

[0133] In this embodiment, a sample data acquisition module obtains several sample remote sensing images, along with band reflectance data and hydrological data for each sample remote sensing image within a target time period. A model building module constructs an algal bloom prediction model based on the band reflectance data and hydrological data of each sample remote sensing image within the target time period. This algal bloom prediction model includes a water quality prediction module, an algal bloom area prediction module, and an algal bloom location prediction module. The water quality prediction module obtains the band reflectance data, water temperature data, and hydrological data of the remote sensing image to be tested. The band reflectance data of the remote sensing image to be tested is input into the water quality prediction module to obtain the water quality prediction data for the remote sensing image to be tested. The algal bloom area prediction module inputs water quality prediction data and water temperature data from the remote sensing image to be tested. Based on several preset prediction windows, it obtains the algal bloom prediction area parameters for each prediction window of the remote sensing image. The algal bloom location prediction module inputs the algal bloom prediction area parameters and hydrological data from each prediction window of the remote sensing image to be tested, obtaining the algal bloom prediction coordinate parameters for each prediction window. The algal bloom region prediction module obtains several algal bloom prediction regions from the remote sensing image based on the algal bloom prediction area parameters and coordinate parameters from each prediction window. Water quality parameters are inverted from the remote sensing image to obtain water quality prediction parameters. Based on these parameters, the algal bloom area is extracted from the remote sensing image. Combined with hydrological data, algal bloom location prediction is performed. This method considers not only the local effects of temporal and spatial objects but also the influence of water quality, hydrology, and meteorological factors on algal blooms, improving the accuracy of algal bloom prediction and achieving precise and efficient algal bloom prediction.

[0134] Please refer to Figure 10 , Figure 10 This is a schematic diagram of the structure of a computer device provided in the sixth embodiment of this application. The computer device 10 includes: a processor 101, a memory 102, and a computer program 103 stored in the memory 102 and executable on the processor 101. The computer device can store multiple instructions, which are applicable to the method steps of the embodiments shown in the first to fourth embodiments above being loaded and executed by the processor 101. For the specific execution process, please refer to the specific description of the embodiments shown in the first to fourth embodiments, which will not be repeated here.

[0135] The processor 101 may include one or more processing cores. The processor 101 connects to various parts of the server using various interfaces and lines. It executes various functions and processes data of the algal bloom prediction device 9 based on remote sensing images by running or executing instructions, programs, code sets, or instruction sets stored in memory 102, and by calling data stored in memory 102. Optionally, the processor 101 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 101 may integrate one or more of the following: a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), and a modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required to be displayed on the touch screen; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 101 and may be implemented as a separate chip.

[0136] The memory 102 may include random access memory (RAM) or read-only memory. Optionally, the memory 102 may include a non-transitory computer-readable storage medium. The memory 102 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 102 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch instructions), instructions for implementing the various method embodiments described above, etc.; the data storage area may store data involved in the various method embodiments described above, etc. Optionally, the memory 102 may also be at least one storage device located remotely from the aforementioned processor 101.

[0137] This application also provides a storage medium that can store multiple instructions. These instructions are applicable to being loaded by a processor and executed by the method steps of the first to fourth embodiments described above. For details of the execution process, please refer to the specific descriptions of the first to fourth embodiments, which will not be repeated here.

[0138] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0139] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0140] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the algorithm. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0141] In the embodiments provided by this invention, it should be understood that the disclosed apparatus / terminal devices and methods can be implemented in other ways. For example, the apparatus / terminal device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0142] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0143] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0144] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms.

[0145] This invention is not limited to the above-described embodiments. If any modifications or variations to this invention do not depart from the spirit and scope of this invention, and if such modifications and variations fall within the scope of the claims and equivalent technologies of this invention, then this invention also intends to include such modifications and variations.

Claims

1. A method for predicting algal bloom areas based on remote sensing images, characterized in that, Includes the following steps: Obtain several sample remote sensing images, as well as band reflectance data and hydrological data of each sample remote sensing image within the target time period; Based on the band reflectance data and hydrological data of each sample remote sensing image within the target time period, an algal bloom prediction model is constructed. This algal bloom prediction model includes a water quality prediction module, an algal bloom area prediction module, and an algal bloom location prediction module. The construction of the algal bloom prediction model based on the band reflectance data and hydrological data of each sample remote sensing image within the target time period includes the following steps: Obtain water quality measurement data of each of the sample remote sensing images within the target time period, wherein the water quality measurement data includes several water quality measurement parameters of several pixels; Based on a preset number of sampling points and window size, a sampling window corresponding to a number of sampling points of each sample remote sensing image is constructed. Based on the measured water quality data and band reflectance data, the band reflectance data and measured water quality data of each sampling window within the target time period are obtained. The band reflection data and actual water quality data of each sampling window within the target time period are input into the water quality prediction module for training to obtain the target water quality prediction module. Based on the band reflection data of each sampling window within the target time period, water bloom pixels are extracted for each sampling window to obtain the number of water bloom pixels corresponding to each time of each sampling window. The spatial resolution of each sampling window is obtained. Based on the number of algal bloom pixels, the spatial resolution, and a preset algal bloom area parameter calculation algorithm, the algal bloom area parameter corresponding to each time step of each sampling window is obtained. The algal bloom area parameter calculation algorithm is as follows: In the formula, For parameters related to algal bloom area, The number of pixels representing algal bloom. Spatial resolution; The band reflection data of each sampling window within the target time period are input into the target water quality prediction module to obtain the water quality prediction data corresponding to each time of each sampling window. The latitude and longitude data of each sampling window and the water temperature parameters corresponding to each time moment are obtained. The latitude and longitude data of each sampling window, the water temperature parameters corresponding to each time moment, the water quality prediction data and the algal bloom area parameters are input into the algal bloom area prediction module. The algal bloom area prediction module is trained to obtain the target algal bloom area prediction module. Obtain offshore distance data for each of the sampling windows, and hydrological data for each of the sampling windows within the target time period. The hydrological data includes hydrological parameters corresponding to each time moment, including wind speed parameters, wind direction parameters, and water flow velocity parameters. The algal bloom location prediction module is trained using the offshore distance of each sampling window, the hydrological data corresponding to each time point, the algal bloom area parameters, and a preset initial algal bloom area parameter prediction algorithm to obtain the target algal bloom location prediction module. The initial algal bloom location parameter prediction algorithm is as follows: In the formula, and These represent the time parameters for the current moment and the next moment, respectively. For the first The x-axis parameter corresponding to the time. For the first The ordinate parameter corresponding to the time. For wind speed parameters, For wind direction parameters, For water flow velocity parameters, l For offshore distance data, The first speed coefficient, The second speed coefficient, This is the third velocity coefficient; For the first The algal bloom area parameters corresponding to the given time; Obtain the band reflectance data, water temperature data, and hydrological data of the remote sensing image to be tested. Input the band reflectance data of the remote sensing image to be tested into the water quality prediction module to obtain the water quality prediction data of the remote sensing image to be tested. The water quality prediction data and water temperature data of the remote sensing image to be tested are input into the algal bloom area prediction module. Based on a number of preset prediction windows, the algal bloom prediction area parameters of each prediction window of the remote sensing image to be tested are obtained. The algal bloom prediction area parameters and hydrological data of each prediction window of the remote sensing image to be tested are input into the algal bloom location prediction module to obtain the algal bloom prediction coordinate parameters of each prediction window of the remote sensing image to be tested. Based on the algal bloom prediction area parameters and algal bloom prediction coordinate parameters of each prediction window of the remote sensing image to be tested, several algal bloom prediction regions of the remote sensing image to be tested are obtained.

2. The method for predicting algal bloom areas based on remote sensing images according to claim 1, characterized in that: The band reflectance data includes green band reflectance, near-infrared band reflectance, and red band reflectance; The step of extracting algal bloom pixels for each sampling window based on the band reflection data to obtain the number of algal bloom pixels at each time point of each sampling window includes the following steps: Based on the band reflection data and the preset normalized vegetation index (NWRI) and normalized water index (NDI) calculation algorithms, the NWRI and NDI corresponding to each pixel at each time are obtained. The NWRI calculation algorithm is as follows: In the formula, The normalized water index, For green band reflectivity, Reflectivity in the near-infrared band; The normalized water index is: In the formula, Normalized Difference Vegetation Index (NDVI) Reflectivity in the red band; Based on the normalized vegetation index, normalized water index, and preset normalized vegetation index thresholds and normalized water index thresholds corresponding to each pixel at each time, water bloom pixels are extracted for each sampling window to obtain the number of water bloom pixels corresponding to each sampling window at each time.

3. The method for predicting algal bloom areas based on remote sensing images according to claim 2, characterized in that: The water quality prediction data includes several water quality prediction parameters for several pixels; the latitude and longitude data includes longitude parameters and latitude parameters; the water quality prediction parameters include total phosphorus content, total nitrogen content, pH, dissolved oxygen content and chlorophyll content of the water area. The step of inputting the latitude and longitude data of each sampling window, the water temperature parameters corresponding to each time moment, the water quality prediction data, and the algal bloom area parameters into the algal bloom area prediction module, and training the algal bloom area prediction module to obtain the target algal bloom area prediction module includes the following steps: Based on the water quality prediction data corresponding to each time point of each sampling window and a preset arithmetic mean calculation algorithm, the arithmetic mean of several water quality prediction parameters corresponding to each time point of each sampling window is obtained, wherein the arithmetic mean calculation algorithm is as follows: In the formula, x This is the arithmetic mean of the water quality prediction parameters. D This represents the total number of pixels in the sampling window. d Indicates the first d One pixel, For the first d The values ​​of water quality prediction parameters for each pixel; Based on the latitude and longitude data of each sampling window, the water temperature parameters at each time point, the algal bloom area parameters, the arithmetic mean of several water quality prediction parameters, and a preset initial algal bloom area parameter prediction algorithm, the algal bloom area prediction module is trained to obtain the target algal bloom area prediction module. The initial algal bloom area parameter prediction algorithm is as follows: In the formula, For the first i The sampling window of the first sampling window t The algal bloom area parameters corresponding to each time point. For the first i The regression constant for each sampling window, For the first i Longitude parameters for each sampling window, For the first i Latitude parameters for each sampling window, For the first i The time parameters corresponding to the times of each sampling window n This represents the total number of types of water quality prediction parameters. k Indicates the first k Various water quality prediction parameters For the first k The first type of water quality prediction parameter affects the... i The regression coefficients for each sampling window, For water quality prediction parameters in the first i The arithmetic mean of the sampling windows. For the algal bloom area prediction module in the first i The residual values ​​of each sampling window. m This represents the total number of sampling windows; The expression for the target algal bloom area prediction module is: In the formula, For time parameters, TP The total phosphorus content of the water body. TN Total nitrogen content, pH pH level DO Dissolved oxygen content, Q For water temperature parameters, Chla Chlorophyll content, The residual value, f ( ) is a nonlinear function.

4. The method for predicting algal bloom areas based on remote sensing images according to claim 1, characterized in that, The step of obtaining several algal bloom prediction regions of the remote sensing image under test based on the algal bloom prediction area parameters and algal bloom prediction coordinate parameters of each prediction window of the remote sensing image under test includes the following steps: Calculate the radius parameter of each prediction window based on the algal bloom prediction area parameter of each prediction window; Based on the radius parameters of each prediction window and the corresponding algal bloom prediction coordinate parameters, a circular region of each prediction window is constructed as the algal bloom prediction region, thereby obtaining several algal bloom prediction regions of the remote sensing image to be tested.

5. The method for predicting algal bloom areas based on remote sensing images according to claim 1, characterized in that, It also includes the following steps: In response to a display command, an electronic map is acquired, and based on several algal bloom prediction areas in the remote sensing image to be tested, several algal bloom prediction areas are displayed and marked on the electronic map.

6. A device for predicting algal bloom areas based on remote sensing images, characterized in that, include: The sample data acquisition module is used to acquire several sample remote sensing images, as well as the band reflectance data and hydrological data of each sample remote sensing image within the target time period. The model building module is used to construct an algal bloom prediction model based on the band reflectance data and hydrological data of each sample remote sensing image within a target time period. The algal bloom prediction model includes a water quality prediction module, an algal bloom area prediction module, and an algal bloom location prediction module. The step of constructing the algal bloom prediction model based on the band reflectance data and hydrological data of each sample remote sensing image within a target time period includes the following steps: Obtain water quality measurement data of each of the sample remote sensing images within the target time period, wherein the water quality measurement data includes several water quality measurement parameters of several pixels; Based on a preset number of sampling points and window size, a sampling window corresponding to a number of sampling points of each sample remote sensing image is constructed. Based on the measured water quality data and band reflectance data, the band reflectance data and measured water quality data of each sampling window within the target time period are obtained. The band reflection data and actual water quality data of each sampling window within the target time period are input into the water quality prediction module for training to obtain the target water quality prediction module. Based on the band reflection data of each sampling window within the target time period, water bloom pixels are extracted for each sampling window to obtain the number of water bloom pixels corresponding to each time of each sampling window. The spatial resolution of each sampling window is obtained. Based on the number of algal bloom pixels, the spatial resolution, and a preset algal bloom area parameter calculation algorithm, the algal bloom area parameter corresponding to each time step of each sampling window is obtained. The algal bloom area parameter calculation algorithm is as follows: In the formula, For parameters related to algal bloom area, The number of pixels representing algal bloom. Spatial resolution; The band reflection data of each sampling window within the target time period are input into the target water quality prediction module to obtain the water quality prediction data corresponding to each time of each sampling window. The latitude and longitude data of each sampling window and the water temperature parameters corresponding to each time moment are obtained. The latitude and longitude data of each sampling window, the water temperature parameters corresponding to each time moment, the water quality prediction data and the algal bloom area parameters are input into the algal bloom area prediction module. The algal bloom area prediction module is trained to obtain the target algal bloom area prediction module. Obtain offshore distance data for each of the sampling windows, and hydrological data for each of the sampling windows within the target time period. The hydrological data includes hydrological parameters corresponding to each time moment, including wind speed parameters, wind direction parameters, and water flow velocity parameters. The algal bloom location prediction module is trained using the offshore distance of each sampling window, the hydrological data corresponding to each time point, the algal bloom area parameters, and a preset initial algal bloom area parameter prediction algorithm to obtain the target algal bloom location prediction module. The initial algal bloom area parameter prediction algorithm is as follows: In the formula, These represent the time parameters for the current moment and the next moment, respectively. For the first The x-axis parameter corresponding to the time. For the first The ordinate parameter corresponding to the time. For wind speed parameters, For wind direction parameters, For water flow velocity parameters, l For offshore distance data, The first speed coefficient, The second speed coefficient, This is the third velocity coefficient; For the first The algal bloom area parameters corresponding to the given time; The water quality prediction module is used to obtain the band reflectance data, water temperature data and hydrological data of the remote sensing image to be tested. The band reflectance data of the remote sensing image to be tested is input into the water quality prediction module to obtain the water quality prediction data of the remote sensing image to be tested. The algal bloom area prediction module is used to input the water quality prediction data and water temperature data of the remote sensing image to be tested into the algal bloom area prediction module, and obtain the algal bloom prediction area parameters of each prediction window of the remote sensing image to be tested according to a number of preset prediction windows. The algal bloom location prediction module is used to input the algal bloom prediction area parameters and hydrological data of each prediction window of the remote sensing image to be measured into the algal bloom location prediction module to obtain the algal bloom prediction coordinate parameters of each prediction window of the remote sensing image to be measured. The algal bloom region prediction module is used to obtain several algal bloom prediction regions of the remote sensing image under test based on the algal bloom prediction area parameters and algal bloom prediction coordinate parameters of each prediction window of the remote sensing image under test.

7. A computer device, characterized in that, include: A processor, a memory, and a computer program stored in the memory and executable on the processor; the computer program, when executed by the processor, implements the steps of the algal bloom region prediction method based on remote sensing images as described in any one of claims 1 to 5.

Images