Estuary algal bloom risk assessment method based on optimization and fusion of multiple water environment indexes

Abstract

The embodiment of the invention provides an estuary algal bloom risk assessment method based on optimization and fusion of multiple water environment indexes, and the method comprises the steps: firstly, determining an inversion algorithm of various water environment key indexes of a target estuary region, and then carrying out the inversion algorithm according to the water environment characteristics of the target estuary region; combining historical algal bloom events, local standards and dominant algae growth characteristics of the target estuary region to determine influence functions of various water environment key indexes on algal blooms, and establishing an algal bloom risk assessment model with fusion of the various water environment key indexes according to the influence functions; then, performing inversion on various water environment key indexes of the target estuary region when an algae bloom event occurs by using an inversion algorithm of various water environment key indexes, and performing structural form and weight parameter optimization on the algae bloom risk assessment model by using a genetic algorithm based on an inversion result to obtain a target algae bloom risk assessment model; and the algae bloom risk of the target estuary region is accurately evaluated based on the model, so that the algae bloom risk evaluation effect is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental assessment, and in particular to an estuarine algal bloom risk assessment method based on the optimized fusion of multiple water environment indicators. Background Art

[0002] Excessive reproduction of algae will form algal blooms, which will lead to a decrease in dissolved oxygen concentration in water bodies and reduce biodiversity. As one of the typical manifestations of eutrophication of water bodies, the frequency and intensity of algal blooms are increasing year by year around the world, seriously threatening human health and water ecological security. Therefore, assessing the risk of algal blooms is of great significance to water resource management and pollution prevention and control.

[0003] As one of the most productive ecosystems, estuaries have the characteristics of salt-fresh water confluence, complex hydrodynamic conditions, high pollution load and uneven distribution, which lead to frequent algal bloom problems. At the same time, affected by these factors, the formation process of algal blooms is complex and highly spatiotemporal heterogeneous, which brings challenges to the monitoring and risk assessment of algal blooms. Remote sensing technology can facilitate large-scale monitoring of algal blooms. However, most of the existing algal bloom risk assessment methods based on remote sensing technology assess algal bloom risks through a single indicator (such as algal biomass and chlorophyll-a concentration). However, algal risk is affected by multiple factors (including temperature, salinity, nutrient concentration, etc.). Currently, a few methods consider multiple indicators, but the interaction between multiple indicators is insufficient, and the complex and dynamic relationship between indicators is not quantitatively considered. It is difficult to accurately assess the algal bloom risk under the combined influence of multiple indicators. Summary of the invention

[0004] In a first aspect, an embodiment of the present invention provides a method for assessing estuarine algal bloom risk based on the optimization and fusion of multiple water environment indicators, the method comprising: Obtain historical remote sensing image data of the target estuary area; Preprocess the historical remote sensing image data to obtain the historical water body remote sensing image data of the target estuary area; For any key water environment indicator that affects algal blooms in the target estuary area, if a known inversion algorithm exists for the key water environment indicator, the inversion algorithm for the key water environment indicator is obtained; otherwise, the inversion algorithm for the key water environment indicator is obtained by performing inversion based on historical water body remote sensing image data and its corresponding historical measured data of the key water environment indicator; According to the water environment characteristics of the target estuary area, combined with the historical algal bloom events, local standards and the growth characteristics of dominant algae in the target estuary area, the influence functions of various key water environment indicators on algal blooms are determined respectively; According to the impact function of various key water environment indicators on algal blooms, an algal bloom risk assessment model integrating multiple key water environment indicators is established; Use the inversion algorithm of various key water environment indicators to invert the key water environment indicators of the target estuary area when an algal bloom event occurs, and use the genetic algorithm to optimize the structure and weight parameters of the algal bloom risk assessment model based on the inversion results to obtain the target algal bloom risk assessment model; The target algal bloom risk assessment model was used to conduct algal bloom risk assessment in the target estuary area.

[0005] In some possible implementations of the first aspect, obtaining historical remote sensing image data of a target estuary area includes: The historical remote sensing image data covering the target estuary area are cropped according to the geographic information vector file of the target estuary area to obtain the historical remote sensing image data of the target estuary area.

[0006] In some implementations of the first aspect, the key water environment indicators are determined by the following steps: The correlation coefficients between various water environment indicators and algal bloom events in the target estuary area were obtained by conducting correlation analysis respectively. Water environment indicators whose correlation coefficients are greater than or equal to a preset threshold are selected from a variety of water environment indicators as key water environment indicators.

[0007] In some implementable embodiments of the first aspect, the key indicators of the water environment are chlorophyll-a concentration, dissolved inorganic nitrogen concentration, dissolved inorganic phosphorus concentration, water surface temperature, and salinity.

[0008] In some implementations of the first aspect, the effect function of chlorophyll-a concentration on algal bloom is determined by the following steps: The minimum chlorophyll-a concentration of the local standard mild algal bloom in the target estuary area was taken as the maximum value of the influence function, and the maximum chlorophyll-a concentration of the target estuary area without algal bloom was taken as the minimum value of the influence function. The linear interpolation method was used to define the influence function value between [0, 1], thereby obtaining the influence function of chlorophyll-a concentration on algal bloom.

[0009] In some implementations of the first aspect, the influence function of dissolved inorganic nitrogen concentration on algal bloom is determined by the following steps: The average value of dissolved inorganic nitrogen concentration in the target estuary area during a typical algal bloom event was taken as the minimum value of the influence function, and the maximum value of dissolved inorganic nitrogen concentration in the target estuary area during a typical algal bloom event was taken as the maximum value of the influence function. The linear interpolation method was used to define the influence function value between [0, 1], thereby obtaining the influence function of dissolved inorganic nitrogen concentration on algal bloom.

[0010] In some implementations of the first aspect, the influence function of dissolved inorganic phosphorus concentration on algal bloom is determined by the following steps: The average value of dissolved inorganic phosphorus concentration in the target estuary area during a typical algal bloom event was used as the minimum value of the influence function, and the maximum value of dissolved inorganic phosphorus concentration in the target estuary area during a typical algal bloom event was used as the maximum value of the influence function. The linear interpolation method was used to define the influence function value between [0, 1], thereby obtaining the influence function of dissolved inorganic phosphorus concentration on algal bloom.

[0011] In some implementations of the first aspect, the influence function of water surface temperature on algal bloom is determined by the following steps: According to the growth rates of dominant algae in the water body at different water surface temperatures when algal bloom events occurred in the target estuary area in the past, the growth curve of the dominant algae was fitted and normalized to obtain the influence function of water surface temperature on algal bloom.

[0012] In some implementations of the first aspect, the effect function of salinity on algal bloom is determined by the following steps: According to the growth rates of dominant algae in the water body at different salinities when algal blooms occurred in the target estuary area in the past, the growth curve of the dominant algae was fitted and normalized to obtain the influence function of salinity on algal blooms.

[0013] In some implementations of the first aspect, the method further includes: Visualize the spatiotemporal distribution of algal bloom risk assessment results.

[0014] In a second aspect, an embodiment of the present invention provides an estuarine algal bloom risk assessment device based on the optimization and fusion of multiple water environment indicators, the device comprising: The acquisition module is used to obtain the historical remote sensing image data of the target estuary area; A preprocessing module is used to preprocess the historical remote sensing image data to obtain the historical water body remote sensing image data of the target estuary area; The inversion module is used to obtain the inversion algorithm of any key water environment indicator that affects algal blooms in the target estuary area if a known inversion algorithm exists for the key water environment indicator. Otherwise, the inversion algorithm is obtained based on the historical water body remote sensing image data and the historical measured data of the corresponding key water environment indicators; A determination module is used to determine the influence functions of various key water environment indicators on algal blooms according to the water environment characteristics of the target estuary area, combined with historical algal bloom events, local standards and growth characteristics of dominant algae in the target estuary area; Establish a module for establishing an algal bloom risk assessment model integrating multiple key water environment indicators based on the impact functions of various key water environment indicators on algal blooms; An optimization module is used to use inversion algorithms of various water environment key indicators to invert various water environment key indicators of the target estuary area when an algal bloom event occurs, and based on the inversion results, use a genetic algorithm to optimize the structure and weight parameters of the algal bloom risk assessment model to obtain a target algal bloom risk assessment model; An assessment module is used to conduct an algal bloom risk assessment on a target estuarine area using a target algal bloom risk assessment model.

[0015] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; 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 described above.

[0016] In a fourth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium storing computer instructions, where the computer instructions are used to enable a computer to execute the method described above.

[0017] In an embodiment of the present invention, an inversion algorithm for various key water environment indicators in a target estuary area is first obtained, and then, based on the water environment characteristics of the target estuary area, combined with historical algal bloom events, local standards and dominant algae growth characteristics of the target estuary area, the influence functions of various key water environment indicators on algal blooms are determined respectively, and an algal bloom risk assessment model integrating multiple key water environment indicators is established. Subsequently, the inversion algorithms for various key water environment indicators are used to invert various key water environment indicators in the target estuary area when an algal bloom event occurs, and based on the inversion results, a genetic algorithm is used to optimize the structural form and weight parameters of the algal bloom risk assessment model to obtain a target algal bloom risk assessment model with outstanding assessment capabilities, and then an accurate assessment of the algal bloom risk in the target estuary area is performed based on the model, thereby effectively improving the algal bloom risk assessment effect.

[0018] It should be understood that the contents described in the summary of the invention are not intended to limit the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other features, advantages and aspects of the embodiments of the present invention will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. The accompanying drawings are used to better understand the present invention and do not constitute a limitation of the present invention. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, wherein: Figure 1 A flow chart of a method for assessing estuarine algal bloom risk based on the optimization and fusion of multiple water environment indicators provided in an embodiment of the present invention; Figure 2 A schematic diagram of the spatial distribution of algal bloom risks in estuary area A in different years provided by an embodiment of the present invention; Figure 3 A structural diagram of an estuarine algal bloom risk assessment device based on the optimization and fusion of multiple water environment indicators provided in an embodiment of the present invention; Figure 4 The figure is a structural diagram of an exemplary electronic device capable of implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] In addition, the term "and / or" in the present invention is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present invention generally indicates that the associated objects before and after are in an "or" relationship.

[0022] In order to solve the technical problems arising from the background technology, the embodiments of the present invention provide a method, device, equipment and storage medium for estuarine algal bloom risk assessment based on the optimization and fusion of multiple water environment indicators. Specifically, firstly, the inversion algorithm of various water environment key indicators of the target estuarine area is obtained, and then, according to the water environment characteristics of the target estuarine area, combined with the historical algal bloom events, local standards and dominant algae growth characteristics of the target estuarine area, the influence functions of various water environment key indicators on algal blooms are determined respectively, and an algal bloom risk assessment model integrating multiple water environment key indicators is established, and then the inversion algorithms of various water environment key indicators are used to invert the various water environment key indicators of the target estuarine area when an algal bloom event occurs, and based on the inversion results, the genetic algorithm is used to optimize the structure and weight parameters of the algal bloom risk assessment model, and a target algal bloom risk assessment model with outstanding assessment capabilities is obtained, and then the algal bloom risk assessment model of the target estuarine area is accurately assessed based on the model, effectively improving the algal bloom risk assessment effect.

[0023] In conjunction with the accompanying drawings, a method, device, equipment and storage medium for assessing estuarine algal bloom risk based on optimized integration of multiple water environment indicators provided by an embodiment of the present invention will be described in detail below through specific embodiments.

[0024] Figure 1A flow chart of a method for assessing estuarine algal bloom risk based on the optimization and fusion of multiple water environment indicators provided by an embodiment of the present invention is shown in FIG. Figure 1 As shown, the estuarine algal bloom risk assessment method 100 may include: S110, acquiring historical remote sensing image data of the target estuary area.

[0025] In some embodiments, historical remote sensing image data covering the target estuary area (ie, the study area) can be acquired and cropped based on the geographic information vector file of the target estuary area (ie, the study area), and the image portion of the target estuary area can be extracted to obtain the historical remote sensing image data of the target estuary area.

[0026] S120, preprocessing the historical remote sensing image data to obtain historical water body remote sensing image data of the target estuary area.

[0027] In some embodiments, the purpose of preprocessing is to improve the quality of image data and ensure its suitability for water body analysis, which specifically includes: eliminating atmospheric interference through atmospheric correction; removing cloud-covered areas using declouding processing; and separating water body areas using water body extraction technology. Finally, based on the above preprocessing, historical water body remote sensing image data of the target estuary area can be generated.

[0028] As an example, remote sensing image data from satellite sensors is obtained in the GEE platform, and atmospheric correction is performed to obtain the pixel brightness value (DN) of the band. The surface reflectance can be obtained by applying a scaling factor to the DN of the surface reflectance band; the water surface temperature can be obtained by applying a scaling factor to the DN of the surface temperature band of the Landsat series satellites, as shown in formulas (1)-(2).

[0029] (1) (2) In the formula, For satellite sensors Surface reflectance in nm; For satellite sensors Remote sensing image pixel brightness value in nm; , are scaling factors respectively. When using Landsat remote sensing image data, , They are 0.0000275 and -0.2 respectively; when using MODIS remote sensing image data, , They are 0.0001 and 0 respectively; is the water surface temperature (℃); It is the pixel brightness value of the surface temperature band of the Landsat series satellites.

[0030] To ensure data quality, it is necessary to remove clouds and extract water bodies from historical remote sensing image data to obtain historical water body remote sensing image data. For cloud removal, the quality bands of Landsat and MODIS are used, and pixels identified as clouds will be removed; for water extraction, the normalized difference water index (NDWI) of water bodies is calculated to extract the area containing water bodies. When the NDWI of a pixel is greater than -0.2, the area covered by the pixel can be considered to be a water body. For example, the calculation of NDWI can be seen in formula (3).

[0031] (3) In the formula, and They are the surface reflectance of the Landsat series satellite sensors in green light and near-infrared light, respectively.

[0032] S130, for any key water environment indicator that affects algal blooms in the target estuary area, if a known inversion algorithm exists for the key water environment indicator, the inversion algorithm for the key water environment indicator is obtained; otherwise, the inversion algorithm for the key water environment indicator is obtained by performing inversion based on historical water body remote sensing image data and its corresponding historical measured data of the key water environment indicator.

[0033] In some embodiments, the above water environment key indicators can be predetermined by the following steps: Correlation analysis was performed between various water environment indicators in the target estuary area and the algal bloom events in the target estuary area, and the correlation coefficients between various water environment indicators and algal bloom events were obtained.

[0034] Water environment indicators whose correlation coefficients are greater than or equal to a preset threshold are selected from a variety of water environment indicators as key water environment indicators.

[0035] As an example, water environment indicators such as chlorophyll-a concentration, dissolved inorganic nitrogen concentration, dissolved inorganic phosphorus concentration, total suspended solids, water transparency, salinity, water surface temperature, photosynthetically active radiation, etc. can be selected for correlation analysis with algal bloom events, and 5 water environment indicators that can be obtained through remote sensing image data are selected as key indicators, namely chlorophyll-a concentration, dissolved inorganic nitrogen concentration, dissolved inorganic phosphorus concentration, water surface temperature, and salinity. For example, it is assumed here that there is a known inversion algorithm for chlorophyll-a concentration and water surface temperature, and there is no known inversion algorithm for dissolved inorganic nitrogen concentration, dissolved inorganic phosphorus concentration, and salinity.

[0036] Among them, the inversion algorithm of chlorophyll-a concentration can be expressed by formulas (4)-(5).

[0037] (4) (5) In the formula, is the chlorophyll-a concentration (mg / m 3 ); and They are the surface reflectance of Landsat series satellite sensors under blue light and green light respectively.

[0038] The inversion algorithm of water surface temperature can be expressed by formula (2), which will not be elaborated here.

[0039] The inversion algorithm for dissolved inorganic nitrogen concentration can be obtained by performing multivariate linear fitting on the historical water remote sensing image data (i.e., the historical satellite sensor surface reflectance data of the water area) and its corresponding historical measured data of dissolved inorganic nitrogen concentration. By comprehensively comparing the fitting performance indicators of different combinations (including determination coefficient, root mean square error, relative percentage difference, etc.), the best performance combination is found as the inversion algorithm for dissolved inorganic nitrogen concentration, which can be specifically expressed by formula (6).

[0040] (6) In the formula, is the concentration of dissolved inorganic nitrogen (mg / L); and are the surface reflectances of MODIS at 645 nm and 469 nm, respectively; , is an undetermined constant, which is obtained by fitting the historical satellite sensor surface reflectivity data with the measured data.

[0041] The inversion algorithm of dissolved inorganic phosphorus concentration can be obtained by inversion using machine learning. Specifically, the longitude and latitude, MODIS surface reflectance at 645 nm, 859 nm, 469 nm, 555 nm, 1240 nm, 1640 nm, and 2130 nm are used as independent variables, and the measured dissolved inorganic phosphorus concentration is used as the dependent variable for machine learning. Preferably, different machine learning algorithms are used for comparison, and the best machine learning model for inverting dissolved inorganic phosphorus concentration is found and applied by comparing the performance indicators of the models.

[0042] The salinity inversion algorithm can be obtained by performing multivariate linear fitting on the historical water remote sensing image data (i.e., the historical satellite sensor surface reflectance data of the water area) and its corresponding historical measured salinity data. By comprehensively comparing the fitting performance indicators of different combinations (including determination coefficient, root mean square error, relative percentage difference, etc.), the best performance combination is found as the salinity inversion algorithm, which can be specifically expressed by formula (7).

[0043] (7) Where S is salinity (PSU); , and They are the surface reflectance of MODIS at 667 nm, 555 nm and 488 nm respectively; , , , is an undetermined constant, which is obtained by fitting the historical satellite sensor surface reflectivity data with the measured data.

[0044] It should be noted here that if there are known inversion algorithms for some of the key water environment indicators that affect algal blooms in the target estuary area, but they do not meet the current needs, they can be inverted based on the historical water body remote sensing image data and the corresponding historical measured data of the key water environment indicators to obtain the inversion algorithm of the key water environment indicators. For example, there is a known inversion algorithm for the dissolved inorganic nitrogen concentration in the target estuary area, but it does not meet the current needs, it can be inverted based on the historical water body remote sensing image data and the corresponding historical measured data of the dissolved inorganic nitrogen concentration to obtain the inversion algorithm of the dissolved inorganic nitrogen concentration.

[0045] S140, according to the water environment characteristics of the target estuary area, combined with the historical algal bloom events, local standards and the growth characteristics of dominant algae in the target estuary area, the influence functions of various key water environment indicators on algal blooms are determined respectively.

[0046] Among them, when the influence function value of the key water environment indicator is 1, it means that under this condition, it has a promoting effect on the occurrence of algal blooms; when the influence function value is 0, it means that under this condition, it has no promoting effect on the occurrence of algal blooms.

[0047] Referring to S130, taking the key water environment indicators as chlorophyll-a concentration, dissolved inorganic nitrogen concentration, dissolved inorganic phosphorus concentration, water surface temperature, and salinity as an example, the influence function of chlorophyll-a concentration, dissolved inorganic nitrogen concentration, dissolved inorganic phosphorus concentration, water surface temperature, and salinity on algal blooms can be determined by the following steps: The effect function of chlorophyll-a concentration on algal blooms: The minimum chlorophyll-a concentration of the local standard mild algal bloom in the target estuary area is used as the maximum value of the influence function, and the maximum chlorophyll-a concentration of the target estuary area without algal bloom is used as the minimum value of the influence function. The linear interpolation method is used to define the influence function value between [0, 1], thereby obtaining the influence function of chlorophyll-a concentration on algal bloom. For details, see formulas (8)-(10).

[0048] (8) (9) (10) In the formula, is the chlorophyll-a concentration (mg / m 3 ); is the function value of the influence of chlorophyll-a concentration on algal bloom; The minimum chlorophyll-a concentration (mg / m 3 ); is the maximum chlorophyll-a concentration in the target estuary area without algal bloom (mg / m 3 ); , is a constant to be determined.

[0049] Function of the effect of dissolved inorganic nitrogen concentration on algal bloom: The average value of dissolved inorganic nitrogen concentration in the target estuary during a typical algal bloom event is used as the minimum value of the influence function, and the maximum value of dissolved inorganic nitrogen concentration in the target estuary during a typical algal bloom event is used as the maximum value of the influence function. The linear interpolation method is used to define the influence function value between [0, 1], thereby obtaining the influence function of dissolved inorganic nitrogen concentration on algal bloom. For details, see formulas (11)-(13).

[0050] (11) (12) (13) In the formula, is the concentration of dissolved inorganic nitrogen (mg / L); is the function value of the effect of dissolved inorganic nitrogen concentration on algal bloom; is the average value of dissolved inorganic nitrogen concentration in the target estuary area during a typical algal bloom event (mg / L); is the maximum concentration of dissolved inorganic nitrogen in the target estuary area during a typical algal bloom event (mg / L); , is a constant to be determined.

[0051] Function of the effect of dissolved inorganic phosphorus concentration on algal bloom: The average value of dissolved inorganic phosphorus concentration in the target estuary during a typical algal bloom event is used as the minimum value of the influence function, and the maximum value of dissolved inorganic phosphorus concentration in the target estuary during a typical algal bloom event is used as the maximum value of the influence function. The influence function value is defined between [0, 1] using linear interpolation, thereby obtaining the influence function of dissolved inorganic phosphorus concentration on algal bloom. For details, see formulas (14)-(16).

[0052] (14) (15) (16) In the formula, is the dissolved inorganic phosphorus concentration (mg / L); is the function value of the effect of dissolved inorganic phosphorus concentration on algal bloom; is the average dissolved inorganic phosphorus concentration in the target estuary area during a typical algal bloom event (mg / L); is the maximum concentration of dissolved inorganic phosphorus in the target estuary area during a typical algal bloom event (mg / L); , is a constant to be determined.

[0053] The effect function of water surface temperature on algal blooms: Based on the growth rates of dominant algae in the water body at different water surface temperatures when algal blooms occurred in the target estuary area in the past, the growth curve of dominant algae was fitted and normalized to obtain the influence function of water surface temperature on algal blooms. For details, see formulas (17)-(18).

[0054] (17) (18) In the formula, is the water surface temperature (℃); is the function value of the effect of water surface temperature on algal bloom; , is an unknown constant, which is obtained by fitting the growth curve of dominant algae at different water surface temperatures through a polynomial.

[0055] The effect function of salinity on algal blooms is determined by the following steps: According to the growth rates of dominant algae in the water body at different salinities when algal blooms occurred in the target estuary area in the past, the growth curve of the dominant algae was fitted and normalized to obtain the effect function of salinity on algal blooms. For details, see formulas (19)-(21).

[0056] (19) (20) (twenty one) In the formula, is salinity (PSU); is the function value of the effect of salinity on algal bloom; , , , , is an unknown constant, which is obtained by fitting the growth curves of dominant algae at different salinities through polynomials.

[0057] In this way, the linear or nonlinear characteristics of the impact of each key water environment indicator on algal growth can be retained, and the differences in units and scales between different indicators can be eliminated, so that the subsequent algal bloom risk assessment model constructed based on this can be suitable for algal bloom risk assessment under various environmental conditions.

[0058] S150, based on the impact functions of various key water environment indicators on algal blooms, an algal bloom risk assessment model integrating multiple key water environment indicators is established.

[0059] Referring to S140, taking the influence function of key water environment indicators on algal blooms as an example, the influence function of chlorophyll-a concentration, dissolved inorganic nitrogen concentration, dissolved inorganic phosphorus concentration, water surface temperature, and salinity on algal blooms, the algal bloom risk assessment model established here that integrates chlorophyll-a concentration, dissolved inorganic nitrogen concentration, dissolved inorganic phosphorus concentration, water surface temperature, and salinity can be shown as formula (22).

[0060] (twenty two) In the formula, is the algal bloom risk assessment value; It is a function that includes the influence of chlorophyll-a concentration, dissolved inorganic nitrogen concentration, dissolved inorganic phosphorus concentration, salinity, and water surface temperature on algal blooms.

[0061] Furthermore, the algal bloom risk assessment model can be in the form of multiple weighted linear combinations, such as those shown in formulas (23)-(24). The specific structural form and weight coefficients can be obtained through the subsequent model optimization process.

[0062] (twenty three) (twenty four) In the formula, is the algal bloom risk assessment value, , , , , are the weight coefficients to be optimized respectively.

[0063] S160, using inversion algorithms for various key water environment indicators to invert various key water environment indicators in the target estuary area when an algal bloom event occurs, and based on the inversion results, using a genetic algorithm to optimize the structure and weight parameters of the algal bloom risk assessment model to obtain a target algal bloom risk assessment model.

[0064] Specifically, the area of ​​the algal bloom event can be used to construct an optimized objective function to quantify the error between the predicted algal bloom area and the actual observed area. In other words, the optimization goal of the genetic algorithm is to minimize the error between the predicted algal bloom area and the measured algal bloom area, where the predicted algal bloom area is determined based on the algal bloom risk assessment results. On this basis, the genetic algorithm minimizes the objective function through continuous iteration to obtain the optimal structure and weight parameters, thereby obtaining the target algal bloom risk assessment model. For example, the objective function can be seen in formula (25), and the genetic algorithm uses the sum of the absolute values ​​of the relative errors in formula (25) to evaluate the performance under the current weight parameters.

[0065] (25) In the formula, represents the objective function value; is the predicted algal bloom area when the ith actual algal bloom event occurs (km 2 ); is the measured algal bloom area when the ith actual algal bloom event occurs (km 2 ); , , , , are the weight coefficients to be optimized respectively; N is the number of algal bloom events used for genetic algorithm optimization.

[0066] S170, conduct an algal bloom risk assessment for the target estuary area using the target algal bloom risk assessment model.

[0067] Specifically, the inversion algorithms of various key water environment indicators can be used to invert the various key water environment indicators of the target estuary area at a specified time, and the inversion results can be input into the target algal bloom risk assessment model to obtain the algal bloom risk assessment results, and then the spatiotemporal distribution of the algal bloom risk assessment results can be visualized.

[0068] For example, an algal bloom risk visualization toolkit can be written based on a target algal bloom risk assessment model. By inputting the key water environment indicator data obtained by inverting the inversion algorithm based on various key water environment indicators into the toolkit, the toolkit can automatically calculate the algal bloom risk assessment results and visualize the spatiotemporal distribution.

[0069] According to the embodiments of the present invention, at least the following technical effects are achieved: In an embodiment of the present invention, an inversion algorithm for various key water environment indicators in a target estuary area is first obtained, and then, based on the water environment characteristics of the target estuary area, combined with historical algal bloom events, local standards and dominant algae growth characteristics of the target estuary area, the influence functions of various key water environment indicators on algal blooms are determined respectively, and an algal bloom risk assessment model integrating multiple key water environment indicators is established. Subsequently, the inversion algorithms for various key water environment indicators are used to invert various key water environment indicators in the target estuary area when an algal bloom event occurs, and based on the inversion results, a genetic algorithm is used to optimize the structural form and weight parameters of the algal bloom risk assessment model to obtain a target algal bloom risk assessment model with outstanding assessment capabilities, and then an accurate assessment of the algal bloom risk in the target estuary area is performed based on the model, thereby effectively improving the algal bloom risk assessment effect.

[0070] Taking a certain estuary area A as an example, the estuary algal bloom risk assessment method 100 provided by the present invention is described in detail. Among them, the key indicators of the water environment of the estuary area A are chlorophyll-a concentration, dissolved inorganic nitrogen concentration, dissolved inorganic phosphorus concentration, water surface temperature, and salinity. Furthermore, there are known inversion algorithms for the chlorophyll-a concentration and water surface temperature here, and they meet current needs, so they can be directly obtained and used; there are known inversion algorithms for dissolved inorganic nitrogen concentration and dissolved inorganic phosphorus concentration, but they do not meet current needs, and there is no known inversion algorithm for salinity, so it is necessary to establish an inversion algorithm for dissolved inorganic nitrogen concentration, dissolved inorganic phosphorus concentration, and salinity.

[0071] (1) Use the GEE platform to obtain monthly Landsat satellite remote sensing image data and MODIS remote sensing image data covering estuary area A from 2003 to 2022.

[0072] (2) The above historical remote sensing image data are cropped according to the geographic information vector file of the estuary area A to obtain the historical remote sensing image data of the estuary area A.

[0073] (3) Perform atmospheric correction, cloud removal, water body extraction and other operations on historical remote sensing image data to obtain historical water body remote sensing image data.

[0074] (4) Obtain the inversion algorithm for the chlorophyll-a concentration and the water surface temperature in the estuary area A; use the historical water body remote sensing image data (i.e., the historical satellite sensor surface reflectance data of the water body area) and the measured dissolved inorganic nitrogen concentration, dissolved inorganic phosphorus concentration, and salinity data of the estuary area A to perform inversion to obtain the inversion algorithm for the dissolved inorganic nitrogen concentration, dissolved inorganic phosphorus concentration, and salinity.

[0075] Among them, the inversion algorithm of chlorophyll-a concentration can be seen in formulas (4)-(5); the inversion algorithm of water surface temperature can be seen in formula (2); the inversion algorithm of dissolved inorganic nitrogen concentration can be seen in formula (26); and the inversion algorithm of salinity can be seen in formula (27).

[0076] (26) In the formula, is the concentration of dissolved inorganic nitrogen (mg / L); and They are the surface reflectance of MODIS at 645 nm and 469 nm, respectively.

[0077]

[0078] (27) Where S is salinity (PSU); , and They are the surface reflectance of MODIS at 667 nm, 555 nm and 488 nm respectively.

[0079] It is worth noting that 8 common machine learning algorithms are compared here: random forest, XGBoosting, K-nearest neighbor, kernel ridge regression, gradient boosting decision tree, support vector machine, and multivariate linear regression, and it is concluded that the kernel ridge regression algorithm works best when inverting dissolved inorganic phosphorus concentration. In view of this, the kernel ridge regression algorithm is used here, with longitude and latitude, MODIS surface reflectance at 645 nm, 859 nm, 469 nm, 555 nm, 1240 nm, 1640 nm, and 2130 nm as independent variables, and measured dissolved inorganic phosphorus concentration as the dependent variable. The machine learning algorithm is applied to invert the dissolved inorganic phosphorus concentration and obtain the inversion algorithm of dissolved inorganic phosphorus concentration.

[0080] (5) Based on the water environment conditions of estuary area A when algal blooms occurred in the past, determine the influence functions of chlorophyll-a concentration, dissolved inorganic nitrogen concentration, dissolved inorganic phosphorus concentration, water surface temperature, and salinity on algal blooms.

[0081] Among them, the influence function of chlorophyll-a concentration on algal bloom can be seen in formulas (28)-(30).

[0082] (28) (29) (30) In the formula, is the chlorophyll-a concentration (mg / m 3 ); is the function value of the influence of chlorophyll-a concentration on algal bloom.

[0083] The influence function of dissolved inorganic nitrogen concentration on algal bloom can be seen in formulas (31)-(33).

[0084] (31) (32) (33) In the formula, is the concentration of dissolved inorganic nitrogen (mg / L); is the function value of the influence of dissolved inorganic nitrogen concentration on algal bloom.

[0085] The influence function of dissolved inorganic phosphorus concentration on algal bloom can be seen in formulas (34)-(36).

[0086] (34) (35) (36) In the formula, is the concentration of dissolved inorganic phosphorus (mg / L); is the function value of the influence of dissolved inorganic phosphorus concentration on algal bloom.

[0087] The influence function of water surface temperature on algal bloom can be seen in formulas (37)-(38).

[0088] (37) (38) In the formula, is the water surface temperature (℃); is the function value of the influence of water surface temperature on algal bloom.

[0089] The influence function of salinity on algal bloom can be seen in formulas (39)-(41).

[0090] (39) (40) (41) In the formula, is salinity (PSU); is the function value of the effect of salinity on algal blooms. Since the maximum salinity in the estuary area generally does not exceed 35 PSU, the area with salinity greater than 35 PSU is not the estuary area studied in this scheme. The effect of salinity on algal blooms was set to 0.

[0091] (6) Based on the impact functions of various key water environment indicators on algal blooms, an algal bloom risk assessment model integrating multiple key water environment indicators is established.

[0092] (7) The inversion algorithms of various key water environment indicators were used to invert the key water environment indicators of estuary area A when an algal bloom event occurred. Based on the inversion results, the genetic algorithm was used to optimize the structure and weight parameters of the algal bloom risk assessment model to obtain the target algal bloom risk assessment model. The termination condition of the genetic algorithm was 500 iterations.

[0093] (8) An algal bloom risk visualization toolkit was compiled based on the target algal bloom risk assessment model. By inputting the key water environment indicator data obtained by inversion algorithms based on various key water environment indicators into the toolkit, the toolkit can automatically calculate the algal bloom risk assessment results and visualize the spatiotemporal distribution.

[0094] Specifically, the toolkit input includes: the key water environment indicator data obtained by inversion from the GEE platform, the specified time and area range, and the spatiotemporal distribution of algal bloom risk in estuary area A can be derived. Figure 2 shown.

[0095] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described order of actions, because according to the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0096] The above is an introduction to a method embodiment. The following is a further explanation of the solution of the present invention through an apparatus embodiment.

[0097] Figure 3 A structural diagram of an estuarine algal bloom risk assessment device based on the optimization and fusion of multiple water environment indicators provided by an embodiment of the present invention, such as Figure 3 As shown, the estuarine algal bloom risk assessment device 300 may include: The acquisition module 310 is used to acquire the historical remote sensing image data of the target estuary area.

[0098] The preprocessing module 320 is used to preprocess the historical remote sensing image data to obtain the historical water body remote sensing image data of the target estuary area.

[0099] The inversion module 330 is used to obtain the inversion algorithm of any key water environment indicator that affects algal blooms in the target estuary area if a known inversion algorithm exists for the key water environment indicator. Otherwise, the inversion algorithm of the key water environment indicator is obtained by inverting the historical water body remote sensing image data and the corresponding historical measured data of the key water environment indicator.

[0100] The determination module 340 is used to determine the influence functions of various key water environment indicators on algal blooms based on the water environment characteristics of the target estuary area, combined with historical algal bloom events, local standards and dominant algae growth characteristics of the target estuary area.

[0101] A module 350 is established to establish an algal bloom risk assessment model integrating multiple water environment key indicators according to the influence functions of various water environment key indicators on algal bloom.

[0102] The optimization module 360 ​​is used to use the inversion algorithm of various water environment key indicators to invert various water environment key indicators of the target estuary area when an algal bloom event occurs, and based on the inversion results, use the genetic algorithm to optimize the structure and weight parameters of the algal bloom risk assessment model to obtain the target algal bloom risk assessment model.

[0103] The assessment module 370 is used to perform an algal bloom risk assessment on the target estuary area using the target algal bloom risk assessment model.

[0104] Understandably, Figure 3 Each module / unit in the estuarine algal bloom risk assessment device 300 has the following functions: Figure 1 The functions of the various steps in the estuarine algal bloom risk assessment method 100 shown and their corresponding technical effects are not described here for the sake of brevity.

[0105] Figure 4 4 is a block diagram of an exemplary electronic device capable of implementing an embodiment of the present invention. Electronic device 400 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic device 400 may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown in the present invention, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required in the present invention.

[0106] like Figure 4As shown, the electronic device 400 may include a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 402 or a computer program loaded from a storage unit 408 into a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the electronic device 400 can also be stored. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0107] Multiple components in the electronic device 400 are connected to the I / O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a disk, an optical disk, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the electronic device 400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0108] The computing unit 401 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 401 performs the various methods and processes described above, such as method 100. For example, in some embodiments, the method 100 may be implemented as a computer program product, including a computer program, which is tangibly contained in a computer-readable medium, such as a storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 400 via the ROM 402 and / or the communication unit 409. When the computer program is loaded into the RAM 403 and executed by the computing unit 401, one or more steps of the method 100 described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the method 100 in any other appropriate manner (e.g., by means of firmware).

[0109] The various embodiments described above in the present invention can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs, which may be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general programmable processor, which may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0110] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code can be executed entirely on the machine, partially on the machine, partially on the machine as a stand-alone software package and partially on a remote machine, or entirely on a remote machine or server.

[0111] In the context of the present invention, a computer-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. A more specific example of a computer-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0112] It should be noted that the present invention also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute method 100 and achieve the corresponding technical effect achieved by executing the method in an embodiment of the present invention. For the sake of concise description, they will not be repeated here.

[0113] In addition, the present invention also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the method 100 is implemented.

[0114] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution disclosed in the present invention can be achieved, and the present invention is not limited here.

[0115] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A risk assessment method for estuarine algal blooms based on the optimization and fusion of multiple water environment indicators, characterized in that: The method comprises: Obtain historical remote sensing image data of the target estuary area; Preprocessing the historical remote sensing image data to obtain historical water body remote sensing image data of the target estuary area; For any key water environment indicator that affects algal blooms in the target estuary area, if a known inversion algorithm exists for the key water environment indicator, the inversion algorithm for the key water environment indicator is obtained; otherwise, the inversion algorithm for the key water environment indicator is obtained by performing inversion based on the historical water body remote sensing image data and the corresponding historical measured data of the key water environment indicator; According to the water environment characteristics of the target estuary area, combined with the historical algal bloom events, local standards and the growth characteristics of dominant algae in the target estuary area, the influence functions of various key water environment indicators on algal blooms are determined respectively; According to the impact function of various key water environment indicators on algal blooms, an algal bloom risk assessment model integrating multiple key water environment indicators is established; Invert various key water environment indicators in the target estuary area when an algal bloom event occurs using an inversion algorithm of various key water environment indicators, and optimize the structure and weight parameters of the algal bloom risk assessment model using a genetic algorithm based on the inversion results to obtain a target algal bloom risk assessment model; The target algal bloom risk assessment model is used to conduct an algal bloom risk assessment on the target estuary area.

2. The method according to claim 1, characterized in that The obtaining of historical remote sensing image data of the target estuary area includes: The historical remote sensing image data covering the target estuary area are cropped according to the geographic information vector file of the target estuary area to obtain the historical remote sensing image data of the target estuary area.

3. The method according to claim 1, characterized in that The key water environment indicators are determined by the following steps: The correlation coefficients between various water environment indicators and algal bloom events in the target estuary area were obtained by conducting correlation analysis respectively. From the multiple water environment indicators, water environment indicators with correlation coefficients greater than or equal to a preset threshold are selected as key water environment indicators.

4. The method according to claim 3, characterized in that The key indicators of water environment are chlorophyll-a concentration, dissolved inorganic nitrogen concentration, dissolved inorganic phosphorus concentration, water surface temperature and salinity.

5. The method according to claim 4, characterized in that The effect function of chlorophyll-a concentration on algal bloom is determined by the following steps: The minimum chlorophyll-a concentration when there is a mild algal bloom in the local standard of the target estuary area is used as the maximum value of the influence function, and the maximum chlorophyll-a concentration when there is no algal bloom in the target estuary area is used as the minimum value of the influence function. The linear interpolation method is used to define the influence function value between [0, 1], so as to obtain the influence function of chlorophyll-a concentration on algal bloom.

6. The method according to claim 4, characterized in that The effect function of dissolved inorganic nitrogen concentration on algal bloom is determined by the following steps: The average value of the dissolved inorganic nitrogen concentration in the target estuary area during a typical algal bloom event is used as the minimum value of the influence function, and the maximum value of the dissolved inorganic nitrogen concentration in the target estuary area during a typical algal bloom event is used as the maximum value of the influence function. The linear interpolation method is used to define the influence function value between [0, 1], so as to obtain the influence function of dissolved inorganic nitrogen concentration on algal bloom.

7. The method according to claim 4, characterized in that The influence function of dissolved inorganic phosphorus concentration on algal bloom is determined by the following steps: The average value of the dissolved inorganic phosphorus concentration in the target estuary area during a typical algal bloom event is used as the minimum value of the influence function, and the maximum value of the dissolved inorganic phosphorus concentration in the target estuary area during a typical algal bloom event is used as the maximum value of the influence function. The linear interpolation method is used to define the influence function value between [0, 1], so as to obtain the influence function of dissolved inorganic phosphorus concentration on algal bloom.

8. The method according to claim 4, characterized in that The influence function of water surface temperature on algal bloom is determined by the following steps: According to the growth rates of dominant algae in the water body at different water surface temperatures when algal bloom events occurred in the target estuary area in the past, the growth curve of the dominant algae was fitted, and the growth curve was normalized to obtain the influence function of water surface temperature on algal bloom.

9. The method according to claim 4, characterized in that The salinity effect function on algal bloom is determined by the following steps: According to the growth rates of dominant algae in the water body at different salinities when algal bloom events occurred in the target estuary area in the past, the growth curve of the dominant algae is fitted, and the growth curve is normalized to obtain the influence function of salinity on algal bloom.

10. The method according to claim 1, characterized in that The method further comprises: Visualize the spatiotemporal distribution of algal bloom risk assessment results.

Images