Method for identifying algal blooms of Harcasia sanguinea and gonyautogea multistriata based on spectral data

Abstract

The invention relates to the technical field of marine ecological disaster monitoring, and discloses a method for identifying algal blooms of Harcasia sanguinea and Gynea multiflora based on spectral data, which comprises the following steps: collecting water spectral data of a water area where algal blooms occur, and executing interference elimination processing on the water spectral data to obtain target spectral data; based on the sensitive wave bands and the reflectivity values of the Harcasia sanguinea and the gonyerea multistriata, identifying the water body type of the water area where the algal blooms occur; constructing a spectral reflectance curve of the Harcasia sanguinea and the gonyautoa multistriata, determining an optimal distinguishing waveband combination of the Harcasia sanguinea and the gonyautoa multistriata, and separating out an algae bloom area of the Harcasia sanguinea and the gonyautoa multistriata; the method comprises the following steps: defining discriminating double indexes of the Harcasia sanguinea and the gonyautogea multistriata, and constructing an algae species differentiating system of the Harcasia sanguinea and the gonyautogea multistriata; and according to the algal bloom growth conditions, after parameter optimization processing of the algal species distinguishing system is executed, an algal bloom identification result of the algal bloom generation water area is output. The method can improve the classification precision of algae species.

Description

Technical Field

[0001] The invention relates to a method for identifying algal blooms of Haematococcus sanguinosa and Goniocarpus polyphylla based on spectral data, and belongs to the technical field of water pollution monitoring. Background Art

[0002] Algal bloom refers to the phenomenon that algae in water bodies multiply in large numbers, causing the water body to appear a certain color or reduce the transparency of the water body. Among them, Hakkana and Gonyaula polymorpha are common toxin-producing algae. The toxins produced by these algae (such as paralytic shellfish toxins) can pose a serious threat to marine ecosystems and human health. For example, paralytic shellfish toxins can accumulate through the food chain, causing humans to become poisoned or even die after eating contaminated seafood. In order to effectively deal with the damage of Hakkana and Gonyaula polymorpha algae blooms to marine ecosystems and human health, it is particularly important to develop a fast and accurate algal bloom identification method.

[0003] The traditional method for identifying algal blooms of Haematococcus sanguineus and Glehnia littoralis mainly uses satellite or aerial remote sensing data to invert chlorophyll concentrations through spectral indices (such as NDVI, FAI) or fixed threshold methods (such as the ratio of Rrs560 and Rrs665) to indirectly infer the distribution of algal blooms. Although this method covers a wide area, it may not be able to distinguish algae species with similar spectral characteristics, and is affected by high turbidity water bodies, resulting in low classification accuracy.

[0004] Therefore, a solution is urgently needed to improve the accuracy of algae species classification. Summary of the invention

[0005] The present invention provides a method for identifying algal blooms of Haematococcus sanguineus and Goniocarpus polyphyllus based on spectral data, the main purpose of which is to improve the accuracy of algal species classification.

[0006] To achieve the above object, the present invention provides a method for identifying algal blooms of Haematococcus sanguinosa and Gonyaena polytricha based on spectral data, comprising:

[0007] Selecting an algal bloom-occurring water area of ​​Haematococcus sanguinosa and Goniocarpus polyphylla, collecting water spectral data of the algal bloom-occurring water area, performing interference elimination processing on the water spectral data, and obtaining target spectral data;

[0008] Based on the target spectral data, the sensitive bands of the sanguineous Hakka algae and the polyphylla serrata are extracted, and the reflectance values ​​of the sensitive bands are measured, and the water body type of the algal bloom-occurring waters is identified according to the reflectance values ​​and the sensitive bands;

[0009] Construct the spectral reflectance curves of *Akashiwo sanguinea* and *Gonyaulax polygramma* according to the target spectral data, and based on the spectral reflectance curves, extract the spectral response characteristics of *Akashiwo sanguinea* and *Gonyaulax polygramma* in the algal bloom occurrence waters;

[0010] Based on the spectral response characteristics, determine the optimal discrimination band combination of *Akashiwo sanguinea* and *Gonyaulax polygramma*, and according to the optimal discrimination band combination, identify the algal bloom areas of *Akashiwo sanguinea* and *Gonyaulax polygramma*;

[0011] Identify the reflectance difference characteristics of *Akashiwo sanguinea* and *Gonyaulax polygramma* under the spectral reflectance curves, and based on the reflectance difference characteristics, define the discrimination double index of *Akashiwo sanguinea* and *Gonyaulax polygramma*, and according to the discrimination double index, construct the algal species discrimination system of *Akashiwo sanguinea* and *Gonyaulax polygramma*;

[0012] Based on the water body type, analyze the algal bloom growth conditions in the algal bloom areas, and according to the algal bloom growth conditions, perform parameter optimization processing on the algal species discrimination system to obtain an optimized algal species discrimination system, and based on the optimized algal species discrimination system, output the algal bloom identification results of the algal bloom occurrence waters.

[0013] Compared with the problems described in the background art, in the embodiments of the present invention, by selecting the water areas where blooms of Akashiwo sanguinea and Gonyaulax polygramma occur, collecting the water body spectral data of the water areas where the blooms occur, and performing interference elimination processing on the water body spectral data to obtain target spectral data, the accuracy and reliability of subsequent analysis can be ensured; further, in the embodiments of the present invention, by extracting the sensitive bands of Akashiwo sanguinea and Gonyaulax polygramma based on the target spectral data and measuring the reflectance values of the sensitive bands, different types of water bodies can be distinguished to improve the accuracy of bloom monitoring; in the embodiments of the present invention, by constructing the spectral reflectance curves of Akashiwo sanguinea and Gonyaulax polygramma according to the target spectral data, the difference in band reflectance between Akashiwo sanguinea and Gonyaulax polygramma can be intuitively displayed; further, in the embodiments of the present invention, by extracting the spectral response characteristics of Akashiwo sanguinea and Gonyaulax polygramma in the water areas where the blooms occur based on the spectral reflectance curves, the bloom areas can be effectively identified and the dominant species can be distinguished, providing a basis for bloom early warning and ecological management; in the embodiments of the present invention, by determining the optimal discrimination band combination of Akashiwo sanguinea and Gonyaulax polygramma based on the spectral response characteristics, the areas where blooms are caused by Akashiwo sanguinea or Gonyaulax polygramma can be quickly and accurately identified in large water areas; further, in the embodiments of the present invention, by identifying the difference characteristics of the reflectance under the spectral reflectance curves of Akashiwo sanguinea and Gonyaulax polygramma and defining the discrimination double index of Akashiwo sanguinea and Gonyaulax polygramma based on the difference characteristics of the reflectance, the types of algae can be accurately distinguished, effectively reducing the misclassification caused by subjective judgment or fuzzy criteria, and significantly improving the accuracy of algae monitoring; in the embodiments of the present invention, by analyzing the bloom growth conditions in the bloom areas based on the water body types and performing parameter optimization processing on the algae species discrimination system to obtain an optimized algae species discrimination system, a scientific basis can be provided for parameter optimization of the algae species discrimination system and the accuracy of algae species discrimination can be improved; in the embodiments of the present invention, by outputting the bloom identification results of the water areas where the blooms occur based on the optimized algae species discrimination system, the identification accuracy of dinoflagellate blooms in turbid water bodies can be significantly improved, and at the same time, the areas, times, and types of algae species where blooms occur can be more accurately identified, realizing the specific management of algae species, improving the efficiency of bloom control, and providing a scientific basis and technical guarantee for marine ecological protection, fishery resource management, and disaster emergency response. Therefore, a method and system for identifying blooms of Akashiwo sanguinea and Gonyaulax polygramma based on spectral data provided by the embodiments of the present invention can improve the accuracy of algae species classification. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 FIG. is a schematic flow chart of a method for identifying blooms of Akashiwo sanguinea and Gonyaulax polygramma based on spectral data provided by an embodiment of the present invention;

[0015] Figure 2Schematic diagram of spectral data for implementing the method for identifying blooms of Akashiwo sanguinea and Gonyaulax polygramma based on spectral data provided by an embodiment of the present invention;

[0016] Figure 3 Schematic diagram of the water body distribution for implementing the method for identifying blooms of Akashiwo sanguinea and Gonyaulax polygramma based on spectral data provided by an embodiment of the present invention;

[0017] Figure 4 Schematic diagram of the higher-order derivative of chlorophyll concentration for implementing the method for identifying blooms of Akashiwo sanguinea and Gonyaulax polygramma based on spectral data provided by an embodiment of the present invention;

[0018] Figure 5 Schematic diagram of algal species classification for implementing the method for identifying blooms of Akashiwo sanguinea and Gonyaulax polygramma based on spectral data provided by an embodiment of the present invention;

[0019] Figure 6 Schematic diagram of algal species classification for implementing the method for identifying blooms of Akashiwo sanguinea and Gonyaulax polygramma based on spectral data provided by an embodiment of the present invention;

[0020] Figure 7 System function module diagram for implementing the method for identifying blooms of Akashiwo sanguinea and Gonyaulax polygramma based on spectral data provided by an embodiment of the present invention.

[0021] The implementation, functional features and advantages of the present invention will be further described with reference to the embodiments and the accompanying drawings. Detailed implementation manners

[0022] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0023] The embodiments of the present application provide a method for identifying blooms of Akashiwo sanguinea and Gonyaulax polygramma based on spectral data. The execution subject of the method for identifying blooms of Akashiwo sanguinea and Gonyaulax polygramma based on spectral data includes but is not limited to at least one of electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiments of the present application. In other words, the method for identifying blooms of Akashiwo sanguinea and Gonyaulax polygramma based on spectral data can be executed by software or hardware installed on a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0024] Example 1:

[0025] Refer to Figure 1As shown in the figure, it is a schematic flowchart of a method for identifying blooms of Akashiwo sanguinea and Gonyaulax polygramma based on spectral data provided by an embodiment of the present invention. In this embodiment, the method for identifying blooms of Akashiwo sanguinea and Gonyaulax polygramma based on spectral data includes:

[0026] S1. Select the waters where blooms of Akashiwo sanguinea and Gonyaulax polygramma occur, collect the water body spectral data of the waters where the blooms occur, and perform interference elimination processing on the water body spectral data to obtain target spectral data.

[0027] In the embodiment of the present invention, by selecting the waters where blooms of Akashiwo sanguinea and Gonyaulax polygramma occur, data support can be provided for subsequent bloom identification. Akashiwo sanguinea refers to a marine planktonic dinoflagellate, belonging to the phylum Dinophyta, class Dinophyceae, family Gymnodiniaceae. Gonyaulax polygramma refers to a marine planktonic dinoflagellate, belonging to the phylum Dinophyta, class Dinophyceae, family Gonyaulacaceae, genus Gonyaulax. The waters where the blooms occur refer to the areas where a large number of algae in the water body multiply and gather.

[0028] Furthermore, in the embodiment of the present invention, by collecting the water body spectral data of the waters where the blooms occur, algae species such as Akashiwo sanguinea and Gonyaulax polygramma can be quickly distinguished, which helps to study the environmental driving factors for the formation of blooms. The water body spectral data refers to the data obtained through spectral measurement technology, reflecting the reflection, absorption, and scattering characteristics of the water body to light of different wavelengths.

[0029] Optionally, the collection of the water body spectral data of the algae-containing water body can be obtained through the OLCI sensor of the Sentinel-3 satellite.

[0030] In the embodiment of the present invention, by performing interference elimination processing on the water body spectral data to obtain target spectral data, the accuracy and reliability of subsequent analysis can be ensured. The interference elimination processing refers to the process of removing or weakening the factors in the water body spectral data that will interfere with the spectral characteristics of the target algae, such as atmospheric correction, noise removal, wavelength calibration, etc. The target spectral data refers to the spectral data that can accurately reflect the spectral characteristics of Akashiwo sanguinea, Gonyaulax polygramma, and their blooms after interference elimination processing.

[0031] Optionally, the interference elimination processing of the water body spectral data can be realized by using a baseline correction algorithm, such as the ALS algorithm.

[0032] Refer to Figure 2 As shown in the figure, it is a schematic diagram of the spectral data for implementing the method for identifying blooms of Akashiwo sanguinea and Gonyaulax polygramma based on spectral data provided by an embodiment of the present invention. In Figure 2 where a represents the wavelength R obtained by the Sentinel-3 satellite rsData, b represents the chlorophyll a (Chl-a) data of Gonyaulax polygramma, and c represents the chlorophyll a (Chl-a) data of Akashiwo sanguinea.

[0033] S2. Based on the target spectral data, extract the sensitive bands of the Akashiwo sanguinea and the Gonyaulax polygramma, measure the reflectance values of the sensitive bands, and identify the water body type of the water area where the algal bloom occurs according to the reflectance values and the sensitive bands.

[0034] In the embodiment of the present invention, by extracting the sensitive bands of the Akashiwo sanguinea and the Gonyaulax polygramma based on the target spectral data and measuring the reflectance values of the sensitive bands, different types of water bodies can be distinguished to improve the accuracy of algal bloom monitoring. The sensitive band refers to a specific wavelength range that responds most significantly to the spectral characteristics of the Akashiwo sanguinea and the Gonyaulax polygramma. For example, the Akashiwo sanguinea may exhibit significant absorption near 440 - 450 nm (fucoxanthin absorption peak) and 670 - 680 nm (chlorophyll a absorption peak). The reflectance value refers to the ratio of the radiant energy reflected by the algal-containing water body to the incident radiant energy.

[0035] Optionally, the extraction of the sensitive bands of the Akashiwo sanguinea and the Gonyaulax polygramma based on the target spectral data can be realized by statistical tests such as the t-test, and the measurement of the reflectance values of the sensitive bands can be obtained by a spectrophotometer.

[0036] Furthermore, in the embodiment of the present invention, by identifying the water body type of the water area where the algal bloom occurs according to the reflectance values and the sensitive bands, accurate classification of the water area where the algal bloom occurs can be achieved, and the pertinence of algal bloom management can be improved. The water body type refers to the category divided according to the types, concentrations, and spectral characteristics of algae in the water body. For example, high reflectance in the blue and green light bands usually indicates clean water, and high reflectance in the red and yellow light bands may indicate algal water or turbid water.

[0037] As an embodiment of the present invention, the identification of the water body type of the water area where the algal bloom occurs according to the reflectance values and the sensitive bands includes: collecting the historical remote sensing data of the water area where the algal bloom occurs and extracting the algal-containing water body in the water area where the algal bloom occurs; determining the numerical change range of the reflectance values based on the historical remote sensing data; analyzing the optical characteristics of the algal-containing water body and identifying the turbidity degree, nutrient level, and salt content of the algal-containing water body according to the optical characteristics; defining the classification evaluation index of the algal-containing water body based on the turbidity degree, the nutrient level, and the salt content; setting the reflectance threshold of the sensitive band according to the numerical change range; and identifying the water body type of the water area where the algal bloom occurs by combining the classification evaluation index and the reflectance threshold.

[0038] Among them, the historical remote sensing data refers to the image data of the water area where algal blooms occur obtained by satellite or aerial remote sensing equipment within a past time range. The numerical change range refers to the range between the maximum and minimum values shown by the reflectance values of a specific band (such as green light, red light, near-infrared) within a certain time range. The optical property refers to the absorption and scattering properties of algae-containing water bodies for electromagnetic waves of different wavelengths. For example, algae can cause a decrease in the red light reflectance and an increase in the near-infrared reflectance. The turbidity refers to the concentration of suspended particulate matter (such as sediment, algal cells) in the water body. The nutrient level refers to the content and distribution of nutrients (such as nitrogen, phosphorus, chlorophyll, etc.) in the water body. The salt content refers to the total concentration of dissolved salts in the water body (such as NaCl). The classification and evaluation index refers to a comprehensive evaluation index constructed based on parameters such as turbidity, nutrient level, and salinity. The reflectance threshold refers to the critical reflectance value used to distinguish different water body types or water quality conditions within a specific band.

[0039] Optionally, the determination of the numerical change range of the reflectance value based on the historical remote sensing data can be obtained through statistical methods, such as the method of calculating extreme values. The extraction of the optical properties of the algae-containing water body can be achieved using spectral analysis methods, such as the band slope analysis method.

[0040] Refer to Figure 3 As shown, it is a schematic diagram of the water body distribution for implementing the method for identifying blooms of Akashiwo sanguinea and Gonyaulax polygramma based on spectral data provided by an embodiment of the present invention. In Figure 3 it, the algal bloom outbreak data is concentrated in the lower right corner, and the clear water and turbid non-algal bloom water bodies are distributed on the left side of the scatter plot ( Figure 3 b). Because the clear water does not have the characteristic of extremely high Rrs(λ) in each band, it will gather in the lower left corner. The turbid non-algal bloom water body has the characteristic of high reflectance in each band and will gather in the upper left part of the image. When using RA and RAB ( Figure 3 a) for separation, it is found that all non-algal bloom water bodies have high RA values. After analysis and determination, the observed values of Rrs(560) < 0.075 sr-1, RA < 0.65, and RAB > 1.5 can be determined as algal bloom water bodies.

[0041] S3. According to the target spectral data, construct the spectral reflectance curves of Akashiwo sanguinea and Gonyaulax polygramma, and based on the spectral reflectance curves, extract the spectral response characteristics of Akashiwo sanguinea and Gonyaulax polygramma in the water area where algal blooms occur.

[0042] In an embodiment of the present invention, by constructing the spectral reflectance curves of Akashiwo sanguinea and Gonyaulax polygramma based on the target spectral data, the band reflectance differences between Akashiwo sanguinea and Gonyaulax polygramma can be visually displayed. The spectral reflectance curve refers to a curve that describes the reflection, absorption, transmission, or emission characteristics of Akashiwo sanguinea and Gonyaulax polygramma for light of different wavelengths.

[0043] Exemplarily, to construct the spectral reflectance curves of Akashiwo sanguinea and Gonyaulax polygramma based on the target spectral data, the target spectral data can be arranged in the order of wavelength, and then a spectral curve can be plotted with the wavelength as the abscissa and the reflectance (or absorption rate, fluorescence intensity, etc.) as the ordinate.

[0044] Furthermore, in an embodiment of the present invention, by extracting the spectral response characteristics of Akashiwo sanguinea and Gonyaulax polygramma in the algal bloom occurrence waters based on the spectral reflectance curves, the algal bloom area can be effectively identified and the dominant species can be distinguished, providing a basis for algal bloom early warning and ecological management. The spectral response characteristics refer to the characteristics of the absorption, reflection, scattering, or emission ability of Akashiwo sanguinea and Gonyaulax polygramma for light of different wavelengths. For example, Akashiwo sanguinea contains abundant chlorophyll and carotenoids, and these pigments show strong absorption peaks in the spectral range of blue light (400 - 500 nm) and red light (600 - 700 nm).

[0045] As an embodiment of the present invention, extracting the spectral response characteristics of Akashiwo sanguinea and Gonyaulax polygramma in the algal bloom occurrence waters based on the spectral reflectance curves includes: identifying the local maximum points and local minimum points in the spectral reflectance curves; determining the reflectance extreme values of Akashiwo sanguinea and Gonyaulax polygramma based on the local maximum points and the local minimum points; measuring the fluorescence peak values of Akashiwo sanguinea and Gonyaulax polygramma; calculating the band slopes corresponding to Akashiwo sanguinea and Gonyaulax polygramma according to the spectral reflectance curves; and extracting the spectral response characteristics of Akashiwo sanguinea and Gonyaulax polygramma by combining the reflectance extreme values, the fluorescence peak values, and the band slopes.

[0046] Among them, the local maximum point refers to the highest reflectance value reached by the spectral curve within a certain specific wavelength range, the local minimum point refers to the lowest reflectance value reached by the spectral curve within a certain specific wavelength range, the reflectance extreme value refers to the highest and lowest points of the reflected light intensity of the algae within a specific wavelength range, the fluorescence peak value refers to the peak value of the fluorescence spectrum emitted by the algae under specific wavelength excitation, and the band slope refers to the change rate of the spectral curve within a specific wavelength range.

[0047] Optionally, based on the spectral reflectance curve, the extraction of the reflectance peaks of *Akashiwo sanguinea* and *Gonyaulax polygramma* can be achieved using the band with the highest reflectance. The reflectance valleys of *Akashiwo sanguinea* and *Gonyaulax polygramma* can be obtained by the envelope elimination method. The measurement of the fluorescence peaks of *Akashiwo sanguinea* and *Gonyaulax polygramma* can be achieved using this fluorescence spectrometer.

[0048] In an optional embodiment of the present invention, according to the spectral reflectance curve, the following formula is used to calculate the band slope corresponding to *Akashiwo sanguinea* and *Gonyaulax polygramma*:

[0049]

[0050] where, R rs _slope(λ1, λ2) represents the band slope corresponding to *Akashiwo sanguinea* and *Gonyaulax polygramma*. λ1 represents the wavelength reference point selected by *Akashiwo sanguinea* and *Gonyaulax polygramma* on the spectral reflectance curve, and λ2 represents another wavelength reference point selected by *Akashiwo sanguinea* and *Gonyaulax polygramma* on the spectral reflectance curve. R rs (λ1) represents the reflectance of *Akashiwo sanguinea* and *Gonyaulax polygramma* at wavelength λ1, and R rs (λ2) represents the reflectance of *Akashiwo sanguinea* and *Gonyaulax polygramma* at wavelength λ2.

[0051] Refer to Figure 4 As shown, it is a schematic diagram of the higher-order derivative of chlorophyll concentration for implementing the method for identifying the blooms of *Akashiwo sanguinea* and *Gonyaulax polygramma* based on spectral data provided by an embodiment of the present invention. Figure 4 (a) represents the first-order derivative graph of *Gonyaulax polygramma* and *Akashiwo sanguinea* with chlorophyll concentrations of 41.88 mg / m3 and 40.39 mg / m3. Figure 4 (b) represents the second-order derivative graph of *Gonyaulax polygramma* and *Akashiwo sanguinea* with chlorophyll concentrations of 41.88 mg / m3 and 40.39 mg / m3. It can be seen from the first-order derivative graph that in the 510 - 560 nm band, *Gonyaulax polygramma* has a higher slope for Rrs(λ). However, the second-order derivative of *Gonyaulax polygramma* at 620 nm is higher than that of *Akashiwo sanguinea* ( Figure 4 b) represents that relative to *Akashiwo sanguinea*, *Gonyaulax polygramma* has a more concave performance at 620 nm, and the slope of *Akashiwo sanguinea* in the 560 - 665 nm band is higher than that of *Gonyaulax polygramma* ( Figure 4 a), and its Rrs(λ) value at each band is also lower. Therefore, the value of Rrs(560) / Rrs(665) will be higher.

[0052] S4. Based on the spectral response characteristics, determine the optimal distinguishing band combination of the Akashiwo sanguinea and the Gonyostomum multicornutum, and according to the optimal distinguishing band combination, extract the algal bloom areas of the Akashiwo sanguinea and the Gonyostomum multicornutum.

[0053] In an embodiment of the present invention, by determining the optimal distinguishing band combination of the Akashiwo sanguinea and the Gonyostomum multicornutum based on the spectral response characteristics, it is possible to quickly and accurately identify the areas where algal blooms are caused by the Akashiwo sanguinea or the Gonyostomum multicornutum in large - area waters. The optimal distinguishing band combination refers to a specific set of bands that can most effectively distinguish the Akashiwo sanguinea from the Gonyostomum multicornutum. For example, if the Akashiwo sanguinea has an obvious reflection peak at 650 nm, while the reflectance of the Gonyostomum multicornutum at this band is relatively low, and at the same time the Gonyostomum multicornutum has a special fluorescence response at 700 nm, while the Akashiwo sanguinea does not, then the two bands of 650 nm and 700 nm can be regarded as the optimal distinguishing band combination.

[0054] As an embodiment of the present invention, the determining of the optimal distinguishing band combination of the Akashiwo sanguinea and the Gonyostomum multicornutum based on the spectral response characteristics includes: based on the spectral response characteristics, identifying the background water bodies of the Akashiwo sanguinea and the Gonyostomum multicornutum; extracting different band factors of the Akashiwo sanguinea, the Gonyostomum multicornutum and the background water bodies; calculating the light reflection amounts of the Akashiwo sanguinea, the Gonyostomum multicornutum and the background water bodies corresponding to the different band factors; according to the light reflection amounts, identifying the difference degrees of the reflectance between the Akashiwo sanguinea and the Gonyostomum multicornutum and the background water bodies; and based on the difference degrees of the reflectance, determining the optimal distinguishing band combination of the Akashiwo sanguinea and the Gonyostomum multicornutum.

[0055] Among them, the background water body refers to the water body that does not contain the Akashiwo sanguinea and the Gonyostomum multicornutum, usually a clean water body or a water body containing other non - target substances (such as suspended solids, sediment, etc.). The different band factors refer to specific bands used for analysis in spectral data, such as the chlorophyll a absorption band: 675 nm. The light reflection amount refers to the light energy reflected by the algae or the background water body under a certain band. The difference degree of the reflectance refers to the difference in the reflectance between the Akashiwo sanguinea and the Gonyostomum multicornutum and the background water body under different bands.

[0056] Optionally, the identification of the background water bodies of the Akashiwo sanguinea and the Gonyostomum multicornutum based on the spectral response characteristics can be determined by the reflectance. The calculation of the light reflection amounts of the Akashiwo sanguinea, the Gonyostomum multicornutum and the background water bodies corresponding to the different band factors can be achieved by using the ratio of the reflected light energy to the incident light energy. The identification of the difference degrees of the reflectance between the Akashiwo sanguinea and the Gonyostomum multicornutum and the background water body according to the light reflection amounts can be determined by the standardized interpolation method.

[0057] Further, in the embodiment of the present invention, by analyzing the algal bloom areas of the Akashiwo sanguinea and the Gonyaulax polygramma according to the optimal discrimination band combination, the dynamic changes of the algal bloom can be monitored, the signs of algal outbreaks can be detected in a timely manner, and thus measures can be taken to prevent the further spread of the algal bloom. The algal bloom area refers to a specific area in the water body where algae multiply and aggregate in large numbers.

[0058] As an embodiment of the present invention, the analysis of the algal bloom areas of the Akashiwo sanguinea and the Gonyaulax polygramma according to the optimal discrimination band combination includes: collecting spectral images of the optimal discrimination band combination and identifying pixel points in the spectral images; obtaining the spectral reflectance of the pixel points in the optimal discrimination band combination; performing cluster analysis processing on the pixel points according to the spectral reflectance to obtain a cluster analysis result and setting a class identifier for the cluster analysis result; collecting the coordinate parameters of the pixel points in the spectral images, and generating a spatial distribution map of the cluster analysis result based on the coordinate parameters and the class identifier; and analyzing the algal bloom areas of the Akashiwo sanguinea and the Gonyaulax polygramma from the spatial distribution map according to the class identifier.

[0059] Among them, the spectral image refers to an image containing spectral information of multiple bands extracted from the target spectral data. The pixel point refers to the smallest unit in the image. The cluster analysis result refers to the result obtained by clustering similar pixel points into the same category according to the spectral reflectance of the pixel points. The spectral reflectance refers to the ratio of the reflected light energy to the incident light energy of the pixel point at a specific band. The class identifier refers to a unique identifier used to distinguish different classes, such as algae being labeled with the number 1 or red color. The coordinate parameters refer to the position information of each pixel point in the spectral image, usually represented in the form of rows and columns. The spatial distribution map refers to an image generated based on the coordinate parameters and class identifier of the pixel points, which can intuitively display the spatial distribution of different classes of algae.

[0060] Optionally, the cluster analysis processing of the pixel points according to the spectral reflectance can be implemented by using the K-means clustering method. The acquisition of the coordinate parameters of the pixel points in the spectral image according to the spectral reflectance can be obtained through the array index in the image, such as row numbers and column numbers.

[0061] S5. Identify the reflectance difference characteristics of the Akashiwo sanguinea and the Gonyaulax polygramma under the spectral reflectance curve. Based on the reflectance difference characteristics, define the discriminant double index of the Akashiwo sanguinea and the Gonyaulax polygramma. According to the discriminant double index, construct a species discrimination system for the Akashiwo sanguinea and the Gonyaulax polygramma.

[0062] In the embodiment of the present invention, by identifying the reflectance difference characteristics of the Akashiwo sanguinea and the Gonyaulax polygramma under the spectral reflectance curve, the algal species can be accurately distinguished, and the accuracy of algal monitoring can be significantly improved. The reflectance difference characteristics refer to the differences in the reflectance values of the Akashiwo sanguinea and the Gonyaulax polygramma at specific wavelengths or multiple wavelengths on the spectral reflectance curve.

[0063] Furthermore, in the embodiment of the present invention, by defining a discriminant double index for the Akashiwo sanguinea and the Gonyaulax polygramma based on the reflectance difference characteristics, the misclassification caused by subjective judgment or fuzzy criteria can be effectively reduced, and the classification accuracy can be improved. The discriminant double index refers to a specific evaluation index used to distinguish the Akashiwo sanguinea and the Gonyaulax polygramma, such as the slope difference index in the 510 - 560 nm wavelength band and the depression feature index in the 560 - 665 nm wavelength band between the Akashiwo sanguinea and the Gonyaulax polygramma.

[0064] As an embodiment of the present invention, defining the discriminant double index for the Akashiwo sanguinea and the Gonyaulax polygramma based on the reflectance difference characteristics includes: extracting the significantly distinguishable wavelength bands of the Akashiwo sanguinea and the Gonyaulax polygramma based on the reflectance difference characteristics; collecting the reflectance data of the significantly distinguishable wavelength bands, and extracting the wavelength band slope corresponding to the significantly distinguishable wavelength bands according to the reflectance data; creating a distinguishing index for the Akashiwo sanguinea of the Akashiwo sanguinea and the Gonyaulax polygramma based on the wavelength band slope and the significantly distinguishable wavelength bands; extracting the remote sensing reflectance of the significantly distinguishable wavelength bands from the reflectance data; constructing a distinguishing index for the Gonyaulax polygramma of the Akashiwo sanguinea and the Gonyaulax polygramma by combining the wavelength band slope, the significantly distinguishable wavelength bands, and the remote sensing reflectance; and defining the discriminant double index for the Akashiwo sanguinea and the Gonyaulax polygramma based on the distinguishing index for the Akashiwo sanguinea and the distinguishing index for the Gonyaulax polygramma.

[0065] Among them, the significantly distinguishable wavelength bands refer to the wavelength bands on the reflectance curve that can significantly distinguish the two algal species. The wavelength band slope refers to the rate of change of the reflectance with respect to the wavelength within the significantly distinguishable wavelength bands. The reflectance data refers to the specific numerical set of the reflected light intensity of each pixel point within a specific wavelength range. The distinguishing index for the Akashiwo sanguinea refers to an index constructed based on the difference in the reflectance data characteristics of the Akashiwo sanguinea and the Gonyaulax polygramma at specific significantly distinguishable wavelength bands, and is used to measure and identify the Akashiwo sanguinea. The remote sensing reflectance refers to the ratio of the upward radiance of the water body to the incident irradiance at different wavelengths obtained by remote sensing means. The distinguishing index for the Gonyaulax polygramma refers to an index constructed based on the unique reflectance data characteristics of the Gonyaulax polygramma at the significantly distinguishable wavelength bands, and is used to characterize and identify the Gonyaulax polygramma.

[0066] Optionally, based on the reflectance difference feature, the extraction of the significant discrimination bands between the Akashiwo sanguinea and the Gonyaulax polygramma can be achieved through Savitzky-Golay smoothing and derivative calculation.

[0067] In an optional embodiment of the present invention, based on the band slope and the significant discrimination bands, the following formula is used to create the Akashiwo sanguinea discrimination index between the Akashiwo sanguinea and the Gonyaulax polygramma:

[0068]

[0069] where GPI represents the Akashiwo sanguinea discrimination index between the Akashiwo sanguinea and the Gonyaulax polygramma, and R rs _slope(560, 510) represents the band slope corresponding to the significant discrimination band of 510 - 560 nm, and R rs _slope(510, 490) represents the band slope corresponding to the significant discrimination band of 490 - 510 nm.

[0070] It should be noted that when comparing different samples or data, subtle differences are difficult to reflect. After magnifying 1000 times, the data differences can be made more obvious, facilitating the observation and analysis of the differences in GPI values corresponding to different algal blooms. Then, by dividing by 2, the weight of R rs _slope(510, 490) in the GPI calculation is reduced, relatively highlighting the role of R rs _slope(560, 510), and realizing the emphasis on the role of the characteristics of this band in differentiating algal blooms.

[0071] In another optional embodiment of the present invention, combining the band slope, the significant discrimination bands, and the remote sensing reflectance, the following formula is used to construct the Gonyaulax polygramma discrimination index between the Akashiwo sanguinea and the Gonyaulax polygramma:

[0072]

[0073] where ASI represents the Gonyaulax polygramma discrimination index between the Akashiwo sanguinea and the Gonyaulax polygramma, and R rs _slope(620, 620) represents the band slope corresponding to the significant discrimination band of 560 - 620 nm, and R rs _slope(620, 665) represents the band slope corresponding to the significant discrimination band of 620 - 665 nm, and R rs _slope(560, 665) represents the band slope corresponding to the significant discrimination band of 560 - 665 nm, and R rs (560) represents the remote sensing reflectance at the wavelength of 560 nm, and R rs (665) represents the remote sensing reflectance at the wavelength of 665 nm.

[0074] In an embodiment of the present invention, by constructing a species discrimination system for Akashiwo sanguinea and Gonyaulax polygramma according to the discrimination dual-index, Akashiwo sanguinea and Gonyaulax polygramma can be accurately distinguished, and the accuracy of algal bloom monitoring can be improved. The species discrimination system refers to a tool that quantifies the spectral feature differences of algae as the discrimination dual-index of algal species and uses these indicators to achieve automatic identification and classification of algal species.

[0075] As an embodiment of the present invention, constructing the species discrimination system for Akashiwo sanguinea and Gonyaulax polygramma according to the discrimination dual-index includes: extracting the cell structures and pigment components of Akashiwo sanguinea and Gonyaulax polygramma; based on the cell structures and the pigment components, identifying the differential characteristic elements of Akashiwo sanguinea and Gonyaulax polygramma; according to the discrimination dual-index, extracting the Akashiwo sanguinea discrimination index and the Gonyaulax polygramma discrimination index corresponding to Akashiwo sanguinea and Gonyaulax polygramma; calculating the correlation coefficients between the Akashiwo sanguinea discrimination index and the Gonyaulax polygramma discrimination index and the differential characteristic elements; when the correlation coefficient is greater than the preset coefficient, generating a comprehensive discrimination index of the Akashiwo sanguinea discrimination index and the Gonyaulax polygramma discrimination index; according to the comprehensive discrimination index, defining the classification thresholds of Akashiwo sanguinea and Gonyaulax polygramma; combining the classification thresholds and the comprehensive discrimination index to construct the species discrimination system for Akashiwo sanguinea and Gonyaulax polygramma.

[0076] Among them, the cell structure refers to the morphological characteristics of Akashiwo sanguinea and Gonyaulax polygramma, including cell shape, organelle characteristics, etc. The pigment component refers to the composition of photosynthetic pigments in Akashiwo sanguinea and Gonyaulax polygramma, such as chlorophylls, carotenoids, etc. The differential characteristic element refers to the element that is the key difference between Akashiwo sanguinea and Gonyaulax polygramma identified based on cell structure and pigment components, such as chlorophyll content. The correlation coefficient refers to a quantitative index used to measure the degree of association between the characteristic elements corresponding to the Akashiwo sanguinea discrimination index and the Gonyaulax polygramma discrimination index and the differential characteristic elements. The preset coefficient refers to a standard used to judge whether the correlation coefficient reaches the relevant degree. The comprehensive discrimination index refers to a comprehensive index calculated based on the Akashiwo sanguinea discrimination index and the Gonyaulax polygramma discrimination index. The classification threshold refers to a critical value defined according to the comprehensive discrimination index, which is used to clearly distinguish Akashiwo sanguinea and Gonyaulax polygramma.

[0077] Optionally, the extraction of the cell structures of the Akashiwo sanguinea and the Gonyaulax polygramma can be achieved by using an electron microscope. The extraction of the pigment components of the Akashiwo sanguinea and the Gonyaulax polygramma can be determined by an organic solvent, such as methanol. The identification of the differential characteristic elements of the Akashiwo sanguinea and the Gonyaulax polygramma can be achieved by the grey relational analysis method. According to the comprehensive discriminant index, the classification threshold definition of the Akashiwo sanguinea and the Gonyaulax polygramma can be realized by using K-means clustering (k = 2) to divide the comprehensive discriminant index values into two groups through the demarcation point between the two groups.

[0078] In an alternative embodiment of the present invention, when the correlation coefficient is greater than a preset coefficient, the following formula is used to generate the comprehensive discriminant index of the Akashiwo sanguinea discrimination index and the Gonyaulax polygramma discrimination index:

[0079]

[0080] where CI represents the comprehensive discriminant index of the Akashiwo sanguinea discrimination index and the Gonyaulax polygramma discrimination index, w k represents the weight of the k-th type of differential characteristic element, and r k represents the correlation coefficient between the Akashiwo sanguinea discrimination index and the Gonyaulax polygramma discrimination index and the k-th differential characteristic element. m represents the number of differential characteristic elements that are significantly correlated with the Akashiwo sanguinea discrimination index and the Gonyaulax polygramma discrimination index, and k represents the category index of the differential characteristic elements.

[0081] Refer to Figure 5 shown, which is a schematic diagram of the algal species classification for implementing the method for identifying Akashiwo sanguinea and Gonyaulax polygramma blooms based on spectral data provided by an embodiment of the present invention. Figure 5 (a) represents the determination result of dinoflagellates by the existing algorithm. Figure 5 (b) represents the classification of Gonyaulax polygramma, Akashiwo sanguinea, and other algal blooms. By comparison, it can be clearly observed that ( Figure 5 b) Gonyaulax polygramma has a higher GPI value and a lower ASI value, so it can be used for the classification and discrimination of Akashiwo sanguinea and Gonyaulax polygramma.

[0082] Refer to Figure 6 shown, which is a schematic diagram of the algal species classification for implementing the method for identifying Akashiwo sanguinea and Gonyaulax polygramma blooms based on spectral data provided by an embodiment of the present invention. Figure 6 Among them, the red dots represent Akashiwo sanguinea, and the blue dots represent Gonyaulax polygramma. From the time dimension, the distribution changes on different dates can reflect the reproduction, diffusion, or migration rules of the two algae.

[0083] S6. Analyze the algal bloom growth conditions in the algal bloom area based on the water body type, and perform parameter optimization processing on the algal species differentiation system according to the algal bloom growth conditions to obtain an optimized algal species differentiation system. Based on the optimized algal species differentiation system, output the algal bloom recognition result of the water area where the algal bloom occurs.

[0084] In the embodiment of the present invention, by analyzing the algal bloom growth conditions in the algal bloom area based on the water body type, a scientific basis can be provided for parameter optimization of the algal species differentiation system, and the accuracy of algal species differentiation can be improved. The algal bloom growth conditions refer to various environmental and ecological conditions that promote the massive reproduction of algae and form algal blooms, such as the chemical properties of the water body, light, etc.

[0085] As an embodiment of the present invention, the analysis of the algal bloom growth conditions in the algal bloom area based on the water body type includes: extracting the nutrient salt concentration and hydrological characteristics of the algal bloom area based on the water body type; analyzing the water body flow characteristics of the algal bloom area according to the hydrological characteristics; identifying the gradient change characteristics of the nutrient salt concentration based on the water body flow characteristics; separating the algal concentration area in the algal bloom area according to the gradient change characteristics; analyzing the algal growth rate in the algal concentration area and analyzing the influencing factors of the algal growth rate; extracting the water temperature and light intensity in the algal concentration area based on the influencing factors; and analyzing the algal bloom growth conditions in the algal bloom area by combining the water temperature, the light intensity, the water body flow characteristics and the nutrient salt concentration.

[0086] Among them, the nutrient salt concentration refers to the content of nutrients such as nitrogen (N) and phosphorus (P) in the water body, the hydrological characteristics refer to the physical and chemical properties of the water body, including water temperature, dissolved oxygen, pH value, conductivity, turbidity, etc., the water body flow characteristics refer to the flow state of the water body, including flow velocity, flow direction, water body mixing situation, etc., the gradient change characteristics refer to the change trend of the nutrient salt concentration in space, such as the gradient change from the high-concentration area to the low-concentration area, the algal concentration area refers to the water area where the algal density is significantly higher than other areas, the algal growth rate refers to the rate of increase in the biomass of algae per unit time, the influencing factors refer to the environmental factors that affect the algal growth rate, including nutrient salt concentration, water temperature, light intensity, water body fluidity, etc., the water temperature refers to the temperature value of the water body in the algal bloom area, and the light intensity refers to the light energy received per unit area.

[0087] Optionally, the analysis of the water body flow characteristics of the algal bloom area according to the hydrological characteristics can be realized through a water body mixing model, the identification of the gradient change characteristics of the nutrient salt concentration based on the water body flow characteristics can be determined by using a time series analysis method, and the analysis of the algal growth rate in the algal concentration area can be realized through a laboratory observation method.

[0088] Furthermore, in the embodiments of the present invention, by performing parameter optimization processing on the algal species differentiation system according to the algal bloom growth conditions, an optimized algal species differentiation system is obtained, which can enhance the environmental adaptability and analysis ability of the algal species differentiation system, thereby providing a more reliable scientific basis for the early warning and treatment of algal blooms. The parameter optimization processing refers to the process of adjusting the algal species differentiation system according to environmental parameters. The optimized algal species differentiation system refers to a mechanism that can dynamically adjust the differentiation parameters and model structure according to changes in environmental conditions (such as nutrient concentration, water temperature, light intensity, etc.) and the growth state of algae.

[0089] As an embodiment of the present invention, the step of performing parameter optimization processing on the algal species differentiation system according to the algal bloom growth conditions to obtain an optimized algal species differentiation system includes: configuring a real-time monitoring device for the algal bloom growth conditions, and collecting real-time parameters of the algal bloom growth conditions based on the real-time monitoring device; collecting historical detection data of the algal bloom growth conditions, and analyzing the parameter change characteristics of the algal bloom growth conditions based on the historical detection data; setting a parameter adjustment threshold for the algal species differentiation system according to the parameter change characteristics; identifying an abnormal state of the algal bloom growth conditions based on the real-time parameters; constructing a feedback network for the abnormal state, and defining an adjustment trigger mechanism for the parameter adjustment threshold according to the feedback network; and performing parameter optimization processing on the algal species differentiation system by combining the parameter adjustment threshold, the feedback network and the adjustment trigger mechanism to obtain an optimized algal species differentiation system.

[0090] Among them, the real-time monitoring device refers to a device or system for real-time monitoring of algal bloom growth conditions, including sensors, data collectors and transmission modules. The real-time parameters refer to the current data of algal bloom growth conditions collected by the real-time monitoring device, such as water temperature, pH value, dissolved oxygen, chlorophyll a concentration, etc. The historical detection data refers to the data of algal bloom growth conditions obtained by monitoring devices or other means over a past period of time. The parameter change characteristics refer to the change rules of algal bloom growth conditions summarized through analysis of historical detection data, such as seasonal fluctuations, nutrient concentration change trends, etc. The parameter adjustment threshold refers to a critical value set according to the parameter change characteristics, used to judge whether the algal bloom growth conditions are abnormal or whether the monitoring strategy needs to be adjusted. The abnormal state refers to the state where the real-time parameters deviate from the normal range. The feedback network refers to a system or mechanism for transmitting and processing abnormal state information, usually including data collection, analysis and decision-making modules. The adjustment trigger mechanism refers to the rule or process for automatically or manually triggering parameter adjustment according to the output of the feedback network.

[0091] Optionally, the configuration of the real-time monitoring device for the algal bloom growth conditions can be implemented using a multi-parameter water quality monitor. Based on the historical detection data, the analysis of the parameter change characteristics of the algal bloom growth conditions can be obtained through a regression model, and the construction of the feedback network for the abnormal state can be implemented using an early warning system.

[0092] In the embodiment of the present invention, by outputting the algal bloom identification result of the algal bloom occurrence water area based on the optimized algal species discrimination system, the identification accuracy of dinoflagellate algal blooms in turbid water can be significantly improved. At the same time, it can more accurately identify the area, time, and algal species type of the algal bloom occurrence, realize the specific management of algal species, improve the algal bloom treatment efficiency, and provide a scientific basis and technical guarantee for marine ecological protection, fishery resource management, and disaster emergency response. The algal bloom identification result refers to the specific information output after comprehensively judging the algal bloom occurrence situation in a specific area based on the optimized algal species discrimination system, such as the cause of the algal bloom outbreak, the algal species type, the development trend of the algal bloom, etc.

[0093] Compared with the problems described in the background art, in the embodiments of the present invention, by selecting the water areas where blooms of Akashiwo sanguinea and Gonyaulax polygramma occur, collecting the water body spectral data of the water areas where the blooms occur, and performing interference elimination processing on the water body spectral data to obtain target spectral data, the accuracy and reliability of subsequent analysis can be ensured; further, in the embodiments of the present invention, by extracting the sensitive bands of Akashiwo sanguinea and Gonyaulax polygramma based on the target spectral data and measuring the reflectance values of the sensitive bands, different types of water bodies can be distinguished to improve the accuracy of bloom monitoring; in the embodiments of the present invention, by constructing the spectral reflectance curves of Akashiwo sanguinea and Gonyaulax polygramma according to the target spectral data, the difference in band reflectance between Akashiwo sanguinea and Gonyaulax polygramma can be intuitively displayed; further, in the embodiments of the present invention, by extracting the spectral response characteristics of Akashiwo sanguinea and Gonyaulax polygramma in the water areas where the blooms occur based on the spectral reflectance curves, the bloom areas can be effectively identified and the dominant species can be distinguished, providing a basis for bloom early warning and ecological management; in the embodiments of the present invention, by determining the optimal discrimination band combination of Akashiwo sanguinea and Gonyaulax polygramma based on the spectral response characteristics, the areas where blooms are caused by Akashiwo sanguinea or Gonyaulax polygramma can be quickly and accurately identified in large water areas; further, in the embodiments of the present invention, by identifying the reflectance difference characteristics of Akashiwo sanguinea and Gonyaulax polygramma under the spectral reflectance curve, and defining the discrimination double index of Akashiwo sanguinea and Gonyaulax polygramma based on the reflectance difference characteristics, the algae species can be accurately distinguished, effectively reducing the misclassification caused by subjective judgment or fuzzy criteria, and significantly improving the accuracy of algae monitoring; in the embodiments of the present invention, by analyzing the bloom growth conditions in the bloom areas based on the water body type and performing parameter optimization processing on the algae species discrimination system to obtain an optimized algae species discrimination system, a scientific basis can be provided for the parameter optimization of the algae species discrimination system, improving the accuracy of algae species discrimination; in the embodiments of the present invention, by outputting the bloom identification results of the water areas where the blooms occur based on the optimized algae species discrimination system, the identification accuracy of dinoflagellate blooms in turbid water bodies can be significantly improved, and at the same time, the areas, times, and algae species types where blooms occur can be more accurately identified, realizing the specific management of algae species, improving the efficiency of bloom control, and providing a scientific basis and technical guarantee for marine ecological protection, fishery resource management, and disaster emergency response. Therefore, a method and system for identifying blooms of Akashiwo sanguinea and Gonyaulax polygramma based on spectral data provided by the embodiments of the present invention can improve the accuracy of algae species classification.

[0094] Embodiment 2:

[0095] As Figure 7 shown, it is a functional module diagram of the system for identifying blooms of Akashiwo sanguinea and Gonyaulax polygramma based on spectral data of the present invention.

[0096] The Alexandrium sanguineum and Gonyaulax polygramma algal bloom recognition system 200 based on spectral data according to the present invention can be installed in an electronic device. According to the functions achieved, the Alexandrium sanguineum and Gonyaulax polygramma algal bloom recognition system based on spectral data may include a spectral data collection module 201, a water body classification module 202, a spectral feature analysis module 203, an algal bloom area extraction module 204, an algal species differentiation module 205, and a result output module 206. The modules in the present invention may also be referred to as units, which refer to a series of computer program segments that can be executed by a processor of an electronic device and can complete fixed functions, and are stored in the memory of the electronic device.

[0097] In the embodiments of the present invention, the functions of each module / unit are as follows:

[0098] The spectral data collection module 201 is used to select the waters where the algal blooms of Alexandrium sanguineum and Gonyaulax polygramma occur, collect the water body spectral data of the waters where the algal blooms occur, perform interference elimination processing on the water body spectral data, and obtain target spectral data;

[0099] The water body classification module 202 is used to, based on the target spectral data, extract the sensitive bands of Alexandrium sanguineum and Gonyaulax polygramma, measure the reflectance values of the sensitive bands, and identify the water body type of the waters where the algal blooms occur according to the reflectance values and the sensitive bands;

[0100] The spectral feature analysis module 203 is used to, according to the target spectral data, construct the spectral reflectance curves of Alexandrium sanguineum and Gonyaulax polygramma, and based on the spectral reflectance curves, extract the spectral response characteristics of Alexandrium sanguineum and Gonyaulax polygramma in the waters where the algal blooms occur;

[0101] The algal bloom area extraction module 204 is used to, based on the spectral response characteristics, determine the optimal discrimination band combination of Alexandrium sanguineum and Gonyaulax polygramma, and according to the optimal discrimination band combination, extract the algal bloom areas of Alexandrium sanguineum and Gonyaulax polygramma;

[0102] The algal species differentiation module 205 is used to identify the reflectance difference characteristics of Alexandrium sanguineum and Gonyaulax polygramma under the spectral reflectance curve, define the discrimination double index of Alexandrium sanguineum and Gonyaulax polygramma based on the reflectance difference characteristics, and construct the algal species differentiation system of Alexandrium sanguineum and Gonyaulax polygramma according to the discrimination double index;

[0103] The result output module 206 is configured to analyze the algal bloom growth conditions in the algal bloom area based on the water body type, perform parameter optimization processing on the algal species differentiation system according to the algal bloom growth conditions, obtain an optimized algal species differentiation system, and output an algal bloom recognition result for the water area where the algal bloom occurs based on the optimized algal species differentiation system.

[0104] Specifically, each module in the algal bloom recognition system 200 for Akashiwo sanguinea and Gonyaulax polygramma based on spectral data in the embodiments of the present invention adopts the same technical means as those in the Figure 1 algal bloom recognition method for Akashiwo sanguinea and Gonyaulax polygramma based on spectral data described above, and can produce the same technical effects, which will not be elaborated here.

[0105] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms.

[0106] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for identifying algal blooms of Haematococcus sanguineus and Goniocarpus polyphyllus based on spectral data, characterized in that: The method comprises: Selecting an algal bloom-occurring water area of ​​Haematococcus sanguinosa and Goniocarpus polyphylla, collecting water spectral data of the algal bloom-occurring water area, performing interference elimination processing on the water spectral data, and obtaining target spectral data; Based on the target spectral data, the sensitive bands of the sanguineous Hakka algae and the polyphylla serrata are extracted, and the reflectance values ​​of the sensitive bands are measured, and the water body type of the algal bloom-occurring waters is identified according to the reflectance values ​​and the sensitive bands; According to the target spectral data, construct the spectral reflectance curves of the sanguinea haka and the multi-lineal Gonyaula, and based on the spectral reflectance curves, extract the spectral response characteristics of the sanguinea haka and the multi-lineal Gonyaula in the algal bloom-occurring waters; Based on the spectral response characteristics, determining the optimal distinguishing band combination of the sanguinea haka and the multi-lineal Gonyaula, and separating the algal bloom areas of the sanguinea haka and the multi-lineal Gonyaula according to the optimal distinguishing band combination; Identify the reflectance difference characteristics of the sanguinea haka and the multi-lineal Gonyaula under the spectral reflectance curve, define a discriminant double index of the sanguinea haka and the multi-lineal Gonyaula based on the reflectance difference characteristics, and construct an algae species differentiation system of the sanguinea haka and the multi-lineal Gonyaula based on the discriminant double index; Based on the water body type, the algal bloom growth conditions in the algal bloom area are analyzed, and according to the algal bloom growth conditions, parameter optimization processing of the algal species differentiation system is performed to obtain an optimized algal species differentiation system, and based on the optimized algal species differentiation system, the algal bloom identification results of the algal bloom occurring waters are output.

2. The method for identifying algal blooms of Haematococcus sanguineus and Gonyaula polymorpha based on spectral data according to claim 1, characterized in that: The step of identifying the water type of the algal bloom-occurring waters according to the reflectivity value and the sensitive band includes: Collecting historical remote sensing data of the algal bloom-occurring waters, and extracting algae-containing water bodies in the algal bloom-occurring waters; Based on the historical remote sensing data, determining a numerical variation interval of the reflectivity value; Analyzing the optical properties of the algae-containing water body, and identifying the turbidity, nutrient level and salinity of the algae-containing water body based on the optical properties; Based on the turbidity level, the nutrient level and the salinity, define a classification evaluation index for the algae-containing water body; According to the value variation range, setting the reflectivity threshold of the sensitive band; The classification evaluation index is combined with the reflectivity threshold to identify the water body type of the algal bloom-occurring waters.

3. The method for identifying algal blooms of Haematococcus sanguineus and Gonyaula polymorpha based on spectral data according to claim 1, characterized in that: The extracting of the spectral response characteristics of the sanguinea algae and the multi-striped hyalopsis algae in the algal bloom-occurring waters based on the spectral reflectance curve comprises: identifying local maxima and local minima in the spectral reflectance curve; Based on the local highest point and the local lowest point, determining the reflectivity extreme values ​​of the sanguinea haka algae and the multi-striped hymenium; measuring the fluorescence peak values ​​of the sanguineous Hakka algae and the multi-striped Gonyaena; According to the spectral reflectance curve, the band slopes corresponding to the sanguinea algae and the multi-striped spathula are calculated; The spectral response characteristics of the Haematococcus sanguineus and the Gonyaula polymorpha are extracted by combining the reflectivity extreme value, the fluorescence peak value and the band slope.

4. The method for identifying algal blooms of Haematococcus sanguineus and Gonyaula polymorpha based on spectral data according to claim 1, characterized in that: The determining of the optimal band combination for distinguishing the sanguineous Hakka algae from the polymorphic Gonyaena based on the spectral response characteristics comprises: Based on the spectral response characteristics, the background water bodies of the sanguineous Hakka algae and the multi-striped Gonyaena are identified; Extracting different band factors of the sanguineous Hakka algae, the multi-striped Gonyaena and the background water body; Calculate the light reflection amounts of the sanguinea haka, the multi-striped hyalopsis algae and the background water body corresponding to the different waveband factors; According to the light reflection amount, identifying the difference degree of reflectivity between the sanguinea haka algae and the multi-striped hyalophora and the background water body; Based on the degree of reflectivity difference, the optimal band combination for distinguishing the sanguinea algae and the multi-striped algae is determined.

5. The method for identifying algal blooms of Haematococcus sanguineus and Gonyaula polymorpha based on spectral data according to claim 1, characterized in that: The method of separating the bloom areas of the Haematococcus sanguineus and the Gonyaena polymorpha according to the optimal distinguishing band combination includes: Collecting the spectral image of the optimal distinguishing band combination, and identifying the pixel points in the spectral image; Obtaining the spectral reflectance of the pixel point in the optimal distinguishing band combination; Performing cluster analysis on the pixel points according to the spectral reflectance to obtain a cluster analysis result, and setting a category identifier of the cluster analysis result; Collecting coordinate parameters of the pixel points in the spectral image, and generating a spatial distribution map of the cluster analysis result based on the coordinate parameters and the category identifier; According to the category identification, the algal bloom areas of the sanguineous Hakkana and the multi-striped Gonyaena are extracted from the spatial distribution map.

6. The method for identifying algal blooms of Haematococcus sanguineus and Gonyaula polymorpha based on spectral data according to claim 1, characterized in that: The dual index for distinguishing the sanguineous Hakka algae from the polymorphic Gonyaena is defined based on the reflectivity difference characteristics, including: Based on the reflectivity difference characteristics, extracting the significant distinguishing bands of the sanguineous Hakka algae and the multi-striped Gonyaena; Collecting reflectance data of the significantly distinguished wavebands, and extracting the waveband slope corresponding to the significantly distinguished wavebands according to the reflectance data; Based on the band slope and the significantly distinguished bands, a Haematococcus sanguineus distinction index between the Haematococcus sanguineus and the Gonyaena polytricha is created; Extracting the remote sensing reflectance of the significantly distinguished band from the reflectance data; Combining the band slope, the significantly distinguished band and the remote sensing reflectance, constructing a Gonyaula polymorpha differentiation index between the Haematococcus sanguineus and the Gonyaula polymorpha; Based on the Hakkana sanguineus index and the Gonyaula polymorpha index, a dual index for distinguishing the Hakkana sanguineus and the Gonyaula polymorpha is defined.

7. The method for identifying algal blooms of Haematococcus sanguineus and Gonyaula polymorpha based on spectral data according to claim 1, characterized in that: The algae species differentiation system of the sanguineous Hakka algae and the multi-striped Gonyaena is constructed according to the discrimination double index, including: Extracting the cell structure and pigment components of the sanguinea haka algae and the polyphylla serrata; Based on the cell structure and the pigment composition, identifying the differential characteristic elements between the sanguinea algae and the multi-striped spathula algae; According to the discriminant double index, extracting the sanguinea hakama distinction index and the multi-lineal Gonyaula distinction index corresponding to the sanguinea hakama and the multi-lineal Gonyaula; Calculating the correlation coefficients of the Haematococcus sanguineus distinction index and the Gonyaula polymorpha distinction index with the differential characteristic elements; When the correlation coefficient is greater than a preset coefficient, a comprehensive discrimination index of the Haematococcus sanguineus discrimination index and the Gonyaula polymorpha discrimination index is generated; According to the comprehensive discrimination index, defining the classification threshold of the sanguinea algae and the multi-striped spathula; By combining the classification threshold and the comprehensive discrimination index, an algae species differentiation system for the sanguineous Hakka alga and the multi-striped Gonyaena is constructed.

8. The method for identifying algal blooms of Haematococcus sanguineus and Gonyaula polymorpha based on spectral data according to claim 1, characterized in that: The analyzing the algal bloom growth conditions of the algal bloom area based on the water body type includes: Based on the water body type, extracting the nutrient concentration and hydrological characteristics of the algal bloom area; Analyzing the water flow characteristics of the algal bloom area according to the hydrological characteristics; Based on the water flow characteristics, identifying the gradient change characteristics of the nutrient concentration; According to the gradient change characteristics, the algae concentration area of ​​the algae bloom area is separated; Analyzing the algae growth rate in the algae concentration area and analyzing the factors affecting the algae growth rate; Based on the influencing factors, extracting the water temperature and light intensity of the algae concentration area; The algal bloom growth conditions in the algal bloom area are analyzed in combination with the water temperature, the light intensity, the water flow characteristics and the nutrient salt concentration.

9. The method for identifying algal blooms of Haematococcus sanguineus and Gonyaula polymorpha based on spectral data according to claim 1, characterized in that: The method of performing parameter optimization processing of the algae species differentiation system according to the algae bloom growth conditions to obtain an optimized algae species differentiation system includes: Configuring a real-time monitoring device for the algal bloom growth conditions, and collecting real-time parameters of the algal bloom growth conditions based on the real-time monitoring device; Collecting historical detection data of the algal bloom growth conditions, and analyzing parameter change characteristics of the algal bloom growth conditions based on the historical detection data; According to the parameter change characteristics, setting the parameter adjustment threshold of the algae species differentiation system; Based on the real-time parameters, identifying an abnormal state of the algal bloom growth condition; Constructing a feedback network of the abnormal state, and defining an adjustment trigger mechanism of the parameter adjustment threshold according to the feedback network; In combination with the parameter adjustment threshold, the feedback network and the adjustment trigger mechanism, parameter optimization processing of the algae species differentiation system is performed to obtain an optimized algae species differentiation system.

10. The method for identifying algal blooms of Haematococcus sanguineus and Gonyaula polymorpha based on spectral data according to claim 7, characterized in that: When the correlation coefficient is greater than a preset coefficient, a comprehensive discrimination index of the sanguinea Haematococcus differentiation index and the polymorpha algae differentiation index is generated, including: When the correlation coefficient is greater than a preset coefficient, a comprehensive discrimination index of the Haematococcus sanguineus distinction index and the Gonyaula polymorpha distinction index is generated.

Images