A method and system for ice surface meltwater depth inversion

Abstract

This invention discloses a method and system for inverting the depth of ice surface meltwater. The method includes: acquiring the ICESat-2ATL03 photon dataset and performing preliminary denoising to obtain target photon data; separating the meltwater surface and bottom photons to obtain meltwater surface photons and meltwater bottom photons; denoising the meltwater surface photons and performing ice surface meltwater retrieval; denoising the meltwater bottom photons and performing ice surface meltwater retrieval; removing shallow meltwater and slush from the ice surface meltwater window; acquiring multispectral image data and combining it with meltwater depth to generate machine learning model training data; and generating the final depth result based on the meltwater band reflectance input from the multispectral image data. This invention can invert the depth of ice surface meltwater over a large area with high temporal resolution and high accuracy, obtaining spatially well-covered and highly accurate ice surface meltwater depth information, and can be widely applied in the field of remote sensing geoscience applications.

Description

Technical Field

[0001] This invention relates to the technical field of remote sensing geoscience applications, and in particular to a method and system for inverting the depth of ice meltwater. Background Technology

[0002] Meltwater is an important phenomenon on ice sheets, occurring mostly in summer and playing a crucial role in the surface mass balance. Understanding the volume and spatial distribution variations of meltwater is essential for studying ice sheet mass loss and surface mass balance. The foundation for meltwater volume inversion lies in the ability to estimate meltwater depth over large areas with high precision.

[0003] Related research on methods for detecting meltwater depth on Greenland ice surfaces includes not only field measurements but also meltwater depth estimation based on satellite multispectral imagery and lidar data. While field measurements offer the highest reliability and accuracy, they are currently relatively scarce due to cost and environmental constraints. Furthermore, field personnel typically only measure the meltwater depth over a small area on a single Greenland ice surface, making it difficult to conduct large-scale melting water depth monitoring across multiple ice surfaces. Therefore, field measurements are generally used only for method validation. Multispectral imagery offers high temporal resolution and facilitates large-scale melting water depth monitoring, but current image-based methods still have significant limitations in accuracy. Meltwater depth estimation based on lidar data offers a clear advantage in accuracy, but its low temporal resolution and limitations in detecting melting water depth on ice surfaces still restrict its application in melting water depth measurement. Summary of the Invention

[0004] The main objective of this invention is to propose a method and system for retrieving ice meltwater depth, which can retrieve ice meltwater depth over a large area with high temporal resolution and high accuracy, and can obtain ice meltwater depth information with good spatial coverage and high accuracy.

[0005] To achieve the above objectives, one aspect of this invention proposes a method for inverting the depth of ice meltwater, comprising the following steps:

[0006] The ICESat-2 ATL03 photon dataset was acquired and preliminarily denoised to obtain the target photon data;

[0007] Photon separation of the meltwater surface and meltwater bottom is performed on the target photon data after preliminary denoising to obtain meltwater surface photons and meltwater bottom photons;

[0008] The photons on the meltwater surface are denoised and the first meltwater search on the ice surface is performed.

[0009] The photons at the bottom of the meltwater are denoised, and a second search for meltwater on the ice surface is performed.

[0010] Based on the results of the first and second ice surface meltwater searches, shallow meltwater and slush removal processes are applied to the ice surface meltwater window.

[0011] Acquire multispectral image data and combine it with meltwater depth to generate machine learning model training data. Input the meltwater band reflectance based on the multispectral image data into the trained machine learning model to generate the final depth result.

[0012] In some embodiments, acquiring the ICESat-2 ATL03 photon dataset and performing preliminary denoising to obtain the target photon data includes the following steps:

[0013] Download the I CESat-2 ATL03 photon dataset for the target location;

[0014] The acquired photon dataset was initially denoised using the DRAGANN algorithm.

[0015] In some embodiments, the step of separating the meltwater surface and meltwater bottom photons from the preliminarily denoised target photon data to obtain meltwater surface photons and meltwater bottom photons includes the following steps:

[0016] The photons after initial noise reduction are divided into 40m processing windows along the orbit with a step size of 20m.

[0017] Within each processing window, photon nuclear density estimation is performed along the vertical height; the formula for calculating the photon nuclear density estimate is as follows: in, This is the probability density estimate at photon point x, where n is the number of samples, h is the smoothing parameter called bandwidth, which controls the width of the kernel function; K is the kernel function; the expression for the kernel function K is: Where u represents It is data point x i The standardized distance from point x;

[0018] Find all points where the corresponding photon nuclear density estimate is the minimum value in the photon nuclear density estimation curve, take their elevation values, and use the maximum value among these elevation values ​​as the threshold.

[0019] Photons with an elevation less than the threshold are considered to be bottom photons of the meltwater, while photons with an elevation greater than the threshold are considered to be surface photons of the meltwater.

[0020] In some embodiments, the denoising process for the photons on the meltwater surface and the first meltwater retrieval on the ice surface include the following steps:

[0021] The 3δ iterative method is used to remove noise photons from the meltwater surface photons;

[0022] When the standard deviation of the photon elevation on the meltwater surface within the processing window is less than 0.12m, the window is considered a meltwater surface window;

[0023] If the distance between two meltwater windows is within 40 meters, they are grouped together.

[0024] Fill each group of meltwater surface windows, and select the meltwater surface window group containing more than 5 windows as the result of the first search for ice surface meltwater.

[0025] In some embodiments, the denoising process for the bottom photons of the meltwater and the second search for meltwater on the ice surface include the following steps:

[0026] First, a Savitzky-Goliay filter is used to generate a fitted curve for the bottom photons. Then, the fitted value is subtracted from the photon height to eliminate the tendency of the bottom photons. The expression for the Savitzky-Goliay filter is as follows: Among them, y i ′ This is the filtered elevation value; y i+j It is the elevation value in the original photon; c j The weighting coefficients of the filter are m, which is the number of points on both sides of the window.

[0027] Remove all bottom photons within 1m below the meltwater surface elevation to avoid the multi-curved surface reflection phenomenon affecting the final extracted meltwater depth;

[0028] Within each meltwater surface window, all photons below the median bottom photon elevation are removed. Then, 3δ iterations are performed in the vertical direction to remove noisy photons, and denoising is performed in the horizontal direction using an elliptical filter kernel.

[0029] If the number of bottom photons in a meltwater window is greater than 10, the window is considered a meltwater window on the ice surface.

[0030] These ice meltwater windows are grouped according to the same criteria as the meltwater windows obtained in the first ice meltwater search.

[0031] In some embodiments, the process of removing shallow meltwater and slush from the ice surface meltwater window based on the results of the first and second ice surface meltwater searches includes the following steps:

[0032] Photons whose first elevation value on both sides of each set of ice meltwater windows exceeds three times the standard deviation of the surface elevation value are retained and used as the edge of the ice meltwater.

[0033] Connect the edge of the meltwater bottom to the meltwater surface, and then generate the final meltwater bottom again using Savitzky-Golay filtering;

[0034] A refractive index of ~1.33 is used to eliminate the refraction effect of meltwater at the height of photons at the bottom of the meltwater.

[0035] Remove meltwater pools with an average depth of less than 1.15m.

[0036] In some embodiments, acquiring multispectral image data and combining it with meltwater depth to generate machine learning model training data, inputting the meltwater band reflectance into the trained machine learning model based on the multispectral image data, and generating the final depth result includes the following steps:

[0037] Acquire multispectral images that correspond to the ATL03 images in time and space, including four types of images: Landsat8 L1 / L2 and Sentinel L2L1C / L2A. These images are no more than 4 days apart from the ATL03 data in time.

[0038] Training data is generated using the median of the depth sampling point within an image pixel and its multi-band reflectance; for Landsat-8, the median depth is paired with the reflectance values ​​of 7 bands; for Sentinel-2, the low-resolution bands are first uniformly sampled to 10m, and the median depth is paired with the reflectance values ​​of 9 bands.

[0039] The training parameters of the two machine learning algorithms, XGBoost and LightGBM, were manually adjusted. The training data was input to obtain the meltwater depth inversion machine learning model. Then, the meltwater band reflectance was input into the model based on multispectral imagery to generate the final depth result.

[0040] Another aspect of this invention provides a system for inverting the depth of ice meltwater, comprising:

[0041] The first module is used to acquire the ICESat-2 ATL03 photon dataset and perform preliminary denoising to obtain the target photon data;

[0042] The second module is used to separate the meltwater surface and meltwater bottom photons from the target photon data after preliminary denoising, so as to obtain meltwater surface photons and meltwater bottom photons.

[0043] The third module is used to perform noise reduction processing on the photons on the meltwater surface and to perform the first ice meltwater retrieval.

[0044] The fourth module is used to denoise the photons at the bottom of the meltwater and to perform a second search for meltwater on the ice surface.

[0045] The fifth module is used to perform shallow meltwater and slush removal processing on the ice surface meltwater window based on the results of the first ice surface meltwater retrieval and the second ice surface meltwater retrieval.

[0046] The sixth module is used to acquire multispectral image data and combine it with meltwater depth to generate machine learning model training data. Based on the multispectral image data, the meltwater band reflectance is input into the trained machine learning model to generate the final depth result.

[0047] To achieve the above objectives, another aspect of the present invention provides an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method described above.

[0048] To achieve the above objectives, another aspect of the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods described above.

[0049] This invention also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium and execute the computer instructions, causing the computer device to perform the aforementioned method.

[0050] The embodiments of this invention include at least the following beneficial effects: This invention provides a method and system for inverting the depth of ice surface meltwater. This method acquires the ICESat-2 ATL03 photon dataset and performs preliminary denoising to obtain target photon data; it then separates the meltwater surface and bottom photons from the preliminarily denoised target photon data to obtain meltwater surface photons and meltwater bottom photons; it further denoises the meltwater surface photons and performs a first ice surface meltwater retrieval; it then denoises the meltwater bottom photons and performs a second ice surface meltwater retrieval; based on the results of the first and second ice surface meltwater retrievals, it removes shallow meltwater and slush from the ice surface meltwater window; it acquires multispectral image data and combines it with meltwater depth to generate machine learning model training data; based on the multispectral image data, it inputs the meltwater band reflectivity into the trained machine learning model to generate the final depth result. The embodiments of this invention can invert the depth of ice surface meltwater over a large area with high temporal resolution and high accuracy, obtaining spatially well-covered and highly accurate ice surface meltwater depth information. Attached Figure Description

[0051] Figure 1 This is a schematic diagram of an implementation environment provided by an embodiment of the present invention;

[0052] Figure 2 This is a flowchart of the overall steps provided in the embodiments of the present invention;

[0053] Figure 3 This is a diagram illustrating the implementation process of the present invention in a specific application scenario.

[0054] Figure 4 This is a schematic diagram showing the results of different methods provided in the embodiments of the present invention for estimating meltwater depth using Landsat8 L1 data, and comparing them one-dimensionally with ICESat-2 meltwater depth data after refraction correction.

[0055] Figure 5 This is a schematic diagram showing a two-dimensional comparison between the depth estimated on test ice lake 2 using different methods provided in this embodiment of the invention and ArcticDEM data;

[0056] Figure 6 This is a schematic diagram of the hardware structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this invention clearer, the 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 merely illustrative of the invention and are not intended to limit the invention. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of this invention; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this invention as detailed in the appended claims.

[0058] It is understood that the terms "first," "second," "third," "fourth," etc. (if present) in the specification and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data used can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0059] It should be understood that in this invention, "at least one (item)" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0060] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein is for the purpose of describing embodiments of the invention only and is not intended to limit the invention.

[0061] The ice meltwater depth inversion method and system provided in this invention relates to the field of remote sensing geoscience applications. The ice meltwater depth inversion method provided in this invention can be applied to a terminal, a server, or software running on a terminal or server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or vehicle terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster composed of multiple physical servers, or a distributed system. It can also be configured as a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application that implements the ice meltwater depth inversion method, but is not limited to the above forms.

[0062] This invention can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This invention can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This invention can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0063] like Figure 1 The diagram shown is a schematic representation of an implementation environment provided by an embodiment of the present invention. (Refer to...) Figure 1 The implementation environment includes at least one terminal 102 and a server 101. The terminal 102 and the server 101 can be connected via a network, either wirelessly or via a wired connection, to complete data transmission and exchange.

[0064] Server 101 can be a standalone physical server, a server cluster or distributed system consisting 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 communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0065] Additionally, server 101 can also be a node server in a blockchain network. Blockchain is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms.

[0066] Terminal 102 can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, etc. It can also be a vehicle-mounted terminal of the various device types described above, but is not limited to these. Terminal 102 and server 101 can be directly or indirectly connected via wired or wireless communication, and this embodiment of the invention does not impose any limitations.

[0067] Exemplary based on Figure 1The implementation environment shown in this embodiment of the invention provides a method for inverting the depth of ice meltwater. The following description uses the application of this method to server 101 as an example. It can be understood that this method can also be applied to terminal 102.

[0068] Reference Figure 2 , Figure 2 The flowchart illustrates a method for retrieving ice meltwater depth applied to a server, as provided in this embodiment of the invention. The execution subject of this method can be any of the aforementioned computer devices (including a server or terminal). (Refer to...) Figure 2 The method may include the following steps:

[0069] The ICESat-2 ATL03 photon dataset was acquired and preliminarily denoised to obtain the target photon data;

[0070] Photon separation of the meltwater surface and meltwater bottom is performed on the target photon data after preliminary denoising to obtain meltwater surface photons and meltwater bottom photons;

[0071] The photons on the meltwater surface are denoised and the first meltwater search on the ice surface is performed.

[0072] The photons at the bottom of the meltwater are denoised, and a second search for meltwater on the ice surface is performed.

[0073] Based on the results of the first and second ice surface meltwater searches, shallow meltwater and slush removal processes are applied to the ice surface meltwater window.

[0074] Acquire multispectral image data and combine it with meltwater depth to generate machine learning model training data. Input the meltwater band reflectance based on the multispectral image data into the trained machine learning model to generate the final depth result.

[0075] In some embodiments, acquiring the ICESat-2 ATL03 photon dataset and performing preliminary denoising to obtain the target photon data includes the following steps:

[0076] Download the ICESat-2 ATL03 photon dataset for the target location;

[0077] The acquired photon dataset was initially denoised using the DRAGANN algorithm.

[0078] In some embodiments, the step of separating the meltwater surface and meltwater bottom photons from the preliminarily denoised target photon data to obtain meltwater surface photons and meltwater bottom photons includes the following steps:

[0079] The photons after initial noise reduction are divided into 40m processing windows along the orbit with a step size of 20m.

[0080] Within each processing window, photon nuclear density estimation is performed along the vertical height; the formula for calculating the photon nuclear density estimate is as follows: in, This is the probability density estimate at photon point x, where n is the number of samples, h is the smoothing parameter called bandwidth, which controls the width of the kernel function; K is the kernel function; the expression for the kernel function K is: Where u represents It is data point x i The standardized distance from point x;

[0081] Find all points where the corresponding photon nuclear density estimate is the minimum value in the photon nuclear density estimation curve, take their elevation values, and use the maximum value among these elevation values ​​as the threshold.

[0082] Photons with an elevation less than the threshold are considered to be bottom photons of the meltwater, while photons with an elevation greater than the threshold are considered to be surface photons of the meltwater.

[0083] In some embodiments, the denoising process for the photons on the meltwater surface and the first meltwater retrieval on the ice surface include the following steps:

[0084] The 3δ iterative method is used to remove noise photons from the meltwater surface photons;

[0085] When the standard deviation of the photon elevation on the meltwater surface within the processing window is less than 0.12m, the window is considered a meltwater surface window;

[0086] If the distance between two meltwater windows is within 40 meters, they are grouped together.

[0087] Fill each group of meltwater surface windows, and select the meltwater surface window group containing more than 5 windows as the result of the first search for ice surface meltwater.

[0088] In some embodiments, the denoising process for the bottom photons of the meltwater and the second search for meltwater on the ice surface include the following steps:

[0089] First, a Savitzky-Goliay filter is used to generate a fitted curve for the bottom photons. Then, the fitted value is subtracted from the photon height to eliminate the tendency of the bottom photons. The expression for the Savitzky-Goliay filter is as follows: Among them, y i ′ This is the filtered elevation value; y i+j It is the elevation value in the original photon; c j The weighting coefficients of the filter are m, which is the number of points on both sides of the window.

[0090] Remove all bottom photons within 1m below the meltwater surface elevation to avoid the multi-curved surface reflection phenomenon affecting the final extracted meltwater depth;

[0091] Within each meltwater surface window, all photons below the median bottom photon elevation are removed. Then, 3δ iterations are performed in the vertical direction to remove noisy photons, and denoising is performed in the horizontal direction using an elliptical filter kernel.

[0092] If the number of bottom photons in a meltwater window is greater than 10, the window is considered a meltwater window on the ice surface.

[0093] These ice meltwater windows are grouped according to the same criteria as the meltwater windows obtained in the first ice meltwater search.

[0094] In some embodiments, the process of removing shallow meltwater and slush from the ice surface meltwater window based on the results of the first and second ice surface meltwater searches includes the following steps:

[0095] Photons whose first elevation value on both sides of each set of ice meltwater windows exceeds three times the standard deviation of the surface elevation value are retained and used as the edge of the ice meltwater.

[0096] Connect the edge of the meltwater bottom to the meltwater surface, and then generate the final meltwater bottom again using Savitzky-Golay filtering;

[0097] A refractive index of ~1.33 is used to eliminate the refraction effect of meltwater at the height of photons at the bottom of the meltwater.

[0098] Remove meltwater pools with an average depth of less than 1.15m.

[0099] In some embodiments, acquiring multispectral image data and combining it with meltwater depth to generate machine learning model training data, inputting the meltwater band reflectance into the trained machine learning model based on the multispectral image data, and generating the final depth result includes the following steps:

[0100] Acquire multispectral images that correspond to the ATL03 images in time and space, including four types of images: Landsat8 L1 / L2 and Sentinel2 L1C / L2A. These images are no more than 4 days apart from the ATL03 data in time.

[0101] Training data is generated using the median of the depth sampling point within an image pixel and its multi-band reflectance; for Landsat-8, the median depth is paired with the reflectance values ​​of 7 bands; for Sentinel-2, the low-resolution bands are first uniformly sampled to 10m, and the median depth is paired with the reflectance values ​​of 9 bands.

[0102] The training parameters of the two machine learning algorithms, XGBoost and LightGBM, were manually adjusted. The training data was input to obtain the meltwater depth inversion machine learning model. Then, the meltwater band reflectance was input into the model based on multispectral imagery to generate the final depth result.

[0103] The specific implementation process of this invention will be described in detail below using a specific application scenario as an example:

[0104] To monitor the volume and spatial distribution of meltwater on the ice surface, this invention proposes a method that combines ICESat-2 ATL03 photon data and multispectral imagery using a machine learning model. This method enables large-area, high-temporal-resolution, and high-precision inversion of meltwater depth on the ice surface.

[0105] The purpose of this invention is to provide a method for retrieving ice meltwater depth over a large area with high temporal resolution and high accuracy. With the support of machine learning technology, it can obtain ice meltwater depth information with good spatial coverage and high accuracy from multispectral image data such as Landsat8 and Sentinel l2.

[0106] Specifically, the ice surface meltwater depth inversion method based on ICESat-2 and multispectral image datasets of the present invention, such as... Figure 3 As shown, the following steps may be included:

[0107] Step 1: Acquire a total of 15 ICESat-2 ATL03 photon datasets, which are spatially concentrated in the dense meltwater area of ​​the southwestern Greenland ice sheet and in the summer (June-August) of 2019-2022. The acquired ATL03 photon datasets are subjected to preliminary denoising processing using the DRAGANN algorithm to facilitate subsequent meltwater retrieval and meltwater depth extraction.

[0108] Step 2: The initially denoised photons are divided into 40m processing windows along the trajectory with a step size of 20m. Within each processing window, photon nuclear density estimation (KDE) is performed vertically, with a bin width of 0.1m. Then, we find all points where the corresponding KDE value is a minimum value in the KDE curve and take their elevation values. We use the maximum value among these elevation values ​​as a threshold. Photons with elevations less than the threshold are considered bottom meltwater photons, and photons with elevations greater than the threshold are considered surface meltwater photons. The photon KDE formula is as follows:

[0109]

[0110] in, This is the probability density estimate at photon point x, where n is the number of samples, h is the smoothing parameter called bandwidth, which controls the width of the kernel function. K is the kernel function; in this experiment, a Gaussian kernel is used, and its formula is as follows:

[0111]

[0112] Step 3: Noise photons in the meltwater surface photons are removed using the 3δ iteration method. When the standard deviation of the surface photon elevation within the processing window is less than 0.12m, the window is considered a meltwater surface window. If the distance between two meltwater surface windows is within 40 meters, they are grouped together. Subsequently, each group of meltwater surface windows is filled, and groups containing more than 5 windows are selected as the results of the first retrieval of ice surface meltwater.

[0113] Step 4: First, a fitted curve for bottom photons is generated using a Savitzky-Golay filter. Then, the fitted value is subtracted from the photon height to eliminate the trend of bottom photons. Subsequently, all bottom photons within 1m below the meltwater surface elevation are removed to avoid the influence of multi-curved surface reflection on the final extracted meltwater depth. All photons below the median elevation of bottom photons are removed within each meltwater surface window. Then, 3δ iterations are performed in the vertical direction to remove noisy photons, and denoising is performed in the horizontal direction using an elliptical filter kernel. If the number of bottom photons in a meltwater surface window is greater than 10, the window is considered a meltwater window. Finally, these meltwater windows are grouped according to the same criteria as the meltwater surface windows in step (3). The Savitzky-Golay filter formula is as follows:

[0114]

[0115] y i ′ This is the filtered elevation value, y i+j It is the elevation value in the original photon, c j The weighting coefficients m of the filter are the number of points on both sides of the window. Assume the length of the input window is N, i.e., N = 2m + 1.

[0116] Step 5: Retain the photons whose elevation values ​​on both sides of each set of ice meltwater windows exceed three times the standard deviation of the surface elevation values, and use these as the edges of the ice meltwater. Then, connect the meltwater bottom edges to the meltwater surface and generate the final meltwater bottom again using Savitzky-Golay filtering. Next, apply a refractive index of ~1.33 to the height of the meltwater bottom photons to eliminate the refraction effect of the meltwater. Shallow meltwater (or slush areas) is too noisy; to improve the confidence of the meltwater pool depth estimation, meltwater pools with an average depth less than 1.15m are removed. Finally, we output the location of the ice meltwater, the signal photons (including location and elevation values) of the meltwater surface and meltwater bottom, the meltwater surface elevation, and the generated meltwater bottom.

[0117] Step 6: Acquire multispectral images that correspond to the ATL03 imagery in both time and space, including four types of images: Landsat 8 L1 / L2 and Sentinel 2 L1C / L2A. These images should be within four days of the ATL03 data. Use the median depth sampled at a single image pixel to generate training data based on its multiband reflectance. For Landsat-8, pair the median depth with reflectance values ​​for seven bands (bands 1, 2, 3, 4, 5, 6, and 7). For Sentinel-2, first uniformly sample the low-resolution bands to 10m, and then pair the median depth with reflectance values ​​for nine bands (bands 2, 3, 4, 5, 6, 7, 8, 11, and 12). Finally, manually adjust the training parameters of the XGBoost and LightGBM machine learning algorithms, input the training data, and derive the meltwater depth inversion machine learning model. Then, input the meltwater band reflectance from the multispectral imagery into the model to generate the final depth result.

[0118] Figure 4 The content describes different methods, including the method of this invention, for estimating one-dimensional meltwater depth using Landsat 8 L1 data, and compares them one-dimensionally with ICESat-2 meltwater depth data after refraction correction. Figure 4 The results show that the method of this invention achieves the best accuracy on Landsat-8L1 imagery. The RMSE calculated by the method of this invention using the refraction-corrected ICESat-2 meltwater depth verification data is 1.68m, 0.66m, and 0.09m lower than the traditional lake depth inversion methods Red-RTE, Green-RTE, and SBR, respectively.

[0119] Figure 5 The content describes the two-dimensional depth estimation results of different methods provided in the embodiments of the present invention on test ice lake 2, and compares them with ArcticDEM data in two dimensions. Figure 5The content shows that, whether on Landsat-8L1 or Sentinel-2L1C imagery, the two-dimensional ice surface lake depth derived by the method of this invention is closer to the validation data ArcticDEM than traditional algorithms.

[0120] Table 1 shows the one-dimensional evaluation results of the meltwater depth accuracy of different algorithms on four types of multispectral images. The results indicate that, except for L2 data, the machine learning method proposed in this invention achieves better accuracy in testing ice surface meltwater than traditional methods based solely on multispectral images, such as RTE and SBR. XGBoost shows the highest accuracy when applied to the Sentinel l-2L1C image, with RMSE, MAE, and MedAE of 0.54m, 0.43m, and 0.36m, respectively, demonstrating the superiority of the proposed method. This method is expected to provide a more effective method for estimating ice surface meltwater depth and lay the foundation for accurate quantification of large surface area meltwater in subsequent research.

[0121] Table 1. Evaluation results of meltwater depth accuracy of different algorithms on four types of multispectral images.

[0122]

[0123] Another aspect of this invention provides a system for inverting the depth of ice meltwater, comprising:

[0124] The first module is used to acquire the ICESat-2 ATL03 photon dataset and perform preliminary denoising to obtain the target photon data;

[0125] The second module is used to separate the meltwater surface and meltwater bottom photons from the target photon data after preliminary denoising, so as to obtain meltwater surface photons and meltwater bottom photons.

[0126] The third module is used to perform noise reduction processing on the photons on the meltwater surface and to perform the first ice meltwater retrieval.

[0127] The fourth module is used to denoise the photons at the bottom of the meltwater and to perform a second search for meltwater on the ice surface.

[0128] The fifth module is used to perform shallow meltwater and slush removal processing on the ice surface meltwater window based on the results of the first ice surface meltwater retrieval and the second ice surface meltwater retrieval.

[0129] The sixth module is used to acquire multispectral image data and combine it with meltwater depth to generate machine learning model training data. Based on the multispectral image data, the meltwater band reflectance is input into the trained machine learning model to generate the final depth result.

[0130] It is understood that the content of the above method embodiments is applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0131] This invention also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method for inverting the depth of ice meltwater. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0132] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0133] Please see Figure 6 , Figure 6 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes:

[0134] The processor 601 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present invention.

[0135] The memory 602 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 602 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 602 and is called and executed by the processor 601 to execute the ice meltwater depth inversion method of the embodiments of this invention.

[0136] The input / output interface 603 is used to implement information input and output;

[0137] The communication interface 604 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0138] Bus 605 transmits information between various components of the device (e.g., processor 601, memory 602, input / output interface 603, and communication interface 604);

[0139] The processor 601, memory 602, input / output interface 603, and communication interface 604 are connected to each other within the device via bus 605.

[0140] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for inverting the depth of ice meltwater.

[0141] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0142] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0143] It should be noted that in various specific embodiments of the present invention, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of the present invention require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to a confirmation page. Only after obtaining the user's separate permission or consent is the necessary user-related data for the normal operation of the embodiments of the present invention acquired.

[0144] The embodiments described in this invention are for the purpose of more clearly illustrating the technical solutions of the embodiments of this invention, and do not constitute a limitation on the technical solutions provided by the embodiments of this invention. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this invention are also applicable to similar technical problems.

[0145] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present invention, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0146] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0147] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0148] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0149] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0150] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0151] If the integrated unit is implemented as 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 all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or 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 capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0152] The preferred embodiments of the present invention have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present invention. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and spirit of the present invention should be within the scope of the claims of the present invention.

Claims

1. A method for inverting the depth of ice surface meltwater, characterized in that, Includes the following steps: The ICESat-2 ATL03 photon dataset was acquired and preliminarily denoised to obtain the target photon data; Photon separation of the meltwater surface and meltwater bottom is performed on the target photon data after preliminary denoising to obtain meltwater surface photons and meltwater bottom photons; The photons on the meltwater surface are denoised and the first meltwater search on the ice surface is performed. The photons at the bottom of the meltwater are denoised, and a second search for meltwater on the ice surface is performed. Based on the results of the first and second ice surface meltwater searches, shallow meltwater and slush removal processes are applied to the ice surface meltwater window. Acquire multispectral image data and combine it with meltwater depth to generate machine learning model training data. Input the meltwater band reflectance based on the multispectral image data into the trained machine learning model to generate the final depth result. The noise reduction process for the photons on the meltwater surface and the initial meltwater search on the ice surface include the following steps: The 3δ iterative method is used to remove noise photons from the meltwater surface photons; When the standard deviation of the photon elevation on the meltwater surface within the processing window is less than 0.12m, the window is considered a meltwater surface window; If the distance between two meltwater windows is within 40 meters, they are grouped together. Fill each group of meltwater surface windows, and select the meltwater surface window group containing more than 5 windows as the result of the first search for ice surface meltwater; The noise reduction process for the bottom photons of the meltwater and the second search for meltwater on the ice surface include the following steps: First, a fitted curve for the bottom photons is generated using a Savitzky-Golay filter. Then, the fitted value is subtracted from the photon height to eliminate the tendency of the bottom photons. The expression for the Savitzky-Golay filter is as follows: ,in, This is the filtered elevation value; It is the elevation value in the original photon; These are the weighting coefficients of the filter; It is the number of points on both sides of the window; , Represents the number of samples; Remove all bottom photons within 1m below the meltwater surface elevation to avoid the multi-curved surface reflection phenomenon affecting the final extracted meltwater depth; Within each meltwater surface window, all photons below the median bottom photon elevation are removed. Then, 3δ iterations are performed in the vertical direction to remove noisy photons, and denoising is performed in the horizontal direction using an elliptical filter kernel. If the number of bottom photons in a meltwater window is greater than 10, the window is considered a meltwater window on the ice surface. These ice meltwater windows are grouped according to the same criteria as the meltwater windows obtained in the first ice meltwater search.

2. The method for inverting the depth of ice surface meltwater according to claim 1, characterized in that, The process of acquiring the ICESat-2ATL03 photon dataset and performing preliminary denoising to obtain the target photon data includes the following steps: Download the ICESat-2 ATL03 photon dataset for the target location; The acquired photon dataset was initially denoised using the DRAGANN algorithm.

3. The method for inverting the depth of ice surface meltwater according to claim 1, characterized in that, The process of separating the meltwater surface and meltwater bottom photons from the preliminarily denoised target photon data to obtain meltwater surface photons and meltwater bottom photons includes the following steps: The photons after initial noise reduction are divided into 40m processing windows along the orbit with a step size of 20m. Within each processing window, photon nuclear density estimation is performed along the vertical height; the formula for calculating the photon nuclear density estimate is as follows: ,in, At the photon point Probability density estimation at [location] It is the number of samples. It is a smoothing parameter, called bandwidth, which controls the width of the kernel function; It is a kernel function; kernel function The expression is: ,in, represent , is data point x i The normalized gap from photon point x; Find all points where the corresponding photon nuclear density estimate is the minimum value in the photon nuclear density estimation curve, take their elevation values, and use the maximum value among these elevation values ​​as the threshold. Photons with an elevation less than the threshold are considered to be bottom photons of the meltwater, while photons with an elevation greater than the threshold are considered to be surface photons of the meltwater.

4. The method for inverting the depth of ice meltwater according to claim 1, characterized in that, The process of removing shallow meltwater and slush from the ice surface meltwater window based on the results of the first and second ice surface meltwater searches includes the following steps: Photons whose first elevation value on both sides of each set of ice meltwater windows exceeds three times the standard deviation of the surface elevation value are retained and used as the edge of the ice meltwater. Connect the edge of the meltwater bottom to the meltwater surface, and then generate the final meltwater bottom again using Savitzky-Golay filtering; A refractive index of ~1.33 is used to eliminate the refraction effect of meltwater at the height of photons at the bottom of the meltwater. Remove meltwater pools with an average depth of less than 1.15 m.

5. The method for inverting the depth of ice surface meltwater according to claim 1, characterized in that, The process of acquiring multispectral image data, combining it with meltwater depth to generate machine learning model training data, and inputting the meltwater band reflectance into the trained machine learning model based on the multispectral image data to generate the final depth result includes the following steps: Acquire multispectral images that correspond to the ATL03 images in time and space, including four types of images: Landsat8 L1 / L2 and Sentinel2 L1C / L2A. These images are no more than 4 days apart from the ATL03 data in time. Training data is generated using the median of the depth sampling point within an image pixel and its multi-band reflectance; for Landsat-8, the median depth is paired with the reflectance values ​​of 7 bands; for Sentinel-2, the low-resolution bands are first uniformly sampled to 10m, and the median depth is paired with the reflectance values ​​of 9 bands. The training parameters of the two machine learning algorithms, XGBoost and LightGBM, were manually adjusted. The training data was input to obtain the meltwater depth inversion machine learning model. Then, the meltwater band reflectance was input into the model based on multispectral imagery to generate the final depth result.

6. A system for implementing the ice surface meltwater depth inversion method as described in any one of claims 1-5, characterized in that, include: The first module is used to acquire the ICESat-2 ATL03 photon dataset and perform preliminary denoising to obtain the target photon data; The second module is used to separate the meltwater surface and meltwater bottom photons from the target photon data after preliminary denoising, so as to obtain meltwater surface photons and meltwater bottom photons. The third module is used to perform noise reduction processing on the photons on the meltwater surface and to perform the first ice meltwater retrieval. The fourth module is used to denoise the photons at the bottom of the meltwater and to perform a second search for meltwater on the ice surface. The fifth module is used to perform shallow meltwater and slush removal processing on the ice surface meltwater window based on the results of the first ice surface meltwater retrieval and the second ice surface meltwater retrieval. The sixth module is used to acquire multispectral image data and combine it with meltwater depth to generate machine learning model training data. Based on the multispectral image data, the meltwater band reflectance is input into the trained machine learning model to generate the final depth result.

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

8. A computer-readable storage medium, characterized in that, The storage medium stores a program that is executed by a processor to implement the method as described in any one of claims 1 to 5.

Images