A method, device, electronic device and storage medium for remotely sensing shallow water depth inversion

Abstract

The present invention discloses a method, device, electronic device and storage medium for remote sensing of shallow sea water depth. The method includes: obtaining satellite remote sensing images and measured water depth data of a to-be-measured area; performing calibration preprocessing on the satellite remote sensing images to obtain spectral data; dividing the measured water depth data based on a preset ratio to obtain a training set and a test set; constructing a partial least squares regression model according to the training set and the spectral data of each corresponding band, and then predicting the spectral data to obtain a prediction result and performing prediction verification; when the result of the prediction verification does not meet the preset conditions, re-dividing the training set and the test set; repeating the previous steps until the result of the prediction verification meets the preset conditions; constructing a support vector machine model through the parrot optimization algorithm based on the training set and the test set; and using the support vector machine model to perform water depth inversion of the target area. The present invention can accurately perform shallow sea water inversion and can be widely applied to the technical field of data inversion.

Description

Technical Field

[0001] The present invention relates to the technical field of data inversion, and particularly to a remote sensing shallow water depth inversion method, device, electronic device and storage medium. Background Art

[0002] Shallow water depth is one of the important parameters of the coastal zone environment, which plays an important role in navigation safety, fishery farming, nearshore engineering and coastal zone ecological environment protection. Traditional sounding methods such as on-site measurement and shipborne sonar are inefficient and have limited coverage. In recent years, airborne lidar has become a supplement to sounding means, but its cost is high, and it cannot reach shallow sea areas with different and complex natural environments. Summary of the Invention

[0003] The present invention aims to solve the problems of related technical limitations at least to a certain extent. For this purpose, the present invention provides a remote sensing shallow water depth inversion method, device, electronic device and storage medium, which can accurately perform remote sensing shallow water depth inversion.

[0004] On the one hand, an embodiment of the present invention provides a remote sensing shallow water depth inversion method, including the following steps:

[0005] Obtain satellite remote sensing images and measured water depth data of the area to be measured;

[0006] Perform calibration preprocessing on the satellite remote sensing images to obtain spectral data;

[0007] Divide the measured water depth data based on a preset ratio to obtain a training set and a test set;

[0008] Construct a partial least squares regression model according to the training set and the spectral data of each band corresponding thereto;

[0009] Use the partial least squares regression model to predict the spectral data to obtain a prediction result;

[0010] Perform prediction verification based on the measured values of the training set and the test set and their corresponding prediction results;

[0011] When the result of the prediction verification does not meet the preset conditions, randomly divide the measured water depth data again based on the preset ratio to obtain a training set and a test set;

[0012] Return to execute the step of constructing a partial least squares regression model according to the training set and the spectral data of each band corresponding thereto until the result of the prediction verification meets the preset conditions;

[0013] Construct a support vector machine model based on the training set and the test set through the parrot optimization algorithm;

[0014] Use the support vector machine model to perform water depth inversion of the target area.

[0015] Optionally, before the step of randomly re - dividing the measured water depth data based on a preset ratio to obtain a training set and a test set, the method further includes the following steps:

[0016] Update and adjust the preset ratio.

[0017] Optionally, pre - processing the satellite remote sensing image to obtain spectral data includes the following steps:

[0018] Perform radiometric calibration, atmospheric correction, and geometric correction pre - processing on the satellite remote sensing image in sequence to obtain water - surface reflectance data;

[0019] Process the green band and near - infrared band in the water - surface reflectance data to obtain a normalized difference water index, and divide the area to be measured into a water area and a non - water area based on the normalized difference water index;

[0020] Perform solar flare correction processing on the water - surface reflectance data of the water area to obtain water - leaving reflectance data.

[0021] Optionally, before the step of dividing the measured water depth data based on a preset ratio to obtain a training set and a test set, the method further includes the following steps:

[0022] Perform tidal correction on the measured water depth data based on pre - acquired tidal observation data values.

[0023] Optionally, constructing a partial least squares regression model based on the training set and the spectral data of its corresponding bands includes the following steps:

[0024] Extract the spectral values of each band of the remote sensing image pixels corresponding to each measured water depth point in the training set from the spectral data;

[0025] Use the spectral values of each band and the measured values of the corresponding measured water depth points as input and output in sequence to construct a partial least squares regression model;

[0026] Among them, before the step of constructing the partial least squares regression model, the spectral values of each band and the measured values of the corresponding measured water depth points are pre - normalized.

[0027] Optionally, performing prediction verification based on the measured values and their corresponding prediction results of the training set and the test set includes the following steps:

[0028] Process the measured values and their corresponding prediction results of the training set to obtain a first root - mean - square error;

[0029] According to the first average value of all the measured values of the training set, combine the measured values and their corresponding prediction results of the training set to obtain a first coefficient of determination;

[0030] The second root mean square error is obtained by processing the measured values based on the test set and their corresponding prediction results;

[0031] The second coefficient of determination is obtained by combining the second average value of all the measured values of the test set with the measured values of the test set and their corresponding prediction results and processing them.

[0032] Optionally, a support vector machine model is constructed based on the training set and the test set through the parrot optimization algorithm, including the following steps:

[0033] An initial support vector machine model is trained using the training set;

[0034] An initial population is randomly generated and used as the target population; the initial population includes a preset number of individuals, and each individual includes a penalty coefficient and a kernel parameter;

[0035] The parameters of the individuals in the target population are applied to the initial support vector machine model, and the fitness of each individual's applied initial support vector machine model is evaluated through the test set using a preset objective function to obtain the optimal individual;

[0036] Other individuals in the target population imitate the optimal individual, and then the target population is adjusted and updated in combination with a preset optimization strategy;

[0037] Return to the step of applying the parameters of the individuals in the target population to the initial support vector machine model until the maximum number of iterations is reached, and output the optimal individual in the last round of iteration;

[0038] A support vector machine model is established using the penalty coefficient and the kernel parameter in the optimal individual.

[0039] On the other hand, an embodiment of the present invention provides a remote sensing shallow water depth inversion device, including:

[0040] A first module for obtaining satellite remote sensing images and measured water depth data of the area to be measured;

[0041] A second module for performing calibration preprocessing on the satellite remote sensing images to obtain spectral data;

[0042] A third module for dividing the measured water depth data based on a preset ratio to obtain a training set and a test set;

[0043] A fourth module for constructing a partial least squares regression model based on the training set and the spectral data of each corresponding band;

[0044] A fifth module for predicting the spectral data using the partial least squares regression model to obtain prediction results;

[0045] A sixth module for performing prediction verification based on the measured values of the training set and the test set and their corresponding prediction results;

[0046] A seventh module, configured to re-randomly divide the measured water depth data into a training set and a test set based on a preset ratio when the result of the prediction verification does not meet the preset conditions;

[0047] An eighth module, configured to return and execute the fourth module until the result of the prediction verification meets the preset conditions;

[0048] A ninth module, configured to construct a support vector machine model based on the training set and the test set through a parrot optimization algorithm;

[0049] A tenth module, configured to perform water depth inversion of the target area by using the support vector machine model.

[0050] Optionally, the apparatus further includes:

[0051] An eleventh module, configured to update and adjust the preset ratio.

[0052] Optionally, the apparatus further includes:

[0053] A twelfth module, configured to perform tidal correction on the measured water depth data based on pre-acquired tidal observation data values.

[0054] On the other hand, an embodiment of the present invention provides an electronic device, including: a processor and a memory; the memory is used to store a program; the processor executes the program to implement the above-mentioned remote sensing shallow water depth inversion method.

[0055] On the other hand, an embodiment of the present invention provides a computer storage medium, in which a program executable by a processor is stored, and the program executable by the processor is used to implement the above-mentioned remote sensing shallow water depth inversion method when executed by the processor.

[0056] In an embodiment of the present invention, satellite remote sensing images and measured water depth data of the area to be measured are obtained; the satellite remote sensing images are corrected and preprocessed to obtain spectral data; the measured water depth data is divided into a training set and a test set based on a preset ratio; a partial least squares regression model is constructed according to the training set and the spectral data of each corresponding band; the spectral data is predicted by using the partial least squares regression model to obtain a prediction result; prediction verification is performed based on the measured values of the training set and the test set and their corresponding prediction results; when the result of the prediction verification does not meet the preset conditions, the measured water depth data is randomly divided into a training set and a test set again based on the preset ratio; the step of constructing a partial least squares regression model according to the training set and the spectral data of each corresponding band is returned until the result of the prediction verification meets the preset conditions; a support vector machine model is constructed by using the parrot optimization algorithm based on the training set and the test set; the water depth of the target area is inverted by using the support vector machine model. Based on satellite remote sensing data, the present invention uses a machine learning model to perform water depth inversion, which can significantly improve the accuracy of the water depth result. Moreover, by continuously iterating and verifying the prediction results of each division, the present invention can avoid overfitting or underfitting phenomena caused by randomly dividing the training set and the test set, and improve the accuracy of water depth inversion. Description of the Drawings

[0057] The drawings are used to provide a further understanding of the technical solutions of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the technical solutions of the present invention, and do not constitute a limitation to the technical solutions of the present invention.

[0058] Figure 1 It is a schematic diagram of an implementation environment for remote sensing shallow water depth inversion provided by an embodiment of the present invention;

[0059] Figure 2 It is a schematic flowchart of a remote sensing shallow water depth inversion method provided by an embodiment of the present invention;

[0060] Figure 3 It is an expanded flowchart of step S200 provided by an embodiment of the present invention;

[0061] Figure 4 It is a schematic diagram of an example of the seabed time structure provided by an embodiment of the present invention;

[0062] Figure 5 It is an expanded flowchart of step S400 provided by an embodiment of the present invention;

[0063] Figure 6 It is an expanded flowchart of step S600 provided by an embodiment of the present invention;

[0064] Figure 7 It is an expanded flowchart of constructing a support vector machine model by using the parrot algorithm provided by an embodiment of the present invention;

[0065] Figure 8 It is a schematic diagram of the overall process of the specific application of the remote sensing shallow water depth inversion method provided by the embodiment of the present invention;

[0066] Figure 9 It is a schematic structural diagram of a remote sensing shallow water depth inversion device provided by the embodiment of the present invention;

[0067] Figure 10 It is a schematic structural diagram of an electronic device provided by the embodiment of the present invention. Detailed implementation manners

[0068] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. 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.

[0069] It should be noted that although functional module division is performed in the system schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order from the module division in the system or the order in the flowchart. Terms such as "first / S100", "second / S200", etc. in the description of the specification, claims and the above drawings are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence.

[0070] Referring to "embodiment" in this article means that the specific features, structures or characteristics described in combination with the embodiment may be included in at least one embodiment of the present invention. The phrase appears in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0071] It can be understood that the remote sensing shallow water depth inversion method provided by the embodiment of the present invention can be applied to any computer device with data processing and computing capabilities, and this computer device can be various types of terminals or servers. When the computer device in the embodiment is a server, the server is an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network, content delivery network), and big data and artificial intelligence platforms. Optionally, the terminal is a smart phone, a tablet computer, a notebook computer, a desktop computer, etc., but is not limited thereto.

[0072] For the convenience of understanding the technical solution of the present invention, first, the technical feature proper nouns that may appear in the embodiments of the present invention are explained:

[0073] As Figure 1 shown, it is a schematic diagram of an implementation environment provided by an embodiment of the present invention. Referring to Figure 1 , this implementation environment includes at least one terminal 102 and a server 101. The terminal 102 and the server 101 can be network-connected by wireless or wired means to complete data transmission and exchange.

[0074] The server 101 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0075] In addition, the server 101 can also be a node server in a blockchain network. Among them, blockchain is a new application mode of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, and encryption algorithms.

[0076] The terminal 102 can be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited thereto. The terminal 102 and the server 101 can be directly or indirectly connected through wired or wireless communication means, and the embodiments of the present invention do not limit this here.

[0077] Exemplarily based on Figure 1 the implementation environment shown, an embodiment of the present invention provides a remote sensing shallow sea water depth inversion method. Taking the application of this remote sensing shallow sea water depth inversion method to the server 101 as an example for illustration, it can be understood that this remote sensing shallow sea water depth inversion method can also be applied to the terminal 102.

[0078] Referring to Figure 2 , Figure 2 is a flowchart of the remote sensing shallow sea water depth inversion method applied to the server provided by an embodiment of the present invention. The execution subject of this remote sensing shallow sea water depth inversion method can be any of the aforementioned computer devices (including servers or terminals). Referring to Figure 2 , this method includes the following steps:

[0079] S100. Obtain satellite remote sensing images and measured water depth data of the area to be measured;

[0080] S200. Perform calibration preprocessing on the satellite remote sensing image to obtain spectral data;

[0081] It should be noted that in some embodiments, such as Figure 3 As shown, performing calibration preprocessing on the satellite remote sensing image to obtain spectral data may include the following steps: S201. Perform radiometric calibration, atmospheric correction, and geometric correction preprocessing on the satellite remote sensing image in sequence to obtain water surface reflectance data; S202. Process the green band and near-infrared band in the water surface reflectance data to obtain the normalized difference water index (NDWI), and divide the area to be measured into a water area and a non-water area based on the NDWI; S203. Perform solar flare correction processing on the water surface reflectance data of the water area to obtain the water-leaving reflectance data.

[0082] Exemplarily, in some specific embodiments, obtain the multi-spectral or hyperspectral satellite remote sensing image of the area to be measured, and perform radiometric calibration, atmospheric correction, and geometric correction preprocessing on the image in sequence to obtain the water surface reflectance data ( R rs ).

[0083] Calculate the normalized difference water index NDWI. NDWI > 0 indicates the water area, NDWI < 0 indicates the non-water area. Extract and retain the water area, and remove the non-water area.

[0084]

[0085] In the formula, NDWI is the normalized difference water index; R rs (green) is the water surface reflectance of the green band; R rs (nir) is the water surface reflectance of the near-infrared band.

[0086] Perform solar flare correction processing on the water surface reflectance data of the water area to obtain the water-leaving reflectance data,

[0087]

[0088] In the formula, R w is the water-leaving reflectance; R rs is the water surface reflectance; b i is the slope after linear fitting of the scatter plot formed by taking the water surface reflectance of the near-infrared band of each pixel in the deep water area as the x-axis and the corresponding water surface reflectance of the visible light band as the y-axis (such as Figure 4 ), where the deep water area usually appears dark blue or black in the remote sensing image, and can be further determined by setting the reflectance thresholds of the blue band and the near-infrared band. Usually in areas with good water quality, R b < 0.04 and R nir< 0.004, and the threshold can be adjusted according to the actual situation of the image. The scatter plot of the water surface reflectance in the blue band and the near-infrared band can be drawn for auxiliary judgment; R b is the water surface reflectance in the blue band; R nir is the water surface reflectance in the near-infrared band; R min-nir is the minimum value of the water surface reflectance in the near-infrared band in the scatter plot.

[0089] S300. Divide the measured water depth data based on a preset ratio to obtain a training set and a test set;

[0090] Exemplarily, in some specific embodiments, the measured water depth data of the area to be measured can be randomly divided into a training set and a test set according to the quantity ratio of 85% and 15%. The ratio can be adjusted according to requirements, and in the actual iteration process, the ratio is continuously adjusted with the prediction verification of each iteration.

[0091] It should be noted that in some embodiments, before the step of dividing the measured water depth data based on a preset ratio to obtain a training set and a test set, the method may further include the following steps: performing tidal correction on the measured water depth data based on the pre-obtained tidal observation data values.

[0092] Exemplarily, in some specific embodiments, the measured water depth data of the area to be measured is obtained, and tidal correction is performed on the measured water depth data to ensure that the tidal height of the measured water depth data is consistent with the tidal height at the time of image shooting. The measured water depth after tidal correction:

[0093]

[0094] In the formula, h is the measured water depth value at the time of image shooting, h met is the measured water depth value, T is the tidal height when the measured water depth data is obtained, h data is the tidal height at the time of image shooting. The tidal height can be obtained by obtaining the nearest tidal observation value from the tidal monitoring website for the area to be measured.

[0095] S400. Construct a partial least squares regression model according to the training set and the spectral data of each corresponding band;

[0096] It should be noted that in some embodiments, such as Figure 5As shown, to construct a partial least squares regression model based on the training set and the spectral data of each band, the following steps may be included: S401. Extract the spectral values of each band of the remote sensing image pixels corresponding to each actual water depth measurement point in the training set from the spectral data; S402. Use the spectral values of each band and the measured values of the corresponding actual water depth measurement points as input and output in sequence to construct a partial least squares regression model; wherein, before the step of constructing the partial least squares regression model, the spectral values of each band and the measured values of the corresponding actual water depth measurement points are pre-normalized.

[0097] Exemplarily, in some specific embodiments, first, extract the spectral values of each band of the remote sensing image pixels corresponding to the actual water depth measurement points in the training set. Then, use the spectral values of each band as input and the corresponding actual water depth values as output. After normalizing the data, construct a partial least squares regression model.

[0098] S500. Use the partial least squares regression model to predict the spectral data to obtain a prediction result;

[0099] Exemplarily, in some specific embodiments, use the constructed model to predict the training set and the test set data respectively, and perform anti-normalization processing on the prediction results to obtain the original data range (i.e., the prediction results).

[0100] S600. Perform prediction verification based on the measured values of the training set and the test set and their corresponding prediction results;

[0101] It should be noted that in some embodiments, as Figure 6 shown, performing prediction verification based on the measured values of the training set and the test set and their corresponding prediction results may include the following steps: S601. Process the measured values of the training set and their corresponding prediction results to obtain the first root mean square error; S602. Based on the first average value of all the measured values of the training set, combine the measured values of the training set and their corresponding prediction results to process and obtain the first determination coefficient; S603. Process the measured values of the test set and their corresponding prediction results to obtain the second root mean square error; S604. Based on the second average value of all the measured values of the test set, combine the measured values of the test set and their corresponding prediction results to process and obtain the second determination coefficient.

[0102] Exemplarily, in some specific embodiments, calculate the root mean square error (RMSE1) and the determination coefficient (R1 2 ) of the results of predicting the training set by the model and the measured water depth data values, and calculate the root mean square error (RMSE2) and the determination coefficient (R2 2 ) of the results of predicting the test set by the model and the measured water depth data values. Wherein:

[0103]

[0104] Wherein, RMSE is the root mean square error, n is the number of water depth points in the training set or the test set, is the measured water depth value of the i-th point, is the calculated value of the model for the i-th point, and i = 1....n.

[0105]

[0106] Wherein, is the coefficient of determination, is the mean value of the measured water depth values in the training set or the test set.

[0107] S700. When the result of the prediction verification does not meet the preset conditions, randomly re-partition the measured water depth data based on a preset ratio to obtain a training set and a test set;

[0108] Among them, in some embodiments, before the step of randomly re-partitioning the measured water depth data based on a preset ratio to obtain a training set and a test set, the method may further include the following steps: updating and adjusting the preset ratio.

[0109] Exemplarily, in some specific embodiments, if the error between RMSE1 and RMSE2 is less than or equal to 0.2, and R2 2 and R2 2 The error of is less than or equal to 0.2, then retain the ratio and partitioning scheme of the existing training set and test set, otherwise randomly re-partition the measured water depth data test set and training set, and / or, by reallocating the ratio of the measured water depth data training set and test set, continue with the original steps until the errors are all within the range of 0.2. The error can be adjusted according to requirements, but it should not be too large, otherwise overfitting or underfitting phenomena of the subsequent model will occur.

[0110] S800. Return to execute the step of constructing a partial least squares regression model based on the training set and the spectral data of each corresponding band until the result of the prediction verification meets the preset conditions;

[0111] S900. Construct a support vector machine model based on the training set and the test set through the parrot optimization algorithm;

[0112] It should be noted that, in some embodiments, such as Figure 7As shown in the figure, a support vector machine model can be constructed through the parrot optimization algorithm based on a training set and a test set, which may include the following steps: S901. Train an initial support vector machine model using the training set; S902. Randomly generate an initial population and use the initial population as the target population; the initial population includes a preset number of individuals, and each individual includes a penalty coefficient and a kernel parameter; S903. Apply the parameters of the individuals in the target population to the initial support vector machine model, and use a preset objective function to evaluate the fitness of each individual's applied initial support vector machine model through the test set to obtain the optimal individual; S904. Let other individuals in the target population imitate the optimal individual, and then adjust and update the target population in combination with a preset optimization strategy; S905. Return to the step of applying the parameters of the individuals in the target population to the initial support vector machine model until the maximum number of iterations is reached, and output the optimal individual in the last round of iteration; S906. Use the penalty coefficient and kernel parameter in the optimal individual to establish a support vector machine model.

[0113] Exemplarily, in some specific embodiments, if the root mean square error and the coefficient of determination of the training set and the test set differ little, the data of the training set and the test set are normalized. Based on the data characteristics, the parrot optimization algorithm is used to obtain the optimal values of the penalty coefficient and the kernel parameter in the support vector machine model.

[0114] Among them, the parrot optimization algorithm (PO) is a population-based stochastic optimization algorithm inspired by the behavior of parrot groups. It simulates the behavior of parrots searching for food and learning the environment in nature, especially focusing on the social learning and memory abilities of parrots. This algorithm is usually applied to the global optimization of high-dimensional complex problems. Through the parrot optimization algorithm, the best parameters of the support vector machine model can be efficiently found, the prediction performance of the model can be improved, and it also has the characteristics of global search ability and fast convergence, and is suitable for dealing with non-linear complex optimization problems.

[0115] Specifically, the optimization steps can be implemented as follows:

[0116] 1. Determine the objective function for evaluating the performance of a given parameter combination, and the following steps can be used to define the objective function:

[0117] (1) Train a support vector machine model using the training set;

[0118] (2) Evaluate the model performance using the test set, for example, through the mean square error, etc.;

[0119]

[0120] In the formula, is the measured water depth value in the test set, The calculated value of the support vector machine model, N is the number of measured water depth points in the test set, and i = 1....N.

[0121] (3) Use the performance index as the fitness value, and the optimization goal is to minimize the error.

[0122] 2. Initialize the population:

[0123] (1) Randomly generate the initial population, and each individual represents the penalty coefficient (C) and the kernel parameter (g);

[0124] (2) Set the search range. For example, the lower limit of the penalty coefficient (C) and the kernel parameter (g) is 0.001, and the upper limit is 100;

[0125] (3) Record the population size (such as 30 individuals) and the maximum number of iterations (such as 100 times).

[0126] 3. Fitness evaluation:

[0127] (1) For each individual, call the objective function to calculate the fitness value.

[0128] (2) Sort according to the fitness value to determine the current optimal individual.

[0129] 4. Imitation and update:

[0130] (1) Let the sub-optimal individuals in the population imitate the behavior of the current optimal individual to narrow the search range;

[0131] (2) Adjust the positions of the individuals according to the optimization strategy, including random perturbation and imitation guidance.

[0132] Update formula: ; where is the position of the i-th individual at the t-th iteration; is the position of the current optimal individual; is the random factor; is the noise term to prevent falling into local optimum.

[0133] 5. Termination:

[0134] When the maximum number of iterations is reached, or the change in the fitness value is less than the threshold, output the current optimal penalty coefficient (C) and kernel parameter (g).

[0135] Use the optimized penalty coefficient and kernel parameter to establish a support vector machine model, and use the model to perform water depth inversion on the area to be measured. In some specific application scenarios, the mean relative error (MRE) and root mean square error (RMSE) can also be used to evaluate the accuracy of the results. The smaller the MRE and RMSE values, the higher the accuracy.

[0136]

[0137] In the formula, n is the number of measured water depth points in the test set; is the measured water depth value of the i-th point in the test set; is the model calculation value; i = 1...n.

[0138] S1000. Use the support vector machine model to perform water depth inversion in the target area.

[0139] Exemplarily, in some specific embodiments, the water depth inversion can be achieved based on the remote sensing image of the target area through the optimized support vector machine model.

[0140] To explain the principle of the technical solution of the present invention in detail, the overall process of the present invention will be described below in conjunction with some specific embodiments. It is easy to understand that the following is an explanation of the technical principle of the present invention and should not be regarded as a limitation of the present invention.

[0141] First of all, it should be noted that with the emergence of machine learning methods, machine learning methods such as support vector machines and random forests have been applied to water depth inversion. Compared with traditional empirical models and semi-analytical models, the accuracy of the water depth results obtained by machine learning methods has been significantly improved.

[0142] However, in the related art, when performing water depth inversion using a machine learning model based on satellite remote sensing data, mainly according to the characteristic relationship between the spectral characteristics of the satellite remote sensing image pixels and the corresponding measured water depth data, a water depth inversion model between the two is constructed, and then the water depth values in a larger range are obtained according to the remote sensing image. In this process, the measured water depth data needs to be divided into a training set and a test set. The training set is used to establish the model, while the test set is used to evaluate the accuracy of the water depth inversion result. Currently, both the training set and the test set are divided randomly, but the random division method often leads to overfitting and underfitting phenomena, ultimately reducing the accuracy of water depth inversion. Overfitting refers to the phenomenon that the machine learning model performs well on the training data but poorly on the test data. This means that the model has learned too many specific details on the training data set, so that it cannot generalize on new and unseen data. Underfitting refers to the phenomenon that the machine learning model performs poorly on both the training data and the test data. This means that the model does not have enough learning ability to capture the key features and patterns in the data.

[0143] To solve the above problems, the present invention provides a shallow water depth inversion method based on satellite remote sensing images, which can solve the overfitting or underfitting phenomena caused by randomly dividing the training set and the test set and improve the accuracy of water depth inversion. Specifically, as Figure 8 shown, the present invention can achieve the following:

[0144] Obtain the multispectral or hyperspectral satellite remote sensing image of the area to be measured, and successively perform preprocessing such as radiometric calibration, atmospheric correction, and geometric correction on the image to obtain the water surface reflectance data ( R rs ).

[0145] Calculate the Normalized Difference Water Index (NDWI). When NDWI > 0, it represents the water area; when NDWI < 0, it represents the non-water area. Extract and retain the water area and remove the non-water area.

[0146]

[0147] In the formula, NDWI is the Normalized Difference Water Index; R rs (green) is the water surface reflectance of the green band; R rs (nir) is the water surface reflectance of the near-infrared band.

[0148] Perform solar flare correction on the water surface reflectance data of the water area to obtain the water-leaving reflectance data.

[0149]

[0150] In the formula, R w is the water-leaving reflectance; R rs is the water surface reflectance; b i is the slope after linear fitting of the scatter plot formed by taking the water surface reflectance of the near-infrared band of each pixel in the deep water area as the x-axis and the corresponding water surface reflectance of the visible light band as the y-axis (such as Figure 4 ). Among them, the deep water area usually appears dark blue or black in the remote sensing image and can be further determined by setting the reflectance thresholds of the blue band and the near-infrared band. Usually, in areas with good water quality, R b < 0.04 and R nir < 0.004. The thresholds can be adjusted according to the actual situation of the image, and the scatter plot of the water surface reflectance of the blue band and the near-infrared band can be drawn for auxiliary judgment; R b is the water surface reflectance of the blue band; R nir is the water surface reflectance of the near-infrared band; R min-nir is the minimum value of the water surface reflectance of the near-infrared band in the scatter plot.

[0151] Obtain the measured water depth data of the area to be measured, and perform tidal correction on the measured water depth data to ensure that the tidal height of the measured water depth data is consistent with the tidal height at the time of image shooting. The measured water depth after tidal correction:

[0152]

[0153] In the formula, h is the measured water depth value at the time of image shooting, h metis the measured water depth value, T is the tide height when obtaining the measured water depth data, and h data is the tide height at the image shooting time. The tide height can be obtained from the tide monitoring website for the tide observation value closest to the area to be measured.

[0154] Randomly divide the measured water depth data of the area to be measured into a training set and a test set according to the quantity ratio of 85% and 15%. The ratio can be adjusted according to requirements, and during the actual iteration process, the ratio is continuously adjusted with the prediction verification of each iteration.

[0155] Extract the spectral values of each band of the remote sensing image pixels corresponding to the measured water depth points in the training set.

[0156] Using the spectral values of each band as the input and the corresponding measured water depth values as the output, after normalizing the data, construct a partial least squares regression model.

[0157] Calculate the root mean square error (RMSE1) and coefficient of determination (R1 2 ) of the results of predicting the training set using the model and the measured water depth data values, and calculate the root mean square error (RMSE2) and coefficient of determination (R2 2 ) of the results of predicting the test set using the model and the measured water depth data values. Among them:

[0158]

[0159] In the formula, RMSE is the root mean square error, n is the number of water depth points in the training set or test set, is the measured water depth value of the i-th point, is the calculated value of the model for the i-th point, i = 1....n.

[0160]

[0161] In the formula, is the coefficient of determination, is the mean value of the measured water depth values in the training set or test set.

[0162] If the error between RMSE1 and RMSE2 is less than or equal to 0.2, and the error between R1 2 and R2 2 is less than or equal to 0.2, then retain the existing ratio and division scheme of the training set and test set; otherwise, by reallocating the ratio of the training set and test set of the measured water depth data, or re-randomly dividing the test set and training set of the measured water depth data, continue with the original steps until the errors are all within the range of 0.2. The error can be adjusted according to requirements, but it should not be too large, otherwise overfitting or underfitting phenomena of the subsequent model will occur.

[0163] If the root mean square error and coefficient of determination of the training set and the test set differ little, normalize the data of the training set and the test set.

[0164] Based on the data characteristics, use the Parrot Optimization Algorithm to obtain the optimal values of the penalty coefficient and kernel parameter in the support vector machine model.

[0165] Among them, the Parrot Optimization Algorithm (PO) is a population-based stochastic optimization algorithm inspired by the behavior of parrot flocks. It simulates the behavior of parrots searching for food and learning the environment in nature, especially focusing on the social learning and memory abilities of parrots. This algorithm is usually applied to the global optimization of high-dimensional complex problems. Through the Parrot Optimization Algorithm, the best parameters of the support vector machine model can be efficiently found, improving the prediction performance of the model. At the same time, it has the characteristics of global search ability and fast convergence, and is suitable for dealing with nonlinear complex optimization problems.

[0166] Specifically, the optimization steps can be implemented as follows:

[0167] 1. Determine the objective function for evaluating the performance of a given parameter combination. The following steps can be used to define the objective function:

[0168] (1) Use the training set to train the support vector machine model;

[0169] (2) Evaluate the model performance using the test set, for example, through the mean squared error, etc.;

[0170]

[0171] In the formula, is the measured water depth value in the test set, is the calculated value of the support vector machine model, N is the number of measured water depth points in the test set, and i = 1....N.

[0172] (3) Take the performance index as the fitness value, and the optimization goal is to minimize the error.

[0173] 2. Initialize the population:

[0174] (1) Randomly generate the initial population, and each individual represents the penalty coefficient (C) and the kernel parameter (g);

[0175] (2) Set the search range. For example, the lower limit of the penalty coefficient (C) and the kernel parameter (g) is 0.001, and the upper limit is 100;

[0176] (3) Record the population size (such as 30 individuals) and the maximum number of iterations (such as 100 times).

[0177] 3. Fitness evaluation:

[0178] For each individual, call the objective function to calculate the fitness value.

[0179] (3) Sort according to the fitness value to determine the current optimal individual.

[0180] 4. Imitation and update:

[0181] (1) Let the sub-optimal individuals in the population imitate the behavior of the current optimal individual to narrow the search range;

[0182] (2) Adjust the positions of the individuals according to the optimization strategy, including random perturbation and imitation guidance.

[0183] Update formula: ; where is the position of the i-th individual at the t-th iteration; is the position of the current optimal individual; is the random factor; is the noise term to prevent falling into local optimum.

[0184] 5. Termination:

[0185] When the maximum number of iterations is reached, or the change in the fitness value is less than the threshold, output the current optimal penalty coefficient (C) and kernel parameter (g).

[0186] Use the optimized penalty coefficient and kernel parameter to establish a support vector machine model, and use the model to perform bathymetric inversion on the area to be measured. Finally, draw a map and evaluate the accuracy of the results using the mean relative error (MRE) and root mean square error (RMSE). The smaller the values of MRE and RMSE, the higher the accuracy.

[0187]

[0188] In the formula, n is the number of measured bathymetric points in the test set; is the measured bathymetric value of the i-th point in the test set; is the model calculation value; i = 1...n.

[0189] In summary, by applying the adaptive training set and test set partitioning strategy, during the process of remote sensing inversion of water depth, an iterative loop is carried out according to whether the errors (RMSE) and coefficient of determination (R²) of the training set and test set are within the threshold range, solving the overfitting and underfitting problems that may be caused by random partitioning. By iteratively optimizing the data partitioning scheme, ensuring that the errors are within the set threshold range, the generalization ability and robustness of the model are improved. In addition, through the hyperparameter optimization of the support vector machine based on the parrot optimization algorithm, specifically, the parrot optimization algorithm is applied to shallow water depth inversion for the first time. Through the mechanism of combining global search and local development, the penalty coefficient and kernel parameter of the support vector machine (SVM) are dynamically optimized, enhancing the adaptability of the model to non-linear features. The parrot optimization algorithm designs an adaptive convergence mechanism, combined with the specific data distribution characteristics of shallow water depth inversion, further enhancing the algorithm efficiency and the accuracy of the solution.

[0190] Compared with the prior art, the present invention has at least the following beneficial effects:

[0191] Effectively solve the overfitting and underfitting problems caused by improper partitioning of the training set and test set during the water depth inversion process. Aiming at the shortcomings of the existing methods that the random partitioning of the training set and test set is likely to lead to model overfitting or underfitting, the present invention ensures the generalization ability and robustness of the model and significantly improves the overall accuracy of water depth inversion by dynamically adjusting the partitioning ratio of the training set and test set and the error evaluation mechanism.

[0192] Combine intelligent optimization algorithms to improve the performance of the water depth inversion model. The present invention introduces the parrot optimization algorithm into the field of shallow water depth inversion for the first time to optimize the penalty coefficient and kernel parameter of the support vector machine. Through the global search and local development capabilities of the parrot algorithm, the model parameters are dynamically adjusted to better adapt to the non-linear features of the complex shallow sea environment, improving the stability and accuracy of the inversion results.

[0193] On the other hand, as Figure 9 shown, an embodiment of the present invention provides a remote sensing shallow water depth inversion device 900, which may include:

[0194] A first module 901 for obtaining satellite remote sensing images and measured water depth data of the area to be measured;

[0195] A second module 902 for performing calibration preprocessing on the satellite remote sensing images to obtain spectral data;

[0196] A third module 903 for partitioning the measured water depth data based on a preset ratio to obtain a training set and a test set;

[0197] A fourth module 904 for constructing a partial least squares regression model according to the training set and the spectral data of each corresponding band;

[0198] The fifth module 905 is used to predict the spectral data by using a partial least squares regression model to obtain a prediction result;

[0199] The sixth module 906 is used to perform prediction verification based on the measured values of the training set and the test set and their corresponding prediction results;

[0200] The seventh module 907 is used to, when the result of the prediction verification does not meet the preset conditions, re-randomly divide the measured water depth data based on a preset ratio to obtain a training set and a test set;

[0201] The eighth module 908 is used to return to execute the fourth module until the result of the prediction verification meets the preset conditions;

[0202] The ninth module 909 is used to construct a support vector machine model based on the training set and the test set through a parrot optimization algorithm;

[0203] The tenth module 910 is used to perform water depth inversion of the target area by using the support vector machine model.

[0204] In some embodiments, the device may further include:

[0205] The eleventh module is used to update and adjust the preset ratio.

[0206] In some embodiments, the device may further include:

[0207] The twelfth module is used to perform tidal correction on the measured water depth data based on pre-acquired tidal observation data values.

[0208] The content of the method embodiments of the present invention is applicable to the device embodiments of the present invention. The functions specifically implemented by the device embodiments of the present invention are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those of the above methods.

[0209] On the other hand, the embodiment of the present invention further provides an electronic device. The electronic device includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the above remote sensing shallow water depth inversion method is implemented. The electronic device can be any intelligent terminal including a tablet computer, a vehicle-mounted computer, etc.

[0210] It can be understood that the content in the above method embodiments is applicable to the device embodiments of the present invention. The functions specifically implemented by the device embodiments of the present invention are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those of the above method embodiments.

[0211] As Figure 10 shown, Figure 10 schematically shows the hardware structure of an electronic device 1000 in another embodiment. The electronic device 1000 includes:

[0212] The processor 1001 can be implemented in the form of a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided by the embodiments of the present invention;

[0213] The memory 1002 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM), etc. The memory 1002 can store an operating system and other application programs. When implementing the technical solutions provided by the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 1002 and are called by the processor 1001 to execute the network node population optimization method of the embodiments of the present invention;

[0214] The input / output interface 1003 is used to implement information input and output;

[0215] The communication interface 1004 is used to implement communication interaction between this device and other devices, and can communicate through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.);

[0216] The bus 1005 transmits information between various components of the device (such as the processor 1001, the memory 1002, the input / output interface 1003, and the communication interface 1004);

[0217] Among them, the processor 1001, the memory 1002, the input / output interface 1003, and the communication interface 1004 are communicatively connected to each other inside the device through the bus 1005.

[0218] The electronic device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solutions of this embodiment.

[0219] The content of the method embodiments of the present invention is applicable to the electronic device embodiments of the present invention. The functions specifically implemented by the electronic device embodiments of the present invention are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those of the above methods.

[0220] Another aspect of the embodiments of the present invention further provides a computer-readable storage medium storing a program, which is executed by a processor to implement the foregoing method.

[0221] It should be noted that the computer-readable medium shown in the embodiments of the present invention can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0222] The content of the method embodiments of the present invention is applicable to the embodiments of this computer-readable storage medium. The functions specifically implemented by the embodiments of this computer-readable storage medium are the same as those of the foregoing method embodiments, and the beneficial effects achieved are also the same as those of the foregoing method.

[0223] The embodiments of the present invention also disclose a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of the computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the foregoing method.

[0224] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code, and the above-mentioned module, segment of a program, or part of code contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, as well as combinations of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0225] It should be noted that although several modules of devices for action execution are mentioned in the above detailed description, such a division is not mandatory. In fact, according to the embodiments of the present invention, the features and functions of two or more of the above-mentioned modules or units can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0226] From the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software, or can be implemented by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present invention can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present invention.

[0227] In some alternative embodiments, the functions / operations mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the functions / operations involved, two consecutive blocks shown may actually be executed substantially simultaneously or the blocks can sometimes be executed in the reverse order. In addition, the embodiments presented and described in the flowcharts of the present invention are provided by way of example for the purpose of providing a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logical flows presented herein. Alternative embodiments are contemplated, where the order of various operations is changed and where sub-operations described as part of a larger operation are executed independently.

[0228] In addition, although the present invention has been described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the functions and / or features may be integrated in a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It should also be understood that a detailed discussion of the actual implementation of each module is not necessary for understanding the present invention. Rather, given the attributes, functions, and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the modules will be understood within the ordinary skills of an engineer. Thus, those skilled in the art can implement the present invention as set forth in the claims without undue experimentation. It should also be understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0229] If a function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0230] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a predefined sequence of executable instructions for implementing a logical function, and can be specifically implemented in any computer-readable medium for use by an instruction execution apparatus, device, or equipment (such as a computer-based device, a device including a processor, or other devices that can fetch and execute instructions from the instruction execution apparatus, device, or equipment), or in combination with these instruction execution apparatuses, devices, or equipment. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in combination with an instruction execution apparatus, device, or equipment.

[0231] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection (electronic device) having one or more wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable media can even be paper or other suitable media on which a program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, then editing, interpreting, or otherwise processing it as appropriate, and then storing it in a computer memory.

[0232] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution device. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having suitable combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), and the like.

[0233] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0234] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the claims and their equivalents.

[0235] The above has specifically described the preferred embodiments of the present invention, but the present invention is not limited to the embodiments. Those skilled in the art can also make various equivalent deformations or substitutions without departing from the spirit of the present invention, and these equivalent deformations or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A method for remotely sensing and retrieving shallow sea water depth, characterized in that, It includes the following steps: Obtain satellite remote sensing images and measured water depth data of the area to be measured; Perform calibration preprocessing on the satellite remote sensing images to obtain spectral data; Divide the measured water depth data based on a preset ratio to obtain a training set and a test set; Construct a partial least squares regression model according to the training set and the spectral data of each band corresponding thereto; Use the partial least squares regression model to predict the spectral data to obtain a prediction result; Perform prediction verification based on the measured values of the training set and the test set and their corresponding prediction results, including the following steps: Process the measured values of the training set and their corresponding prediction results to obtain a first root mean square error; According to the first average value of all the measured values of the training set, combine the measured values of the training set and their corresponding prediction results to process and obtain a first coefficient of determination; Process the measured values of the test set and their corresponding prediction results to obtain a second root mean square error; According to the second average value of all the measured values of the test set, combine the measured values of the test set and their corresponding prediction results to process and obtain a second coefficient of determination; When the result of the prediction verification does not meet the preset conditions, randomly divide the measured water depth data again based on the preset ratio to obtain the training set and the test set; the preset conditions are that the error between the first root mean square error and the second root mean square error and the error between the first coefficient of determination and the second coefficient of determination are both less than or equal to the regulation error; the preset ratio is a fixed value; Return to execute the step of constructing a partial least squares regression model according to the training set and the spectral data of each band corresponding thereto until the result of the prediction verification meets the preset conditions; Construct a support vector machine model based on the training set and the test set through the parrot optimization algorithm; Use the support vector machine model to perform water depth inversion of the target area.

2. The remote sensing shallow sea water depth inversion method according to claim 1, characterized in that, The step of performing calibration preprocessing on the satellite remote sensing images to obtain spectral data includes the following steps: Perform radiometric calibration, atmospheric correction, and geometric correction preprocessing on the satellite remote sensing images in sequence to obtain water surface reflectance data; Process the green band and near-infrared band in the water surface reflectance data to obtain a normalized difference water index, and divide the area to be measured into a water area and a non-water area based on the normalized difference water index; Perform solar flare correction processing on the water surface reflectance data of the water area to obtain water-leaving reflectance data.

3. The remote sensing shallow water depth inversion method according to claim 1, characterized in that Before the step of dividing the measured water depth data based on a preset ratio to obtain a training set and a test set, the method further includes the following steps: Perform tidal correction on the measured water depth data based on pre-acquired tidal observation data values.

4. The remote sensing shallow water depth inversion method according to claim 1, wherein The step of constructing a partial least squares regression model according to the training set and the spectral data of each band corresponding thereto includes the following steps: Extract the spectral values of each band of the remote sensing image pixels corresponding to each water depth measurement point in the training set from the spectral data; Taking the spectral values of each band and the measured values of the corresponding measured water depth points as input and output in sequence, a partial least squares regression model is constructed; Among them, before the step of constructing the partial least squares regression model, the spectral values of each band and the measured values of the corresponding measured water depth points are pre-normalized.

5. The remote sensing shallow sea water depth inversion method according to claim 1, wherein The support vector machine model constructed by the parrot optimization algorithm based on the training set and the test set includes the following steps: Training an initial support vector machine model using the training set; Randomly generating an initial population and taking the initial population as the target population; the initial population includes a preset number of individuals, and each individual includes a penalty coefficient and a kernel parameter; Applying the parameters of the individuals in the target population to the initial support vector machine model, and using a preset objective function to evaluate the fitness of the initial support vector machine model applied by each individual through the test set to obtain the optimal individual; Letting other individuals in the target population imitate the optimal individual, and then adjusting and updating the target population in combination with a preset optimization strategy; Returning to the step of applying the parameters of the individuals in the target population to the initial support vector machine model until the maximum number of iterations is reached, and outputting the optimal individual in the last round of iteration; Establishing the support vector machine model using the penalty coefficient and the kernel parameter in the optimal individual.

6. A remote sensing device for shallow sea water depth inversion, characterized in that, Including: The first module is used to obtain the satellite remote sensing image and the measured water depth data of the area to be measured; The second module is used to perform calibration preprocessing on the satellite remote sensing image to obtain spectral data; The third module is used to divide the measured water depth data based on a preset ratio to obtain a training set and a test set; The fourth module is used to construct a partial least squares regression model according to the training set and the spectral data of each corresponding band; The fifth module is used to predict the spectral data using the partial least squares regression model to obtain a prediction result; The sixth module is used to perform prediction verification based on the measured values of the training set and the test set and their corresponding prediction results; Among them, the prediction verification based on the measured values of the training set and the test set and their corresponding prediction results includes the following steps: Processing the measured values of the training set and their corresponding prediction results to obtain the first root mean square error; According to the first average value of all the measured values of the training set, combining the measured values of the training set and their corresponding prediction results to process and obtain the first coefficient of determination; Processing the measured values of the test set and their corresponding prediction results to obtain the second root mean square error; According to the second average value of all the measured values of the test set, combining the measured values of the test set and their corresponding prediction results to process and obtain the second coefficient of determination; A seventh module, configured to, when the result of the prediction verification does not meet a preset condition, re-randomly divide the measured water depth data based on the preset ratio to obtain the training set and the test set; the preset condition is that the error between the first root mean square error and the second root mean square error and the error between the first coefficient of determination and the second coefficient of determination are both less than or equal to a regulation error; the preset ratio is a fixed value; An eighth module, configured to return to execute the fourth module until the result of the prediction verification meets the preset condition; A ninth module, configured to construct a support vector machine model based on the training set and the test set through a parrot optimization algorithm; A tenth module, configured to perform water depth inversion of a target area by using the support vector machine model.

7. An electronic device, characterized in that, It includes a processor and a memory; The memory is used to store programs; The processor executes the program to implement the method according to any one of claims 1 to 5.

8. A computer storage medium storing a program executable by a processor, characterized in that, The program executable by the processor, when executed by the processor, is used to implement the method according to any one of claims 1 to 5.

Images