AIS data-based port navigable water depth calculation method

Abstract

The invention relates to an AIS data-based port navigable water depth calculation method. The method comprises the following steps of: 1, preprocessing AIS data, namely cleaning and correcting wrong data in the AIS; a second step of structured grid subdivision: subdividing the AIS data into structured grids of a port area; step 3, navigable water depth reliability evaluation: evaluating the ship record reliability of the AIS points in each grid; and 4, calculating the navigable water depth, namely generating the navigable water depth through the immersion depth according to a ship reliability evaluation result. According to the method, the problems that the depth of a port area is difficult to measure, the cost is high and the timeliness is poor are solved, automatic calculation of the navigable water depth is realized, a reliable port navigable water depth calculation method based on AIS data is provided, and a process thought is provided for automatically extracting available information based on other big data.

Description

Technical Field

[0001] The invention relates to a method for calculating the navigable water depth of a port based on AIS data, and in particular to a method for automatically calculating the navigable water depth and evaluating the reliability of a ship based on AIS data. Background Art

[0002] As maritime trade grows with the development of economic globalization, the size of ships and traffic density also increase, increasing the risk of ship accidents. Among many ship accidents, ship grounding may lead to oil spills and ship capsizing, threatening the environment and life safety. Ports are one of the most important hubs of modern global trade and a distribution center for all kinds of goods. They play a key role in international trade. Ports are generally built near the coast, with lower water depths. Due to the action of waves and tides, there will be siltation, especially in ports near sandy coasts, muddy coasts, and estuaries. There will be more serious siltation, and ship grounding accidents occur from time to time. Therefore, it is very important to study a method for calculating the navigable water depth of ports based on AIS data.

[0003] Usually, the water depth of the port is measured by sonar. Although this method has high accuracy in measuring water depth, it has the disadvantages of high cost and low efficiency. It is not suitable for large-scale and frequent measurements and cannot meet the growing shipping needs. In terms of the use of AIS data for water depth, some scholars have determined the required depth contour area interpolation based on AIS and marine accident data. In addition, some researchers have been exploring methods to generate water depth maps using AIS data. According to machine learning algorithms, water depth is predicted through nautical charts and AIS data. This ignores the in-depth evaluation of data reliability and poses a huge risk to preventing potential safety issues. Therefore, it is necessary to conduct in-depth research on the calculation and reliability evaluation methods of port navigable water depth based on AIS data, and provide a more practical, accurate and comprehensive method for calculating navigable water depth. Summary of the invention

[0004] The technical problem to be solved by the present invention is: to overcome the above-mentioned deficiencies of the prior art and propose a method for calculating the navigable depth of a port based on AIS data. Compared with the traditional method, the present invention fully considers factors such as errors in big data, realizes the reliability evaluation of the navigable depth, solves the problem of navigable depth calculation, proposes a method for calculating the navigable depth of a port based on AIS data, and provides a scientific implementation method for calculating the navigable depth of a port.

[0005] In order to solve the above technical problems, the present invention provides a method for calculating the navigable water depth of a port based on AIS data, comprising the following steps:

[0006] Step 1: AIS data preprocessing: Select the target port area to extract AIS data, and extract the AIS track data of the ship within one year according to the MMSI identification code of the ship in the area, and clean the track error and attribute error of the extracted AIS data;

[0007] Step 2: Structured grid generation: Generate a structured grid in the port area, divide the extracted AIS data into grids according to spatial position, and perform statistics on the AIS data in the grid, including the number of ships, ship types, and draft depth distribution of ships in the grid;

[0008] Step 3: Navigable water depth reliability assessment - Analyze the factors related to navigable water depth reliability, establish a navigable water depth reliability index system, and use the hierarchical analysis method to divide it into two aspects: single ship AIS record reliability assessment and grid ship reliability assessment. Specifically, it is divided into the following 7 points:

[0009] 1) Calculate the annual draft dispersion D of the ship by the following formula:

[0010]

[0011] Where n is the number of ship tracks, d i is the draft of the i-th position in the ship's trajectory; when D is 0, it means that the data has no discrete degree, that is, the data concentration is very high, and the data are almost completely equal; when D is 1, the data has the highest discrete degree, that is, the data concentration is extremely low, and the discrete degree between the data is very large;

[0012] 2) Calculate the ship's annual track integrity G according to the following formula:

[0013]

[0014] Among them, n is the number of ship trajectories, Q1 is the first quartile of the number of annual AIS trajectories of ships in the region, and Q3 is the third quartile of the number of annual AIS trajectories of ships in the region;

[0015] 3) For each type of ship, calculate the frequency T of the draft depth of the ship of this type not being 0 according to the following formula:

[0016] T=1-R1 / R2

[0017] Among them, R1 is the number of ships of this type with a draft of 0, and R2 is the total number of ships of this type;

[0018] 4) Calculate the ship voyage data integrity S according to the following formula:

[0019]

[0020] Among them, S is the completeness of the ship's voyage data in the ship's trajectory, and L is the number of key fields in the ship's voyage data, including: ship status, destination, ETA, S j is the missing rate of the jth key field, u is the number of missing jth fields in the ship’s trajectory, and n is the number of ship trajectories;

[0021] 5) The reliability X of the single ship record of each ship's AIS record is evaluated by four factors: the ship's annual draft dispersion D, the ship's annual track integrity G, the frequency T of the ship's draft depth not being 0, and the ship's voyage data integrity S:

[0022] X=α*D+β*G+γ*T+δ*S

[0023] Among them, α, β, γ and δ are the weights of each factor. The weights of each factor are determined by combining expert scoring and the analytic hierarchy process (AHP). The specific method is as follows:

[0024] First, a hierarchical structure is established: the target layer is the reliability of single ship records X; the standard layer includes the ship's annual draft dispersion D, the ship's annual track integrity G, the frequency of the ship's draft depth not being 0 T, and the ship's voyage data integrity S;

[0025] Secondly, construct a judgment matrix: for each factor in the standard layer, use the ratio of 1 to 9 to compare two factors, and construct the judgment matrix A as follows:

[0026]

[0027] Among them, a DG Indicates the importance of annual trajectory integrity G compared with annual draft dispersion D, a DT Indicates the importance of the frequency T of the ship's draft depth not being zero compared to the annual draft dispersion D; a DS Indicates the importance of the completeness S of the ship's voyage data in the ship's trajectory compared with the annual draft dispersion D; a GS Indicates the importance of the integrity of the ship's voyage data S in the ship's trajectory compared with the annual trajectory integrity G; a GT Indicates the importance of the frequency T of the ship's draft not being zero compared to the annual track integrity G; a TS Indicates the importance of the completeness S of the ship's voyage data in the ship's trajectory compared to the frequency T of the ship's draft depth not being 0;

[0028] Then, calculate the weight vector: Use the characteristic root method to concentrate on calculating the maximum characteristic root λ of the judgment matrix A max and its corresponding eigenvector W;

[0029] Finally, the consistency check is performed according to the following formula:

[0030]

[0031] Among them, CI is the consistency index, v is the order of the judgment matrix, find the average random consistency index RI≈9.0 corresponding to the fourth-order matrix, and calculate the consistency ratio

[0032] If CR < 0.1, the judgment matrix is ​​considered to have satisfactory consistency, otherwise the judgment matrix needs to be adjusted; after passing the consistency test, the weight vector obtained is the weight of each parameter;

[0033] 6) Calculate the relative dispersion of draft depth RD according to the following formula:

[0034]

[0035] Where, d k is the draft of the ship in grid k, d me is the median of the draft in the ship's trajectory; the larger the RD is, the more discrete the draft is and the lower the reliability is; otherwise, the reliability is higher;

[0036] 7) Calculate the navigable water depth reliability index Gra of grid k according to the following formula: k :

[0037]

[0038] Among them, H max is the maximum draft depth in grid k, H w is the draft of other ships w in grid k, X max is the single ship record reliability of the ship with the maximum draft in grid k, X w is the single ship record reliability of other ships w in grid k, is the relative dispersion of the draft of the ship with the maximum draft in grid k, RD w is the relative dispersion of the draft depths of other ships w in grid k;

[0039] Step 4: Calculation of navigable water depth: Based on the statistical results of the distribution of ship draft depths in the grid and the reliability assessment results of the navigable water depth, the maximum draft depth in the grid that meets the reliability threshold is calculated to obtain the navigable water depth.

[0040] The present invention first pre-processes the AIS data to clean the errors in the trajectory and attributes. Secondly, a grid is generated, and the ships and draft depths in the grid are analyzed. By identifying the main influencing factors of the reliability of navigable water depth, such as the annual draft dispersion, the annual trajectory completeness, the ship type, and the ship voyage data, the reliability of single ship records is analyzed and quantitatively studied. Afterwards, taking the reliability of single ship records as the starting point, the characteristics of the ships themselves in the grid and their relationship with other ships in the grid are fully considered to evaluate the reliability of extracting the navigable water depth of the port through AIS. Finally, the navigable water depth products with different reliabilities are calculated and generated based on the results.

[0041] The effective benefits of the port navigable water depth calculation method proposed by the present invention are as follows:

[0042] (1) The present invention realizes automatic cleaning of AIS data from two dimensions: trajectory and attribute, especially considering the correlation between ship draft and length;

[0043] (2) The present invention establishes a navigable water depth reliability evaluation system based on the annual draft dispersion, annual trajectory integrity, ship type, ship voyage data, relative draft dispersion, and reliability interaction between ships with similar draft depths, thus overcoming the problem of unreliable big data;

[0044] (3) The present invention uses reliability evaluation and ship draft statistics to calculate the navigable water depth, thereby reducing the cost of measuring the water depth.

[0045] The present invention solves the problem of calculating the navigable water depth through AIS data, realizes the reliability evaluation of the navigable water depth, proposes a reliable method for calculating the navigable water depth of a port based on AIS data, and provides a process idea for the calculation and reliability evaluation based on other big data. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The present invention will be further described below in conjunction with the accompanying drawings.

[0047] Figure 1 It is an overall flow chart of an example of the present invention.

[0048] Figure 2 Port area and AIS data of the present invention.

[0049] Figure 3 This is a correlation diagram between the ship length and the draft depth of the example of the present invention.

[0050] Figure 4 The figure is a comparison of the number of grids and water depth conditions under different navigable water depth reliability thresholds of the examples of the present invention.

[0051] Figure 5 This is a reliability result diagram of the navigable water depth in the port area of ​​the present invention.

[0052] Figure 6 This is a result diagram of the navigable water depth in the port area of ​​the example of the present invention. DETAILED DESCRIPTION

[0053] The present invention is described in detail below with reference to the accompanying drawings to make the technical route and operation steps of the present invention clearer.

[0054] The present invention is applicable to ports covered by AIS data. The more AIS data there are, the more accurate the assessment of navigable water depth is, such as a port in Southeast Asia. A port in Southeast Asia is one of the busiest ports in the world, with an average of 140,000 ships docking each year, and the amount of AIS data is relatively large.

[0055] As one of the busiest seaports in the world, a port in Southeast Asia has narrow space, turbulent water flow, and uneven seabed topography, which makes it difficult to measure its water depth. Secondly, the complexity of the port is reflected in its high accident rate. The strait where a port in Southeast Asia is located has an average of about 2,000 accidents per month.

[0056] Therefore, this example takes the study area as an example to illustrate a method for calculating the navigable water depth of a port based on AIS data. Figure 1 As shown in the flow chart, the following steps are specifically included:

[0057] Step 1, AIS data preprocessing - select the target port area for AIS data extraction, and extract the AIS track data of these ships within one year according to the identification code MMSI of the ships in the area. In order to improve the data quality, the extracted AIS data is cleaned for track errors and attribute errors in terms of track and attribute, mainly including track cleaning such as position errors and shared MMSI, and cleaning of attributes such as ship type, length, width, speed, etc., as well as draft attribute cleaning based on the relationship between the ship's draft depth and length. The specific conditions are as follows:

[0058]

[0059]

[0060] By analyzing a large amount of data on ship length and draft, it is observed that ship length is positively correlated with draft. Figure 3 The correlation between draft and length of different types of ships is shown.

[0061] Too small a draft will affect the stability of the ship when it is unloaded, which is not conducive to navigation safety. Therefore, the ship must have a reasonable ballast. It is generally believed that when an unloaded ship is ballasted, the draft in summer should be at least 50% greater than the full-load draft. When sailing in winter, due to the strong winds and waves, the draft should be greater than 55% of the full-load draft in summer. Therefore, according to the length and type of the ship, find out the maximum design draft of the ship of that length, and calculate the unloaded draft accordingly. The draft limit is obtained, and the ship's draft should be within this range. For example, the design draft of a 200-meter-long cargo ship is 11.40 to 11.52 meters. Then its unloaded draft should not be less than 5.70 meters. Therefore, for a cargo ship of about 200 meters, its draft should be 5.70-11.52 meters. However, according to the actual situation, the ship may be overloaded or the record may be incorrect. For example, in February 2017, the length of a cargo ship with an mmsi of 477845200 was 201m, and the recorded draft was 13.60m, so the maximum design draft should be increased by a 20% upper limit. For a 200m cargo ship, its draft should be between 5.70 and 13.82m. The draft of a cargo ship of about 200 meters should be between 5.70 and 13.82 meters. If the draft of the ship is not within this range, it is considered that the draft is incorrect and needs to be cleaned up. Therefore, the draft limit is determined based on the length and draft of the ship. The data is cleaned up accordingly;

[0062] Step 2, structured grid division - generate a structured grid in the port area. The present invention takes 50×50 meter cells as an example. The actual cell size can be adjusted as needed. The extracted AIS data is divided into grids according to the spatial position. Compared with a single value, the draft provided by the grid can better reflect the dimensional information of the spatial area. Considering that the navigable water depth is usually defined as the minimum water depth for ships to prevent bottoming, all ship draft values ​​and ship key information are recorded in each cell, corresponding to the trajectory sets of different ships. Statistics are performed on the AIS data in the grid, including statistics on the number of ships in the grid, ship types, and the distribution of ship drafts;

[0063] Step 3: Navigable water depth reliability assessment - Analyze the factors related to navigable water depth reliability, establish a navigable water depth reliability index system, and use the hierarchical analysis method to divide it into two aspects: single ship AIS record reliability assessment and grid ship reliability assessment. Specifically, it is divided into the following 7 points:

[0064] 1) Calculate the annual draft dispersion D of the ship. The annual draft dispersion of the ship refers to the range of variation of the draft depth recorded by the ship in a year. The greater the dispersion, the greater the variation of the draft depth of the ship, which reflects the instability of the record. The calculation is performed by reflecting the dispersion degree through the coefficient of variation;

[0065] The annual draft dispersion D of the ship is calculated by the following formula. The smaller the coefficient of variation, the higher the reliability, and vice versa:

[0066]

[0067] Where n is the number of ship tracks, d i is the draft of the i-th position in the ship's trajectory; when D is 0, it means that the data has no discreteness, that is, the data concentration is very high, and the data are almost completely equal; when D is 1, the data discreteness is the highest, that is, the data concentration is extremely low, and the discreteness between the data is very large.

[0068] 2) Calculate the ship's annual track integrity G. The ship's annual track integrity refers to whether the ship's navigation track in a year is complete. The higher the integrity, the higher the reliability of the record. It is calculated based on the number of AIS tracks of the ship in a year.

[0069] If the ship is far away from the base station, the ship's track may be incomplete, resulting in no records. In addition, the ship's sailing time will also affect the number of AIS records. If the ship's track is incomplete, the reliability of its recorded draft will be low. Statistical methods are used to investigate the completeness of AIS records. Among the ships in the port area, the number of AIS records for each ship in one year is recorded. The first quartile (Q1) is used as the minimum threshold, indicating that ships with a small number of records may have incomplete tracks; the third quartile (Q3) is used as the maximum threshold, indicating that ships with a large number of records may have complete tracks;

[0070] The annual track integrity G of the ship is calculated according to the following formula:

[0071]

[0072] Among them, G is the trajectory completeness, n is the number of ship trajectories, Q1 is the first quartile of the annual number of AIS ship trajectories in the region: 7955, and Q3 is the third quartile of the annual number of AIS ship trajectories in the region: 83909.

[0073] 3) Calculate the frequency T of the draft depth of each type of ship not being 0. Different types of ships have different operating requirements, so the number of times and accuracy of their draft depth records will vary, which is crucial for the reliability analysis of navigable water depth;

[0074] There are many cases where the draft of a ship is recorded as 0. Statistics are collected on the cases where the draft of different types of ships is 0. If the proportion of the draft of a ship type is 0 is higher, the reliability of the record of this type of ship is lower. If more than half of the points of a ship have a draft of 0, the draft of the ship is counted as 0.

[0075] For each type of ship, the frequency T of the draft depth of the ship of this type not being 0 is calculated according to the following formula:

[0076] T=1-R1 / R2

[0077] Among them, R1 is the number of ships of this type with a draft of 0, and R2 is the total number of ships of this type.

[0078] Taking the empty draft ratio of various types of ships in 2017 as an example, see the table below:

[0079]

[0080]

[0081] 4) Calculate the integrity S of the ship's voyage data. AIS voyage data contains draft, so the integrity of the voyage data reflects the reliability of the draft record to a certain extent;

[0082] AIS information provides three types of data. Static ship data includes ship name, call sign, MMSI, IMO, ship type, length, width, etc.; dynamic ship data includes longitude, latitude, ground course (COG), ground speed (SOG), etc.; ship voyage data includes ship status, draft, destination, estimated time of arrival (ETA), etc. The more complete the voyage data, the higher the reliability of the draft record. For each key information field such as ship status, destination, ETA, etc., the missing rate must be calculated. The missing rate is the ratio of the number of records with missing data in the field to the total number of records. A unified weight is used to calculate the comprehensive score for the missing rate of each field.

[0083] The ship voyage data integrity S is calculated according to the following formula:

[0084]

[0085] Among them, S is the completeness of the ship voyage data in the ship trajectory, L is the number of key fields of the ship voyage data (including: ship status, destination, ETA), S j is the missing rate of the jth key field, u is the number of missing jth fields in the ship’s trajectory, and n is the number of ship trajectories.

[0086] 5) Single ship record reliability assessment model, which assesses the single ship record reliability X of each ship's AIS record through four factors: annual draft dispersion D, annual track integrity G, frequency T of ship draft depth not being 0, and ship voyage data integrity S:

[0087] X=α*D+B*G+γ*T+δ*S

[0088] Among them, α, β, γ and δ are the weights of each factor.

[0089] In order to determine the weight of each parameter, a method combining expert scoring and the analytic hierarchy process (AHP) was used. AHP is a method that combines qualitative and quantitative methods. It analyzes complex factors by decomposing complex problems into several levels and factors, comparing and calculating the order weight that reflects the relative importance of a factor among various factors, and calculating the weight that reflects the relative importance order of all factors through the total ranking between various levels. The specific method is as follows:

[0090] First, a hierarchical structure is established: the target layer is the reliability of single ship records (X); the standard layer includes annual draft dispersion D, annual trajectory integrity G, the frequency of ship draft depth not being 0 T, and the completeness of ship voyage data in ship trajectory S.

[0091] Secondly, a judgment matrix is ​​constructed: for each factor in the standard layer, a ratio of 1 to 9 is used for pairwise comparison. The constructed judgment matrix A is as follows:

[0092]

[0093] Among them, a DG Indicates the importance of annual trajectory integrity G compared with annual draft dispersion D, a DT Indicates the importance of the frequency T of the ship's draft depth not being zero compared to the annual draft dispersion D; a DS Indicates the importance of the completeness S of the ship's voyage data in the ship's trajectory compared with the annual draft dispersion D; a GS Indicates the importance of the integrity of the ship's voyage data S in the ship's trajectory compared with the annual trajectory integrity G; a GT Indicates the importance of the frequency T of the ship's draft not being zero compared to the annual track integrity G; a TS Indicates the importance of the completeness S of the ship's voyage data in the ship's trajectory compared to the frequency T of the ship's draft depth not being 0. For each factor in the standard layer, a scale of 1-9 is used for pairwise comparison, and scores are given from 1-9 according to importance (expert scoring). For example, 1 means equally important, 3 means slightly important, 5 means very important, 7 means very important, 9 means extremely important, 2, 4, 6 and 8 are intermediate values, indicating an importance between two adjacent levels; the reciprocal indicates the opposite importance.

[0094] Then, calculate the weight vector: Use the characteristic root method to concentrate on calculating the maximum characteristic root λ of the judgment matrix A max and its corresponding eigenvector W.

[0095] Finally, the consistency check is performed according to the following formula:

[0096]

[0097] Among them, CI is the consistency index, v is the order of the judgment matrix, find the average random consistency index RI≈9.0 corresponding to the fourth-order matrix, and calculate the consistency ratio

[0098] If CR<0.1, the judgment matrix is ​​considered to have satisfactory consistency, otherwise the judgment matrix needs to be adjusted; after passing the consistency test, the weight vector obtained is the weight of each parameter.

[0099] In this example, the maximum eigenvalue λ_max of matrix A is determined to be 4.077, the consistency index CI is 0.026, the consistency ratio CR is 0.0029<0.1, and the matrix is ​​judged to have satisfactory consistency. The corresponding eigenvector W is [0.948, 0.259, 0.098, 0.157]. W is normalized to obtain the weight vector [0.648, 0.177, 0.067, 0.107].

[0100] The weights of each factor are set as follows: the annual draft dispersion has the highest weight, which is 0.648; the track completeness has the second highest weight, which is 0.177; the ship type has a weight of 0.067; the ship voyage data has a weight of 0.107;

[0101] 6) Calculate the relative dispersion of draft depth RD. The relative dispersion of draft depth means that in a specific area, the draft of a ship will be different from the median of its draft depth records in a year. If the dispersion is large, it means that the reliability of the draft depth records in the area is low.

[0102] In a specific area, the draft of a ship may be different from its draft record in a year. If the difference is too large, the reliability of the record will be lower. Therefore, the relative dispersion of the median of the ship's draft is used to detect the reliability of the draft in the grid in the draft of the ship throughout the year. Relative dispersion of draft:

[0103]

[0104] Where, d k is the draft of the ship in grid k, d me is the median of the draft in the ship’s trajectory; the larger the RD is, the more discrete the draft is and the lower the reliability is; otherwise, the reliability is higher.

[0105] 7) Reliability interaction between ships with similar draft depths refers to the impact of ships with similar draft depths on the navigable water depth in the same area. If there are many ships with similar draft depths and the reliability of ship records is high, it may also affect the reliability of the navigable water depth;

[0106] The reliability level of ship records is taken as the mass of the ship, and the difference in draft depth is taken as the distance between ships; at this time, the reliability of ship records is proportional to gravity, and the difference in draft depth is inversely proportional to gravity, which is consistent with cognition.

[0107] The reliability index Gra of the navigable water depth of grid k is calculated according to the following formula: k :

[0108]

[0109] Among them, H max is the maximum draft depth in grid k, H w is the draft of other ships w in grid k, X max is the single ship record reliability of the ship with the maximum draft in grid k, X w is the single ship record reliability of other ships w in grid k, RD max is the relative dispersion of the draft of the ship with the maximum draft in grid k, RD w is the relative discreteness of the draft depths of other ships w in grid k.

[0110] Step 4: Calculate the navigable water depth - The statistical results of the ship draft distribution in the grid and the reliability assessment results of the navigable water depth are compared with the water depth on the nautical chart to form a Figure 4 ,according to Figure 4 The reliability threshold is determined to be 0.53, and the reliability result of navigable water depth is formed as follows: Figure 5 , where the lighter the grid color, the higher the reliability. The maximum draft depth within the grid where the reliability meets the threshold is calculated, and the navigable water depth is obtained as Figure 6 As shown, the lighter the grid color, the deeper the water depth.

[0111] In order to verify the reliability and stability of the port navigable water depth calculation method based on AIS data, the chart water depth data was used for comparison, and the Pearson correlation coefficient (r), root mean square error (RMSE) and average relative error (ARE) were calculated respectively. The larger the r, the better the effect of the navigable water depth. On the contrary, the smaller the RMSE and ARE, the better the effect of the navigable water depth.

[0112] After calculation, the results of each statistic for different areas (such as docks, in-port channels, anchorages and main channels of straits) and the port as a whole are shown in the following table. The results for docks and channels are better, while those for anchorages and main channels of straits are relatively worse, because the water depths of anchorages and main channels of straits are usually deeper. In contrast, when the water depth is limited to less than 25 meters, the statistical results of different areas will be improved, especially in anchorages and main channels of straits. Therefore, when using AIS data to estimate the navigable water depth, it will be more accurate to limit the water depth to less than 25 meters.

[0113]

[0114]

[0115] The method for calculating the navigable depth of a port based on AIS data of the present invention is not limited to the specific technical solutions and implementation areas described in the above embodiments, and all technical solutions formed by equivalent replacement are within the protection scope required by the present invention.

Claims

1. A method for calculating the navigable water depth of a port based on AIS data, comprising the following steps: Step 1: AIS data preprocessing: Select the target port area to extract AIS data, and extract the AIS track data of the ship within one year according to the MMSI identification code of the ship in the area, and clean the track error and attribute error of the extracted AIS data; Step 2: Structured grid generation: Generate a structured grid in the port area, divide the extracted AIS data into grids according to spatial position, and perform statistics on the AIS data in the grid, including the number of ships, ship types, and draft depth distribution of ships in the grid; Step 3: Navigable water depth reliability assessment - Analyze the factors related to navigable water depth reliability, establish a navigable water depth reliability index system, and use the hierarchical analysis method to divide it into two aspects: single ship AIS record reliability assessment and grid ship reliability assessment. Specifically, it is divided into the following 7 points: 1) Calculate the annual draft dispersion D of the ship by the following formula: in, n is the number of ship tracks, d i is the draft of the i-th position in the ship's trajectory; when D is 0, it means that the data has no discrete degree, that is, the data concentration is very high, and the data are almost completely equal; when D is 1, the data has the highest discrete degree, that is, the data concentration is extremely low, and the discrete degree between the data is very large; 2) Calculate the ship's annual track integrity G according to the following formula: Among them, G is the track completeness, n is the number of ship tracks, Q1 is the first quartile of the number of AIS track of ships in the region, and Q3 is the third quartile of the number of AIS track of ships in the region; 3) For each type of ship, calculate the frequency T of the draft depth of the ship of this type not being 0 according to the following formula: T=1-R1 / R2 Among them, R1 is the number of ships of this type with a draft of 0, and R2 is the total number of ships of this type; 4) Calculate the ship voyage data integrity S according to the following formula: Among them, S is the completeness of the ship's voyage data in the ship's trajectory, and L is the number of key fields in the ship's voyage data, including: ship status, destination, ETA, S j is the missing rate of the jth key field, u is the number of missing jth fields in the ship’s trajectory, and n is the number of ship trajectories; 5) The reliability X of the single ship record of each ship's AIS record is evaluated by four factors: annual draft dispersion D, annual track integrity G, frequency T of the ship's draft depth not being 0, and ship voyage data integrity S: X=α*D+β*G+γ*T+δ*S Among them, α, β, γ and δ are the weights of each factor. The weights of each factor are determined by combining expert scoring and the analytic hierarchy process (AHP). The specific method is as follows: First, a hierarchical structure is established: the target layer is the reliability of single ship records X; the standard layer includes annual draft dispersion D, annual track integrity G, the frequency of ship draft depth not being 0 T, and ship voyage data integrity S; Secondly, construct a judgment matrix: for each factor in the standard layer, use the ratio of 1 to 9 to compare two factors, and construct the judgment matrix A as follows: Among them, a DG Indicates the importance of annual trajectory integrity G compared with annual draft dispersion D, a DT Indicates the importance of the frequency T of the ship's draft depth not being zero compared to the annual draft dispersion D; a DS Indicates the importance of the completeness S of the ship's voyage data in the ship's trajectory compared with the annual draft dispersion D; a GS Indicates the importance of the integrity of the ship's voyage data S in the ship's trajectory compared with the annual trajectory integrity G; a GT Indicates the importance of the frequency T of the ship's draft not being zero compared to the annual track integrity G; a TS Indicates the importance of the completeness S of the ship's voyage data in the ship's trajectory compared to the frequency T of the ship's draft depth not being 0; Then, calculate the weight vector: Use the characteristic root method to concentrate on calculating the maximum characteristic root λ of the judgment matrix A max and its corresponding eigenvector W; Finally, the consistency check is performed according to the following formula: Among them, CI is the consistency index, v is the order of the judgment matrix, find the average random consistency index RI≈9.0 corresponding to the fourth-order matrix, and calculate the consistency ratio If CR < 0.1, the judgment matrix is ​​considered to have satisfactory consistency, otherwise the judgment matrix needs to be adjusted; after passing the consistency test, the weight vector obtained is the weight of each parameter; 6) Calculate the relative dispersion of draft depth RD according to the following formula: Where, d k is the draft of the ship in grid k, d me is the median of the draft depth in the ship's trajectory; the larger the RD is, the more discrete the draft is and the lower the reliability is; otherwise, the reliability is higher; 7) Calculate the navigable water depth reliability index Gra of grid k according to the following formula: k : Among them, H max is the maximum draft depth in grid k, H w is the draft of other ships w in grid k, X max is the single ship record reliability of the ship with the maximum draft in grid k, X w is the single ship record reliability of other ships w in grid k, RD max is the relative dispersion of the draft of the ship with the maximum draft in grid k, RD w is the relative dispersion of the draft depths of other ships w in grid k; Step 4: Calculation of navigable water depth: Based on the statistical results of the distribution of ship draft depths in the grid and the reliability assessment results of the navigable water depth, the maximum draft depth in the grid that meets the reliability threshold is calculated to obtain the navigable water depth.

2. The method for calculating the navigable water depth of a port based on AIS data according to claim 1, characterized in that: Data cleaning mainly includes the cleaning of ship type, length, width, speed and draft attribute according to the relationship between ship draft and length.

3. The method for calculating the navigable water depth of a port based on AIS data according to claim 1 is characterized in that: In step 1, the judgment basis for track error cleaning is that the AIS point is not on land, and the average speed between any track point of the same MMSI ship and two adjacent track points in time is less than 120 knots; the judgment basis for attribute error cleaning is that the ship type, time, and draft are not empty, the length threshold is 460 meters, the width threshold is 80 meters, and the speed threshold is 30 knots.

4. The method for calculating the navigable water depth of a port based on AIS data according to claim 1 is characterized in that: In step 2, the grid division can be set by yourself, the default is 50 meters.

5. The method for calculating the navigable water depth of a port based on AIS data according to claim 1 is characterized by: In step 3, the hierarchical analysis method is used, which is divided into two aspects: reliability assessment of single ship AIS records and reliability assessment of ships in the grid. The reliability assessment of single ship AIS records includes four factors: annual draft dispersion, annual trajectory integrity, ship type, and ship voyage data. The reliability assessment of ships in the grid includes two parts: relative dispersion of draft depth and reliability interaction between ships with similar draft depths.

6. The method for calculating the navigable water depth of a port based on AIS data according to claim 1 is characterized by: In step 3, the maximum and minimum thresholds of annual trajectory completeness are the third quartile and the first quartile, respectively.

7. The method for calculating the navigable water depth of a port based on AIS data according to claim 1 is characterized by: In step 4, the intra-grid reliability threshold is 53%.

Images