A method and system for selecting a site for a marine engineering demonstration area based on machine learning

Through the site selection method of marine engineering demonstration zone based on machine learning, the suitability of marine engineering site selection is analyzed using neural network models, and the problem of lack of scientific planning for marine ranch construction is solved, and efficient utilization of marine resources and the improvement of comprehensive benefits is achieved.

CN113496355BActive Publication Date: 2024-12-03SHANDONG UNIV
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202110753500.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-07-02
Publication Date
2024-12-03
Estimated Expiration
2041-07-02

AI Technical Summary

Technical Problem

At this stage, the construction of marine ranches lacks in-depth scientific research and planning, resulting in underutilization of sea resources, vacant and waste in some sea areas, imbalance in the development and layout of marine ranches, lack of forward-looking and overall planning guidance, resulting in the failure of comprehensive benefits. Give full play.

Method used

Using the site selection method of marine engineering demonstration zones based on machine learning, the first-level indicators of geology, meteorology, water quality and environmental conditions are obtained, and the weight indicators are screened out through sensitivity analysis, and neural network models are constructed to provide existing marine engineering demonstration zones. The suitability evaluation results are trained and learned to form an evaluation model, which is used to analyze the suitability of the candidate areas and determine the final site selection area.

Benefits of technology

It can effectively analyze the suitability of marine engineering site selection, provide important reference, provide scientific site selection basis for marine engineering construction, and improve the resource utilization efficiency and comprehensive benefits of marine ranches.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113496355B_ABST
    Figure CN113496355B_ABST
Patent Text Reader

Abstract

The present invention provides a method and system for selecting a site for an ocean engineering demonstration area based on machine learning, which obtains geological conditions, meteorological conditions, water quality conditions, water quality conditions and environmental conditions of an existing ocean engineering demonstration area as primary indicators; uses machine learning to perform sensitivity analysis on each sub-indicator of the primary indicator, and screens out weight indicators that meet the requirements as secondary indicators; obtains the suitability evaluation results of the existing ocean engineering demonstration area; constructs a neural network model, uses a transfer function to calculate the number of nodes of the neural network model, uses the neural network model to train and learn the suitability evaluation results of the existing ocean engineering demonstration area, and forms an evaluation model; obtains secondary indicator parameters of each candidate area, uses the evaluation model to analyze the secondary indicator parameters, obtains the suitability analysis results of each candidate area, and determines the final site selection area according to the analysis results.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of marine engineering site selection, and specifically relates to a method and system for marine engineering demonstration area site selection based on machine learning. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] The protection and development of the bay is a new urban development concept proposed by coastal cities to re-examine their urban positioning under the new situation. It is not only a profound reshaping of the urban development landscape, but also an efficient integration of urban resources.

[0004] However, at the current stage, the construction of marine ranches is in a spontaneous state in the early stage, and there is a lack of in-depth research and planning as a whole; there has been no in-depth scientific research on the construction of domestic marine ranches, and there is a lack of demonstration and guidance, and there is a lack of foresight; the development and layout of some marine ranches are still unbalanced, and large-scale construction is not yet mature, and there is a lack of overall planning guidance. Some sea areas suitable for the construction of marine ranches have not been effectively utilized, and there are vacant and wasted sea areas. The management mechanism of marine ranches with good suitability is not yet perfect, resulting in a reduction in the amount of resources in some sea areas. The layout characteristics of marine ranches are not yet obvious, the degree of industrial integration is low, the characteristic, diversified and differentiated development is not prominent enough, and the comprehensive benefits have not been fully utilized. The overall construction scale of the project is large, and the construction suitability is obviously affected and restricted by the regional geological environment. Summary of the invention

[0005] In order to solve the above problems, the present invention proposes a method and system for site selection of marine engineering demonstration areas based on machine learning. The present invention can determine the adaptability of site selection of each marine engineering demonstration area and provide a certain reference for site selection of demonstration areas.

[0006] According to some embodiments, the present invention adopts the following technical solutions:

[0007] A method for selecting a site for an ocean engineering demonstration area based on machine learning comprises the following steps:

[0008] Obtain the geological conditions, meteorological conditions, water quality conditions, water quality conditions and environmental conditions of the existing marine engineering demonstration areas as primary indicators;

[0009] Use machine learning to analyze the sensitivity of each sub-indicator of the first-level indicator and select the weighted indicators that meet the requirements as the second-level indicators;

[0010] Obtain the suitability evaluation results of existing marine engineering demonstration areas;

[0011] Construct a neural network model, use the transfer function to calculate the number of nodes of the neural network model, and use the neural network model to train and learn the suitability evaluation results of existing marine engineering demonstration areas to form an evaluation model;

[0012] The secondary index parameters of each candidate area are obtained, and the secondary index parameters are analyzed using the evaluation model to obtain the suitability analysis results of each candidate area, and the final site selection area is determined based on the analysis results.

[0013] As an optional implementation method, the hierarchical analysis method is used to analyze the sub-indicators of the first-level indicator to obtain the weights of different sub-indicators, and the sub-indicators with weights greater than the set value are used as second-level indicators.

[0014] As a further limitation, before using the hierarchical analysis method to analyze the sub-indicators of the first-level indicators, the evaluation scores of the first-level indicators are obtained, the consistency index and the random consistency index are introduced, and the scoring results are tested for consistency. After satisfying the consistency test, the weights of the sub-indicators are calculated.

[0015] As an optional implementation, the secondary indicators include basic rock quality indicators, rainstorm period, strong wind period, pH value, comprehensive nutrition, building density and environmental safety level.

[0016] As an optional implementation, the specific process of calculating the number of nodes of the neural network model using the transfer function includes determining the number of hidden layer neurons according to the number of output layer nodes and the number of output layer nodes in the empirical formula.

[0017] As an optional implementation method, the specific process of using the neural network model to train and learn the suitability evaluation results of existing marine engineering demonstration areas is to obtain the secondary indicator measurement data of the existing marine engineering demonstration areas based on the evaluation results of the existing marine engineering demonstration areas, use the suitability level as the output indicator, and conduct neural network learning and training until the set conditions are met.

[0018] As an optional implementation, the specific process of analyzing the secondary indicator parameters using the evaluation model includes taking each indicator in the secondary indicator as an input node unit, passing the input node unit to the hidden layer through processing, and the transfer function Sigmoid function of the hidden layer then processes the node of the input unit to generate a new node unit, and outputs the suitability level of the candidate area.

[0019] A marine engineering demonstration area site selection system based on machine learning, comprising:

[0020] The primary indicator acquisition module is configured to acquire geological conditions, meteorological conditions, water quality conditions, water quality conditions and environmental conditions of the existing marine engineering demonstration area as primary indicators;

[0021] The secondary indicator screening module is configured to use machine learning to perform sensitivity analysis on each sub-indicator of the primary indicator and screen out weighted indicators that meet the requirements as secondary indicators;

[0022] An evaluation result acquisition module is configured to acquire the suitability evaluation results of existing marine engineering demonstration areas;

[0023] The evaluation model building module is configured to build a neural network model, calculate the number of nodes of the neural network model using a transfer function, and use the neural network model to train and learn the suitability evaluation results of existing marine engineering demonstration areas to form an evaluation model;

[0024] The site selection evaluation module is configured to obtain the secondary indicator parameters of each candidate area, analyze the secondary indicator parameters using the evaluation model, obtain the suitability analysis results of each candidate area, and determine the final site selection area based on the analysis results.

[0025] An electronic device comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor. When the computer instructions are executed by the processor, the steps in the above method are completed.

[0026] A computer-readable storage medium is used to store computer instructions, and when the computer instructions are executed by a processor, the steps in the above method are completed.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] The present invention can analyze the suitability of marine engineering site selection, and then obtain the suitability analysis results of each candidate area. According to the analysis results, the final site selection area is determined, providing an important reference basis for similar projects.

[0029] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0031] Figure 1 Schematic diagram of the evaluation index system;

[0032] Figure 2 Neural network model training steps and principles;

[0033] Figure 3 Neural network model training results. DETAILED DESCRIPTION

[0034] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0035] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0036] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0037] A machine learning method for evaluating the suitability of marine engineering construction site selection. The specific process and calculation principle are shown in the figure:

[0038] First, based on relevant background and engineering experience, the evaluation indicators for the suitability of marine engineering site selection are selected and explained as follows:

[0039] 1. Geological conditions

[0040] Geological conditions are an important basis for determining whether a site area can be used for engineering construction. Generally speaking, superior geological conditions, that is, stable foundations and no adverse geological conditions, are suitable for marine engineering construction and development, while unstable foundations, large-scale fracture zones in the shallow foundation, and poor geological conditions are not suitable for engineering construction. Therefore, according to geological conditions, the suitability of geological conditions is divided into four levels, namely poor geological conditions, general geological conditions, good geological conditions, and very good geological conditions. Geological conditions are represented by the basic rock mass quality index BQ:

[0041] BQ=100+3Rc+250K v (1)

[0042] According to the quantitative index of the classification factor, the uniaxial saturated compressive strength of rock R c (MPa) and rock mass integrity factor K v , further, the following classifications are made for different basic rock mass quality indicators and their corresponding characteristics:

[0043] Table 1 Basic rock mass quality indicators and corresponding suitability classification standards

[0044]

[0045] 2. Weather conditions

[0046] Marine engineering relies on the ocean, and its construction characteristics and purpose are beyond doubt. Therefore, the local climate level is also very important, and the climate level is expressed by the climate level. Priority is given to using the annual rainstorm period and the annual strong wind period as the basis for judging meteorological conditions.

[0047] The annual rainstorm period refers to the number of days with rainstorms in a year; the definition of rainstorms is as follows:

[0048] Heavy rain: Heavy rain: A rainfall process with a precipitation of 30-70mm in 12 hours or 50-100mm in 24 hours. Heavy rain: A rainfall process with a precipitation of 70-140mm in 12 hours or 100-250mm in 24 hours. Extremely heavy rain: A rainfall process with a precipitation of more than 140mm in 12 hours or more than 250mm in 24 hours. Light rain: Raindrops are clearly visible without floating; they do not splash on the ground; water accumulates slowly in depressions; the sound of rain on the roof is weak, and there is only dripping from the eaves; the precipitation is less than 5mm in 12 hours or less than 10mm in 24 hours. Moderate rain: Rain falls like a line, and raindrops are difficult to distinguish; they splash on hard ground; water accumulates quickly in depressions; there is a rustling sound of rain on the roof; the precipitation is 5-15mm in 12 hours or 10-25mm in 24 hours.

[0049] For strong winds, the number of days in a year when the instantaneous wind speed reaches or exceeds 17 m / s (or the wind force reaches or exceeds level 8 by visual estimation) is used as the grading evaluation standard for strong winds. That is:

[0050] Table 2 Suitability levels for different meteorological conditions

[0051]

[0052] 3. Water quality conditions

[0053] For marine sites, water quality conditions not only play a very important role in soil, but also an important guarantee for surrounding residents and engineering construction. The water quality conditions mainly include the pH value and comprehensive nutrient content of water. Preferably, the pH value is obtained based on the actual measurement of the on-site water quality monitoring experiment. For water quality, the higher the pH value, the more alkaline the water quality is, and the lower the pH value, the more acidic the water quality is. Therefore, when the pH is around 4, the water quality is more suitable.

[0054] Table 3 Different pH values ​​and corresponding suitability levels

[0055]

[0056] The nutrient quality index NQI of water quality is calculated based on the potassium permanganate index (COD), total nitrogen (TN), chlorophyll (Chla), and total phosphorus (TP) contained in the water.

[0057]

[0058] Further, as shown in Table 4:

[0059] Table 4 Eutrophication level of seawater

[0060]

[0061] 4. Environmental conditions:

[0062] Environmental conditions generally refer to environmental safety conditions. The present invention preferably selects building density and environmental safety level. Building density refers to the building density of the local environment. For the marine engineering demonstration area, the empty coastal buildings are more conducive to marine engineering construction. The denser the coastal buildings, the more difficult it is to carry out marine engineering construction. Therefore, the suitability analysis of building density is shown in Table 4:

[0063] Table 5 Environmental safety level

[0064]

[0065]

[0066] In summary, three categories of indicators, namely geological conditions, meteorological conditions and water quality conditions, are selected to analyze and evaluate the suitability of marine engineering site selection. Building density refers to the building coverage rate. Priority is given to the ratio of the sum of all base areas within the engineering demonstration area to the planned construction land. It can be seen that the greater the building density, the smaller the available development site, and further, it means that the site selection suitability is poor. The standards for measuring site selection suitability by building density are shown in Table 5:

[0067] Table 6 Building density and site suitability level

[0068]

[0069] Furthermore, for different suitability levels, different quantitative and qualitative expressions are also required. Prioritize, this paper selects annual economic benefits and annual large-scale engineering construction volume as expression indicators, among which the annual large-scale engineering construction volume is the construction volume of construction projects with a construction cost of more than 30 million yuan within one year. The hierarchical expression of annual benefits and annual large-scale engineering construction volume is shown in Table 7:

[0070] Table 7 Environmental safety levels

[0071]

[0072]

[0073] The hierarchical analysis method (AHP) is used to analyze these three types of indicators and obtain the subjective weights of different indicators. Figure 1 As shown:

[0074] First-level indicators: geological conditions, meteorological conditions, water quality conditions, and environmental conditions. Second-level indicators: basic rock quality indicators, rainstorm period, strong wind period, pH value, comprehensive nutrition, building density, and environmental safety level.

[0075] Furthermore, considering that the present invention involves the calculation of two-layer influencing indicators, the analytic hierarchy process is used to calculate the weight values ​​of the indicators, such as Figure 1 shown.

[0076] Calculation of primary indicator weights:

[0077] Priority is given to inviting experts in marine geology, geotechnical engineering, and engineering geology to score the first-level indicators of geological conditions, meteorological conditions, water quality conditions, and environmental conditions, and n rounds of scoring and discussion are carried out until a consensus is reached on the final result.

[0078]

[0079] As shown in Table 6, let e1, e2, e3, and e4 in the first-level indicators be compared in pairs, and the final scoring results of experts and scholars are 1→1 , e 1→2 , e 1→3 , e 1→4 , …e 4→4 , fill in the corresponding position in the table, and further calculate the maximum eigenvalue α of the matrix e according to the maximum eigenvalue calculation principle, as shown in formula (5):

[0080] e·α=λ·α (5)

[0081] Experts and scholars in different fields have different knowledge backgrounds. Therefore, in order to ensure that there are no contradictions in the judgment during the scoring process, the consistency index CI and the random consistency index RI are introduced to test the consistency of the scoring process. The value of RI is shown in Table 8, and it is believed that when CR>0.1, the judgment process meets the indicator consistency criterion. Further, the indicator weight w' is calculated according to Formula 7

[0082] Table 8 Expert scoring table

[0083]

[0084] CI=(λ max -α) / (n-1) (6)

[0085]

[0086] Furthermore, the analytic hierarchy process is used to calculate the weight w″ of the secondary index, and the final weight w is calculated according to formula (8):

[0087] w=w'·w″ (8)

[0088] In summary, after calculating the weight set of indicators (w"1, w"2, w"3, w"4, ... w" n ), screen and remove redundant indicators with weights less than 0.1, and further redistribute the remaining indicator weights to obtain the final weight set (w1, w2, w3, w4, ... w n ,). Further, in order to obtain the final suitability evaluation result, the present invention adopts BP neural network algorithm to predict and evaluate the final site suitability evaluation result, and the steps are as follows:

[0089] The first step is to select and optimize the initial weights:

[0090] The second step is to select a suitable transfer function to calculate the number of nodes of the neural network. Preferably, the present invention determines the number M of hidden layer neurons according to the number m of output layer nodes and the number n of output layer nodes in the empirical formula, and α is a constant between [0,10].

[0091]

[0092] After completing the above steps, the BP neural network algorithm is fitted according to the selected indicators and the corresponding measured data. According to the selected 7 indicators, 7 input node units are given, and then the input node units are processed and transferred to the hidden layer. The transfer function Sigmoid function of the hidden layer processes the nodes of the input units to generate new node units, and outputs one or more groups of node units. The target node output by the present invention is the site suitability level of the marine engineering demonstration area. Therefore, a group of output units is set. Figure 2 As shown, the forward propagation process of the neural network is formed.

[0093] Furthermore, according to the selected indicators, the field measured data of seven indicators, including basic rock mass quality indicators, rainstorm period, strong wind period, pH value, comprehensive nutritional status, building density, and environmental safety level, were selected to establish a small database of input indicators, and the suitability level was used as the output indicator for neural network learning and training. Figure 3 As shown in the figure, when the training results reach the ideal error range, the training can be considered completed. This process is implemented through MATLAB software.

[0094] Using the trained model, each candidate area can be analyzed to obtain the final site selection result.

[0095] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0096] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0097] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0098] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0099] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0100] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A method for selecting a site for a marine engineering demonstration area based on machine learning, characterized by: The following steps are involved: Obtain the geological conditions, meteorological conditions, water quality conditions and environmental conditions of existing marine engineering demonstration areas as primary indicators; Machine learning is used to analyze the sensitivity of each sub-indicator of the first-level indicator, and the weighted indicators that meet the requirements are screened out as the second-level indicators; specifically, the hierarchical analysis method is used to analyze each sub-indicator of the first-level indicator, and the weights of different sub-indicators are obtained, and the sub-indicators with weights greater than the set value are used as the second-level indicators; before the process of using the hierarchical analysis method to analyze each sub-indicator of the first-level indicator, the evaluation score of the first-level indicator is obtained, the consistency index and the random consistency index are introduced, and the scoring results are tested for consistency. After the consistency test is satisfied, the weight of each sub-indicator is calculated; the second-level indicators include basic rock quality indicators, rainstorm period, strong wind period, pH value, comprehensive nutrient content, building density and environmental safety level; After calculating the weight set of indicators, screen and redistribute the remaining indicator weights to obtain the final weight set; Obtain the suitability evaluation results of existing marine engineering demonstration areas; Construct a neural network model, use a transfer function to calculate the number of nodes of the neural network model, and the specific process of using the transfer function to calculate the number of nodes of the neural network model includes determining the number of hidden layer neurons according to the number of output layer nodes in the empirical formula and the number of nodes in the output layer; use the neural network model to train and learn the suitability evaluation results of the existing marine engineering demonstration area to form an evaluation model; wherein, the specific process of using the neural network model to train and learn the suitability evaluation results of the existing marine engineering demonstration area is to obtain the secondary indicator measurement data of the existing marine engineering demonstration area based on the evaluation results of the existing marine engineering demonstration area, and use the suitability level as the output indicator to perform neural network learning and training until the set conditions are met; specifically, according to the selected indicators, select the basic rock mass quality indicators, rainstorm period, windy period, pH value, comprehensive nutritional status, building density, environmental safety level, and seven indicators of field measured data, establish a small database of input indicators, use the suitability level as the output indicator, and perform neural network learning and training, and when the training result reaches the ideal error range, the training is considered to be completed; The secondary index parameters of each candidate area are obtained, and the secondary index parameters are analyzed using the evaluation model to obtain the suitability analysis results of each candidate area, and the final site selection area is determined based on the analysis results.

2. The method for selecting a site for an ocean engineering demonstration area based on machine learning as claimed in claim 1, characterized in that: The specific process of analyzing the secondary index parameters using the evaluation model includes taking each indicator in the secondary index as an input node unit, transferring the input node unit to the hidden layer through processing, and the transfer function Sigmoid function of the hidden layer then processes the nodes of the input unit to generate a new node unit, and outputs the suitability level of the candidate area.

3. A marine engineering demonstration area site selection system based on machine learning, characterized by: include: The primary indicator acquisition module is configured to acquire geological conditions, meteorological conditions, water quality conditions and environmental conditions of the existing marine engineering demonstration area as primary indicators; The secondary indicator screening module is configured to use machine learning to perform sensitivity analysis on each sub-indicator of the primary indicator, and screen out weighted indicators that meet the requirements as secondary indicators; specifically, the sub-indicators of the primary indicator are analyzed using the hierarchical analysis method to obtain the weights of different sub-indicators, and the sub-indicators with weights greater than the set values ​​are used as secondary indicators; before the process of using the hierarchical analysis method to analyze each sub-indicator of the primary indicator, the evaluation score of the primary indicator is obtained, the consistency index and the random consistency index are introduced, and the scoring results are tested for consistency. After the consistency test is satisfied, the weights of each sub-indicator are calculated; the secondary indicators include basic rock quality indicators, rainstorm period, strong wind period, pH value, comprehensive nutrient content, building density and environmental safety level; After calculating the weight set of indicators, screen and redistribute the remaining indicator weights to obtain the final weight set; An evaluation result acquisition module is configured to acquire the suitability evaluation results of existing marine engineering demonstration areas; The evaluation model construction module is configured to construct a neural network model, and calculate the number of nodes of the neural network model using a transfer function. The specific process of calculating the number of nodes of the neural network model using a transfer function includes determining the number of hidden layer neurons according to the number of output layer nodes in the empirical formula and the number of nodes of the output layer; using the neural network model to train and learn the suitability evaluation results of the existing marine engineering demonstration area to form an evaluation model; wherein the specific process of using the neural network model to train and learn the suitability evaluation results of the existing marine engineering demonstration area is to obtain the secondary indicator measurement data of the existing marine engineering demonstration area based on the evaluation results of the existing marine engineering demonstration area, and use the suitability level as the output indicator to perform neural network learning and training until the set conditions are met; specifically, according to the selected indicators, the field measured data of 7 indicators including basic rock mass quality indicators, rainstorm period, strong wind period, pH value, comprehensive nutritional status, building density, and environmental safety level are selected, a small database of input indicators is established, and the suitability level is used as the output indicator to perform neural network learning and training. When the training result reaches the ideal error range, the training is considered to be completed; The site selection evaluation module is configured to obtain the secondary indicator parameters of each candidate area, analyze the secondary indicator parameters using the evaluation model, obtain the suitability analysis results of each candidate area, and determine the final site selection area based on the analysis results.

4. An electronic device, characterized in that: The method comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the steps in the method according to any one of claims 1 to 2 are completed.

5. A computer-readable storage medium, characterized in that: Used to store computer instructions, which, when executed by a processor, complete the steps of the method according to any one of claims 1 to 2.