Green tide distribution area prediction method and device, equipment and storage medium

Abstract

The invention provides a green tide distribution area prediction method and device, equipment and a storage medium, and the method comprises the steps: determining the historical green tide distribution area data of a monitoring region corresponding to a historical green tide distribution region at each historical moment based on historical satellite remote sensing data; acquiring a plurality of environmental influence factors corresponding to the historical green tide distribution area; screening out at least one target environmental impact factor from the environmental impact factors based on the correlation between the environmental impact factors and the first part of data in the historical green tide distribution area data; establishing at least one initial prediction model based on the at least one target environmental impact factor; screening and optimizing the at least one initial prediction model based on historical green tide distribution area data to obtain a green tide distribution area prediction model; and performing green tide distribution area prediction based on the green tide distribution area prediction model. Through the technical scheme of the invention, the green tide distribution area can be predicted more accurately.

Description

Technical Field

[0001] The present application relates to the field of green tide monitoring, and in particular to a method, device, equipment and storage medium for predicting the distribution area of ​​green tide. Background Art

[0002] In related technologies, numerical simulation methods are usually used to make short-term predictions of green tide drift trajectories. However, the occurrence and development of green tides require large-scale and long-term drifts. Numerical simulation methods require a lot of computing resources and are only suitable for short-term predictions of green tide disasters, and cannot meet the actual needs of green tide disaster prevention and mitigation. Summary of the invention

[0003] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0004] In the first aspect, the present application proposes a method for predicting green tide distribution area, the method comprising: obtaining historical satellite remote sensing data of a monitored area at multiple historical moments within a preset historical period; determining the historical green tide distribution area data of the monitored area corresponding to the historical green tide distribution area at each historical moment based on the historical satellite remote sensing data; obtaining multiple environmental impact factors corresponding to the historical green tide distribution area; based on the correlation between the environmental impact factors and the first part of the data in the historical green tide distribution area data, screening at least one target environmental impact factor from the environmental impact factors; establishing at least one initial prediction model based on the at least one target environmental impact factor; screening and optimizing the at least one initial prediction model based on the historical green tide distribution area data to obtain a green tide distribution area prediction model; and predicting the green tide distribution area based on the green tide distribution area prediction model.

[0005] In one implementation, the historical green tide distribution area data of the monitoring area corresponding to the historical green tide distribution area at each historical moment is determined based on the historical satellite remote sensing data, including: calculating the normalized vegetation index of each pixel in the historical satellite remote sensing data at each historical moment based on the historical satellite remote sensing data at each historical moment; obtaining the pixel whose normalized vegetation index is greater than a preset threshold as the target pixel; and obtaining the pixel area of ​​the target pixel as the historical green tide distribution area data corresponding to each historical moment.

[0006] In one implementation, based on the correlation between the environmental impact factors and the first part of the data in the historical green tide distribution area data, at least one target environmental impact factor is screened out from the environmental impact factors, including: calculating and obtaining a first correlation coefficient between the first part of the data and each of the historical environmental impression factors in multiple preset sub-periods within the historical period; obtaining the mean of the first correlation coefficient as the second correlation coefficient; and screening out at least one target environmental impact factor from the environmental impact factors based on the second correlation coefficient.

[0007] In one implementation, the establishing of at least one initial prediction model based on the at least one target environmental impact factor includes: establishing at least one target factor combination from the at least one target factor; wherein the target factors included in different target factor combinations are not completely the same, and the same target factor combination may include the same target factors; and using a univariate prediction regression method and / or a multivariate prediction regression method to establish at least one initial prediction model corresponding to each target factor combination.

[0008] In one implementation, the screening and optimization of the at least one initial prediction model based on the historical green tide distribution area data to obtain a green tide distribution area prediction model includes: performing predictions based on each of the initial prediction models respectively to obtain a predicted green tide area corresponding to the first part of the data predicted by each of the initial prediction models; obtaining a prediction deviation value between the predicted green tide distribution area corresponding to each of the initial prediction models and the first part of the data; screening the at least one initial prediction model based on the data difference to obtain a target prediction model; optimizing the parameters of the target prediction model based on the second part of the data in the historical green tide distribution area data to obtain a green tide distribution area prediction model;

[0009] In one implementation, the environmental influencing factor includes at least one of the following: sea surface temperature; temperature at a first preset height from the sea surface; specific humidity; precipitation rate; wind speed at a second preset height from the sea surface; and seawater salinity.

[0010] In the second aspect, the present application proposes a prediction device for green tide distribution area, which includes: a first acquisition module, used to obtain historical satellite remote sensing data of a monitored area at multiple historical moments within a preset historical period; a first processing module, used to determine the historical green tide distribution area data of the monitored area corresponding to the historical green tide distribution area at each historical moment based on the historical satellite remote sensing data; a second acquisition module, used to obtain multiple environmental impact factors corresponding to the historical green tide distribution area; a second processing module, used to screen out at least one target environmental impact factor from the environmental impact factors based on the correlation between the environmental impact factor and the first part of the data in the historical green tide distribution area data; a third processing module, used to establish at least one initial prediction model based on the at least one target environmental impact factor; a fourth processing module, used to screen and optimize the at least one initial prediction model based on the historical green tide distribution area data to obtain a green tide distribution area prediction model; a fifth processing module, used to predict the green tide distribution area based on the green tide distribution area prediction model.

[0011] In one implementation, the historical green tide distribution area data of the monitoring area corresponding to the historical green tide distribution area at each historical moment is determined based on the historical satellite remote sensing data, including: calculating the normalized vegetation index of each pixel in the historical satellite remote sensing data at each historical moment based on the historical satellite remote sensing data at each historical moment; obtaining the pixel whose normalized vegetation index is greater than a preset threshold as the target pixel; and obtaining the pixel area of ​​the target pixel as the historical green tide distribution area data corresponding to each historical moment.

[0012] In one implementation, based on the correlation between the environmental impact factors and the first part of the data in the historical green tide distribution area data, at least one target environmental impact factor is screened out from the environmental impact factors, including: calculating and obtaining a first correlation coefficient between the first part of the data and each of the historical environmental impression factors in multiple preset sub-periods within the historical period; obtaining the mean of the first correlation coefficient as the second correlation coefficient; and screening out at least one target environmental impact factor from the environmental impact factors based on the second correlation coefficient.

[0013] In one implementation, the establishing of at least one initial prediction model based on the at least one target environmental impact factor includes: establishing at least one target factor combination from the at least one target factor; wherein the target factors included in different target factor combinations are not completely the same, and the same target factor combination may include the same target factors; and using a univariate prediction regression method and / or a multivariate prediction regression method to establish at least one initial prediction model corresponding to each target factor combination.

[0014] In one implementation, the screening and optimization of the at least one initial prediction model based on the historical green tide distribution area data to obtain a green tide distribution area prediction model includes: performing predictions based on each of the initial prediction models respectively to obtain a predicted green tide area corresponding to the first part of the data predicted by each of the initial prediction models; obtaining a prediction deviation value between the predicted green tide distribution area corresponding to each of the initial prediction models and the first part of the data; screening the at least one initial prediction model based on the data difference to obtain a target prediction model; optimizing the parameters of the target prediction model based on the second part of the data in the historical green tide distribution area data to obtain a green tide distribution area prediction model;

[0015] In one implementation, the environmental influencing factor includes at least one of the following: sea surface temperature; temperature at a first preset height from the sea surface; specific humidity; precipitation rate; wind speed at a second preset height from the sea surface; and seawater salinity.

[0016] In a third aspect, the present application proposes an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for predicting the green tide distribution area as described in the first aspect.

[0017] In a fourth aspect, the present application proposes a computer-readable storage medium for storing instructions, which, when executed, enables the method described in the first aspect to be implemented.

[0018] In a fifth aspect, the present application proposes a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the method for predicting the green tide distribution area as described in the first aspect.

[0019] The prediction method, device, equipment and storage medium of the green tide distribution area provided in the present application can obtain the historical green tide distribution surface of the historical green tide distribution area based on satellite remote sensing data, and screen out at least one target environmental impact factor from the environmental impact factor based on the correlation between the environmental impact factor and the first part of the data in the historical green tide distribution area data, so as to establish at least one initial prediction model based on the target environmental impact factor, thereby screening and optimizing the at least one initial prediction model based on the historical green tide distribution area data, obtaining a green tide distribution area prediction model, and finally predicting the green tide distribution area based on the green tide distribution area prediction model. A green tide distribution area prediction model with a higher prediction accuracy can be established to make a more accurate prediction of the green tide distribution area.

[0020] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0022] Figure 1 It is a flow chart of a method for predicting green tide distribution area provided in an embodiment of the present application;

[0023] Figure 2 It is a flow chart of another method for predicting the green tide distribution area provided in an embodiment of the present application;

[0024] Figure 3 It is a flow chart of another method for predicting the green tide distribution area provided in an embodiment of the present application;

[0025] Figure 4 It is a flow chart of another method for predicting the green tide distribution area provided in an embodiment of the present application;

[0026] Figure 5 It is a flow chart of another method for predicting the green tide distribution area provided in an embodiment of the present application;

[0027] Figure 6 This is a flow chart of a method for predicting green tide distribution area based on remote sensing data provided in an embodiment of the present application;

[0028] Figure 7 It is a structural schematic diagram of a device for predicting green tide distribution area provided in an embodiment of the present application;

[0029] Figure 8 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0031] The following describes the method and device for predicting the green tide distribution area according to the embodiments of the present application with reference to the accompanying drawings.

[0032] Figure 1 FIG. 1 is a flow chart of a method for predicting the green tide distribution area provided in an embodiment of the present application. Figure 1As shown, the method may include but is not limited to the following steps:

[0033] Step S101: Acquire historical satellite remote sensing data of a monitoring area at multiple historical moments within a preset historical period.

[0034] Exemplarily, historical satellite remote sensing data of the monitoring area at multiple times in the current year and the previous year are obtained.

[0035] It should be noted that, in the embodiments of the present application, the above-mentioned satellite remote sensing data includes the reflectivity of the near-infrared band and the reflectivity of the infrared band.

[0036] Step S102: determining historical green tide distribution area data corresponding to the historical green tide distribution area of ​​the monitoring area at each historical moment based on historical satellite remote sensing data.

[0037] Exemplarily, data preprocessing is performed on each historical satellite remote sensing data to obtain a high-resolution optical satellite reflectivity image, and the optical satellite reflectivity image is masked to obtain a reflectivity image of the monitored area. Green tides are identified based on the reflectivity image using a pre-selected remote sensing index algorithm to obtain historical green tide distribution area data of the green tide distribution area at each historical moment.

[0038] Step S103: obtaining multiple environmental impact factors corresponding to the historical green tide distribution area.

[0039] Exemplarily, atmospheric and ocean reanalysis data are obtained, and environmental impact factors corresponding to green tide distribution areas are extracted from the above data.

[0040] Among them, in an embodiment of the present application, the above-mentioned environmental influencing factors include at least one of the following: sea surface temperature; temperature at a first preset height from the sea surface; specific humidity; precipitation rate; wind speed at a second preset height from the sea surface; and seawater salinity.

[0041] Exemplarily, the first preset height may be 2 meters.

[0042] Exemplarily, the second preset height may be 10 meters.

[0043] Step S104: based on the correlation between each environmental impact factor and the first part of the data in the historical green tide distribution area data, at least one target environmental impact factor is screened out from the environmental impact factors.

[0044] Exemplarily, the correlation coefficient between each historical environmental impact shadow and a selected portion of the historical green tide distribution area data is obtained, and the environmental impact factor corresponding to the environmental impact factor with a correlation coefficient greater than or equal to a preset threshold is taken as the target environmental impact factor.

[0045] Step S105: Establish at least one initial prediction model based on at least one target environmental impact factor.

[0046] Exemplarily, at least one target environmental impact factor is arranged and combined to obtain a plurality of target environmental impact factor combinations, and at least one initial prediction model is established based on different regression prediction methods for different target environmental impact factor combinations.

[0047] It should be noted that, in the embodiments of the present application, the combination of different target environmental impact factors includes at least one different target environmental impact factor.

[0048] Step S106: Screening and optimizing at least one initial prediction model based on historical green tide distribution area data to obtain a green tide distribution area prediction model.

[0049] Exemplarily, the prediction effect of each initial prediction model is tested based on the other parts of the historical green tide distribution area data except the first part of the data, and the model with the best prediction effect is obtained as the green tide distribution area prediction model.

[0050] Step S107: predicting the green tide distribution area based on the green tide distribution area prediction model.

[0051] Exemplarily, the influencing factor type included in the green tide distribution area prediction model is obtained to obtain the influencing factor data corresponding to the influencing factor type in the current period, so as to predict the green tide distribution area based on the influencing factor data and the green tide distribution area prediction model.

[0052] By implementing the embodiments of the present application, the historical green tide distribution surface of the historical green tide distribution area can be obtained based on satellite remote sensing data, and at least one target environmental impact factor can be screened out from the environmental impact factor based on the correlation between the environmental impact factor and the first part of the data in the historical green tide distribution area data, so as to establish at least one initial prediction model based on the target environmental impact factor, thereby screening and optimizing at least one initial prediction model based on the historical green tide distribution area data, obtaining a green tide distribution area prediction model, and finally predicting the green tide distribution area based on the green tide distribution area prediction model. A green tide distribution area prediction model with a higher prediction accuracy can be established to make a more accurate prediction of the green tide distribution area.

[0053] In some embodiments, historical satellite remote sensing data can be processed to obtain historical green tide distribution area data. As an example, see Figure 2 , Figure 2 FIG. 1 is a flow chart of another method for predicting the green tide distribution area provided in an embodiment of the present application. Figure 2 As shown, the method may include but is not limited to the following steps:

[0054] Step S201: Acquire historical satellite remote sensing data of a monitoring area at multiple historical moments within a preset historical period.

[0055] In the embodiments of the present application, step S201 can be implemented by any of the methods in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0056] Step S202: Calculate the normalized vegetation index of each pixel in the historical satellite remote sensing data at each historical moment based on the historical satellite remote sensing data at each historical moment.

[0057] Exemplarily, the normalized vegetation index of each pixel in the historical satellite remote sensing data at each historical moment is calculated based on the following formula:

[0058]

[0059] Among them, NDVI (Normalized Difference Vegetation Index) is the normalized vegetation index, NIR is the reflectivity of the near-infrared band, and R is the reflectivity of the infrared band.

[0060] Step S203: obtaining pixels whose normalized difference vegetation index is greater than a preset threshold as target pixels.

[0061] Exemplarily, pixels whose normalized vegetation index corresponding to pixels in the satellite remote sensing data corresponding to each historical moment is greater than or equal to a preset threshold are taken as target pixels.

[0062] Step S204: Obtain the pixel area of ​​the target pixel as the historical green tide distribution area data corresponding to each historical moment.

[0063] For example, the following formula can be used to calculate and obtain the historical green tide distribution area data corresponding to each historical moment:

[0064] S=N×r 2

[0065] Among them, S is the green tide distribution area, N is the number of target pixels in the historical satellite remote sensing data corresponding to each historical moment, and r is the spatial resolution of the satellite.

[0066] Step S205: obtaining multiple environmental impact factors corresponding to the historical green tide distribution area.

[0067] In the embodiments of the present application, step S205 can be implemented in any of the ways in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0068] Step S206: based on the correlation between each environmental impact factor and the first part of the data in the historical green tide distribution area data, at least one target environmental impact factor is screened out from the environmental impact factors.

[0069] In the embodiments of the present application, step S206 can be implemented by any of the methods in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0070] Step S207: Establish at least one initial prediction model based on at least one target environmental impact factor.

[0071] In the embodiments of the present application, step S207 can be implemented by any of the methods in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0072] Step S208: Screening and optimizing at least one initial prediction model based on historical green tide distribution area data to obtain a green tide distribution area prediction model.

[0073] In the embodiments of the present application, step S208 can be implemented in any of the ways in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0074] Step S209: predicting the green tide distribution area based on the green tide distribution area prediction model.

[0075] In the embodiments of the present application, step S209 can be implemented in any of the ways in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0076] By implementing the embodiments of the present application, the normalized vegetation index in the historical period can be calculated based on the historical satellite remote sensing data, so as to obtain the green tide distribution area of ​​the green tide distribution area in the historical period based on the normalized vegetation index. The green tide distribution area prediction model can be established using the historical remote sensing data, thereby realizing the prediction of the green tide distribution area.

[0077] In some embodiments, the target environmental impact factor can be obtained based on the correlation between the mean value of the environmental impact factor and the historical green tide distribution area data. As an example, see Figure 3 , Figure 3 FIG. 2 is a flow chart of another method for predicting the green tide distribution area provided in an embodiment of the present application. Figure 3 As shown, the method may include but is not limited to the following steps:

[0078] Step S301: Acquire historical satellite remote sensing data of a monitoring area at multiple historical moments within a preset historical period.

[0079] In the embodiments of the present application, step S301 can be implemented in any of the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0080] Step S302: determining historical green tide distribution area data corresponding to the historical green tide distribution area of ​​the monitoring area at each historical moment based on historical satellite remote sensing data.

[0081] In the embodiments of the present application, step S302 can be implemented by any of the methods in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0082] Step S303: obtaining multiple environmental impact factors corresponding to the historical green tide distribution area.

[0083] In the embodiments of the present application, step S303 can be implemented by any of the methods in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0084] Step S304: Calculate and obtain a first correlation coefficient between the first portion of data and each historical environmental impact factor in a plurality of preset sub-periods within the historical period.

[0085] Exemplarily, the average of the correlation coefficients corresponding to the environmental impact factors of each green algae-related environmental impact factor in the same year and each month of the previous year is calculated as the first correlation coefficient.

[0086] The above correlation coefficient may be a Pearson correlation coefficient.

[0087] Step S305: Obtain the mean of the first correlation coefficient as the second correlation coefficient.

[0088] Exemplarily, the mean of the first correlation coefficients corresponding to each environmental impact factor is obtained as the second correlation coefficient.

[0089] Step S306: Screening out at least one target environmental impact factor from the environmental impact factors based on the second correlation coefficient.

[0090] Exemplarily, an environmental factor whose second correlation coefficient is greater than or equal to a preset threshold is used as a target environmental influencing factor.

[0091] Step S307: Establish at least one initial prediction model based on at least one target environmental impact factor.

[0092] In the embodiments of the present application, step S307 can be implemented by any of the methods in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0093] Step S308: Screening and optimizing at least one initial prediction model based on historical green tide distribution area data to obtain a green tide distribution area prediction model.

[0094] In the embodiments of the present application, step S308 can be implemented in any of the ways in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0095] Step S309: predicting the green tide distribution area based on the green tide distribution area prediction model.

[0096] In the embodiments of the present application, step S309 can be implemented in any of the ways in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0097] By implementing the embodiments of the present application, target environmental impact factors that have a greater impact on green tides can be screened out based on the correlation between environmental impact factors and historical green tide distribution area data, thereby improving the prediction accuracy of the prediction model established in subsequent steps.

[0098] In some embodiments, multiple target impact factors may be combined to establish initial prediction models corresponding to different combinations of target impact factors. Figure 4 , Figure 4 FIG. 2 is a flow chart of another method for predicting the green tide distribution area provided in an embodiment of the present application. Figure 4 As shown, the method may include but is not limited to the following steps:

[0099] Step S401: Acquire historical satellite remote sensing data of a monitoring area at multiple historical moments within a preset historical period.

[0100] In the embodiments of the present application, step S401 can be implemented by any of the methods in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0101] Step S402: determining historical green tide distribution area data corresponding to the historical green tide distribution area of ​​the monitoring area at each historical moment based on historical satellite remote sensing data.

[0102] In the embodiments of the present application, step S402 can be implemented by any of the methods in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0103] Step S403: obtaining multiple environmental impact factors corresponding to the historical green tide distribution area.

[0104] In the embodiments of the present application, step S403 can be implemented by any of the methods in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0105] Step S404: based on the correlation between each environmental impact factor and the first part of the data in the historical green tide distribution area data, at least one target environmental impact factor is screened out from the environmental impact factors.

[0106] In the embodiments of the present application, step S404 can be implemented by any of the methods in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0107] Step S405: Create at least one target factor combination from at least one target factor.

[0108] Among them, the target factors contained in different target factor combinations are not completely the same, and the same target factor combination can contain the same target factor;

[0109] Step S406: using a univariate prediction regression method and / or a multivariate prediction regression method to establish at least one initial prediction model corresponding to each target factor combination.

[0110] Step S407: Screening and optimizing at least one initial prediction model based on historical green tide distribution area data to obtain a green tide distribution area prediction model.

[0111] In the embodiments of the present application, step S407 can be implemented by any of the methods in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0112] Step S408: predicting the green tide distribution area based on the green tide distribution area prediction model.

[0113] In the embodiments of the present application, step S408 can be implemented in any of the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0114] By implementing the embodiments of the present application, at least one initial prediction model can be established based on at least one target environmental impact factor to screen the initial prediction models and obtain a model with the smallest prediction error, thereby improving the accuracy of model prediction.

[0115] In some embodiments, the initial prediction model can be screened based on a portion of the historical green tide distribution area data to obtain the screened initial prediction model, and the screened model can be optimized based on another portion of the data to obtain the green tide distribution area prediction model. As an example, see Figure 5 , Figure 5FIG. 2 is a flow chart of another method for predicting the green tide distribution area provided in an embodiment of the present application. Figure 5 As shown, the method may include but is not limited to the following steps:

[0116] Step S501: Acquire historical satellite remote sensing data of a monitoring area at multiple historical moments within a preset historical period.

[0117] In the embodiments of the present application, step S501 can be implemented by any of the methods in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0118] Step S502: determining historical green tide distribution area data corresponding to the historical green tide distribution area of ​​the monitoring area at each historical moment based on historical satellite remote sensing data.

[0119] In the embodiments of the present application, step S502 can be implemented by any of the methods in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0120] Step S503: obtaining multiple environmental impact factors corresponding to the historical green tide distribution area.

[0121] In the embodiments of the present application, step S503 can be implemented by any of the methods in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0122] Step S504: based on the correlation between each environmental impact factor and the first part of the data in the historical green tide distribution area data, at least one target environmental impact factor is screened out from the environmental impact factors.

[0123] In the embodiments of the present application, step S504 can be implemented in any of the ways in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0124] Step S505: Establish at least one initial prediction model based on at least one target environmental impact factor.

[0125] In the embodiments of the present application, step S505 can be implemented by any of the methods in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0126] Step S506: Predictions are made based on each initial prediction model respectively, and the predicted green tide distribution area corresponding to the first part of data predicted by each initial prediction model is obtained.

[0127] Exemplarily, the target environmental impact factor of the historical moment corresponding to the first part of the data is obtained, so as to obtain the predicted green tide distribution area of ​​the historical moment corresponding to the first part of the data based on the target environmental impact factor and each initial prediction model.

[0128] It can be understood that the above-mentioned first part of data may include green tide distribution areas at multiple historical moments, and the predicted green tide distribution area at each historical moment can be predicted based on each initial prediction model as the predicted green tide distribution area corresponding to the first part of data.

[0129] Step S507: Obtain the prediction deviation value between the predicted green tide distribution area corresponding to each initial prediction model and the first part of data.

[0130] Exemplarily, the predicted green tide distribution area at each historical moment predicted by each initial prediction model is obtained, and the area difference between the predicted green tide distribution area data at each corresponding historical moment is obtained, and the average of the above multiple area differences is used as the prediction deviation value corresponding to each initial prediction model.

[0131] Step S508: Screen at least one initial prediction model based on the prediction deviation value to obtain a target prediction model.

[0132] Exemplarily, the initial prediction model with the smallest corresponding prediction deviation value is used as the target prediction model.

[0133] Step S509: Optimize the parameters of the target prediction model based on the second part of the historical green tide distribution area data to obtain a green tide distribution area prediction model.

[0134] Exemplarily, the historical environmental impact shadow of the historical moment corresponding to the second part of the data in the historical green tide distribution is obtained, and the historical environmental impact factor is input into the target prediction model to obtain the predicted green tide distribution area corresponding to the above historical moment, and the target prediction model is optimized based on the difference between the predicted green tide distribution area and the second part of the data in the historical green tide distribution area data to obtain a green tide distribution area prediction model.

[0135] Step S510: predicting the green tide distribution area based on the green tide distribution area prediction model.

[0136] In the embodiments of the present application, step S510 can be implemented in any of the ways in the embodiments of the present application, and the embodiments of the present application do not limit this and will not be described in detail.

[0137] By implementing the embodiment of the present application, the prediction deviation values ​​of different initial prediction models can be obtained based on the first part of the data in the green tide distribution area data and the corresponding prediction factors, so as to screen and obtain the target prediction model based on the prediction deviation value, and optimize the parameters of the target prediction model based on the second part of the data in the green tide distribution area data to obtain the green tide distribution area prediction model. Thus, the prediction accuracy of the obtained green tide distribution area prediction model is improved.

[0138] See also Figure 6 , Figure 6 This is a flow chart of a method for predicting green tide distribution area based on remote sensing data provided in an embodiment of the present application. Figure 6 As shown, firstly, the normalized vegetation index of each pixel is determined based on the reflectivity of the near-infrared and infrared bands in the high-resolution satellite remote sensing data, so as to determine the corresponding area of ​​green algae distribution based on the normalized vegetation index, and extract the environmental impact factors related to green algae (for example, sea surface temperature, 2m height thermometer specific humidity, precipitation rate, 10m height wind, salinity) from the atmospheric and ocean reanalysis data related to green algae, and calculate the monthly average regional average of the environmental impact factors related to the corresponding area of ​​green algae distribution in the same year and the previous year.

[0139] Then, the green algae distribution area data were divided into two groups, A and B, and the Pearson correlation coefficients of the green tide distribution area data in group A and the monthly average of each environmental influencing factor in the same year and the previous year were calculated. Environmental influencing factors with a strong correlation with the green tide distribution area (for example, the Pearson correlation coefficient is greater than or equal to 0.4) were selected as the predictors of the green tide distribution area. A statistical regression prediction model of the predictor factors and the green tide distribution area was established, and a prediction model of the green tide distribution area and each predictor factor was established using a univariate or multivariate prediction regression method.

[0140] The green tide distribution area data A and the corresponding prediction factors are used to obtain the error of different regression equations in predicting the green tide distribution area. The error of different regression equations in predicting the green tide distribution area is compared, and the prediction model with the smallest prediction error of the green tide distribution area is selected as the optimal prediction model.

[0141] The optimal prediction model was used to predict the predicted green tide distribution area of ​​the green algae group B at the corresponding time, and the prediction error of the optimal prediction model was obtained. Based on the prediction error, the model was tested and the model parameters were optimized to improve the prediction model. Finally, the improved optimal prediction model was used to predict the green tide distribution area.

[0142] See also Figure 7 , Figure 7 Schematic diagram of a device for predicting green tide distribution area provided in an embodiment of the present application. Figure 7As shown, the device 700 includes: a first acquisition module 701, which is used to obtain historical satellite remote sensing data of the monitored area at multiple historical moments within a preset historical period; a first processing module 702, which is used to determine the historical green tide distribution area data of the monitored area corresponding to the historical green tide distribution area at each historical moment based on the historical satellite remote sensing data; a second acquisition module 703, which is used to obtain multiple environmental impact factors corresponding to the historical green tide distribution area; a second processing module 704, which is used to screen out at least one target environmental impact factor from the environmental impact factors based on the correlation between the environmental impact factor and the first part of the data in the historical green tide distribution area data; a third processing module 705, which is used to establish at least one initial prediction model based on at least one target environmental impact factor; a fourth processing module 706, which is used to screen and optimize at least one initial prediction model based on the historical green tide distribution area data to obtain a green tide distribution area prediction model; a fifth processing module 707, which is used to predict the green tide distribution area based on the green tide distribution area prediction model.

[0143] In one implementation, the first processing module 702 can be used to: calculate the normalized vegetation index of each pixel in the historical satellite remote sensing data at each historical moment based on the historical satellite remote sensing data at each historical moment; obtain the pixels whose normalized vegetation index is greater than a preset threshold as the target pixels; obtain the pixel area of ​​the target pixel as the historical green tide distribution area data corresponding to each historical moment.

[0144] In one implementation, the second processing module 704 can be used to: calculate and obtain a first correlation coefficient between the first part of the data and each historical environmental impression factor in multiple preset sub-periods within a historical period; obtain the mean of the first correlation coefficient as the second correlation coefficient; and screen out at least one target environmental impact factor from the environmental impact factors based on the second correlation coefficient.

[0145] In one implementation, the third processing module 705 can be used to: establish at least one target factor combination from at least one target factor; wherein the target factors included in different target factor combinations are not exactly the same, and the same target factor combination can include the same target factors; and use a univariate prediction regression method and / or a multivariate prediction regression method to establish at least one initial prediction model corresponding to each target factor combination.

[0146] In one implementation, the fourth processing module 706 can be used to: perform predictions based on each initial prediction model respectively, and obtain the predicted green tide area corresponding to the first part of the data predicted by each initial prediction model; obtain the predicted deviation value between the predicted green tide distribution area corresponding to each initial prediction model and the first part of the data; screen at least one initial prediction model based on the data difference to obtain a target prediction model; optimize the parameters of the target prediction model based on the second part of the data in the historical green tide distribution area data to obtain a green tide distribution area prediction model;

[0147] In one implementation, the environmental influencing factor includes at least one of the following: sea surface temperature; temperature at a first preset height from the sea surface; specific humidity; precipitation rate; wind speed at a second preset height from the sea surface; and seawater salinity.

[0148] Through the device of the embodiment of the present application, the historical green tide distribution surface of the historical green tide distribution area can be obtained based on satellite remote sensing data, and at least one target environmental impact factor can be screened out from the environmental impact factor based on the correlation between the environmental impact factor and the first part of the data in the historical green tide distribution area data, so as to establish at least one initial prediction model based on the target environmental impact factor, thereby screening and optimizing the at least one initial prediction model based on the historical green tide distribution area data, obtaining a green tide distribution area prediction model, and finally predicting the green tide distribution area based on the green tide distribution area prediction model. A green tide distribution area prediction model with a higher prediction accuracy can be established to make a more accurate prediction of the green tide distribution area.

[0149] It should be noted that the above explanations of the embodiment of the method for predicting the green tide distribution area are also applicable to the device for predicting the green tide distribution area of ​​this embodiment, and will not be described in detail here.

[0150] In order to implement the above embodiment, the present application also proposes an electronic device. Figure 8 , Figure 8 Schematic diagram of the structure of the electronic device provided in the embodiment of the present application. Figure 8 As shown, the electronic device 800 includes: a processor 801, and a memory 802 communicatively connected to the processor 801; the memory 802 stores computer-executable instructions; the processor 801 executes the computer-executable instructions stored in the memory to implement the method provided in the aforementioned embodiment.

[0151] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0152] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0153] In the description of this application, unless otherwise specified, “ / ” means or, for example, A / B can mean A or B; “and / or” in this article is merely a way to describe the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0154] In the description of the aforementioned embodiments, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0155] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0156] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0157] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0158] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0159] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0160] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0161] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for predicting green tide distribution area, characterized in that: include: Obtain historical satellite remote sensing data of the monitoring area at multiple historical moments within a preset historical period; Determine the historical green tide distribution area data of the monitoring area corresponding to the historical green tide distribution area at each historical moment based on the historical satellite remote sensing data; Obtaining multiple environmental impact factors corresponding to the historical green tide distribution area; Based on the correlation between the environmental impact factor and the first part of the data in the historical green tide distribution area data, at least one target environmental impact factor is screened out from the environmental impact factors; Establishing at least one initial prediction model based on the at least one target environmental impact factor; Screening and optimizing the at least one initial prediction model based on the historical green tide distribution area data to obtain a green tide distribution area prediction model; The green tide distribution area is predicted based on the green tide distribution area prediction model.

2. The method according to claim 1, characterized in that The determining, based on the historical satellite remote sensing data, the historical green tide distribution area data corresponding to the historical green tide distribution area of ​​the monitoring area at each historical moment comprises: Calculating the normalized vegetation index of each pixel in the historical satellite remote sensing data at each historical moment based on the historical satellite remote sensing data at each historical moment; Acquire the pixel whose normalized difference vegetation index is greater than a preset threshold as the target pixel; The pixel area of ​​the target pixel is obtained as the historical green tide distribution area data corresponding to each historical moment.

3. The method according to claim 1, characterized in that The step of selecting at least one target environmental impact factor from the environmental impact factors based on the correlation between the environmental impact factor and the first part of the data in the historical green tide distribution area data comprises: Calculate and obtain a first correlation coefficient between the first part of data and each of the historical environmental impression factors in a plurality of preset sub-periods within the historical period; Obtaining the mean of the first correlation coefficients as the second correlation coefficient; At least one target environmental impact factor is screened out from the environmental impact factors based on the second correlation coefficient.

4. The method according to claim 1, characterized in that The establishing of at least one initial prediction model based on the at least one target environmental impact factor comprises: Establishing at least one target factor combination from the at least one target factor; wherein the target factors included in different target factor combinations are not completely the same, and the same target factor combination may include the same target factor; A univariate prediction regression method and / or a multivariate prediction regression method is used to establish at least one initial prediction model corresponding to each target factor combination.

5. The method according to claim 1, characterized in that The step of screening and optimizing the at least one initial prediction model based on the historical green tide distribution area data to obtain a green tide distribution area prediction model includes: Predicting based on each of the initial prediction models respectively, and obtaining the predicted green tide area corresponding to the first part of data predicted by each of the initial prediction models; Obtaining a prediction deviation value between the predicted green tide distribution area corresponding to each of the initial prediction models and the first part of the data; Screening the at least one initial prediction model based on the data difference to obtain a target prediction model; Based on the second part of the historical green tide distribution area data, the target prediction model is optimized in parameters to obtain a green tide distribution area prediction model.

6. The method according to claim 1, characterized in that The environmental impact factors include at least one of the following: Sea surface temperature; The temperature at a first preset height above the sea surface; Specific humidity rate; precipitation rate; wind speed at a second preset height above the sea surface; Seawater salinity.

7. A device for predicting green tide distribution area, characterized in that: include: The first acquisition module is used to acquire historical satellite remote sensing data of the monitoring area at multiple historical moments within a preset historical period; A first processing module is used to determine the historical green tide distribution area data corresponding to the historical green tide distribution area of ​​the monitoring area at each historical moment based on the historical satellite remote sensing data; A second acquisition module is used to acquire multiple environmental impact factors corresponding to the historical green tide distribution area; A second processing module is used to screen out at least one target environmental impact factor from the environmental impact factors based on the correlation between the environmental impact factor and the first part of the data in the historical green tide distribution area data; A third processing module, configured to establish at least one initial prediction model based on the at least one target environmental impact factor; A fourth processing module, configured to screen and optimize the at least one initial prediction model based on the historical green tide distribution area data to obtain a green tide distribution area prediction model; The fifth processing module is used to predict the green tide distribution area based on the green tide distribution area prediction model.

8. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, they are used to implement the method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The method comprises a computer program, which implements the method according to any one of claims 1 to 6 when being executed by a processor.

Images