Global chlorophyll-a remote sensing inversion optimization method and device covering high latitude area

Abstract

The application discloses a global chlorophyll-a remote sensing inversion optimization method and device covering high latitude areas, and comprises the following steps: performing spatio-temporal matching on sea surface temperature based on a measured data set of measured remote sensing reflectivity and measured chlorophyll-a concentration, and integrating and constructing a training data set, which contains five bands of measured remote sensing reflectivity (412, 443, 490, 555 and 670 nm), sea surface temperature, longitude, latitude and measured chlorophyll-a concentration; applying a BP neural network to construct a global chlorophyll-a remote sensing inversion model covering high latitude areas and training the model by using the training data set, the initial weight and threshold of the BP neural network are obtained by iterative optimization of a genetic algorithm, and a trained global chlorophyll-a remote sensing inversion model is obtained; and inputting satellite remote sensing reflectivity to be inverted, matched sea surface temperature, longitude and latitude into the trained global chlorophyll-a remote sensing inversion model, and inverting to obtain chlorophyll-a concentration. The application can effectively improve the global remote sensing inversion precision of chlorophyll-a.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of ocean color remote sensing, and particularly relates to a global chlorophyll-a remote sensing inversion optimization method and device covering high latitude regions. BACKGROUND

[0002] The north and south poles are sensitive zones of climate change, and the warming rate of the north pole is more than twice the global average. With the melting of the ice cover surface and the increase in extreme weather events, the marine ecosystems of the north and south poles have undergone great changes. Chlorophyll-a (Chla) is a commonly used indicator of phytoplankton biomass in water bodies, and long-term continuous large-area observation of water Chla by satellite remote sensing is an important means of studying the response of high-latitude marine ecosystems to climate change. The existing remote sensing Chla standard algorithm is an empirical algorithm based on the blue-green band ratio of remote sensing reflectance (Rrs). According to the radiation transfer theory, Rrs is determined by the absorption and backscattering signals of the water body. In the vast ocean water body, phytoplankton is the main water color component, and the phytoplankton absorption dominates the variation of the water optical signal, and the functional relationship between the phytoplankton light absorption coefficient and Chla is relatively stable, so the standard empirical algorithm has good inversion performance. However, the water environment in the high-latitude region is special, and due to long-term adaptation to low temperature and weak light conditions, the intracellular pigment concentration of phytoplankton is high, and the light absorption capacity of the same order of Chla is significantly lower than that in other sea areas. At the same time, similar to other coastal areas, the CDOM content is high in some regions of the high-latitude region affected by runoff input. Affected by the special water optical properties, the standard remote sensing chlorophyll Chla product in the high-latitude region has the phenomenon of overestimation in the low-value area and underestimation in the high-value area.

[0003] Based on the in-situ observation of high-latitude water optical data, researchers have developed different high-latitude Chla optimization algorithms. One of the optimization algorithms is to revise the parameters of the standard empirical algorithm by applying the matched blue-green band Rrs and Chla, and to propose the OC4L algorithm suitable for the water body of the Arctic Ocean. Another optimization algorithm is to further subdivide the Arctic Ocean into interior shelves and inflow / outflow shelves on the basis of a large number of in-situ observation data, to adjust the parameters of the standard empirical algorithm in different regions, and to establish the AO.Reg.emp algorithm. In addition, it is tried to apply the genetic algorithm to the regional adjustment of the parameters of the semi-analytical algorithm GSM on the basis of multi-band Rrs, Chla, absorption and scattering observation data, and to optimize and establish the AO.GSM algorithm. These high-latitude Chla inversion algorithms are basically based on regional optimization of algorithm parameters, and although they solve the problem of the special properties of high-latitude water optical properties and improve the inversion accuracy of high-latitude Chla, the algorithms all have regional application limitations. So far, there is still a lack of an algorithm that can cover high-latitude regions and be applicable to other regions around the world.

[0004] Application of multi-band spectrum instead of blue-green band spectrum as algorithm input has been applied in complex water bodies such as coastal and lake. Combined with the advantage of machine learning in nonlinear fitting, the introduction of multi-band remote sensing reflectance in addition to blue and green bands, especially the ultraviolet band Rrs412, can better separate the contribution of non-pigment components such as CDOM or suspended sediment and phytoplankton to remote sensing signals, and reduce the uncertainty of Chla inversion to a certain extent. However, the use of multi-band spectrum to invert Chla cannot eliminate the uncertainty of inversion caused by the time and space variation of water optical characteristics (such as the difference in light absorption capacity of phytoplankton in high latitude and non-high latitude). Sea surface temperature (SST) is an important factor affecting the structure, pigment composition and growth rate of phytoplankton population. At the same time, SST is significantly affected by solar radiation, wind, ocean current and other factors, and has significant spatial and temporal distribution characteristics, and is an important indicator of water mass distribution. Some studies use the correlation between remote sensing SST and Chla, and use remote sensing SST as an auxiliary parameter to establish an algorithm based on the spatial and temporal Bayesian maximum entropy characteristics of Chla, which is mainly used to improve the spatial coverage of remote sensing Chla. There has been no attempt to directly combine multi-band spectral signals and SST, longitude and latitude information to optimize the inversion of remote sensing Chla. SUMMARY

[0005] The purpose of the present application is to propose a global chlorophyll a remote sensing inversion optimization method and device covering high latitude areas in view of the above-mentioned technical problems.

[0006] In a first aspect, the present application provides a global chlorophyll a remote sensing inversion optimization method covering high latitude areas, comprising the following steps:

[0007] A measured data set based on measured remote sensing reflectance and measured chlorophyll a concentration is constructed, and the spatial and temporal matching of sea surface temperature is performed on the measured data set to extract the sea surface temperature corresponding to each sample in the measured data set, and a training data set is constructed by integration, which contains measured remote sensing reflectance, sea surface temperature, longitude, latitude and measured chlorophyll a concentration, and the measured remote sensing reflectance includes five central bands of 412, 443, 490, 555 and 670 nm;

[0008] A global chlorophyll a remote sensing inversion model covering high latitude areas is constructed by using BP neural network, the initial weight and threshold value of the BP neural network are obtained by iterative optimization solution through genetic algorithm, and the global chlorophyll a remote sensing inversion model is trained by using the training data set to obtain a trained global chlorophyll a remote sensing inversion model;

[0009] The satellite remote sensing reflectance to be inverted and its matched sea surface temperature, longitude and latitude are input into the trained global chlorophyll a remote sensing inversion model, and the chlorophyll a concentration is inverted.

[0010] Preferably, the measured remote sensing reflectance is selected from the field observation data within the range of + / - 6 nm of the central wavelengths of 412, 443, 490, 555 and 670 nm of the SeaWiFS sensor; and the measured chlorophyll-a concentration is measured by HPLC or fluorescence method.

[0011] Preferably, the measured data set is matched in space and time with the sea surface temperature to obtain the sea surface temperature corresponding to each sample in the measured data set, specifically including:

[0012] The sampling time, longitude and latitude of each sample in the measured data set are matched in time and space with the 4 km resolution Aqua-MODIS multi-year climatological monthly mean sea surface temperature data to obtain the sea surface temperature corresponding to each sample in the measured data set.

[0013] Preferably, the BP neural network includes an input layer, a first hidden layer, a second hidden layer and an output layer, the number of nodes of the input layer is 8, the 8 nodes of the input layer correspond to the remote sensing reflectance of 412, 443, 490, 555 and 670 nm and the sea surface temperature, longitude and latitude matched in space and time, the number of nodes of the output layer is 1, corresponding to the chlorophyll-a concentration; the number of nodes of the first hidden layer and the second hidden layer is 4.

[0014] In a second aspect, the application provides a global chlorophyll-a remote sensing inversion optimization device covering high latitude regions, comprising:

[0015] The training data construction module is configured to construct a measured data set based on measured remote sensing reflectance and measured chlorophyll-a concentration, match the measured data set in space and time with the sea surface temperature to obtain the sea surface temperature corresponding to each sample in the measured data set, and integrate to construct a training data set, the training data set containing measured remote sensing reflectance, sea surface temperature, longitude, latitude and measured chlorophyll-a concentration, the measured remote sensing reflectance including five band values of 412, 443, 490, 555 and 670 nm;

[0016] The model construction module is configured to apply a BP neural network to construct a global chlorophyll-a remote sensing inversion model covering high latitude regions, the initial weights and thresholds of the BP neural network are obtained by iterative optimization of a genetic algorithm, the training data set is used to train the global chlorophyll-a remote sensing inversion model to obtain a trained global chlorophyll-a remote sensing inversion model;

[0017] The inversion module is configured to input the satellite remote sensing reflectance to be inverted and the matched sea surface temperature, longitude and latitude into the trained global chlorophyll-a remote sensing inversion model to obtain the chlorophyll-a concentration.

[0018] In a third aspect, the present application provides an electronic device, comprising one or more processors; and a storage device storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any implementation manner of the first aspect.

[0019] In a fourth aspect, the present application provides a computer-readable storage medium, having stored thereon a computer program, which, when executed by a processor, implements the method as described in any implementation manner of the first aspect.

[0020] In a fifth aspect, the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the method as described in any implementation manner of the first aspect.

[0021] Compared with the prior art, the present application has the following beneficial effects:

[0022] (1) The global chlorophyll-a remote sensing inversion optimization method covering high latitude areas proposed by the present application fully considers the interference of CDOM and suspended particles in the blue-green band on chlorophyll-a inversion and the spatial and temporal differences of water optical characteristics (absorption and backscattering of each component), especially the special problems of water optical characteristics in high latitude areas. The chlorophyll-a concentration is inversed by applying multi-band spectrum combined with SST and longitude and latitude, and the advantages of BP neural network in nonlinear fitting are comprehensively utilized, which can effectively improve the global remote sensing inversion accuracy of chlorophyll-a, and the inversion effect in high latitude areas is particularly significant. The present application can provide strong technical support for the research on the response of global marine ecosystem including high latitude areas to climate change.

[0023] (2) The global chlorophyll-a remote sensing inversion optimization method covering high latitude areas proposed by the present application is established on the basis of the open field data set recognized in the international water color remote sensing field. The data is distributed in various sea areas around the world, covering different types of water bodies. The global inversion uses a unified algorithm model, avoiding the inversion uncertainty problem caused by different regional algorithm models.

[0024] (3) In the global chlorophyll-a remote sensing inversion optimization method covering high latitude areas proposed by the present application, the remote sensing reflectance in the training data set is selected from the field observation data within + / - 6nm range of 412, 443, 490, 555 and 670nm center bands in SeaWiFS sensor, i.e. the remote sensing reflectance with a default center band difference of + / - 6nm has no significant difference. Therefore, for other water color satellite sensors such as MODIS, MERIS, VIIRS, etc., if they have 412, 443, 490, 555, 670nm + / - 6nm five center bands, this model is also applicable, which is conducive to the fusion and application of different water color satellite chlorophyll-a concentration inversion products. BRIEF DESCRIPTION OF DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and all other drawings obtained by those of ordinary skill in the art without creative effort based on these drawings also belong to the protection scope of the present application.

[0026] Figure 1 A flowchart of the global chlorophyll-a remote sensing inversion optimization method covering high-latitude regions according to an embodiment of the present application;

[0027] Figure 2 A model construction flowchart of the global chlorophyll-a remote sensing inversion optimization method covering high-latitude regions according to an embodiment of the present application;

[0028] Figure 3 A schematic diagram of the BP neural network of the global chlorophyll-a remote sensing inversion optimization method covering high-latitude regions according to an embodiment of the present application;

[0029] Figure 4 A figure of the chlorophyll-a inversion accuracy evaluation results of the trained global chlorophyll-a remote sensing inversion model and the NASA standard OCI algorithm of the global chlorophyll-a remote sensing inversion optimization method covering high-latitude regions according to an embodiment of the present application (gray: low-mid latitude region; black: high-latitude region), wherein (a) the NASA standard OCI algorithm, (b) the trained global chlorophyll-a remote sensing inversion model (GBP) of the present application;

[0030] Figure 5 A figure of the inversion results of the trained global chlorophyll-a remote sensing inversion model of the global chlorophyll-a remote sensing inversion optimization method covering high-latitude regions according to an embodiment of the present application;

[0031] Figure 6 A schematic diagram of the global chlorophyll-a remote sensing inversion optimization device covering high-latitude regions according to an embodiment of the present application;

[0032] Figure 7 A hardware structure schematic diagram of the electronic device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0033] In order to make the objects, technical solutions and advantages of the present application more clear, the present application will be further described in detail below with reference to the drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort also belong to the protection scope of the present application.

[0034] Figure 1The embodiment of the application provides a global chlorophyll-a remote sensing inversion optimization method covering a high-latitude area, and the method comprises the following steps:

[0035] S1, constructing a measured data set based on measured remote sensing reflectivity and measured chlorophyll-a concentration, performing spatiotemporal matching of sea surface temperature on the measured data set to obtain the sea surface temperature corresponding to each sample in the measured data set, and integrating to construct a training data set, wherein the training data set comprises measured remote sensing reflectivity, sea surface temperature, longitude, latitude and measured chlorophyll-a concentration, and the measured remote sensing reflectivity comprises five central bands of 412 nm, 443 nm, 490 nm, 555 nm and 670 nm.

[0036] In specific embodiments, the measured remote sensing reflectivity selects field observation data within + / - 6 nm of the five central bands of 412 nm, 443 nm, 490 nm, 555 nm and 670 nm of the SeaWiFS sensor; and the measured chlorophyll-a concentration adopts HPLC measurement results or fluorescence measurement results.

[0037] In specific embodiments, the spatiotemporal matching of sea surface temperature on the measured data set is performed to obtain the sea surface temperature corresponding to each sample in the measured data set, and specifically comprises:

[0038] The sampling time, longitude and latitude of each sample in the measured data set are matched in time and space in the 4km resolution Aqua-MODIS multi-year climatological monthly mean sea surface temperature data to obtain the sea surface temperature corresponding to each sample in the measured data set.

[0039] Specifically, with reference to Figure 2 The embodiment of the application constructs a measured data set matched with synchronous sampling of measured remote sensing reflectivity (Rrs) and measured chlorophyll-a concentration based on an open field data set (same as the NASA Chla standard algorithm) recognized in the international water color remote sensing field. The measured remote sensing reflectivity selects field observation data within + / - 6 nm of the five central bands of 412 nm, 443 nm, 490 nm, 555 nm and 670 nm of the SeaWiFS sensor; and the measured chlorophyll-a concentration adopts HPLC measurement results or fluorescence measurement results. When there are HPLC measurement results and fluorescence measurement results at the same time, the HPLC measurement results are preferentially selected, and the fluorescence measurement results are secondarily selected. The measured data set further comprises sampling time, longitude and latitude of each sample in addition to the measured remote sensing reflectivity and the measured chlorophyll-a concentration.

[0040] The measured data set is matched in space and time with sea surface temperature (SST). The Aqua-MODIS multi-year climatological monthly mean sea surface temperature data (with a spatial resolution of 4 km) are downloaded from the NASA ocean color website, and the sea surface temperature corresponding to each sample in the measured data set is matched according to the sampling time and the longitude and latitude of each sample. The training data set for the global chlorophyll-a remote sensing inversion model is constructed by integrating the measured remote sensing reflectance, sea surface temperature, longitude, latitude and measured chlorophyll-a concentration of the five bands (412, 443, 490, 555 and 670 nm) in the measured data set and the sea surface temperature matched in space and time.

[0041] A test data set is established. The satellite remote sensing reflectance and measured chlorophyll-a concentration in the test data set used in the embodiments of the present application are directly used as the validation data set for detecting the SeaWiFS satellite water color product by NASA SeaBASS. The sea surface temperature corresponding to each sample in the validation data set is matched according to the longitude and latitude information and the sampling time in the same way as described above. The matched data of satellite remote sensing reflectance (412, 443, 490, 555, 670 nm), sea surface temperature (SST), longitude, latitude and measured chlorophyll-a concentration are integrated as the test data set for the global chlorophyll-a remote sensing inversion model.

[0042] S2, a global chlorophyll-a remote sensing inversion model covering high latitude areas is constructed by applying a BP neural network. The initial weight and threshold of the BP neural network are obtained by iterative optimization through a genetic algorithm. The global chlorophyll-a remote sensing inversion model is trained using the training data set, and a trained global chlorophyll-a remote sensing inversion model is obtained.

[0043] In specific embodiments, the BP neural network includes an input layer, a first hidden layer, a second hidden layer and an output layer. The number of nodes of the input layer is 8, and the 8 nodes of the input layer correspond to 412, 443, 490, 555, 670 nm remote sensing reflectance and its space-time matched sea surface temperature, longitude and latitude, respectively. The number of nodes of the output layer is 1, corresponding to the chlorophyll-a concentration. The number of nodes of the first hidden layer and the second hidden layer is 4.

[0044] Specifically, the global chlorophyll-a remote sensing inversion model covering high latitude regions mentioned in the embodiments of the present application adopts a BP neural network, and initial weights and thresholds of the BP neural network are obtained by iterative optimization through a genetic algorithm. In the training process of the global chlorophyll-a remote sensing inversion model, a training data set is used to train the global chlorophyll-a remote sensing inversion model, and a trained global chlorophyll-a remote sensing inversion model is obtained. The performance of the trained global chlorophyll-a remote sensing inversion model is evaluated using a test data set, and the inversion accuracy of the global chlorophyll-a remote sensing inversion model is evaluated. The evaluation indexes mainly include MAPD (Mean absolute percentage difference), RMSE, and the linear regression coefficient R of the chlorophyll-a concentration obtained by inversion and the measured chlorophyll-a concentration 2 . The specific formulas of MAPD and RMSE are as follows:

[0045]

[0046] wherein n represents the total number of samples, C satellite represents the chlorophyll-a concentration obtained by inversion, and C in situ represents the measured chlorophyll-a concentration.

[0047] The inversion accuracy evaluation results of the trained global chlorophyll-a remote sensing inversion model and the inversion accuracy evaluation results of the NASA standard OCI algorithm are shown in Figure 4 . After comparison, the inversion accuracy of the trained global chlorophyll-a remote sensing inversion model proposed in the embodiments of the present application is higher, especially in high latitude regions.

[0048] S3, inputting the satellite remote sensing reflectance to be inverted, the matched sea surface temperature, longitude and latitude into the trained global chlorophyll-a remote sensing inversion model, and obtaining the chlorophyll-a concentration by inversion.

[0049] Specifically, the trained global chlorophyll-a remote sensing inversion model is deployed, and a water color remote sensing file is read as needed to export the satellite remote sensing reflectance, longitude and latitude, and sampling date corresponding to the wave bands (412, 443, 490, 555 and 670 nm); the sea surface temperature of each pixel point is matched according to the spatial and temporal matching method according to the longitude, latitude and sampling date information. The satellite remote sensing reflectance corresponding to the wave bands (412, 443, 490, 555, 670 nm), the sea surface temperature, the longitude and the latitude are input into the trained global chlorophyll-a remote sensing inversion model, and the inversion result output after the model runs is the chlorophyll-a concentration, and the chlorophyll-a concentration is mapped according to the longitude and the latitude. Taking the inversion of the monthly average remote sensing chlorophyll-a concentration of VIIRS_SNPP in April 2020 as an example, the inversion result obtained by the trained global chlorophyll-a remote sensing inversion model is shown in Figure 5 .

[0050] Further referring to Figure 6 , as an implementation of the method shown in the above figures, the application provides an embodiment of a global chlorophyll-a remote sensing inversion optimization device covering high latitude areas, which corresponds to the method embodiment shown in Figure 1 , and the device can be specifically applied to various electronic devices.

[0051] The application embodiment provides a global chlorophyll-a remote sensing inversion optimization device covering high latitude areas, which comprises:

[0052] The training data construction module 1 is configured to construct a measured data set based on measured remote sensing reflectivity and measured chlorophyll-a concentration, to perform spatio-temporal matching of sea surface temperature on the measured data set to extract the sea surface temperature corresponding to each sample in the measured data set, and to integrate and construct a training data set, wherein the training data set comprises measured remote sensing reflectivity, sea surface temperature, longitude, latitude and measured chlorophyll-a concentration, and the measured remote sensing reflectivity includes five band values of 412, 443, 490, 555 and 670 nm.

[0053] The model construction module 2 is configured to apply a BP neural network to construct a global chlorophyll-a remote sensing inversion model covering high latitude areas, to obtain initial weights and thresholds of the BP neural network through iterative optimization by a genetic algorithm, to train the global chlorophyll-a remote sensing inversion model by using the training data set, and to obtain a trained global chlorophyll-a remote sensing inversion model.

[0054] The inversion module 3 is configured to input satellite remote sensing reflectivity to be inverted, its matched sea surface temperature, longitude and latitude into the trained global chlorophyll-a remote sensing inversion model, and to invert to obtain a chlorophyll-a concentration.

[0055] Figure 7 The hardware structure schematic diagram of the electronic device provided by the application embodiment is shown in the figure. Figure 7 As shown in the figure, the electronic device of the embodiment comprises a processor 701 and a memory 702; the memory 702 is used for storing computer execution instructions; and the processor 701 is used for executing the computer execution instructions stored in the memory to realize each step performed by the electronic device in the above embodiment. For details, please refer to the related description in the foregoing method embodiment.

[0056] Optionally, the memory 702 can be independent or integrated with the processor 701.

[0057] When the memory 702 is independently set, the electronic device further comprises a bus 703 for connecting the memory 702 and the processor 701.

[0058] The embodiment of the present application further provides a computer storage medium, and the computer storage medium stores computer execution instructions, and when the processor 701 executes the computer execution instructions, the method described above is realized.

[0059] The embodiment of the present application further provides a computer program product, and the computer program product comprises a computer program, and when the processor 701 executes the computer program, the method described above is realized.

[0060] In the embodiments of the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic, for example, the division of the modules is merely a logical function division, and actual implementation can have another division mode, for example, a plurality of modules can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed modules can be indirect coupling or communication connection through some interfaces, devices or modules, and can be electrical, mechanical or other forms.

[0061] The modules described as separate components can or can not be physically separated, and the components displayed as modules can or can not be physical units, that is, can be located in one place, or can be distributed on a plurality of network units. Part or all of the modules can be selected according to actual needs to implement the embodiment scheme.

[0062] In addition, the functional modules in each embodiment of the present application can be integrated in one processing unit, or each module can be physically present alone, or two or more modules can be integrated in one unit. The unit formed by the above modules can be realized in the form of hardware or in the form of hardware plus software function unit.

[0063] The integrated modules realized in the form of software function modules can be stored in a computer readable storage medium. The software function modules described above are stored in a storage medium, and comprise a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or the processor 701 to execute part of the steps of the method of each embodiment of the present application.

[0064] It should be appreciated that the processor 701 described above can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), or the like. The general-purpose processor can be a microprocessor or the processor 701 can be any conventional processor 701, and the like. The steps of the methods disclosed in the present application can be directly embodied as the execution of the processor 701 in hardware, or be executed by a combination of hardware and software modules in the processor 701.

[0065] The memory 702 can include a high-speed RAM memory, and can also include a non-volatile storage NVM, such as at least one disk memory, and can also be a U disk, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk, and the like.

[0066] The bus 703 can be an industry standard architecture (ISA), a peripheral component interconnect (PCI) bus, or an extended industry standard architecture (EISA) bus, or the like. The bus 703 can be divided into an address bus, a data bus, a control bus, and the like. For the sake of convenience, the bus 703 in the drawings of the present application does not limit to only one bus 703 or one type of bus 703.

[0067] The storage medium described above can be realized by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk, and the like. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0068] An example storage medium is coupled to the processor 701 such that the processor 701 can read information from, and can write information to, the storage medium. Of course, the storage medium can be a part of the processor 701. Consistent with the teachings provided herein, the processor 701 and the storage medium can be located in a ASIC. The teachings provided herein can be used in other electronic devices such as a computer system, a consumer electronics device, or any other device that includes a processor and a storage medium.

[0069] Those skilled in the art can understand that all or part of the steps of the foregoing method embodiments can be completed by a program instruction related to hardware. The foregoing program can be stored in a computer readable storage medium. When the program is executed, the steps of the foregoing method embodiments are executed; and the foregoing storage medium includes various media capable of storing program codes, such as ROM, RAM, magnetic disk, or optical disk.

[0070] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than limit the present application; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some or all of the technical features can be replaced by equivalents; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A global chlorophyll a remote sensing inversion optimization method covering high latitudes, characterized in that: The following steps are involved: Construct a measured dataset based on measured remote sensing reflectance and measured chlorophyll a concentration, perform spatiotemporal matching of sea surface temperature on the measured dataset to extract the sea surface temperature corresponding to each sample in the measured dataset, and integrate the data to construct a training dataset. The training dataset contains measured remote sensing reflectance, sea surface temperature, longitude, latitude, and measured chlorophyll a concentration. The measured remote sensing reflectance includes five central bands of 412, 443, 490, 555, and 670 nm. A BP neural network is used to construct a global chlorophyll-a remote sensing inversion model covering high latitudes, wherein initial weights and thresholds of the BP neural network are obtained by iterative optimization using a genetic algorithm, and the global chlorophyll-a remote sensing inversion model is trained using a training data set to obtain a trained global chlorophyll-a remote sensing inversion model; The satellite remote sensing reflectivity to be inverted and its matching sea surface temperature, longitude and latitude are input into the trained global chlorophyll a remote sensing inversion model to invert and obtain the chlorophyll a concentration.

2. The global chlorophyll a remote sensing inversion optimization method covering high latitudes according to claim 1, characterized in that: The measured remote sensing reflectance is selected from the field observation data within the range of + / - 6nm of the five central bands of 412, 443, 490, 555 and 670nm in the SeaWiFS sensor; the measured chlorophyll a concentration adopts the HPLC measurement result or the fluorescence measurement result.

3. The global chlorophyll a remote sensing inversion optimization method covering high latitudes according to claim 1, characterized in that: Performing spatiotemporal matching of sea surface temperatures on the measured data set to extract the sea surface temperature corresponding to each sample in the measured data set specifically includes: The sampling time, longitude and latitude of each sample in the measured data set are temporally and spatially matched in the 4km resolution Aqua-MODIS multi-year climatological monthly mean sea surface temperature data to obtain the sea surface temperature corresponding to each sample in the measured data set.

4. The global chlorophyll a remote sensing inversion optimization method covering high latitudes according to claim 1, characterized in that: The BP neural network includes an input layer, a first hidden layer, a second hidden layer and an output layer. The number of nodes in the input layer is 8, and the 8 nodes in the input layer correspond to the remote sensing reflectance of 412, 443, 490, 555, and 670 nm and the sea surface temperature, longitude and latitude matched with the time and space. The number of nodes in the output layer is 1, corresponding to the chlorophyll a concentration; the number of nodes in the first hidden layer and the second hidden layer are both 4.

5. A global chlorophyll a remote sensing inversion optimization device covering high latitudes, characterized in that: include: a training data construction module configured to construct a measured data set based on measured remote sensing reflectance and measured chlorophyll a concentration, perform spatiotemporal matching of sea surface temperature on the measured data set to extract the sea surface temperature corresponding to each sample in the measured data set, and integrate the data to construct a training data set, wherein the training data set includes measured remote sensing reflectance, sea surface temperature, longitude, latitude, and measured chlorophyll a concentration, wherein the measured remote sensing reflectance includes five band values ​​of 412, 443, 490, 555, and 670 nm; a model construction module configured to apply a BP neural network to construct a global chlorophyll-a remote sensing inversion model covering high latitudes, wherein initial weights and thresholds of the BP neural network are obtained by iterative optimization using a genetic algorithm, and the global chlorophyll-a remote sensing inversion model is trained using a training data set to obtain a trained global chlorophyll-a remote sensing inversion model; The inversion module is configured to input the satellite remote sensing reflectivity to be inverted and its matching sea surface temperature, longitude and latitude into the trained global chlorophyll a remote sensing inversion model to invert and obtain the chlorophyll a concentration.

6. An electronic device comprising: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

8. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images