Submarine topography quality evaluation system and method based on multi-dimensional indexes

Abstract

The invention provides a submarine topography quality evaluation system and method based on a multi-dimensional index, and the system comprises a shipborne water depth precision verification module which is used for carrying out the refinement processing of shipborne water depth data, calculating the root-mean-square error of a submarine topography product to be evaluated and the shipborne water depth data, and obtaining the precision index of a submarine topography inversion product; the terrain structure similarity matching module is used for comparing the structure similarity indexes of the submarine topography product to be evaluated and the authoritative terrain model to obtain the structure similarity index of the submarine topography inversion product; and the geological boundary goodness of fit comparison module is used for aligning the fault zone boundary predicted by the submarine topography inversion product with the geological structure label data space, calculating the F1-score of the predicted fault zone boundary and the geological structure label, and obtaining the geological boundary goodness of fit index of the submarine topography to be evaluated. The method has the advantage that multi-dimensional, comprehensive and comprehensive submarine topography quality evaluation information can be obtained.

Description

Technical Field

[0001] This application belongs to the field of marine remote sensing mapping, and specifically relates to a seabed terrain quality evaluation system and method based on multi-dimensional indicators. Background Art

[0002] Seabed terrain is important basic data for marine geographic information. High-quality terrain data is required for marine resource exploration, seabed pipeline laying, navigation safety, etc. Otherwise, it may lead to wrong decisions, such as inaccurate resource positioning, engineering accidents or navigation hazards. In addition, seabed terrain data also plays an important role in climate change research and geological disaster early warning (such as tsunamis), and the data quality directly affects the accuracy of these models. According to the statistics of the United Nations Decade of Ocean Science (2021 - 2030), about 40% of the global marine mapping data has not been effectively utilized due to quality problems, highlighting the urgency of quality evaluation.

[0003] Currently, the seabed terrain quality evaluation method mainly relies on shipborne sounding data for spot checks of local areas, lacking a systematic evaluation of the whole area, and focusing on absolute accuracy (such as RMSE) or resolution (such as grid size). This leads to the current seabed terrain model products only focusing on improving the numerical values of accuracy or resolution indicators, and performing poorly in details of geomorphic features such as terrain structure and geological boundaries. With the continuous development of seabed terrain detection technologies (such as multibeam sounding, high-resolution satellite altimetry gravity prediction), the quality of seabed terrain model products has been gradually improved. In order to comprehensively measure the quality of seabed terrain products, a more systematic multi-dimensional indicator seabed terrain quality evaluation system is needed. However, the single accuracy indicator commonly used in existing seabed terrain quality evaluation methods does not consider detail feature indicators such as terrain structure similarity and geological boundary coincidence, and a seabed terrain quality evaluation system based on multi-dimensional indicators has not been established. Summary of the Invention

[0004] The purpose of this application is to overcome the deficiency of only using a single accuracy indicator in existing seabed terrain quality evaluation, and establish a multi-dimensional indicator seabed terrain quality evaluation system including terrain structure similarity and geological boundary coincidence.

[0005] To achieve the above purpose, this application proposes a seabed terrain quality evaluation system based on multi-dimensional indicators, including:

[0006] A shipborne sounding accuracy verification module, which is used to refine the shipborne sounding data, calculate the root mean square error between the seabed terrain product to be evaluated and the shipborne sounding data, and obtain the accuracy indicator of the seabed terrain inversion product;

[0007] The topographic structure similarity matching module is used to determine the comparison area range by matching the submarine topographic product to be evaluated with the global authoritative topographic model, compare the structure similarity index between the submarine topographic product to be evaluated and the authoritative topographic model, and obtain the structure similarity index of the submarine topographic inversion product;

[0008] The geological boundary coincidence degree comparison module: is used to spatially align the predicted fault zone boundary of the submarine topographic inversion product with the geological structure label data, calculate the F1-score between the predicted fault zone boundary and the geological structure label, and obtain the geological boundary coincidence degree index of the submarine topographic product to be evaluated.

[0009] As an improvement of the above system, the processing process of the shipborne bathymetric accuracy verification module includes:

[0010] Step A1: Perform long-wave error correction and datum unification on the shipborne bathymetric data according to the sounding line time, longitude and latitude information, and the effective water depth value range to suppress noise, and obtain the refined shipborne bathymetric data;

[0011] Step A2: Combine the land-sea mask information, calculate the root mean square error between the submarine topographic product to be evaluated and the shipborne bathymetric data, and obtain the accuracy index of the submarine topographic inversion product :

[0012]

[0013] Wherein, is the shipborne bathymetric value of the th verification point; is the submarine topographic value of the product to be evaluated at the th verification point; is the land-sea mask value of the th verification point; is the total number of verification points.

[0014] As an improvement of the above system, the processing process of the topographic structure similarity matching module includes:

[0015] Step B1: Match the global authoritative topographic model according to the longitude and latitude of the submarine topographic product to be evaluated to the same spatial range and resolution to ensure that the evaluation areas completely coincide;

[0016] Step B2: Taking the authoritative topographic model as a reference, compare the structure similarity index between the inverted topography and the reference topography, and obtain the structure similarity index of the submarine topographic inversion product :

[0017]

[0018] Wherein, respectively represent the inverted topography and the reference topography The mean value; respectively represent the standard deviation of the inverted topography and the reference topography and the covariance between the two; is the stability constant.

[0019] As an improvement to the above system, the value of the stability constant is:

[0020] ,

[0021] wherein, is the difference between the maximum and minimum values of the topography within the evaluation area.

[0022] As an improvement to the above system, the processing process of the geological boundary matching degree comparison module includes:

[0023] Step C1: Unify the coordinate system, resample and crop the fault zone boundary predicted by the seabed topography inversion product and the geological structure label data to achieve consistency in spatial reference, resolution and range;

[0024] Step C2: Calculate the F1-score of the fault zone boundary predicted by the seabed topography inversion product and the geological structure label to obtain the geological boundary matching degree index of the seabed topography to be evaluated:

[0025]

[0026] wherein, P represents the precision rate:

[0027]

[0028] R represents the recall rate:

[0029]

[0030] wherein, is the number of pixels predicted as the boundary and with the true label as the boundary; is the number of pixels predicted as the boundary but with the true label as non-boundary; is the number of pixels with the true label as the boundary but predicted as non-boundary.

[0031] This application also provides a seabed topography quality evaluation method based on multi-dimensional indicators, implemented based on the above system, including:

[0032] Step 1: Perform long-wave error correction and datum unification on the ship-measured water depth data according to the sounding line time, longitude and latitude information and the effective water depth range to suppress noise, and obtain the refined ship-measured water depth data;

[0033] Step 2: Combine the land-sea mask information, calculate the root mean square error between the submarine terrain product to be evaluated and the ship-measured bathymetric data, and obtain the accuracy index of the submarine terrain inversion product;

[0034] Step 3: Match the global authoritative terrain model to the same spatial range and resolution according to the longitude and latitude of the submarine terrain product to be evaluated, ensuring that the evaluation areas completely coincide;

[0035] Step 4: Taking the authoritative terrain model as a reference, compare the structural similarity index between the inverted terrain and the reference terrain, and obtain the structural similarity index of the submarine terrain inversion product;

[0036] Step 5: Unify the coordinate systems, resample and crop the fracture zone boundaries predicted by the submarine terrain inversion product and the geological structure label data to achieve consistency in spatial reference, resolution, and range;

[0037] Step 6: Calculate the F1-score between the fracture zone boundaries predicted by the submarine terrain inversion product and the geological structure labels to obtain the geological boundary coincidence index of the submarine terrain to be evaluated.

[0038] Compared with the prior art, the advantages of this application are as follows:

[0039] 1. The submarine terrain quality evaluation system based on multi-dimensional indicators proposed in this application embeds a terrain structure similarity matching module and a geological boundary coincidence comparison module, and constructs a quantitative and extensible submarine terrain quality evaluation system.

[0040] 2. The submarine terrain quality evaluation method based on multi-dimensional indicators proposed in this application introduces terrain detail feature indicators such as terrain structure similarity and geological boundary coincidence during traditional accuracy evaluation, and can obtain multi-dimensional, comprehensive, and comprehensive submarine terrain quality evaluation information. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 Shown is the structural diagram of the submarine terrain quality evaluation system based on multi-dimensional indicators;

[0042] Figure 2 Shown is the flowchart of the submarine terrain quality evaluation method based on multi-dimensional indicators. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] The technical solutions of this application will be described in detail below with reference to the accompanying drawings.

[0044] The submarine terrain quality evaluation system and method based on multi-dimensional indicators proposed in this application introduce terrain detail feature indicators such as terrain structure similarity and geological boundary coincidence during traditional accuracy evaluation, construct a quantitative and extensible submarine terrain quality evaluation system, and can obtain multi-dimensional, comprehensive, and comprehensive submarine terrain quality evaluation information.

[0045] Example 1

[0046] As Figure 1 shown, this application proposes a seabed terrain quality evaluation system based on multi-dimensional indicators, including a ship-measured water depth accuracy verification module, a terrain structure similarity matching module, and a geological boundary coincidence degree comparison module.

[0047] The design of each module is as follows:

[0048] 1. Ship-measured water depth accuracy verification module: After refining the ship-measured water depth data, it calculates the root mean square error between the seabed terrain product to be evaluated and the ship-measured water depth data to obtain the accuracy index of the seabed terrain inversion product;

[0049] The processing process of the ship-measured water depth accuracy verification module includes:

[0050] Step 1: Refine the ship-measured data; correct the long-wave error and unify the reference of the ship-measured water depth data according to the survey line time, longitude and latitude information, and the effective water depth range to suppress noise, and obtain the refined ship-measured water depth data;

[0051] Step 2: Calculate the accuracy index; combine the land-sea mask information to calculate the root mean square error between the seabed terrain product to be evaluated and the ship-measured water depth data, and obtain the accuracy index of the seabed terrain inversion product.

[0052]

[0053] In the formula, is the ship-measured water depth value of the th verification point; is the seabed terrain value of the product to be evaluated at the th verification point; is the land-sea mask value of the th verification point, 0 for land and 1 for ocean; is the total number of verification points.

[0054] 2. Terrain structure similarity matching module: It is used to match the global authoritative terrain model according to the seabed terrain product to be evaluated to determine the comparison area range, and compare the structure similarity index between the seabed terrain product to be evaluated and the authoritative terrain model to obtain the structure similarity index of the seabed terrain inversion product;

[0055] The processing process of the terrain structure similarity matching module includes:

[0056] Step 1: Match the terrain comparison area; match the global authoritative terrain model to the same spatial range and resolution according to the longitude and latitude of the seabed terrain product to be evaluated to ensure that the evaluation areas are completely coincident;

[0057] Step 2: Compare the topographic structure similarity; taking the authoritative topographic model as a reference, compare the structure similarity index between the inverted topography and the reference topography to obtain the structure similarity index of the seabed topography inversion product.

[0058]

[0059] In the formula, respectively represent the mean values of the inverted topography and the reference topography ; respectively represent and the reference topography 's standard deviation and covariance; is a stability constant, usually set to , , is the dynamic range of the topographic data, that is, the difference between the maximum and minimum values of the topography within the evaluation area.

[0060] 3. Geological boundary matching degree comparison module: used to spatially align the predicted fault zone boundary of the seabed topography inversion product with the geological structure label data, calculate the F1-score between the predicted fault zone boundary and the geological structure label, and obtain the geological boundary matching degree index of the seabed topography to be evaluated.

[0061] The processing process of the geological boundary matching degree comparison module includes:

[0062] Step 1: Geological boundary spatial alignment; unify the coordinate system, resample and crop the predicted fault zone boundary of the seabed topography inversion product and the geological structure label data to achieve consistency in spatial reference, resolution and range;

[0063] Step 2: Boundary matching degree comparison; calculate the F1-score between the predicted fault zone boundary of the seabed topography inversion product and the geological structure label to obtain the geological boundary matching degree index of the seabed topography to be evaluated.

[0064] Precision (Precision, P):

[0065]

[0066] Recall (Recall, R):

[0067]

[0068] F1-score:

[0069]

[0070] In the formula, is the number of pixels predicted as the boundary and with the true label as the boundary; The number of pixels predicted as boundaries but with true labels as non-boundaries; The number of pixels with true labels as boundaries but predicted as non-boundaries. The closer the F1-score is to 1, the higher the degree of coincidence between the predicted boundary and the USGS label, and the better the inversion accuracy.

[0071] Example 2

[0072] As Figure 2 shown, the present application also proposes a method for evaluating the quality of submarine topography based on multi-dimensional indicators, implemented based on the above system, including:

[0073] Step 1) Refine the shipborne survey data; perform long-wave error correction and datum unification on the shipborne bathymetric data according to the survey line time, longitude and latitude information, and the effective water depth range to suppress noise, and obtain the refined shipborne bathymetric data;

[0074] Step 2) Calculate the accuracy index; combine the land-sea mask information, calculate the root mean square error between the submarine topography product to be evaluated and the shipborne bathymetric data, and obtain the accuracy index of the submarine topography inversion product;

[0075] Step 3) Match the terrain comparison area; match the global authoritative terrain model to the same spatial range and resolution according to the longitude and latitude of the submarine topography product to be evaluated to ensure that the evaluation areas are completely coincident;

[0076] Step 4) Compare the terrain structure similarity; take the authoritative terrain model as a reference, compare the structure similarity index between the inverted terrain and the reference terrain, and obtain the structure similarity index of the submarine topography inversion product;

[0077] Step 5) Geologic boundary spatial alignment; unify the coordinate system, resample and crop the fault zone boundary predicted by the submarine topography inversion product and the geologic structure label data to achieve consistency in spatial reference, resolution and range;

[0078] Step 6) Boundary coincidence comparison; calculate the F1-score between the fault zone boundary predicted by the submarine topography inversion product and the geologic structure label to obtain the geologic boundary coincidence index of the submarine topography to be evaluated;

[0079] Step 7) Obtain a comprehensive evaluation of the submarine topography by integrating multi-dimensional indicators.

[0080] The present application can also provide a computer device, including: at least one processor, a memory, at least one network interface and a user interface. Each component in the device is coupled together through a bus system. It can be understood that the bus system is used to realize the connection and communication between these components. In addition to the data bus, the bus system also includes a power bus, a control bus and a status signal bus.

[0081] Among them, the user interface may include a display, a keyboard, or a pointing device. For example, a mouse, a trackball, a touchpad, or a touch screen, etc.

[0082] It can be understood that the memory in the disclosed embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchlink dynamic random access memory (SLDRAM), and direct rambus random access memory (DRRAM). The memory described herein is intended to include but not be limited to these and any other suitable types of memory.

[0083] In some embodiments, the memory stores the following elements, executable modules, or data structures, or subsets thereof, or extended sets thereof: an operating system and application programs.

[0084] Among them, the operating system includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., and is used to implement various basic services and process hardware-based tasks. The application programs include various application programs, such as a media player and a browser, etc., and are used to implement various application services. The program for implementing the method of the disclosed embodiments of the present application can be included in the application programs.

[0085] In the above embodiments, by calling the programs or instructions stored in the memory, specifically, the programs or instructions stored in the application programs, the processor is used for:

[0086] Execute the steps of the above method.

[0087] The above method can be applied to or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in the processor or the instructions in the form of software. The above processor may be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed above. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. Combining the steps of the above disclosed method can be directly embodied as being completed by the execution of the hardware decoding processor, or by the combination of the hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the above method.

[0088] It can be understood that the embodiments described in this application can be implemented by hardware, software, firmware, middleware, microcode, or a combination thereof. For hardware implementation, the processing unit can be implemented in one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers, microprocessors, other electronic units for performing the functions described in this application, or a combination thereof.

[0089] For software implementation, the technology of this application can be implemented by executing the functional modules of this application (such as procedures, functions, etc.). The software code can be stored in the memory and executed by the processor. The memory can be implemented inside or outside the processor.

[0090] The present application may also provide a non-volatile storage medium for storing a computer program. When the computer program is executed by a processor, each step in the above method embodiments can be implemented.

[0091] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and not to limit them. Although the present application has been described in detail with reference to the embodiments, those of ordinary skill in the art should understand that any modification or equivalent replacement of the technical solutions of the present application does not depart from the spirit and scope of the technical solutions of the present application, and they should all be covered by the scope of the claims of the present application.

Claims

1. A submarine terrain quality evaluation system based on multi-dimensional indicators, characterized in that, Including: A ship-measured water depth accuracy verification module, which is used to refine the ship-measured water depth data, calculate the root mean square error between the submarine topography product to be evaluated and the ship-measured water depth data, and obtain the accuracy index of the submarine topography inversion product; A terrain structure similarity matching module, which is used to determine the comparison area range by matching the global authoritative terrain model according to the submarine topography product to be evaluated, and compare the structure similarity index between the submarine topography product to be evaluated and the authoritative terrain model to obtain the structure similarity index of the submarine topography inversion product; and A geological boundary coincidence degree comparison module: which is used to spatially align the predicted fracture zone boundary of the submarine topography inversion product with the geological structure label data, calculate the F1-score between the predicted fracture zone boundary and the geological structure label, and obtain the geological boundary coincidence degree index of the submarine topography to be evaluated.

2. The submarine terrain quality evaluation system based on multi-dimensional indicators according to claim 1, characterized in that, The processing process of the ship-measured water depth accuracy verification module includes: Step A1: Perform long-wave error correction and datum unification on the ship-measured water depth data according to the sounding line time, longitude and latitude information, and the effective water depth value range to suppress noise, and obtain the refined ship-measured water depth data; Step A2: Combine the land and sea mask information, calculate the root mean square error between the submarine topography product to be evaluated and the shipborne bathymetric data, and obtain the accuracy index of the submarine topography inversion product : ； Among them, is the ship-measured water depth value of the th verification point; is the seabed terrain value of the product to be evaluated at the th verification point; is the land-sea mask value of the th verification point; is the total number of verification points.

3. The seabed terrain quality evaluation system based on multi-dimensional indicators according to claim 1, characterized in that The processing process of the terrain structure similarity matching module includes: Step B1: Match the global authoritative terrain model according to the longitude and latitude of the submarine topography product to be evaluated to the same spatial range and resolution to ensure that the evaluation areas completely coincide; Step B2: Taking the authoritative topographic model as a reference, compare the structural similarity index between the inverted topography and the reference topography to obtain the structural similarity index of the seabed topography inversion product : ； Among them, respectively represent the mean value of the inverted terrain and the reference terrain ; respectively represent the standard deviation of the inverted terrain and the reference terrain and the covariance between the two; is the stability constant.

4. The submarine terrain quality evaluation system based on multi-dimensional indicators according to claim 3, characterized in that The value of the stability constant is: 、 ； Among them, is the difference between the maximum and minimum values of the terrain in the evaluation area.

5. The seabed terrain quality evaluation system based on multi-dimensional indicators according to claim 1, characterized in that The processing process of the geological boundary coincidence degree comparison module includes: Step C1: Unify the coordinate system, resample and crop the predicted fracture zone boundary of the submarine topography inversion product and the geological structure label data to achieve consistency in spatial reference, resolution and range; Step C2: Calculate the F1-score between the predicted fracture zone boundary of the submarine topography inversion product and the geological structure label to obtain the geological boundary coincidence degree index of the submarine topography to be evaluated: ； Where P represents precision: ； R represents recall: ； Among them, is the number of pixels predicted as boundaries and with true labels as boundaries; is the number of pixels predicted as boundaries but with true labels as non-boundaries; is the number of pixels with true labels as boundaries but predicted as non-boundaries.

6. A method for evaluating the quality of submarine topography based on multi-dimensional indicators, implemented based on the system according to any one of claims 1-5, including: Step 1: Perform long-wave error correction and datum unification on the ship-measured water depth data according to the sounding line time, longitude and latitude information, and the effective water depth value range to suppress noise, and obtain the refined ship-measured water depth data; Step 2: Combine the land-sea mask information, calculate the root mean square error between the submarine topography product to be evaluated and the ship-measured water depth data, and obtain the accuracy index of the submarine topography inversion product; Step 3: Match the global authoritative terrain model according to the longitude and latitude of the submarine topography product to be evaluated to the same spatial range and resolution to ensure that the evaluation areas completely coincide; Step 4: Taking the authoritative terrain model as a reference, compare the structure similarity index between the inverted terrain and the reference terrain to obtain the structure similarity index of the submarine topography inversion product; Step 5: Unify the coordinate system, resample and crop the predicted fracture zone boundary of the submarine topography inversion product and the geological structure label data to achieve consistency in spatial reference, resolution and range; Step 6: Calculate the F1-score between the predicted fracture zone boundary of the submarine topography inversion product and the geological structure label to obtain the geological boundary coincidence degree index of the submarine topography to be evaluated.

Images