A method and system for predicting water level of coastal waters and evaluating navigation capacity

Abstract

The present application relates to the technical field of navigation, and is a coastal water level prediction and navigation capacity evaluation method and system. The problem that a single data source cannot comprehensively capture water level change influencing factors is solved. Through integration of GIS, ultrasonic detection and deep learning models, a set of high-precision and comprehensive water level monitoring and prediction technology is formed. The advantages of various data sources are fully utilized, the fusion and optimization of multi-dimensional information such as water level, tide, weather, etc. are realized, the applicability and reliability of the system in complex marine environments are significantly improved, and the safety and efficiency of the waterway navigation are ensured.

Description

Technical Field

[0001] This invention relates to the field of navigation technology, and in particular to a method and system for predicting water levels and assessing navigation capacity in coastal waters. Background Technology

[0002] With the increasing frequency of economic activities in coastal areas, the monitoring and assessment of waterway navigation capacity and safety have become increasingly important. In practical engineering applications, especially in water transport involving shallow coastal waters, such as during construction transport, large vessels cannot pass due to the shallow water level and the fact that these are not conventional waterways. Furthermore, the significant impact of tides makes the summarization and prediction of tidal level changes crucial. To ensure smooth transport operations, it is necessary to fully utilize the characteristic of seawater intrusion and water level rise during high tide to ensure that the necessary transport water level is reached.

[0003] Traditional waterway monitoring and management systems suffer from several major problems: First, traditional waterway monitoring methods rely primarily on manual measurement of fixed-point water levels to predict the overall waterway level, resulting in low timeliness and accuracy of the monitoring data. Second, traditional methods fail to adequately account for the lag properties of tidal rise and fall, making it impossible to comprehensively assess the impact of water level changes on waterway navigation capacity. Finally, existing waterway support systems lack automated integration and processing capabilities for real-time data, resulting in untimely data acquisition, difficulty in dynamic updates, and an inability to adapt to the complex real-time changes in waterways. Moreover, existing waterway support systems are also limited in their decision support for vessel navigation, typically providing only static water level information and lacking dynamic comprehensive analysis of vessel positions, water level changes, and navigation paths, thus failing to effectively mitigate potential risks in the waterway. Summary of the Invention

[0004] The purpose of this invention is to address the limitations of existing waterway auxiliary systems in supporting ship navigation decisions. These systems typically only provide static water level information and lack dynamic comprehensive analysis of ship positions, water level changes, and navigation paths, thus failing to effectively mitigate potential risks in waterways. This invention provides a method and system for predicting water levels and assessing navigation capacity in coastal waters.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] In a first aspect, the present invention provides a method for predicting water levels and assessing navigation capacity in coastal waters, comprising the following steps:

[0007] Several measurement points are set up along the waterway to obtain the first information, which includes the water area information of the waterway, including the geodetic coordinates and elevation of each measurement point, as well as the water level information, and to establish a three-dimensional model of the underwater topography of the waterway.

[0008] Based on the three-dimensional model, combined with the historical monitoring data of local water levels at various measurement points, the Splice-LSTM deep learning model is used to establish the corresponding mapping relationship between the local point water level and the water level at each coordinate point of the waterway, thus obtaining a future prediction model for the coastal waterway.

[0009] The second information is obtained through virtual mouse technology. The second information includes tidal prediction information from hydrological stations and weather forecast information. The tidal prediction information includes water level and flow velocity, and the weather forecast information includes daily rainfall.

[0010] Accuracy was evaluated by adding water level, flow velocity, and daily rainfall as feature parameters to the Splice-LSTM model, and the weighting factors of each feature parameter were obtained.

[0011] Based on the weighting factors of each feature parameter, the reciprocal weighted average method of error is used for correction, and a future prediction model of coastal waterway integrating multi-source information is established.

[0012] A future prediction model for coastal waterways, which integrates multi-source information, is used to assess the navigation capacity of waterways, predict navigation windows, and provide early warnings of water level changes during navigation.

[0013] As a preferred technical solution of the present invention, the first information is obtained based on GIS + ultrasonic detection technology;

[0014] Based on spline interpolation, continuous and smooth interpolation points are generated near the known measurement points by fitting piecewise functions to the water level data of known measurement points.

[0015] By integrating the three-dimensional coordinate data of known measurement points and interpolation points, including geodetic coordinates and corresponding elevation information, a three-dimensional coordinate system for the underwater topography of the waterway is established.

[0016] As a preferred technical solution of the present invention, several observation water level gauges are arranged at the beginning-middle-end positions of the waterway to obtain water level information of several measurement points in real time. The water level information includes time, flow velocity and water level.

[0017] As a preferred technical solution of the present invention, the historical water level data is preprocessed based on the obtained multi-point historical water level information to remove outliers and obtain optimized data;

[0018] Feature extraction of time series data is based on the Splice-LSTM model architecture, which includes several sub-modules. Each sub-module consists of three Splice-LSTM layers and one fully connected layer. Each of the three Splice-LSTM layers contains at least 50 hidden units to capture long-term dependencies in the time series data. The fully connected layer contains one neuron to output the prediction results.

[0019] Set the parameters of the Splice-LSTM model, including setting the training epochs to at least 500, standardizing the input data, and setting the normalization range of both feature data and label data to [0,1].

[0020] Mean squared error is used as the loss function to measure the error between the predicted and actual values ​​of the Splice-LSTM model, thereby optimizing the prediction accuracy of the Splice-LSTM model.

[0021] After training, the trained Splice-LSTM model is evaluated using a test dataset. The mean squared error is calculated to quantify the model's predictive performance, and a future prediction model for coastal waterways is established.

[0022] As a preferred technical solution of the present invention, the virtual mouse mode is used to navigate to the corresponding hydrological station tidal observation website and weather forecast website around the waterway;

[0023] Locate specific data information on a webpage, including water level, flow rate, and daily rainfall;

[0024] Initialize the data storage list and set the initial mouse position;

[0025] Simulate moving a virtual mouse at the corresponding data chart location, and obtain water level, flow rate, and daily rainfall data for each time period within the next 24 hours by continuously changing the mouse position.

[0026] As a preferred technical solution of the present invention, data is collected and preprocessed to obtain a training set. The data includes water level, flow velocity, and daily rainfall. The training set is evaluated using the Splice-LSTM model.

[0027] Based on the Splice-LSTM model, multiple single-model evaluations are performed successively on the training set, and the prediction results of the Splice-LSTM model are analyzed. The final evaluation result label is expressed by the formula:

[0028] H = α1w + α2f + α3p

[0029] In the formula, H is the water level result in the full waterway coordinate system output by the multi-source information complementary fusion model; α1, α2 and α3 represent the water level results in the full waterway coordinate system obtained by using water level w, flow velocity f and daily rainfall p as single feature parameters, respectively.

[0030] Weighting factors for each individual feature parameter:

[0031]

[0032] In the formula, ε1, ε2 and ε3 represent the accuracy of the water level results obtained in the full waterway coordinate system as single characteristic parameters, namely water level, flow velocity and daily rainfall.

[0033] As a further preferred technical solution of the present invention, the weighting factors α1, α2 and α3 are 0.60, 0.31 and 0.09, respectively.

[0034] Secondly, the present invention also provides a system for predicting water levels and assessing navigation capacity in coastal waters, utilizing the method for predicting water levels and assessing navigation capacity in coastal waters as described in any of the above claims. The assessment system includes:

[0035] The 3D topographic map display module establishes a 3D model of the underwater topography of the waterway based on the first information, and realizes dynamic interactive display of the underwater topography based on the interactive visualization technology of the Plotly library;

[0036] The future water level prediction module obtains secondary information by setting a specified date and using virtual mouse technology. It then processes the secondary information and uses a splice-LSTM model to predict water level changes in the future.

[0037] The waterway transportation window module automatically obtains the bridge water level prediction data from the future water level prediction module, merges the date and time information, generates time series data of the predicted water level, analyzes the water level prediction data, filters out the time periods that meet the requirements based on the water level threshold conditions, uses a dynamic time segmentation algorithm to identify and calculate the continuous time windows that meet the transportation requirements, automatically calculates the total duration of each continuous time period based on the time interval of the water level prediction data, and uses a preset continuous duration threshold to filter out the valid transportation window periods that meet the conditions.

[0038] The real-time water level change module connects to the observation water level gauge via an interface protocol, automatically receives the real-time water level data collected by the observation water level gauge, and uploads the real-time water level data through a communication protocol to realize real-time water level change correction.

[0039] The real-time navigation vessel early warning module includes an AIS system based on image recognition algorithms installed on the waterway to accurately read the size and draft parameters of vessels entering the waterway. Based on the satellite navigation system positioning technology configured on the vessel, it performs accurate spatial positioning by combining waterway water level data. It adopts the Dijkstra algorithm for path optimization based on dynamic environmental perception to calculate the optimal navigation route in real time, avoiding areas in the waterway where the water level does not meet the vessel's draft requirements. It integrates water level perception and vessel position data to monitor the relative position of the vessel to the water level in real time, and automatically alarms when the vessel's position approaches the critical draft value.

[0040] Thirdly, the present invention also provides an electronic device, comprising:

[0041] A memory on which computer programs are stored;

[0042] A processor for executing the program in the memory to implement the coastal water level prediction and navigation capacity assessment method as described in any of the preceding embodiments.

[0043] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that, when the program is executed by a processor, it implements the method for predicting water levels and assessing navigation capacity in coastal waters as described in any of the preceding claims.

[0044] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0045] The present invention provides a method and system for predicting water levels and assessing navigation capacity in coastal waters. This method solves the problem that a single data source cannot fully capture the factors influencing water level changes. By integrating GIS, ultrasonic detection, and deep learning models, a high-precision and comprehensive water level monitoring and prediction technology is formed. Furthermore, it fully utilizes the advantages of each data source to achieve the fusion and optimization of multi-dimensional information such as water level, tides, and weather. This significantly improves the applicability and reliability of the system in complex marine environments, ensuring the safety and efficiency of waterway navigation. Attached Figure Description

[0046] Figure 1 A flowchart illustrating the methods for predicting water levels and assessing navigation capacity in coastal waters;

[0047] Figure 2 This is a three-dimensional schematic diagram of underwater topography based on spline interpolation.

[0048] Figure 3 This is a schematic diagram of real-time water level monitoring.

[0049] Figure 4 A schematic diagram illustrating the prediction accuracy of the LSTM model;

[0050] Figure 5 This is a schematic diagram illustrating the prediction accuracy of the Splice-LSTM model.

[0051] Figure 6 A diagram illustrating page information obtained using virtual mouse technology;

[0052] Figure 7 A schematic diagram of the display interface of a system for predicting water levels and assessing navigation capacity in coastal waters. Detailed Implementation

[0053] The present invention will be further described in detail below with reference to experimental examples and specific embodiments. However, this should not be construed as limiting the scope of the above-mentioned subject matter of the present invention to the following embodiments; all technologies implemented based on the content of the present invention fall within the scope of the present invention.

[0054] Unless otherwise specified, the use of terms such as "upper," "lower," "left," "right," "center," "inner," and "outer" to indicate orientation or positional relationships in the description of specific embodiments of the present invention is based on the orientation or positional relationships shown in the accompanying drawings, or the orientation or positional relationship in which the product / equipment / device is typically placed during use. These terms are merely for the purpose of facilitating the description of the present invention or simplifying the description in specific embodiments, enabling those skilled in the art to quickly understand the solution, and do not indicate or imply that a particular device / component / element must have a specific orientation, or be constructed and operated in a specific positional relationship. Therefore, they should not be construed as limitations on the present invention.

[0055] Furthermore, the use of terms such as "horizontal," "vertical," "suspended," and "parallel" does not imply that the corresponding device / component / element must be absolutely horizontal, vertical, suspended, or parallel, but rather that it can be slightly tilted or have a deviation. For example, "horizontal" merely means that its direction is more horizontal relative to "vertical," not that the structure must be completely horizontal, but that it can be slightly tilted. Alternatively, it can be simplified to mean that the corresponding device / component / element, when set in a "horizontal," "vertical," "suspended," or "parallel" direction, can have an error / deviation of ±10% relative to the corresponding direction, more preferably within ±8%, more preferably within ±6%, more preferably within ±5%, and more preferably within ±4%. As long as the corresponding device / component / element is within the error / deviation range, it can still achieve its function in the present invention.

[0056] Furthermore, the use of terms such as "first," "second," and "third" in terminology is merely for distinguishing descriptions of identical or similar components and should not be interpreted as emphasizing or implying the relative importance of a particular component.

[0057] Furthermore, in the description of the embodiments of the present invention, "several", "more than", and "a number of" represent at least two. The number can be any number, such as 2, 3, 4, 5, 6, 7, 8, or 9, and can even exceed nine.

[0058] Furthermore, in the description of the technical solution of this invention, unless otherwise explicitly specified / limited / restricted, the terms "set up," "install," "connect," "link," "provided with," "laid out," and "arranged" should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to common connection methods in the art, such as welding, riveting, bolting, and threaded connections. Such connections can be mechanical, electrical, or communication connections; they can be direct connections or indirect connections through an intermediate medium; and they can refer to the internal communication between two components.

[0059] In related technologies, existing waterway auxiliary systems are also relatively limited in their decision support for ship navigation. They typically only provide static water level information and lack dynamic comprehensive analysis of ship position, water level changes, and navigation paths, thus failing to effectively avoid potential risks in waterways. Therefore, the technical solution of this application was developed, which is described below in conjunction with... Figures 1 to 7 To elaborate.

[0060] Example 1

[0061] In a certain canal construction project, the large-scale arch rib transportation construction was carried out in the shallow coastal waters. The water transport route was 1.5 kilometers long and located in an unconventional waterway. Due to the shallow water level, large ships could not pass directly. The construction had to make full use of the water level rise caused by seawater backflow during high tide to ensure that the necessary transport water level was reached.

[0062] Due to the significant tidal variations in the waters where the construction is located, water level prediction is crucial to the smooth progress of the construction. Accurate prediction of tidal level changes is necessary to ensure the timely transportation and hoisting of the arch ribs.

[0063] like Figures 1 to 6 As shown, the method for predicting water levels and assessing navigation capacity in coastal waters according to the present invention includes the following steps:

[0064] Step 1: Set up several measurement points along the waterway and obtain the first information based on GIS (Geographic Information System) + ultrasonic detection technology. The first information includes the water area information of the waterway, and the water area view covers the entire waterway. The water area information includes the geodetic coordinates and elevation of each measurement point, as well as the water level information, as shown in Table 1.

[0065] Table 1. Channel Coordinate Information Table

[0066]

[0067]

[0068] Based on spline interpolation, continuous and smooth interpolation points are generated near the known measurement points by fitting piecewise functions to the water level data of known measurement points.

[0069] By integrating the three-dimensional coordinate data of known measurement points and interpolated points, including geodetic coordinates and corresponding elevation information, a three-dimensional coordinate system for the underwater topography of the waterway is established, forming a system as follows: Figure 2 The image shows a detailed three-dimensional model of the underwater topography of the waterway.

[0070] Step 2: Based on the 3D model and combined with the historical monitoring data of local water levels at various measurement points on site, the corresponding mapping relationship between local point water levels and water levels at various coordinate points in the waterway is established through the Sp1ice-LSTM deep learning model, thus obtaining a future prediction model for the coastal waterway.

[0071] At several measurement points located at the beginning, middle, and end points of the waterway, an observation water level gauge is installed to acquire real-time water level information at each measurement point. This information includes time, flow velocity, and water level, such as... Figure 3 As shown.

[0072] Based on the historical water level information of each measurement point, the historical water level data is preprocessed to remove outliers and obtain optimized data.

[0073] Feature extraction of time series data is based on the Splice-LSTM model architecture, which includes several sub-modules, each consisting of three Splice-LSTM layers and one fully connected layer.

[0074] Each of the three Spice-LSTM layers contains at least 50 hidden units; in this embodiment, each layer may contain 100 hidden units to capture long-term dependencies in time series data. The pseudocode is shown below:

[0075] model = Sequential()

[0076] model.add(Input(shape=(X_train.shape[1],X_train.shape[2])))

[0077] model.add(LSTM(100,return_sequences=True))

[0078] model.add(LSTM(100,return_sequences=True))

[0079] model.add(LSTM(100))

[0080] model.add(Dense(3))

[0081] model.compile(optimizer='adam',loss='mean_squared_error')

[0082] A fully connected layer contains one neuron, which is used to output the prediction result.

[0083] Configure the Splice-LSTM model parameters, including setting the training epochs to at least 500 (in this embodiment, 1000 epochs are optional) to ensure the model fully learns the data features; set the batch size to 32 to balance model training efficiency and memory usage; and standardize the input data, with the normalization range for both feature data and label data set to [0,1].

[0084] Mean squared error is used as the loss function to measure the error between the predicted and actual values ​​of the Splice-LSTM model, thereby optimizing the prediction accuracy of the Splice-LSTM model.

[0085] After training, the trained Splice-LSTM model is evaluated using a test dataset. The mean squared error is calculated to quantify the model's predictive performance, establishing a future prediction model for coastal waterways. Figure 5 As shown.

[0086] It's important to note that while LSTM (Long Short-Term Memory) models have been widely used in time series forecasting, natural language processing, and various complex time series data analyses, traditional LSTM models also have some limitations in practical applications. First, LSTM models are primarily used for predicting single time series data; when dealing with the fusion of multi-source data (not single time series), they often struggle to comprehensively capture the interrelationships between different data sources. Second, the prediction accuracy of LSTM models may decrease when processing complex multivariate time series data due to the complex dependencies between features. Furthermore, when processing multi-scale or multi-level spatiotemporal data, the simplicity of the LSTM model structure limits its ability to extract deep-level features from the data.

[0087] Splice-LSTM, by introducing multiple parallel or cascaded LSTM layers, can better capture and fuse complex dependencies between multi-source data, thereby improving the model's prediction accuracy. Compared to traditional LSTM, Splice-LSTM has the ability to process multi-scale and multi-level data; its optimized model structure can effectively extract deep-level features from the data. This enhanced LSTM model can more accurately predict water level changes in waterway water level monitoring and navigation capacity assessment, and better cope with the challenges posed by multivariate time-series data, significantly improving the overall performance and reliability of the system. (Comparison is possible.) Figure 4 and Figure 5 Obviously Figure 5 The Splice-LSTM model used has a higher prediction accuracy than Figure 4 The prediction accuracy of the LSTM model used.

[0088] Step 3: Use virtual mouse technology to obtain the second information, which includes hydrological station tidal prediction information and weather forecast information. The tidal prediction information includes water level and flow velocity, and the weather forecast information includes daily rainfall.

[0089] Using a virtual mouse, navigate to the corresponding hydrological station's tidal observation website and weather forecast website around the waterway. Locate specific data information on the webpage, including water level, flow velocity, and daily rainfall. Initialize the data storage list and set the initial mouse position. Simulate moving the virtual mouse at the corresponding data chart location. By continuously changing the mouse position, obtain water level, flow velocity, and daily rainfall data for each time period within the next 24 hours. Figure 6 As shown.

[0090] It's important to note that since channel water level prediction requires the continuous acquisition of future characteristic parameters, traditional methods typically rely on manual reading or web crawling to obtain predicted data from water level observation points. However, traditional web crawling techniques often require applications based on complex data exchange protocols, and high-frequency crawling operations can overload the target website's server, even posing network risks. In contrast, virtual mouse technology simulates the human operation process, acquiring the necessary data by mimicking human actions on a webpage. This approach effectively reduces the pressure on website servers, lowers potential network security risks, and thus provides a safer and more efficient means of data acquisition in water level prediction.

[0091] Step 4: Add water level, flow velocity, and daily rainfall as feature parameters to the Spice-LSTM model to evaluate accuracy and obtain the weighting factors for each feature parameter.

[0092] Data was collected and preprocessed to obtain a training set, which included water level, flow velocity, and daily rainfall. The training set was evaluated using the Splice-LSTM model.

[0093] Based on the Sp1ice-LSTM model, multiple single-model evaluations are performed successively on the training set, and the prediction results of the Sp1ice-LSTM model are analyzed. The final evaluation result label is expressed by the formula:

[0094] H = α1w + α2f + α3p

[0095] In the formula, H is the water level result in the full waterway coordinate system output by the multi-source information complementary fusion model; α1, α2 and α3 represent the water level results in the full waterway coordinate system obtained by using water level w, flow velocity f and daily rainfall p as single feature parameters, respectively.

[0096] Weighting factors for each individual feature parameter:

[0097]

[0098] In the formula, ε1, ε2 and ε3 represent the accuracy of the water level results obtained in the full waterway coordinate system as single characteristic parameters, namely water level, flow velocity and daily rainfall.

[0099] In an optional implementation, the weighting factors α1, α2, and α3 are 0.60, 0.31, and 0.09, respectively.

[0100] Step 5: Based on the weighting factors of each feature parameter, the reciprocal weighted average method of error is used for correction to establish a future prediction model for coastal waterways that integrates multi-source information.

[0101] Step 6: Utilize a future prediction model for coastal waterways that integrates multi-source information to assess waterway navigation capacity, predict navigation windows, and provide early warnings of water level changes during navigation.

[0102] The present invention provides a method for predicting water levels and assessing navigation capacity in coastal waters. This method solves the problem that a single data source cannot fully capture the factors influencing water level changes. By integrating GIS, ultrasonic detection, and deep learning models, a high-precision and comprehensive water level monitoring and prediction technology is formed. Furthermore, it fully utilizes the advantages of each data source to achieve the fusion and optimization of multi-dimensional information such as water level, tides, and weather. This significantly improves the applicability and reliability of the system in complex marine environments, ensuring the safety and efficiency of waterway navigation.

[0103] Example 2

[0104] like Figure 7As shown, the present invention provides a system for predicting water levels and assessing navigation capacity in coastal waters. This system utilizes the method for predicting water levels and assessing navigation capacity in coastal waters as described in Example 1. The system includes a three-dimensional topographic map display module, a future water level prediction module, a waterway transport window module, a real-time water level change module, and a real-time navigation vessel early warning module.

[0105] The 3D terrain map display module includes a first acquisition unit and a modeling unit.

[0106] The first acquisition unit obtains the first information and transmits it to the modeling unit. The modeling unit builds a 3D model of the underwater topography of the waterway based on the first information and integrates it into the system through a program. Based on the interactive visualization technology of the Plotly library, it supports users to zoom and rotate the topographic map in real time, and click to view the coordinates and water level information of each point, realizing a dynamic interactive display of the underwater topography. The pseudocode is shown below:

[0107] fig=go.Figure(data=[go.Surface(z=z,x=x,y=y)]).

[0108] The future water level prediction module includes a second acquisition unit and a data processing unit.

[0109] The second data acquisition unit, by setting a specified date (e.g., a acquisition frequency of 7 days / time), utilizes virtual mouse technology to automatically acquire secondary information. This involves automatically navigating to designated tidal data and weather forecast webpages, simulating user operation, and retrieving 24-hour future 7-day water level data for the upper, middle, and lower reaches of the waterway, as well as daily rainfall data. Figure 6 As shown.

[0110] This system seamlessly integrates the second information into the data processing unit through a preset data stream processing mechanism, and performs water level prediction using a previously trained splice-LSTM model, automatically predicting future water level changes.

[0111] The waterway transportation window period module includes a data import unit, an analysis and filtering unit, a window period calculation unit, and a results display unit.

[0112] The data import unit automatically obtains the predicted water level under the bridge from the future water level prediction module, imports the data into the system platform, and merges the date and time information to generate time series data of the predicted water level.

[0113] The analysis and screening unit analyzes the water level prediction data using a preset algorithm. Based on water level thresholds (such as 1.2 meters and 1.5 meters, which correspond to the draft of the two workboats respectively), it selects the time periods that meet the requirements. It uses a dynamic time segmentation algorithm to identify and calculate continuous time windows that meet the transportation requirements, ensuring the continuity and rationality of the transportation window period.

[0114] The window period calculation unit automatically calculates the total duration of each continuous time period based on the time interval of the water level prediction data, and uses a preset continuous duration threshold (e.g., a threshold of 6 hours means that the shortest continuous duration is 6 hours) to filter out the valid transportation window periods that meet the conditions.

[0115] The results display unit automatically shows the calculated valid transportation window period on the system interface, allowing users to interactively view the start and end times of the transportation window for a specific date.

[0116] The real-time water level change module includes several observation water level gauges deployed at the beginning, middle, and end points of the waterway. It connects to the observation water level gauges through an interface protocol and automatically receives real-time water level data collected by the observation water level gauges within 24 hours. The real-time water level data is uploaded to the system platform through a standardized communication protocol to realize real-time water level change correction.

[0117] The real-time navigation vessel early warning module includes an AIS (Automatic Identification System) unit, a navigation path planning unit, and a critical water level early warning unit.

[0118] The AIS unit, based on image recognition algorithms, is deployed at the starting point of waterway monitoring. It accurately reads key parameters such as vessel size and draft entering the waterway. By combining real-time data acquisition with edge computing technology, the system can efficiently process and transmit basic vessel information, ensuring low latency and high accuracy in data acquisition. The AIS unit includes a high-resolution camera (1080P or higher) with waterproof, dustproof, and night vision capabilities to ensure all-weather vessel monitoring. This camera connects to an edge computing device using a GPU (Graphics Processing Unit) or FPGA (Field-Programmable Gate Array) to accelerate image data processing and utilize deep learning algorithms to identify vessel features. The image recognition algorithm, based on deep learning frameworks (such as YOLO and Faster R-CNN), automatically extracts key parameters such as vessel size and draft. The AIS receiver is responsible for capturing and processing static information about the vessel (such as vessel ID, speed, and heading).

[0119] The navigation path planning unit (NPR) utilizes the positioning technology of the ship's satellite navigation system (such as the BeiDou Navigation Satellite System (BDS) or enhanced GNSS global navigation satellite system), combined with channel water level data, to achieve precise spatial positioning. The NPR employs a Dijkstra algorithm based on dynamic environmental perception for path optimization, calculating the optimal navigation route in real time to avoid areas within the channel where the water level does not meet the ship's draft requirements, ensuring navigational safety. The BDS module and enhanced GNSS module are installed on the ship to acquire its real-time position information. The BDS module achieves high-precision positioning through communication with the BeiDou satellites. The enhanced GNSS module can simultaneously receive data from multiple global satellites to enhance positioning accuracy and stability. The navigation system is equipped with real-time dynamic differential processing software for decoding and processing multi-source satellite signals. Through the navigation control system, the ship can optimize its path based on water level prediction information and real-time channel data.

[0120] It should be noted that traditional waterway management systems are relatively lagging in data transmission and communication technologies, typically relying on manual intervention or timed data transmission, lacking fully automated data interaction capabilities. Therefore, existing systems have significant shortcomings in data transmission efficiency and real-time response capabilities. Furthermore, real-time vessel monitoring and navigation warning functions during waterway transportation are not fully implemented in existing systems, resulting in vessels not receiving timely warnings when encountering low water levels or other navigation risks, increasing navigational safety risks. The lack of intelligent path planning and dynamic management of navigation windows makes it difficult for existing systems to effectively guide vessels to avoid dangerous waters.

[0121] In an alternative implementation, the AIS unit, BDS module, and GNSS module can communicate with the main system platform via RESTful API and WebSocket technology to achieve automated data transmission and real-time feedback between devices.

[0122] The critical water level early warning unit integrates water level sensing and ship position data to monitor the relative position of the ship and the water level in real time. When the ship's position approaches the critical draft value, the critical water level early warning unit will automatically issue a timely and accurate early warning signal through SMS, on-site alarms, and other means to ensure that the ship takes measures to avoid danger.

[0123] This system employs a distributed communication architecture. The 3D topographic map display module, future water level prediction module, waterway transportation window module, real-time water level change module, and real-time navigation vessel early warning module interact with each other via RESTful APIs and WebSocket technology, ensuring real-time and reliable data transmission. The second acquisition unit and data processing unit achieve asynchronous data transmission through message queue technology (such as Kafka or RabbitMQ), guaranteeing efficient data transmission and processing between different units without manual intervention. Real-time water level change data is automatically uploaded to the system platform via Internet of Things (IoT) communication protocols (such as MQTT or CoAP) and pushed to relevant modules in real time via WebSocket. The system uses encrypted secure transmission protocols (such as TLS / SSL) to ensure data transmission security, combined with distributed fault detection and recovery mechanisms, ensuring high reliability and data consistency even under high load.

[0124] The present invention provides a system for predicting water levels and assessing navigation capacity in coastal waters. This system solves the problem that a single data source cannot fully capture the factors influencing water level changes. By integrating GIS, ultrasonic detection, and deep learning models, it forms a high-precision and comprehensive water level monitoring and prediction technology. Furthermore, it fully utilizes the advantages of each data source to achieve the fusion and optimization of multi-dimensional information such as water level, tides, and weather. This significantly improves the system's applicability and reliability in complex marine environments, ensuring the safety and efficiency of waterway navigation.

[0125] Example 3

[0126] An electronic device according to the present invention includes:

[0127] A memory on which computer programs are stored;

[0128] A processor is used to execute the program in the memory to implement the method for predicting water levels and assessing navigation capacity in coastal waters as described in Embodiment 1.

[0129] As an optional embodiment, the electronic device may include a processor, a memory, and may also include one or more of a multimedia component, an input / output (I / O) interface, and a communication component.

[0130] The processor controls the overall operation of the electronic device to complete all or part of the steps in the aforementioned method for predicting water levels and assessing navigation capacity in coastal waters.

[0131] Memory is used to store various types of data to support the operation of the electronic device. This data may include, for example, instructions for any application or method used to operate on the electronic device, as well as application-related data. Memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0132] The multimedia component may include a screen and an audio component, wherein the screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals; for example, the audio component may include a microphone for receiving external audio signals, the received audio signals may be further stored in memory or transmitted via a communication component; the audio component may also include at least one speaker for outputting audio signals.

[0133] I / O interfaces provide interfaces between the processor and other interface modules, such as keyboards, mice, buttons, etc.; these buttons can be virtual buttons or physical buttons.

[0134] The communication component is used for wired or wireless communication between the electronic device and other devices; wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, 5G or 5.5G, or one or more combinations thereof, and the corresponding communication component may include: Wi-Fi module, Bluetooth module, Star Flash module, NFC module, mobile communication module.

[0135] As an optional embodiment, the electronic device may be implemented by 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), controllers, microcontrollers, microprocessors, or other electronic components to perform the aforementioned method for predicting water levels and assessing navigation capabilities in coastal waters.

[0136] In addition, the computer-readable storage medium provided in this embodiment can be the memory including program instructions, which can be executed by the processor of an electronic device to complete the above-mentioned method for predicting the water level and assessing the navigation capacity of coastal waters.

[0137] Example 4

[0138] The present invention discloses a computer-readable storage medium storing a computer program, characterized in that, when the program is executed by a processor, it implements the method for predicting water levels and assessing navigation capacity in coastal waters as described in Example 1.

[0139] Computer-readable storage media are used to store various types of data to support the operation of the electronic device. This data may include, for example, instructions for any application or method used to operate on the electronic device, as well as application-related data. The memory may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0140] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for predicting water levels and assessing navigation capacity in coastal waters, characterized in that, Includes the following steps: Several measurement points are set up along the waterway to obtain the first information, which includes the water area information of the waterway, including the geodetic coordinates and elevation of each measurement point, as well as the water level information, and to establish a three-dimensional model of the underwater topography of the waterway. Based on the three-dimensional model, combined with the historical monitoring data of local water levels at various measurement points, the Splice-LSTM deep learning model is used to establish the corresponding mapping relationship between the local point water level and the water level at each coordinate point of the waterway, thus obtaining a future prediction model for the coastal waterway. The second information is obtained through virtual mouse technology. The second information includes tidal prediction information from hydrological stations and weather forecast information. The tidal prediction information includes water level and flow velocity, and the weather forecast information includes daily rainfall. Accuracy was evaluated by adding water level, flow velocity, and daily rainfall as feature parameters to the Splice-LSTM model, and the weighting factors of each feature parameter were obtained. Based on the weighting factors of each feature parameter, the reciprocal weighted average method of error is used for correction, and a future prediction model of coastal waterway integrating multi-source information is established. A future prediction model for coastal waterways, which integrates multi-source information, is used to assess the navigation capacity of waterways, predict navigation windows, and provide early warning of water level changes during navigation. Among them, based on the obtained historical water level information from multiple points, the historical water level data is preprocessed to remove outliers and obtain optimized data; Feature extraction of time series data is based on the Splice-LSTM model architecture, which includes several sub-modules. Each sub-module consists of three Splice-LSTM layers and one fully connected layer. Each of the three Splice-LSTM layers contains at least 50 hidden units to capture long-term dependencies in the time series data. The fully connected layer contains one neuron to output the prediction results. Set the parameters of the Splice-LSTM model, including setting the training epochs to at least 500, standardizing the input data, and setting the normalization range of both feature data and label data to [0,1]. Mean squared error is used as the loss function to measure the error between the predicted and actual values ​​of the Splice-LSTM model, thereby optimizing the prediction accuracy of the Splice-LSTM model. After training, the trained Splice-LSTM model is evaluated using a test dataset. The mean squared error is calculated to quantify the model's predictive performance, and a future prediction model for coastal waterways is established.

2. The method for predicting water levels and assessing navigation capacity in coastal waters according to claim 1, characterized in that, First information is obtained based on GIS + ultrasonic detection technology; Based on spline interpolation, continuous and smooth interpolation points are generated near the known measurement points by fitting piecewise functions to the water level data of known measurement points. By integrating the three-dimensional coordinate data of known measurement points and interpolation points, including geodetic coordinates and corresponding elevation information, a three-dimensional coordinate system for the underwater topography of the waterway is established.

3. The method for predicting water levels and assessing navigation capacity in coastal waters according to claim 1, characterized in that, Several water level gauges are deployed at the beginning, middle, and end points of the waterway to obtain water level information at several measurement points in real time. The water level information includes time, flow velocity, and water level.

4. The method for predicting coastal water levels and assessing navigation capacity according to claim 1, characterized in that, Navigate to the corresponding hydrological station tidal observation website and weather forecast website around the waterway using the virtual mouse mode; Locate specific data information on a webpage, including water level, flow rate, and daily rainfall; Initialize the data storage list and set the initial mouse position; Simulate moving a virtual mouse at the corresponding data chart location, and obtain water level, flow rate, and daily rainfall data for each time period within the next 24 hours by continuously changing the mouse position.

5. The method for predicting coastal water levels and assessing navigation capacity according to any one of claims 1-4, characterized in that, Data was collected and preprocessed to obtain a training set, which included water level, flow velocity, and daily rainfall. The training set was evaluated using the Splice-LSTM model. Based on the Splice-LSTM model, multiple single-model evaluations are performed successively on the training set, and the prediction results of the Splice-LSTM model are analyzed. The final evaluation result label is expressed by the formula: In the formula, The water level result in the full waterway coordinate system output by the multi-source information complementary fusion model; , and Representing water levels w Flow rate f Daily rainfall p The water level result in the entire waterway coordinate system is obtained as a single feature parameter; Weighting factors for each individual feature parameter: In the formula, and These represent the accuracy of the water level results in the full waterway coordinate system obtained by using water level, flow velocity, and daily rainfall as single characteristic parameters, respectively.

6. The method for predicting water levels and assessing navigation capacity in coastal waters according to claim 5, characterized in that, Weighting factors , and The values ​​are 0.60, 0.31, and 0.09, respectively.

7. A system for predicting water levels and assessing navigation capacity in coastal waters, characterized in that, The assessment system, utilizing the coastal water level prediction and navigation capacity assessment method as described in any one of claims 1-6, comprises: The 3D topographic map display module establishes a 3D model of the underwater topography of the waterway based on the first information, and realizes dynamic interactive display of the underwater topography based on the interactive visualization technology of the Plotly library; The future water level prediction module obtains secondary information by setting a specified date and using virtual mouse technology. It then processes the secondary information and uses a splice-LSTM model to predict water level changes in the future. The waterway transportation window module automatically obtains the bridge water level prediction data from the future water level prediction module, merges the date and time information, generates time series data of the predicted water level, analyzes the water level prediction data, filters out the time periods that meet the requirements based on the water level threshold conditions, uses a dynamic time segmentation algorithm to identify and calculate the continuous time windows that meet the transportation requirements, automatically calculates the total duration of each continuous time period based on the time interval of the water level prediction data, and uses a preset continuous duration threshold to filter out the valid transportation window periods that meet the conditions. The real-time water level change module connects to the observation water level gauge via an interface protocol, automatically receives the real-time water level data collected by the observation water level gauge, and uploads the real-time water level data through a communication protocol to realize real-time water level change correction. The real-time navigation vessel early warning module includes an AIS system based on image recognition algorithms installed on the waterway to accurately read the size and draft parameters of vessels entering the waterway. Based on the satellite navigation system positioning technology configured on the vessel, it performs accurate spatial positioning by combining waterway water level data. It adopts the Dijkstra algorithm for path optimization based on dynamic environmental perception to calculate the optimal navigation route in real time, avoiding areas in the waterway where the water level does not meet the vessel's draft requirements. It integrates water level perception and vessel position data to monitor the relative position of the vessel to the water level in real time, and automatically alarms when the vessel's position approaches the critical draft value.

8. An electronic device, characterized in that, include: A memory on which computer programs are stored; A processor for executing the program in the memory to implement the method for predicting water levels and assessing navigation capacity in coastal waters as described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, It stores a computer program, characterized in that, when executed by a processor, the program implements the method for predicting water levels and assessing navigation capacity in coastal waters as described in any one of claims 1-6.

Images