Ballast water ashore biological inactivation method

Abstract

The invention relates to the technical field of biochemical data processing, in particular to a ballast water ashore biological inactivation method. The method comprises the following steps: acquiring image data of a shoreside area; performing background separation on the shoreside area image data to obtain a shoreside biological separation image and shoreside geographic information separation data; carrying out biological distribution feature extraction on the shoreside biological separation image to generate a shoreside biological distribution feature data set; performing biological population spatial analysis on the shoreside biological distribution characteristic data set and the shoreside geographic information separation data to generate biological population spatial distribution data; obtaining water area geographic information data; performing sensor network connection according to the water area geographic information data to generate a shore biological activity sensor network; carrying out real-time data acquisition by utilizing an ashore biological activity sensing network to obtain original real-time water quality data; according to the method, data integration, accurate prediction and inactivator optimization are carried out on water area geography and biological populations, so that the inactivation safety and accuracy are improved.

Description

Technical Field

[0001] The invention relates to the technical field of biochemical data processing, and in particular to a method for inactivating organisms on shore in ballast water. Background Art

[0002] Ballast water ships play a vital role in global trade. However, they also bring a serious problem: organisms attached to the surface of ships (biofouling) can cause ecosystem collapse and cause great damage to the marine environment. In order to meet this challenge, scientists began to explore ways to inactivate organisms in ballast water. With the development of science and technology, physical inactivation methods have gradually become the focus of attention. One widely studied method is the use of ultrasound technology. By introducing ultrasound in ballast water, scientists have found that they can effectively destroy organisms attached to the surface of ships, thereby preventing them from spreading in new waters. In recent years, the development of nanotechnology has begun to be applied to this field. Nanomaterials have extremely small sizes and special chemical properties that can interact with organisms at the microscopic level. Scientists have begun to study the introduction of nanoparticles into ballast water and the use of their special physical properties to inactivate organisms. However, there is usually a lack of accurate prediction and real-time monitoring of biological distribution and water quality changes, and it is impossible to simulate discharge treatment and water risk calculations to accurately predict and evaluate the discharge effect, resulting in low safety and accuracy of inactivation. Summary of the invention

[0003] Based on this, it is necessary to provide a method for inactivating organisms on shore in ballast water to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for inactivating organisms on shore in ballast water is provided, the method comprising the following steps:

[0005] Step S1: Acquire shore area image data; perform background separation on the shore area image data to obtain shore biological separation images and shore geographic information separation data; perform biological distribution feature extraction on the shore biological separation images to generate shore biological distribution feature data sets; perform biological population spatial analysis on the shore biological distribution feature data sets and shore geographic information separation data to generate biological population spatial distribution data;

[0006] Step S2: Acquire water area geographic information data; connect a sensor network according to the water area geographic information data to generate a shore biological activity sensor network; use the shore biological activity sensor network to collect real-time data to obtain original real-time water quality data; use a convolutional neural network algorithm to model the original real-time water quality data to generate a water quality change prediction model;

[0007] Step S3: Based on the water quality change prediction model, the original real-time water quality data is predicted to change water quality, and water quality change prediction data is generated; the biological population spatial distribution data and the water quality change prediction data are integrated to generate biological water quality integrated data; the biological water quality integrated data is imported into the water quality change prediction model to associate the biological-water quality model, and a biological water quality association index is generated;

[0008] Step S4: Screening inactivators according to the biological water quality correlation index to obtain a candidate list of inactivators; performing molecular structure simulation on the candidate list of inactivators to generate optimized structure data of inactivating molecules; performing biological effect testing on the activity evaluation data of the inactivating molecules to generate inactivation performance evaluation data; comparing the inactivation performance evaluation data with a preset inactivation evaluation threshold to generate a ballast water inactivation plan;

[0009] Step S5: simulate the discharge treatment through the ballast water inactivation scheme to generate simulated discharge range data; calculate the water area risk of the simulated discharge range data to generate a water area pollution index; optimize the discharge range of the range inactivation effect evaluation data according to the water area pollution index to generate ballast water discharge range optimization data;

[0010] Step S6: Conducting ballast water discharge biological population statistics based on the ballast water discharge range optimization data to generate first statistical data on the onshore biological population; conducting a second onshore biological population statistics on the first statistical data on the onshore biological population at a preset time interval to generate second statistical data on the onshore biological population; conducting actual inactivation statistics based on the first statistical data on the onshore biological population and the second statistical data on the onshore biological population to generate a biological inactivation statistical report.

[0011] The present invention helps to extract shore organisms and geographical information through background separation, making subsequent analysis more accurate. Through the extraction of biological distribution characteristics, a biological distribution characteristic data set is generated, which can be used to deeply understand the distribution of shore organisms. Real-time water quality data is obtained by using sensor network connection, providing instant monitoring of water quality. A water quality change prediction model is constructed using a convolutional neural network, providing prediction capabilities for future water quality changes. Combining the spatial distribution data of biological populations and the water quality change prediction data, a biological water quality association index is generated, providing a comprehensive assessment of the health status of the ecosystem. Through the biological water quality association index, a candidate list of inactivators is obtained, providing a potential solution for water quality improvement. The data generated by molecular structure simulation helps to design more effective inactivators, provides a simulation effect of the ballast water inactivation scheme, and provides a reference for decision-making. Through water risk calculation and discharge range optimization, the inactivation effect is effectively controlled and the negative impact on the water area is minimized. Through two biological population statistics and actual inactivation statistics, a comprehensive biological inactivation statistical report is generated to evaluate the inactivation effect. By integrating biological and water quality monitoring data, as well as the design and optimization of inactivators, a comprehensive water ecosystem management plan is provided. This helps to monitor water quality in real time, predict water quality changes, and improve the health of aquatic ecosystems through inactivator screening and simulated discharge treatment. Therefore, the present invention improves the safety and accuracy of inactivation by integrating data, accurately predicting and optimizing inactivators for aquatic geography and biological populations.

[0012] The beneficial effect of the present invention is that by acquiring image data of the shore area, separating biological and geographic information, extracting distribution features from the separated biological images, generating a data set, performing spatial analysis on biological classification and geographic information, and obtaining spatial distribution data of biological populations. Acquire water area geographic information data, establish a sensor network, collect water quality data in real time, and use a convolutional neural network to build a water quality change prediction model. Predict water quality changes, generate water quality change prediction data, integrate biological population distribution and water quality prediction data, and establish a biological water quality correlation index. Screen a candidate list of inactivators according to the correlation index, perform molecular structure simulation and activity evaluation on the candidate inactivators, and generate performance evaluation data. Through simulated emission, obtain emission range data, calculate the water pollution index, and optimize the emission range to evaluate the inactivation effect. Count the changes in the biological population on the shore, generate statistical data, perform actual inactivation statistics, and generate a biological inactivation statistical report. Combined with biological distribution and water quality prediction, screen out suitable inactivators, optimize the inactivation plan through simulated emission and water area risk calculation, reduce the potential impact on the water area, actually count the changes in the biological population, evaluate the inactivation effect, and provide feedback and improvement basis for the inactivation plan. Improve the inactivation effect of organisms in ballast water and evaluate and optimize their impact on the environment. Therefore, the present invention improves the safety and accuracy of inactivation by integrating data on water geography and biological populations, accurately predicting and optimizing inactivators. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 A schematic diagram of the steps of a method for inactivating organisms on shore in ballast water;

[0014] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0015] Figure 3 for Figure 1 Detailed implementation steps of step S4 in FIG.

[0016] Figure 4 for Figure 1 Detailed implementation steps of step S5;

[0017] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0018] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0019] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0020] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0021] To achieve this, please refer to Figures 1 to 4 , a method for inactivating organisms on shore in ballast water, the method comprising the following steps:

[0022] Step S1: Acquire shore area image data; perform background separation on the shore area image data to obtain shore biological separation images and shore geographic information separation data; perform biological distribution feature extraction on the shore biological separation images to generate shore biological distribution feature data sets; perform biological population spatial analysis on the shore biological distribution feature data sets and shore geographic information separation data to generate biological population spatial distribution data;

[0023] Step S2: Acquire water area geographic information data; connect a sensor network according to the water area geographic information data to generate a shore biological activity sensor network; use the shore biological activity sensor network to collect real-time data to obtain original real-time water quality data; use a convolutional neural network algorithm to model the original real-time water quality data to generate a water quality change prediction model;

[0024] Step S3: Based on the water quality change prediction model, the original real-time water quality data is predicted to change water quality, and water quality change prediction data is generated; the biological population spatial distribution data and the water quality change prediction data are integrated to generate biological water quality integrated data; the biological water quality integrated data is imported into the water quality change prediction model to associate the biological-water quality model, and a biological water quality association index is generated;

[0025] Step S4: Screening inactivators according to the biological water quality correlation index to obtain a candidate list of inactivators; performing molecular structure simulation on the candidate list of inactivators to generate optimized structure data of inactivating molecules; performing biological effect testing on the activity evaluation data of the inactivating molecules to generate inactivation performance evaluation data; comparing the inactivation performance evaluation data with a preset inactivation evaluation threshold to generate a ballast water inactivation plan;

[0026] Step S5: simulate the discharge treatment through the ballast water inactivation scheme to generate simulated discharge range data; calculate the water area risk of the simulated discharge range data to generate a water area pollution index; optimize the discharge range of the range inactivation effect evaluation data according to the water area pollution index to generate ballast water discharge range optimization data;

[0027] Step S6: Conducting ballast water discharge biological population statistics based on the ballast water discharge range optimization data to generate first statistical data on the onshore biological population; conducting a second onshore biological population statistics on the first statistical data on the onshore biological population at a preset time interval to generate second statistical data on the onshore biological population; conducting actual inactivation statistics based on the first statistical data on the onshore biological population and the second statistical data on the onshore biological population to generate a biological inactivation statistical report.

[0028] The present invention helps to extract shore organisms and geographical information through background separation, making subsequent analysis more accurate. Through the extraction of biological distribution characteristics, a biological distribution characteristic data set is generated, which can be used to deeply understand the distribution of shore organisms. Real-time water quality data is obtained by using sensor network connection, providing instant monitoring of water quality. A water quality change prediction model is constructed using a convolutional neural network, providing prediction capabilities for future water quality changes. Combining the spatial distribution data of biological populations and the water quality change prediction data, a biological water quality association index is generated, providing a comprehensive assessment of the health status of the ecosystem. Through the biological water quality association index, a candidate list of inactivators is obtained, providing a potential solution for water quality improvement. The data generated by molecular structure simulation helps to design more effective inactivators, provides a simulation effect of the ballast water inactivation scheme, and provides a reference for decision-making. Through water risk calculation and discharge range optimization, the inactivation effect is effectively controlled and the negative impact on the water area is minimized. Through two biological population statistics and actual inactivation statistics, a comprehensive biological inactivation statistical report is generated to evaluate the inactivation effect. By integrating biological and water quality monitoring data, as well as the design and optimization of inactivators, a comprehensive water ecosystem management plan is provided. This helps to monitor water quality in real time, predict water quality changes, and improve the health of aquatic ecosystems through inactivator screening and simulated discharge treatment. Therefore, the present invention improves the safety and accuracy of inactivation by integrating data, accurately predicting and optimizing inactivators for aquatic geography and biological populations.

[0029] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of a method for inactivating organisms on shore in ballast water according to the present invention. In this example, the method for inactivating organisms on shore in ballast water includes the following steps:

[0030] Step S1: Acquire shore area image data; perform background separation on the shore area image data to obtain shore biological separation images and shore geographic information separation data; perform biological distribution feature extraction on the shore biological separation images to generate shore biological distribution feature data sets; perform biological population spatial analysis on the shore biological distribution feature data sets and shore geographic information separation data to generate biological population spatial distribution data;

[0031] In the embodiment of the present invention, remote sensing technology, such as satellite imagery or drone aerial photography, is used to obtain high-resolution images of the shore area, ensuring that the image quality and coverage are sufficient for biological analysis and geographic information extraction. Image processing algorithms, such as background subtraction or segmentation algorithms, are used to separate the background from the foreground (organisms) in the shore area image, and factors such as illumination, shadows, and water fluctuations are considered to improve the separation accuracy, and two data sets are obtained, one containing only images of organisms, and the other containing geographic information (which may be the shoreline, the edge of the water, etc.). Using geographic information data, biological analysis can be associated with a specific geographic location, and computer vision techniques, such as image segmentation and feature extraction algorithms, are used to identify and extract the features of shore organisms. The features may include color, texture, shape, etc., to describe the distribution of organisms in the image. The features extracted from the biological separation image are organized into a data set, and each data point represents the biological distribution feature of a specific location. The data set will be used for subsequent biological population spatial analysis, and combined with biological classification label data and geographic information separation data, spatial analysis is performed to understand the distribution of organisms in the shore area. Geographic Information System (GIS) tools can be used for analysis, considering factors such as terrain and water flow.

[0032] Step S2: Acquire water area geographic information data; connect a sensor network according to the water area geographic information data to generate a shore biological activity sensor network; use the shore biological activity sensor network to collect real-time data to obtain original real-time water quality data; use a convolutional neural network algorithm to model the original real-time water quality data to generate a water quality change prediction model;

[0033] In the embodiment of the present invention, the geographical information of the water area, including the shape, size, depth, etc. of the water area, is obtained by using satellite remote sensing technology, and the geographical features around the water area, such as nearby land use, topography, hydrological features, etc., are obtained by using a water area geographic information system (GIS) tool. A water quality sensor network is deployed to cover key locations in the water area, and suitable sensors are selected, including parameters for measuring water quality such as temperature, pH value, dissolved oxygen, turbidity, etc. Modern communication technologies, such as the Internet of Things (IoT) technology, are used to establish a communication network between sensors. The data acquisition frequency of the sensor is set to ensure that high-frequency real-time data can be obtained. The real-time collected data may include time series data of water quality parameters, such as once every hour or every minute. The water quality data collected in real time is used as a training data set, and the data set is divided into a training set and a test set for model training and verification, and a deep learning algorithm such as a convolutional neural network (CNN) is used to build the model. CNN has advantages in processing spatiotemporal data and can effectively extract the spatial and temporal characteristics of water quality changes. Train the model and adjust parameters to improve the accuracy of water quality change predictions. Apply the trained model to real-time data to predict water quality changes. Use a sliding window approach to continuously update the model to adapt to changing water quality conditions. Set thresholds for the prediction results, and if the thresholds are exceeded, subsequent control and treatment measures are triggered.

[0034] Step S3: Based on the water quality change prediction model, the original real-time water quality data is predicted to change water quality, and water quality change prediction data is generated; the biological population spatial distribution data and the water quality change prediction data are integrated to generate biological water quality integrated data; the biological water quality integrated data is imported into the water quality change prediction model to associate the biological-water quality model, and a biological water quality association index is generated;

[0035] In an embodiment of the present invention, biological water quality integrated data is formed by integrating the spatial distribution data of biological populations with the water quality change prediction data. This may involve matching the time and space information of the two, and using the biological water quality integrated data to establish a biological-water quality model. This can use statistical methods, machine learning methods or other related methods to determine the correlation between biological population changes and water quality changes. The integrated data is predicted using the established model to generate a biological water quality correlation index. This index can represent the degree of correlation between the activity of the biological population and the water quality change, as a basis for subsequent steps. The biological water quality correlation index can be used to guide the screening of inactivators in step S4. A high correlation index may mean that some organisms are more sensitive to water quality changes, so this factor should be considered in the selection of inactivators. The biological water quality correlation index can also be used to evaluate the effect of ballast water inactivation schemes. A higher correlation index may mean that while affecting the water quality, it also affects the biological population, and the quality of the inactivation effect can be evaluated by comparing the correlation index before and after.

[0036] Step S4: Screening inactivators according to the biological water quality correlation index to obtain a candidate list of inactivators; performing molecular structure simulation on the candidate list of inactivators to generate optimized structure data of inactivating molecules; performing biological effect testing on the activity evaluation data of the inactivating molecules to generate inactivation performance evaluation data; comparing the inactivation performance evaluation data with a preset inactivation evaluation threshold to generate a ballast water inactivation plan;

[0037] In the embodiment of the present invention, a series of potential inactivators are evaluated by using the biological water quality association index to screen out candidate inactivators with high correlation with water quality and biological populations. Molecular structure simulation of the selected inactivator can be performed using computational chemistry methods, such as quantum mechanics calculation or molecular mechanics simulation, and environmental factors such as temperature, pressure and water quality conditions are considered in the simulation. Based on the simulation results, the molecular structure of the inactivator is optimized to improve its effect in practical applications. The optimization may include changing the atomic arrangement, adding specific functional groups, etc. The optimized inactivation molecules are subjected to laboratory or field biological effect tests. The test may include observations of the survival, reproduction and behavior of aquatic organisms to evaluate the biological safety of the inactivator. Based on the results of the biological effect test, the performance evaluation data of the inactivator is generated, and the data should include biological effects, dose-response relationships and possible side effects. The inactivation performance evaluation data is compared with a preset inactivation evaluation threshold, which can be a series of standards for biological effects and water quality changes, used to determine whether the inactivator meets the expected environmental effects. Based on the evaluation results, the final ballast water inactivation plan is determined.

[0038] Step S5: simulate the discharge treatment through the ballast water inactivation scheme to generate simulated discharge range data; calculate the water area risk of the simulated discharge range data to generate a water area pollution index; optimize the discharge range of the range inactivation effect evaluation data according to the water area pollution index to generate ballast water discharge range optimization data;

[0039] In an embodiment of the present invention, by using a previously determined ballast water inactivation scheme, discharge treatment is carried out in a simulated environment, which may include simulating the release and diffusion process of ballast water in a simulation software or laboratory environment. Through simulation, the diffusion range data after the ballast water is discharged is collected and recorded, and the data should include parameters such as the diffusion rate, range and time of the ballast water in the water area. The simulated discharge range data is used to evaluate and calculate the water area risk, considering the possible impact of the chemicals contained in the ballast water on the water ecosystem and biological population. According to the results of the water area risk calculation, a water area pollution index is generated. The index can be a comprehensive assessment, taking into account the degree of pollution and possible ecological risks in the water area. Based on the previous inactivation scheme and evaluation data, evaluation data on the inactivation effect within the ballast water discharge range is generated, including the effect changes of the inactivator within different diffusion ranges, the response of the biological population, etc. According to the water area pollution index and the range inactivation effect evaluation data, the discharge range is optimized. Possible optimization strategies include adjusting the discharge location, dosage or release method, etc., to minimize the impact on the water ecosystem. During the optimization process, the measures and adjustments taken are collected and recorded, and data records of emission range optimization are formed. These data may include improved pollution index, changes in diffusion range, etc.

[0040] Step S6: Conducting ballast water discharge biological population statistics based on the ballast water discharge range optimization data to generate first statistical data on the onshore biological population; conducting a second onshore biological population statistics on the first statistical data on the onshore biological population at a preset time interval to generate second statistical data on the onshore biological population; conducting actual inactivation statistics based on the first statistical data on the onshore biological population and the second statistical data on the onshore biological population to generate a biological inactivation statistical report.

[0041] In an embodiment of the present invention, biological monitoring equipment, such as cameras, sonars, mousetraps, etc., are deployed in the ballast water discharge area and surrounding areas to record the existence and number of biological populations, and data generated by the monitoring equipment are regularly collected, including information such as biological species, number, and distribution. These data will be used to generate a first statistical data of the onshore biological population. A second biological population statistic is performed at a preset time interval, such as every certain time (day, week, month), and data is collected at each time point, and a second statistic is performed on the onshore biological population. Changes in the number of organisms are recorded, especially changes compared with the previous statistics. The first and second biological population statistical data are compared, and the changes in the number of organisms are analyzed. Based on the changes in the biological population, the inactivation effect of the ballast water discharge is evaluated. This may require consideration of factors such as the type of organism and its adaptability to the environment. Generate a biological inactivation statistical report, including information such as the biological impact of ballast water discharge, inactivation effects, possible improvement suggestions, etc.

[0042] Preferably, step S1 comprises the following steps:

[0043] Step S11: using satellite sensors to obtain shore area image data;

[0044] Step S12: performing image preprocessing on the shore area image data to generate standard shore area image data, wherein the image preprocessing includes image denoising, image correction and image enhancement;

[0045] Step S13: performing background separation on the standard shore area image data to obtain a shore organism separation image and shore geographic information separation data; performing biological distribution feature extraction on the shore organism separation image to generate a shore organism distribution feature data set;

[0046] Step S14: classifying the shore biological distribution characteristic data set based on computer vision technology to generate shore biological classification data; and identifying the species of the shore biological classification data to generate biological classification label data;

[0047] Step S15: Integrate the biological classification label data and the shore geographic information separation data to generate shore biological distribution data; import the shore biological distribution data into the GIS system for three-dimensional reconstruction to generate biological distribution map data; perform biological population spatial analysis on the biological distribution map data to generate biological population spatial distribution data.

[0048] The present invention provides wide coverage of shore area information by using image data obtained by satellite sensors, providing basic data for subsequent analysis. Through preprocessing steps such as denoising, correction and enhancement, the quality of shore area images can be improved, useful information can be enhanced, and the accuracy and reliability of subsequent analysis can be improved. Background separation helps to focus on shore organisms, and the extracted biological distribution feature data set provides a basis for subsequent biological classification. By using computer vision technology to classify the biological distribution feature data set, automatic biological identification can be achieved, and shore biological classification data and biological classification label data are generated. The biological classification label data and the shore geographic information separation data are integrated to generate shore biological distribution data. By importing these data into the GIS system and performing three-dimensional reconstruction, biological distribution map data is generated. This step helps to intuitively display the distribution of organisms in geographic space. Spatial analysis of biological distribution map data can reveal information such as the distribution pattern and density of biological populations, providing important references for environmental protection, ecological research, etc.

[0049] In the embodiment of the present invention, by using satellite remote sensing technology, suitable satellite sensors such as MODIS, Landsat, etc. are selected to obtain high-resolution shore area image data. Digital image processing algorithms such as median filtering, Gaussian filtering, etc. are applied to reduce noise in the image, and geometric correction technology is used to correct deformation and distortion in the image to ensure that the image accurately reflects the surface conditions. Histogram equalization, contrast enhancement and other technologies are used to improve the visibility and information richness of the image, and generate standard shore area image data. Image segmentation algorithms such as threshold segmentation and regional growth are used to separate shore organisms from the background, and image processing and computer vision technologies are used to extract features in the shore organism distribution image, such as texture, color, shape, etc. Deep learning technology is used to use models such as convolutional neural networks (CNN) for biological classification. The input of the training model is a shore organism distribution feature data set, and the output is biological classification data. Integrate biological classification label data and shore geographic information separation data to form shore biological distribution data. Use professional geographic information systems (GIS), such as ArcGIS or QGIS, to import shore biological distribution data into the system and reconstruct three-dimensional maps. Use GIS tools to perform spatial analysis of biological populations, including density analysis and heat map generation, to obtain the spatial distribution of biological populations.

[0050] Preferably, step S2 comprises the following steps:

[0051] Step S21: Acquire water area geographic information data; deploy ocean sensors according to the water area geographic information data and generate an ocean sensor deployment sub-bureau map; deploy ground sensors according to the biological population spatial distribution data and generate a ground sensor deployment sub-bureau map;

[0052] Step S22: Connecting the sensor network using the ocean sensor deployment sub-bureau map and the ground sensor deployment sub-bureau map to generate a shore biological activity sensor network; collecting real-time data through the shore biological activity sensor network to obtain original real-time water quality data;

[0053] Step S23: performing data cleaning on the original real-time water quality data to generate real-time water quality cleaning data; performing data correction on the real-time water quality cleaning data to generate real-time water quality correction data; performing frequency domain feature extraction on the real-time water quality correction data based on the fast Fourier transform method to generate a water quality frequency domain feature data set;

[0054] Step S24: divide the water quality frequency domain feature data set to generate a model training set and a model test set; use the convolutional neural network algorithm to construct a water quality change model for the model training set to generate a water quality change prediction model; use the model test set to optimize the water quality change prediction model to generate a water quality change prediction model.

[0055] The present invention can provide more comprehensive and multi-dimensional water area information by deploying ocean and ground sensors to comprehensively obtain water area geographic information and biological population distribution data. The onshore biological activity sensor network can collect water quality data in real time, provide more timely and accurate real-time information, and help to monitor and respond to changes in water areas in a timely manner. Cleaning and correcting the original real-time water quality data can effectively remove noise and outliers, and improve the accuracy and reliability of the data. Frequency domain feature extraction of water quality correction data based on methods such as fast Fourier transform can help extract frequency domain information in the data and provide more features for subsequent model construction. Using algorithms such as convolutional neural networks to build a water quality change pre-model, and through model optimization, the trend of water quality change can be predicted to help prevent water quality problems or take countermeasures as soon as possible. Based on the obtained data and prediction model, it is possible to better understand the changes in water environment, water quality fluctuations, etc., which is helpful for ecological environmental protection and water resource management. Real-time monitoring and prediction of water quality changes can help to warn of possible water quality problems in advance, take corresponding preventive and emergency measures, and reduce possible environmental disasters.

[0056] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0057] Step S21: Acquire water area geographic information data; deploy ocean sensors according to the water area geographic information data and generate an ocean sensor deployment sub-bureau map; deploy ground sensors according to the biological population spatial distribution data and generate a ground sensor deployment sub-bureau map;

[0058] In the embodiment of the present invention, the water area geographic information data including the topography, water depth, temperature, salinity and other related information of the water area are obtained by using satellite remote sensing technology, and more detailed water area geographic information such as seabed topography, water quality, etc. are obtained by using surveying vessels or underwater detection equipment. According to the water area geographic information data, the areas and key points to be monitored are determined, and appropriate ocean sensors such as water quality sensors, temperature sensors, salinity sensors, etc. are selected in consideration of the water area characteristics and monitoring purposes. For the selected monitoring points, the ocean sensors are deployed by ships, buoys or other fixed devices, and the specific location and depth of the ocean sensor deployment can be adjusted according to the water area geographic information and monitoring requirements. The deployment location and related information of the ocean sensors are organized into data available to the geographic information system (GIS), and the ocean sensor deployment sub-bureau map is drawn using GIS tools to clearly display the location and monitoring range of each sensor. The sub-bureau map can be used for subsequent data management, analysis and visualization. Utilize the spatial distribution data of biological populations to determine the distribution of biological populations that need to be monitored, especially biological information related to water quality, select appropriate ground sensors, such as cameras, sonar, etc., to monitor the spatial distribution of biological populations, determine the deployment density and location of ground sensors according to the density and distribution of populations, organize the deployment location and related information of ground sensors into data available to GIS, and use GIS tools to draw a ground sensor deployment branch map to clearly display the location and monitoring range of each sensor. The branch map can be combined with the marine sensor deployment branch map to form an overall sensor network distribution map.

[0059] Step S22: Connecting the sensor network using the ocean sensor deployment sub-bureau map and the ground sensor deployment sub-bureau map to generate a shore biological activity sensor network; collecting real-time data through the shore biological activity sensor network to obtain original real-time water quality data;

[0060] In the embodiment of the present invention, by establishing a wireless communication network or a wired network, the ocean sensors and the ground sensors are connected to the onshore data center or monitoring station, and the communication protocol is used to ensure the effective communication between the sensors, such as using the Internet of Things (IoT) protocol, Wi-Fi, Bluetooth, etc., and introducing data transmission and security protocols in the sensor network to ensure the integrity and confidentiality of the data. The connection topology between the sensors is determined by using the information of the ocean sensor deployment sub-bureau map and the ground sensor deployment sub-bureau map, and a central control node is established on the shore to coordinate the data exchange between the sensors and manage the entire sensor network, ensuring that the coverage and density of the sensor network are sufficient to meet the monitoring needs, especially in key areas and moments. The data collection cycle and trigger conditions are set to ensure that real-time data is obtained when needed, and the data of the ocean sensors and the ground sensors are collected through the sensor network, including water quality information, biological activity data, etc. The real-time nature of the sensor network is used to timely discover and respond to changes in the water area. The data collected by the sensor is processed and analyzed in real time to obtain original real-time water quality data.

[0061] Step S23: performing data cleaning on the original real-time water quality data to generate real-time water quality cleaning data; performing data correction on the real-time water quality cleaning data to generate real-time water quality correction data; performing frequency domain feature extraction on the real-time water quality correction data based on the fast Fourier transform method to generate a water quality frequency domain feature data set;

[0062] In an embodiment of the present invention, outliers, noise and inaccurate measurement data are removed from the original real-time water quality data. This can be done by using filtering techniques (such as median filtering and mean filtering) to smooth the data and exclude outliers. Interpolation methods are used to fill in possible missing data to ensure the integrity of the data. For abnormal data points, threshold methods can be used for detection and correction. The cleaned real-time water quality data is corrected to improve the accuracy and reliability of the data. The correction may include zero drift correction and sensitivity correction of the sensor. This needs to rely on the technical specifications and calibration methods of the sensor, and use advanced mathematical models or statistical methods to correct the real-time water quality data based on known calibration data. The real-time water quality correction data is converted to the frequency domain using the fast Fourier transform (FFT) method. FFT converts time domain data into frequency domain representation, allowing the analysis of the components of the signal at different frequencies and extracting key features in the frequency domain, such as spectrograms, main frequencies, harmonics, etc. These frequency domain features can provide information about specific changes or pollution sources in the water body, which is of great significance to water quality monitoring and analysis.

[0063] Step S24: divide the water quality frequency domain feature data set to generate a model training set and a model test set; use the convolutional neural network algorithm to construct a water quality change model for the model training set to generate a water quality change prediction model; use the model test set to optimize the water quality change prediction model to generate a water quality change prediction model.

[0064] In an embodiment of the present invention, the water quality frequency domain feature data set is divided into two parts: a model training set and a model test set. Generally, a ratio of 80-20 or 70-30 can be used for division. Define the architecture of a convolutional neural network (CNN). CNN is a deep learning model suitable for image and sequence data, which can effectively capture the spatial and temporal characteristics of the data. The input layer should match the dimension of the water quality frequency domain features, and may include a convolution layer, a pooling layer, a fully connected layer, etc. The number of nodes in the output layer should be related to the change in water quality or a specific goal. For example, if it is a binary classification task (normal / abnormal water quality), the number of nodes in the output layer is 2. Select an appropriate loss function and optimizer. For example, a binary cross entropy loss and an Adam optimizer can be used for a binary classification task. Use the model training set to train the CNN model. During training, the model learns the complex relationship between water quality frequency domain features and water quality changes. Iterate the training and adjust the model parameters through the back propagation algorithm to minimize the loss function. Use the model test set to evaluate the performance of the model. This can be achieved by calculating indicators such as accuracy, precision, recall, and F1 score. Analyze the performance of the model on the test set to ensure the model's generalization ability to unseen data. Based on the test results, adjust and optimize the model. This may include adjusting hyperparameters (learning rate, batch size, etc.), changing the model architecture, adding regularization, etc. Repeat the training and testing process until a satisfactory performance level is achieved. Once a satisfactory performance level is achieved, a water quality change prediction model can be generated.

[0065] Preferably, step S3 comprises the following steps:

[0066] Step S31: predicting water quality changes of the original real-time water quality data based on the water quality change prediction model to generate water quality change prediction data; integrating the biological population spatial distribution data and the water quality change prediction data to generate biological water quality integration data;

[0067] Step S32: performing correlation analysis on the biological water quality integrated data to generate biological water quality related data; performing peak correlation screening on the biological water quality related data to generate high correlation analysis result data;

[0068] Step S33: importing the high correlation analysis result data into the water quality change prediction model to associate the biological-water quality model, thereby generating a biological-water quality association model; performing a model effect evaluation on the biological-water quality association model to generate model evaluation data;

[0069] Step S34: Compare the model evaluation data with the preset model evaluation threshold. When the model evaluation data is greater than or equal to the model evaluation threshold, the biological water quality correlation model is used to predict the biological water quality comprehensive evaluation index to generate a biological water quality correlation index; when the model evaluation data is less than the model evaluation threshold, return to step S32.

[0070] The present invention predicts real-time water quality data based on a water quality change prediction model, can understand the trend and possible changes of water quality in advance, and provide real-time monitoring and early warning functions for water quality management. The water quality change prediction data is integrated with the spatial distribution data of biological populations to lay the foundation for subsequent biological water quality association. Correlation analysis can reveal the relationship between water quality changes and biological population distribution, providing a basis for further analysis. Peak correlation screening can help determine the key association between organisms and water quality changes, filter out noise or insignificant associations, and improve the accuracy of subsequent analysis. By importing high correlation analysis results into the water quality change prediction model, a biological water quality association model is established, which helps to deeply understand the relationship between water quality and biological populations. The biological water quality association model is evaluated to ensure the quality and reliability of the model. This helps to verify the performance of the model in practical applications. Model evaluation data and model evaluation thresholds are used to determine whether to use the biological water quality association model to predict the biological water quality comprehensive evaluation index. This provides a comprehensive evaluation method based on biological information for water quality management. The whole process is based on real-time water quality data, and the system can provide timely monitoring and feedback, which helps to quickly respond to water quality changes and take necessary measures.

[0071] In an embodiment of the present invention, a prediction model is established based on historical water quality data by adopting appropriate machine learning or statistical methods. This may involve time series analysis, regression models or deep learning networks, etc. Real-time water quality data is continuously collected, and a prediction model is used to predict water quality changes and generate prediction data. Integrating real-time water quality data with biological population spatial distribution data may require the use of database technology or data processing tools to integrate and clean data to create biological water quality integrated data. Statistical methods or correlation indicators (such as Pearson correlation coefficient, Spearman, etc.) are used to analyze biological water quality integrated data to explore the correlation between biological population data and water quality changes. Based on the results of the correlation analysis, data points or features with high correlation are screened out, and thresholds or algorithms may be applied to determine the significance and importance of the correlation. The high correlation analysis result data is imported into the water quality change prediction model, and the model is further improved to consider biological data to form a biological water quality association model. The biological water quality association model is evaluated, and cross-validation, error analysis, ROC curve or other evaluation indicators can be used to evaluate the accuracy and reliability of the model. The model evaluation data is compared with the preset model evaluation threshold to determine whether a sufficient model effect has been achieved. If the model evaluation data reaches or exceeds the threshold, the biological water quality correlation model is used to predict the biological water quality comprehensive evaluation index and generate the biological water quality correlation index.

[0072] Preferably, step S4 comprises the following steps:

[0073] Step S41: Analyze the biological population characteristics of the onshore biological population according to the biological water quality association index and the biological water quality association model to generate a biological population characteristic data set;

[0074] Step S42: Screening inactivators based on the biological population characteristic data set to obtain a candidate list of inactivators; performing molecular structure simulation on the candidate list of inactivators using molecular simulation technology to generate molecular structure simulation data; optimizing the molecular structure of the inactivator using the molecular structure simulation data to generate optimized structure data of the inactivator molecule;

[0075] Step S43: performing molecular activity evaluation on the optimized structure data of the inactivated molecule to generate inactivated molecule activity evaluation data; performing biological effect test on the inactivated molecule activity evaluation data using a biological effect evaluation formula to generate inactivated performance evaluation data;

[0076] Step S44: Compare the inactivation performance evaluation data with the preset inactivation evaluation threshold. When the inactivation performance evaluation data is greater than or equal to the inactivation evaluation threshold, an inactivation mechanism plan is formulated based on the activity performance evaluation data to generate a ballast water inactivation plan; when the inactivation performance evaluation data is less than the inactivation evaluation threshold, return to step S42 to re-screen the inactivator.

[0077] The present invention conducts an in-depth analysis of the onshore biological population through the biological water quality correlation index and the correlation model. This helps to understand the impact of water quality on the biological population and form a biological population characteristic data set. Through characteristic analysis, the impact of water quality changes on the ecosystem can be better understood, providing more targeted information for subsequent inactivator screening. Using the biological population characteristic data set, inactivator screening is performed to obtain a potential inactivator candidate list. Molecular structure simulation and optimization of the candidate list by molecular simulation technology helps to understand the relationship between molecular structure and activity, while improving the effectiveness and selectivity of the inactivator. The optimized structure of the inactivation molecule is evaluated for molecular activity to generate activity evaluation data. The activity evaluation data of the inactivation molecule is tested using a biological effect evaluation formula to determine its impact on the target biological population. The inactivation performance evaluation data is compared with the inactivation evaluation threshold to determine whether a sufficient inactivation effect is achieved. When the inactivation performance evaluation data meets the requirements, a ballast water inactivation plan is formulated based on the activity performance evaluation data, which may involve the formulation of dosage, operation methods, etc. By combining the biological water quality correlation model, the screening of inactivators can be more targeted and the screening efficiency can be improved. Through molecular structure optimization and biological effect testing, the inactivation mechanism can be developed more accurately, which is expected to improve the inactivation effect. Through in-depth understanding of the ecosystem, more eco-friendly inactivation plans can be developed to reduce negative impacts on the environment.

[0078] As an example of the present invention, refer to Figure 3 As shown, in this example, step S4 includes:

[0079] Step S41: Analyze the biological population characteristics of the onshore biological population according to the biological water quality association index and the biological water quality association model to generate a biological population characteristic data set;

[0080] In an embodiment of the present invention, data related to onshore biological populations, such as biodiversity, density, distribution, and ecosystem health status, are collected. Water quality data required for the biological water quality association index is prepared, which may involve temperature, pH, dissolved oxygen, nutrient content, etc. Develop or select a suitable model to understand the relationship between biological population characteristics and water quality. This may include statistical models, machine learning methods, or ecological models. Train the model so that the model can perform predictions or association analysis based on given water quality parameters and biological population data. The collected biological population data is associated with the water quality data, and data processing and analysis are performed based on the biological water quality association model to explore the degree and pattern of association between biological population characteristics and water quality indicators. Based on the association model and analysis results, an in-depth analysis of the onshore biological population is performed, including but not limited to characteristics in terms of biodiversity, community structure, and ecosystem function, to identify the response patterns of biological populations under different water quality conditions, and to compare the effects of different parameters on biological communities. The results of the biological population characteristics obtained from the analysis will be collated and summarized to form a data set, which may include specific indicators of the onshore biological community, responses to different water quality conditions and other information, providing basic data for subsequent inactivator screening and inactivation mechanism formulation.

[0081] Step S42: Screening inactivators based on the biological population characteristic data set to obtain a candidate list of inactivators; performing molecular structure simulation on the candidate list of inactivators using molecular simulation technology to generate molecular structure simulation data; optimizing the molecular structure of the inactivator using the molecular structure simulation data to generate optimized structure data of the inactivator molecule;

[0082] In an embodiment of the present invention, the key characteristics and indicators for screening are determined based on the biological population characteristic data set. This may include toxicity to biological populations, factors affecting the stability of ecosystems, etc. Screening rules and thresholds are formulated to screen out compounds that may have inactivation effects from a potential compound library. Using the screening rules, the compound library is screened to obtain a group of potential inactivator candidate substances, and molecular simulation techniques, such as molecular dynamics simulation or quantum chemical calculations, are used to perform structural simulation on the compounds in the inactivator candidate list. Through simulation, the three-dimensional structure, charge distribution, energy state and other information of the compound are obtained, and the data obtained during the simulation process are sorted to form a molecular structure simulation data set for each compound, which may include trajectory data, energy changes, intermolecular interactions and other information during the simulation. Based on the molecular structure simulation data, the molecular structure of the inactivator is optimized. This may involve modifying the atomic position, functional group, charge distribution, etc., and through optimization, a molecular structure with higher activity and better biocompatibility is found. The results of molecular structure optimization are sorted to form an optimized structure data set of inactivating molecules, which may include information such as optimized molecular structure, predicted biological activity, and physical and chemical properties.

[0083] Step S43: performing molecular activity evaluation on the optimized structure data of the inactivated molecule to generate inactivated molecule activity evaluation data; performing biological effect test on the inactivated molecule activity evaluation data using a biological effect evaluation formula to generate inactivated performance evaluation data;

[0084] In the embodiment of the present invention, the predicted activity of the inactivated molecule is evaluated by using computational chemistry methods, such as molecular docking, pharmacophore analysis, quantum chemical calculation, etc., and the optimized inactivated molecule can be docked with the target protein using molecular docking software to evaluate the binding ability and possible activity between them, perform pharmacophore analysis, identify the functional groups related to biological activity in the molecule, and use computational methods to estimate the biological activity of the molecule, such as inhibition constant, bioavailability, etc. The results of the molecular activity evaluation are sorted out to form an inactivated molecule activity evaluation data set, which may include information such as the predicted activity and binding ability of each inactivated molecule, formulate a biological effect test plan, select an appropriate biological experimental model or in vitro test system, and verify the actual biological activity of the inactivated molecule through experiments, such as the inhibitory effect at the cellular level, toxicity test, etc., and cell culture experiments, animal models, etc. can be used for biological effect testing, and the experimental data are converted into quantitative biological activity indicators using biological effect evaluation formulas, which may be based on biological principles, such as inhibition concentration, half inhibition concentration (IC50), inhibition constant (Ki), etc. Organize the results of biological effect tests to form an inactivation performance evaluation data set, which may include experimentally measured biological activity data, such as IC50 values, toxicity data, etc.

[0085] Step S44: Compare the inactivation performance evaluation data with the preset inactivation evaluation threshold. When the inactivation performance evaluation data is greater than or equal to the inactivation evaluation threshold, an inactivation mechanism plan is formulated based on the activity performance evaluation data to generate a ballast water inactivation plan; when the inactivation performance evaluation data is less than the inactivation evaluation threshold, return to step S42 to re-screen the inactivator.

[0086] In an embodiment of the present invention, the inactivation performance evaluation data is compared with a preset inactivation evaluation threshold. This can be done by simple numerical comparison or using statistical methods. If the inactivation performance evaluation data is greater than or equal to the inactivation evaluation threshold, it means that the performance of the inactivator reaches the expected level, and the inactivation mechanism scheme can be continued to be formulated. If the inactivation performance evaluation data is less than the inactivation evaluation threshold, it means that the performance does not meet the requirements, and the inactivator screening needs to be re-performed, and the process returns to step S42. The specific mechanism of action of the inactivator is determined using the inactivation performance evaluation data. This may involve analysis of the structure-activity relationship of the molecule, the interaction with the target, etc. Based on these analyses, an inactivation mechanism scheme is formulated, including possible reaction pathways, biological activity regulation strategies, etc. Based on the inactivation mechanism scheme, a ballast water inactivation scheme is designed. This may include parameters such as the formulation of the inactivator, the concentration used, and the treatment time. Consider the actual application scenario to ensure that the ballast water inactivation scheme is feasible in actual operation and achieves the expected effect. If the inactivation performance does not meet expectations, it may be necessary to return to step S42, reselect or optimize the structure of the inactivator, and then evaluate it again.

[0087] Preferably, the biological effect evaluation formula in step S43 is as follows:

[0088]

[0089] Where, E represents the biological effect assessment result, t represents the time range of the assessment, and C {drug} Expressed as the drug concentration at time t, C {target} It is expressed as the target concentration at time (t), α is expressed as the degree of enhancement of the biological effect of the drug, β is expressed as the degree of inhibition of the biological effect of the drug, γ is expressed as the influence index of the drug concentration, δ is expressed as the inhibition factor of the target concentration, ∈ is expressed as the influence index of the target concentration, and μ is expressed as the abnormal adjustment value for the biological effect evaluation.

[0090] The present invention constructs a biological effect evaluation formula, the drug concentration part in the formula is: Describes the effect of drug concentration on biological effects. The parameters α and β in the numerator control the enhancement and inhibition effects of the drug, and γ represents the degree of influence of drug concentration on biological effects. When the drug concentration increases, the effect of α enhances the biological effect, while the effect of (\beta) limits the increase in biological effect to avoid excessive drug effect. The target concentration part of the formula Describes the effect of target concentration on biological effects. Parameter δ represents the inhibitory factor of target concentration, and ∈ represents the degree of influence of target concentration on biological effects. When the target concentration increases, the effect of δ limits the increase of biological effects to avoid excessive target activation. A functional relationship is formed based on the relationship between the parameters controlling the response speed and the above parameters:

[0091]

[0092] By integrating the drug concentration part and the target concentration part within the time range, it means that the biological effect is cumulatively calculated within the entire time range. Through the integration operation, the changes in time can be comprehensively considered to capture the cumulative effects of drug and target concentrations on biological effects. When the drug concentration increases, the effects of α and β enhance the biological effect and can more effectively activate the target, thereby improving the biological effect. The effect of β limits the excessive increase of the biological effect by the drug concentration to avoid the toxic side effects of the drug. It has an inhibitory effect at high drug concentrations, keeping the biological effect within a controllable range. The regulatory effect of target concentration on biological effects. When the target concentration increases, the effect of δ limits the excessive increase of the biological effect to avoid excessive activation of the target. And ∈ controls the degree of influence of the target concentration on the biological effect, so that the biological effect can adapt to the changes in the target concentration. The abnormal adjustment value μ is evaluated by the biological effect to correct the errors and deviations caused by the complexity and non-ideality of the actual system. It can correct the difference between the theoretical assumptions in the formula and the actual system, improve the accuracy and reliability of the biological effect evaluation, and generate the biological effect evaluation result R more accurately. At the same time, the parameters such as the influence index of the drug concentration in the formula and the degree of enhancement of the drug on the biological effect can be adjusted according to the actual situation, so as to adapt to different biological effect evaluation scenarios, thereby improving the applicability and flexibility of the algorithm. When using the conventional biological effect evaluation formula in the field, the biological effect evaluation result can be obtained. By applying the biological effect evaluation formula provided by the present invention, the biological effect evaluation result can be calculated more accurately. The interaction of parameters can regulate the influence of drug and target concentration on the biological effect, thereby realizing accurate evaluation and regulation of the biological effect, so as to improve the therapeutic effect and reduce potential side effects.

[0093] Preferably, the inactivation mechanism scheme in step S44 is specifically formulated as follows:

[0094] Collect ship ballast tank data;

[0095] Determine the ship motion state corresponding to the ship's ballast water tank. When the ship is static, perform a first pressure discharge on the ship's ballast water tank data to obtain first discharge pressure data. When the ship is dynamic, perform a second pressure discharge on the ship's ballast water tank data to obtain second discharge pressure data.

[0096] Performing a first ballast water discharge path analysis on the first discharge pressure data to generate first discharge path data; performing a second ballast water discharge path analysis on the second discharge pressure data to generate second discharge path data;

[0097] The discharge water flow resistance is calculated by the second discharge path data and the second discharge pressure data to generate the discharge water flow resistance data; the pressure water discharge diffusion analysis is performed on the first discharge path data to generate the first discharge diffusion data; the pressure water discharge diffusion analysis is performed on the second discharge path data based on the discharge water flow resistance data to generate the second discharge diffusion data;

[0098] The first discharge diffusion data and the second discharge diffusion data are visualized by using a data visualization method to generate a first discharge diffusion map and a second discharge diffusion map; the first discharge diffusion map and the second discharge diffusion map are compared in diffusion depth to generate repeated diffusion depth data and non-repeated diffusion depth data; the ballast water tank is dynamically pressure adjusted by using the non-repeated diffusion depth data to generate repeated diffusion depth data;

[0099] The ballast water inactivation scheme is derived by adaptively controlling the discharge based on repeated diffusion depth data through a feedback loop.

[0100] The present invention obtains the basic data of the ship's ballast water tank, which may include the capacity, structural information, and initial pressure of the water tank, and provides necessary input data for analysis and calculation of subsequent steps. According to the motion state of the ship, the corresponding pressure discharge is performed, and the corresponding discharge pressure data is obtained to ensure that the influence of the ship's motion on the pressure in the ballast water tank is considered, and the discharge pressure data under actual operating conditions is obtained. The path of ballast water discharge is analyzed, and the water flow resistance is calculated, providing key information that can be used for subsequent diffusion analysis and pressure adjustment. The diffusion of ballast water during the discharge process is analyzed to understand the distribution of water after discharge, providing a basis for subsequent adjustments. The diffusion data is presented by a visualization method, and a diffusion map is generated, making the data easier to understand and helping to compare the diffusion under different discharge conditions. The diffusion depth under different discharge conditions is compared, and dynamic pressure adjustment is performed on the basis of non-repetitive diffusion depth, the discharge conditions are optimized, and the inactivator reaches the target area and reduces the impact on non-target areas. Discharge adaptive control is performed based on repeated diffusion depth data, and real-time adjustment of the discharge process is achieved through a feedback mechanism, thereby improving the inactivation effect and reducing the impact on the environment.

[0101] In an embodiment of the present invention, the ship's ballast water tank is monitored and data collected by using sensors, measuring instruments and other equipment, and sensors are installed and configured to record relevant data such as water tank capacity, pressure, and temperature. The motion state of the ship is detected by using inertial navigation systems, shipboard sensors and other equipment, and the ship is judged whether it is static or dynamic according to the detection results, and the first or second pressure discharge is performed respectively. The discharge path analysis is performed using a fluid mechanics model and a path analysis algorithm, the water flow resistance is calculated using the hydrodynamic principle, and the discharge path and water flow resistance are calculated using numerical simulation or experimental data. Using a diffusion model, the diffusion analysis is performed considering factors such as wind speed and water flow speed, and the pressure water discharge diffusion data is generated using numerical simulation or experimental data. Data visualization tools such as charts and graphs are used to display the diffusion data, and tools such as Matplotlib, Plotly, etc. are used to create a first discharge diffusion map and a second discharge diffusion map. Compare the two discharge diffusion maps to determine the repeated diffusion depth and the non-repeated diffusion depth. Dynamic pressure adjustment is performed according to the non-repeated diffusion depth data, and the discharge pressure of the ballast water tank is dynamically adjusted using an algorithm or a control system to optimize the diffusion effect. Design a feedback control system to monitor repeated diffusion depth data and adaptively adjust emissions. Based on real-time monitoring data, adopt a feedback control strategy to adjust emission parameters to achieve adaptive control of emissions.

[0102] Preferably, step S5 comprises the following steps:

[0103] Step S51: performing simulated discharge processing through the ballast water inactivation scheme to generate simulated discharge data;

[0104] Step S52: Determine the emission range based on the simulated emission data to generate simulated emission range data; evaluate the range inactivation effect on the simulated emission range data to generate range inactivation effect evaluation data;

[0105] Step S53: using the water pollution risk index calculation formula to calculate the water risk of the range inactivation effect assessment data to generate a water pollution index;

[0106] Step S54: Optimize the discharge range of the range inactivation effect evaluation data according to the water pollution index to generate ballast water discharge range optimization data.

[0107] Through simulation, the present invention can evaluate the effect of the ballast water inactivation scheme before the actual discharge, so as to avoid the irreversible impact of the actual discharge on the water area. The generated simulated discharge data provides a comprehensive understanding of the discharge behavior and provides a basis for subsequent evaluation and optimization. Through the range inactivation effect evaluation based on the simulated discharge data, the spread and impact range of the scheme in the water area can be quantified. The generated range inactivation effect evaluation data provides input for the subsequent water area risk calculation, helping to evaluate the actual effect of the scheme. Using the water area pollution risk index calculation formula, the range inactivation effect evaluation data is used to calculate the water area risk, providing a comprehensive evaluation index. The generated water area pollution index provides a quantitative standard for evaluating the potential impact of the ballast water inactivation scheme on the water area. According to the water area pollution index, the discharge range of the range inactivation effect evaluation data is optimized to minimize the negative impact on the water area. The generated discharge range optimization data provides a basis for formulating a more environmentally friendly and sustainable discharge strategy, which helps to protect the aquatic ecosystem.

[0108] As an example of the present invention, refer to Figure 4 As shown, in this example, step S5 includes:

[0109] Step S51: performing simulated discharge processing through the ballast water inactivation scheme to generate simulated discharge data;

[0110] In an embodiment of the present invention, a simulation environment is constructed, including a water area model, a water flow model, etc. This may involve the use of professional simulation software or the development of a custom simulation model to determine the key parameters of the ballast water inactivation scheme, such as the type and concentration of the inactivator, the treatment time and temperature of the ballast water, etc. These parameters will be used in the simulation to design simulated discharge scenarios, including discharge points, discharge rates, discharge duration, etc. These scenarios need to match the conditions in actual applications to ensure the reliability of the simulation results. The ballast water inactivation scheme is simulated using the selected simulation software or a custom developed simulation model. During the simulation process, factors such as the geographical characteristics of the water area and the dynamics of the water flow are considered. During the simulation run, key parameters and the effects of simulated discharge are monitored in real time. The simulated discharge data is recorded, including information such as the diffusion of the inactivator in the water area and changes in concentration.

[0111] Step S52: Determine the emission range based on the simulated emission data to generate simulated emission range data; evaluate the range inactivation effect on the simulated emission range data to generate range inactivation effect evaluation data;

[0112] In an embodiment of the present invention, the scope of actual discharge in the water area is determined by using simulated emission data. This may include information such as the diffusion pattern of the emission, the shape and size of the affected area, etc. A geographic information system (GIS) tool can be used to assist in determining the emission range. Using the results of the emission range determination, simulated emission range data is generated. This may include time series data reflecting the evolution of the emission range over time, and spatial data describing the distribution of the emission range in the water area. Indicators and standards for range inactivation effect evaluation are formulated. This may involve factors such as the concentration distribution of the inactivator within the emission range and the change of the inactivation effect over time. The selection of specific indicators should be related to the actual application scenario and the inactivation target. Using the generated simulated emission range data, the range inactivation effect is evaluated. This may include analyzing the inactivation effect of different areas within the emission range, as well as the trend of change over time. Based on the evaluation results, range inactivation effect evaluation data is generated. This may include tables, charts, visualizations, etc., to clearly present the inactivation effect within the emission range.

[0113] Step S53: using the water pollution risk index calculation formula to calculate the water risk of the range inactivation effect assessment data to generate a water pollution index;

[0114] In an embodiment of the present invention, a water pollution risk index calculation formula suitable for the application scenario is determined. This may involve considering various indicators in the inactivation effect evaluation data, such as inactivator concentration, water characteristics, environmental factors, etc. A common calculation formula may include the weighted sum of various factors. Ensure the quality and accuracy of the range inactivation effect evaluation data. This may include inactivation effect data within the discharge range, water characteristics data, and other factor data that may affect the water pollution risk. For the parameters in the calculation formula, set appropriate values. Sometimes it may be necessary to standardize the data to ensure that the weights of different indicators are relatively consistent. Using the determined calculation formula, the water risk calculation is performed on the range inactivation effect evaluation data. This may involve substituting various indicators into the formula and calculating the final water pollution risk index. Explain the calculated water pollution risk index. This may include explaining the meaning of the index and the correlation between the index and the actual water pollution risk.

[0115] Step S54: Optimize the discharge range of the range inactivation effect evaluation data according to the water pollution index to generate ballast water discharge range optimization data.

[0116] In an embodiment of the present invention, by utilizing the water pollution index data generated in the previous steps, it is ensured that these data are calculated based on factors such as inactivation effect evaluation and water characteristics. Determine the quality standards and targets of the discharged water body. This may involve understanding relevant regulations, environmental standards, and sustainable development goals within the company. Develop or select a discharge range optimization algorithm suitable for the situation. This may include mathematical programming, optimization algorithms, or simulation algorithms to minimize the water pollution index and meet discharge standards and targets. Input data such as discharge range, water characteristics, and inactivation effects into the discharge optimization model. Ensure that the model accurately reflects the actual situation, including changes in the water pollution index and the impact of the discharge range. Run the discharge range optimization model to calculate the optimal ballast water discharge range. This may involve an iterative process until the optimal solution is found. Record and save the optimization result data, including the optimal discharge range, the corresponding water pollution index, and other relevant information. Evaluate the generated ballast water discharge range optimization data. Ensure that the optimal solution meets the discharge standards and targets, and that the water pollution index is significantly reduced.

[0117] Preferably, the water pollution risk index calculation formula in step S53 is as follows:

[0118]

[0119] In the formula, Z represents the water pollution risk index, N represents the number of pollution sources, M represents the number of monitoring points, L represents the number of degradation coefficients, O represents the number of pollutant emission sources, Q represents the number of environmental loads, R represents the number of environmental load assessment points, S represents the number of water quality sensitivity factors, U represents the number of water quality sensitivity assessment points, V represents the number of ecological risk factors, W represents the number of ecological risk assessment points, and C represents the number of water quality sensitivity factors, W represents the number of ecological risk assessment points, and C represents the number of water quality sensitivity factors, W represents the number of ecological risk assessment points, and C represents the number of water quality sensitivity factors, W represents the number of ecological risk assessment points, and C represents the number of water quality sensitivity factors, U represents the number of water quality sensitivity assessment points, V represents the number of ecological risk ... ecological risk factors, W represents the number of ecological risk assessment points, and C represents the number of environmental load assessment points. i Expressed as the concentration of the i-th pollution source, P j It is expressed as the area of ​​the jth monitoring point, A k Expressed as the degradation coefficient of the kth pollution source, B l Expressed as the emission of the lth pollutant emission source, D m Expressed as the value of the mth environmental load, E n Expressed as the area of ​​the nth environmental load assessment point, F p Expressed as the value of the pth water quality sensitivity factor, G q It is expressed as the area of ​​the qth water quality sensitivity assessment point, H r Expressed as the value of the rth ecological risk factor, I s It is represented as the area of ​​the sth ecological risk assessment point, and c is the assessment time range.

[0120] The present invention constructs a water pollution risk index calculation formula, which calculates the concentration C of all pollution sources. iThe sum is calculated and added to the area P of the monitoring point. j The total impact of pollution sources on water pollution can be reflected by dividing the total impact of pollution sources on water pollution. This part of the calculation can provide an assessment of the overall contribution of pollution sources. k Sum them and add them to the emission of pollutant emission source B l The sum of the environmental loads D is divided by the total, taking into account the impact of pollutant degradation and discharge on water pollution. This part of the calculation can evaluate the risk mitigation effect of pollutant treatment and emission control. m The sum is calculated and compared with the area E of the environmental load assessment point. n The negative impact of environmental load on water pollution is taken into account by dividing the sum of the above parameters. This part of the calculation can evaluate the pressure of environmental load on water quality. According to the relationship between the number of pollution sources and the above parameters, a functional relationship is formed:

[0121]

[0122] By calculating the value of all water quality sensitivity factors F p The sum is calculated and added to the area G of the water quality sensitivity assessment point. q The calculation of this part can assess the responsiveness of water quality sensitivity to pollution by dividing the value of all ecological risk factors H by r The sum is calculated and compared with the area I of the ecological risk assessment point s The calculation of this part can evaluate the potential damage degree of ecological risk to aquatic ecosystems. At the same time, parameters such as the number of monitoring points and the evaluation time range in the formula can be adjusted according to actual conditions to adapt to different water pollution risk index calculation scenarios, thereby improving the applicability and flexibility of the algorithm. When using the conventional water pollution risk index calculation formula in this field, the water pollution risk index can be obtained. By applying the water pollution risk index calculation formula provided by the present invention, the water pollution risk index can be calculated more accurately. By integrating the above parameters, the water pollution risk index Z calculated by the formula comprehensively considers the impact of pollution sources, monitoring points, degradation coefficients, emission sources, environmental loads, water quality sensitivity, and ecological risks on water pollution. Through this index, the overall pollution risk level of the water area can be evaluated, providing a scientific basis for formulating pollution control and protection strategies.

[0123] Preferably, step S6 comprises the following steps:

[0124] Step S61: discharging ballast water according to the ballast water discharge range optimization data, and recording the discharge time to obtain a first discharge time; performing onshore biological population statistics according to the first discharge time to generate first onshore biological population statistics;

[0125] Step S62: Conduct a second onshore biological population statistic on the first onshore biological population statistic at a preset time interval to generate a second onshore biological population statistic; conduct actual inactivation statistics based on the first onshore biological population statistic and the second onshore biological population statistic to generate a biological inactivation statistics report.

[0126] The present invention optimizes the data according to the aforementioned discharge range, performs actual ballast water discharge, and records the time of discharge. This ensures that the time point and conditions of the experiment are consistent with the previous model optimization, obtains the time of the first discharge, and provides a time reference for the subsequent biological population statistics and inactivation statistics. The shore biological population statistics are performed at the first discharge time point. This may include recording the types and numbers of shore plants, small animals and other organisms, and generating the first statistical data of the shore biological population based on the data of the first biological population statistics. For the first statistical data, the second shore biological population statistics are performed at a preset time interval. This can be within a few hours, days or weeks after the discharge, depending on the experimental design and purpose. The second statistical data of the shore biological population is generated based on the data of the second biological population statistics. The first and second biological population statistical data are compared to identify any changes or trends, and actual biological inactivation statistics are performed based on the comparison results. This may involve a detailed assessment of the survival status, number and type of the affected organisms, and a biological inactivation statistical report is generated based on the actual inactivation statistical data. The report should include experimental methods, data results, conclusions, and possible suggestions or improvement measures. By comparing the biological population statistics and inactivation statistics before and after, the actual impact of the discharge on the onshore biological population is evaluated. Based on the actual results, possible improvement measures are proposed, such as adjusting the discharge time, improving the discharge water quality, etc., to minimize the negative impact on the ecosystem, ensure that the discharge behavior complies with relevant regulations and standards, and promote sustainable practices.

[0127] In the embodiment of the present invention, the optimal ballast water discharge range is determined by using pre-collected data and models. This may include consideration of factors such as the depth, flow rate, and temperature of the water body to minimize the potential impact on shore organisms. When discharging ballast water, ensure that the start time of the discharge is accurately recorded to obtain the first discharge time. Define the specific area for shore biological population statistics, which may be a specific location along the coast, and use appropriate biological sampling methods, which may include standard ecological survey methods, to record the types and numbers of organisms. Organize the collected biological data into a format that can be used for analysis, perform statistical analysis of biological population statistics, and generate the first statistical data of shore biological populations. According to the experimental design, set the time interval between the first and second shore biological population statistics, and repeat the biological population statistics process in step S61 to obtain the second biological statistical data. Organize the biological data collected for the second time into a format that can be used for analysis, perform statistical analysis of the second biological population statistics, and generate the second statistical data of shore biological populations. Compare the first and second statistical data to identify any changes or trends in biological populations. On the basis of comparative analysis, evaluate the survival status of the organisms, determine whether there is biological inactivation, and record the number and type of affected organisms. The actual inactivation statistics data is organized into a format that can be used for reporting, and a biological inactivation statistics report is generated.

[0128] The beneficial effect of the present invention is that by acquiring image data of the shore area, separating biological and geographic information, extracting distribution features from the separated biological images, generating a data set, performing spatial analysis on biological classification and geographic information, and obtaining spatial distribution data of biological populations. Acquire water area geographic information data, establish a sensor network, collect water quality data in real time, and use a convolutional neural network to build a water quality change prediction model. Predict water quality changes, generate water quality change prediction data, integrate biological population distribution and water quality prediction data, and establish a biological water quality correlation index. Screen a candidate list of inactivators according to the correlation index, perform molecular structure simulation and activity evaluation on the candidate inactivators, and generate performance evaluation data. Through simulated emission, obtain emission range data, calculate the water pollution index, and optimize the emission range to evaluate the inactivation effect. Count the changes in the biological population on the shore, generate statistical data, perform actual inactivation statistics, and generate a biological inactivation statistical report. Combined with biological distribution and water quality prediction, screen out suitable inactivators, optimize the inactivation plan through simulated emission and water area risk calculation, reduce the potential impact on the water area, actually count the changes in the biological population, evaluate the inactivation effect, and provide feedback and improvement basis for the inactivation plan. Improve the inactivation effect of organisms in ballast water and evaluate and optimize their impact on the environment. Therefore, the present invention improves the safety and accuracy of inactivation by integrating data on water geography and biological populations, accurately predicting and optimizing inactivators.

[0129] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0130] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for inactivating organisms on shore in ballast water, characterized in that: The following steps are involved: Step S1: Acquire shore area image data; perform background separation on the shore area image data to obtain shore biological separation images and shore geographic information separation data; perform biological distribution feature extraction on the shore biological separation images to generate shore biological distribution feature data sets; perform biological population spatial analysis on the shore biological distribution feature data sets and shore geographic information separation data to generate biological population spatial distribution data; Step S2: Acquire water area geographic information data; connect a sensor network according to the water area geographic information data to generate a shore biological activity sensor network; use the shore biological activity sensor network to collect real-time data to obtain original real-time water quality data; use a convolutional neural network algorithm to model the original real-time water quality data to generate a water quality change prediction model; Step S3: Based on the water quality change prediction model, the original real-time water quality data is predicted to change water quality, and water quality change prediction data is generated; the biological population spatial distribution data and the water quality change prediction data are integrated to generate biological water quality integrated data; the biological water quality integrated data is imported into the water quality change prediction model to associate the biological-water quality model, and a biological water quality association index is generated; Step S4: Screening inactivators according to the biological water quality correlation index to obtain a candidate list of inactivators; performing molecular structure simulation on the candidate list of inactivators to generate optimized structure data of inactivating molecules; performing biological effect testing on the activity evaluation data of the inactivating molecules to generate inactivation performance evaluation data; comparing the inactivation performance evaluation data with a preset inactivation evaluation threshold to generate a ballast water inactivation plan; Step S5: simulate the discharge treatment through the ballast water inactivation scheme to generate simulated discharge range data; calculate the water area risk of the simulated discharge range data to generate a water area pollution index; optimize the discharge range of the range inactivation effect evaluation data according to the water area pollution index to generate ballast water discharge range optimization data; Step S6: Conducting ballast water discharge biological population statistics based on the ballast water discharge range optimization data to generate first statistical data on the onshore biological population; conducting a second onshore biological population statistics on the first statistical data on the onshore biological population at a preset time interval to generate second statistical data on the onshore biological population; conducting actual inactivation statistics based on the first statistical data on the onshore biological population and the second statistical data on the onshore biological population to generate a biological inactivation statistical report.

2. The method for inactivating organisms onshore in ballast water according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: using satellite sensors to obtain shore area image data; Step S12: performing image preprocessing on the shore area image data to generate standard shore area image data, wherein the image preprocessing includes image denoising, image correction and image enhancement; Step S13: performing background separation on the standard shore area image data to obtain a shore organism separation image and shore geographic information separation data; performing biological distribution feature extraction on the shore organism separation image to generate a shore organism distribution feature data set; Step S14: classifying the shore biological distribution characteristic data set based on computer vision technology to generate shore biological classification data; and identifying the species of the shore biological classification data to generate biological classification label data; Step S15: Integrate the biological classification label data and the shore geographic information separation data to generate shore biological distribution data; import the shore biological distribution data into the GIS system for three-dimensional reconstruction to generate biological distribution map data; perform biological population spatial analysis on the biological distribution map data to generate biological population spatial distribution data.

3. The method for inactivating organisms onshore in ballast water according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: Acquire water area geographic information data; deploy ocean sensors according to the water area geographic information data and generate an ocean sensor deployment sub-bureau map; deploy ground sensors according to the biological population spatial distribution data and generate a ground sensor deployment sub-bureau map; Step S22: Connecting the sensor network using the ocean sensor deployment sub-bureau map and the ground sensor deployment sub-bureau map to generate a shore biological activity sensor network; collecting real-time data through the shore biological activity sensor network to obtain original real-time water quality data; Step S23: performing data cleaning on the original real-time water quality data to generate real-time water quality cleaning data; performing data correction on the real-time water quality cleaning data to generate real-time water quality correction data; performing frequency domain feature extraction on the real-time water quality correction data based on the fast Fourier transform method to generate a water quality frequency domain feature data set; Step S24: divide the water quality frequency domain feature data set to generate a model training set and a model test set; use the convolutional neural network algorithm to construct a water quality change model for the model training set to generate a water quality change prediction model; use the model test set to optimize the water quality change prediction model to generate a water quality change prediction model.

4. The method for inactivating organisms onshore in ballast water according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: predicting water quality changes of the original real-time water quality data based on the water quality change prediction model to generate water quality change prediction data; integrating the biological population spatial distribution data and the water quality change prediction data to generate biological water quality integration data; Step S32: performing correlation analysis on the biological water quality integrated data to generate biological water quality related data; performing peak correlation screening on the biological water quality related data to generate high correlation analysis result data; Step S33: importing the high correlation analysis result data into the water quality change prediction model to associate the biological-water quality model, thereby generating a biological-water quality association model; performing a model effect evaluation on the biological-water quality association model to generate model evaluation data; Step S34: Compare the model evaluation data with the preset model evaluation threshold. When the model evaluation data is greater than or equal to the model evaluation threshold, the biological water quality correlation model is used to predict the biological water quality comprehensive evaluation index to generate a biological water quality correlation index; when the model evaluation data is less than the model evaluation threshold, return to step S32.

5. The method for inactivating organisms onshore in ballast water according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: Analyze the biological population characteristics of the onshore biological population according to the biological water quality association index and the biological water quality association model to generate a biological population characteristic data set; Step S42: Screening inactivators based on the biological population characteristic data set to obtain a candidate list of inactivators; performing molecular structure simulation on the candidate list of inactivators using molecular simulation technology to generate molecular structure simulation data; optimizing the molecular structure of the inactivator using the molecular structure simulation data to generate optimized structure data of the inactivator molecule; Step S43: performing molecular activity evaluation on the optimized structure data of the inactivated molecule to generate inactivated molecule activity evaluation data; performing biological effect test on the inactivated molecule activity evaluation data using a biological effect evaluation formula to generate inactivated performance evaluation data; Step S44: Compare the inactivation performance evaluation data with the preset inactivation evaluation threshold. When the inactivation performance evaluation data is greater than or equal to the inactivation evaluation threshold, an inactivation mechanism plan is formulated based on the activity performance evaluation data to generate a ballast water inactivation plan; when the inactivation performance evaluation data is less than the inactivation evaluation threshold, return to step S42 to re-screen the inactivator.

6. The method for inactivating organisms onshore in ballast water according to claim 5, characterized in that: The biological effect evaluation formula in step S43 is as follows: Where, E represents the biological effect assessment result, t represents the time range of the assessment, and C {drug} Expressed as the drug concentration at time t, C {target} It is expressed as the target concentration at time (t), α is expressed as the degree of enhancement of the biological effect of the drug, β is expressed as the degree of inhibition of the biological effect of the drug, γ is expressed as the influence index of the drug concentration, δ is expressed as the inhibition factor of the target concentration, ∈ is expressed as the influence index of the target concentration, and μ is expressed as the abnormal adjustment value for the biological effect evaluation.

7. The method for inactivating organisms onshore in ballast water according to claim 5, characterized in that: The inactivation mechanism scheme in step S44 is specifically formulated as follows: Collect ship ballast tank data; Determine the ship motion state corresponding to the ship's ballast water tank. When the ship is static, perform a first pressure discharge on the ship's ballast water tank data to obtain first discharge pressure data. When the ship is dynamic, perform a second pressure discharge on the ship's ballast water tank data to obtain second discharge pressure data. Performing a first ballast water discharge path analysis on the first discharge pressure data to generate first discharge path data; performing a second ballast water discharge path analysis on the second discharge pressure data to generate second discharge path data; The discharge water flow resistance is calculated by using the second discharge path data and the second discharge pressure data to generate the discharge water flow resistance data; the pressure water discharge diffusion analysis is performed on the first discharge path data to generate the first discharge diffusion data; Performing pressurized water discharge diffusion analysis on the second discharge path data based on the discharge water flow resistance data to generate second discharge diffusion data; The first discharge diffusion data and the second discharge diffusion data are visualized by using a data visualization method to generate a first discharge diffusion map and a second discharge diffusion map; the first discharge diffusion map and the second discharge diffusion map are compared in diffusion depth to generate repeated diffusion depth data and non-repeated diffusion depth data; the ballast water tank is dynamically pressure adjusted by using the non-repeated diffusion depth data to generate repeated diffusion depth data; The ballast water inactivation scheme is derived by adaptively controlling the discharge based on repeated diffusion depth data through a feedback loop.

8. The method for inactivating organisms onshore in ballast water according to claim 1, characterized in that: Step S5 includes the following steps: Step S51: performing simulated discharge processing through the ballast water inactivation scheme to generate simulated discharge data; Step S52: Determine the emission range based on the simulated emission data to generate simulated emission range data; evaluate the range inactivation effect on the simulated emission range data to generate range inactivation effect evaluation data; Step S53: using the water pollution risk index calculation formula to calculate the water risk of the range inactivation effect assessment data to generate a water pollution index; Step S54: Optimize the discharge range of the range inactivation effect evaluation data according to the water pollution index to generate ballast water discharge range optimization data.

9. The method for inactivating organisms onshore in ballast water according to claim 8, characterized in that: The water pollution risk index calculation formula in step S53 is as follows: In the formula, Z represents the water pollution risk index, N represents the number of pollution sources, M represents the number of monitoring points, L represents the number of degradation coefficients, O represents the number of pollutant emission sources, Q represents the number of environmental loads, R represents the number of environmental load assessment points, S represents the number of water quality sensitivity factors, U represents the number of water quality sensitivity assessment points, V represents the number of ecological risk factors, W represents the number of ecological risk assessment points, and C represents the number of water quality sensitivity factors, W represents the number of ecological risk assessment points, and C represents the number of water quality sensitivity factors, W represents the number of ecological risk assessment points, and C represents the number of water quality sensitivity factors, W represents the number of ecological risk assessment points, and C represents the number of water quality sensitivity factors, U represents the number of water quality sensitivity assessment points, V represents the number of ecological risk ... ecological risk factors, W represents the number of ecological risk assessment points, and C represents the number of environmental load assessment points. i Expressed as the concentration of the i-th pollution source, P j It is expressed as the area of ​​the jth monitoring point, A k Expressed as the degradation coefficient of the kth pollution source, B l Expressed as the emission of the lth pollutant emission source, D m Expressed as the value of the mth environmental load, E n Expressed as the area of ​​the nth environmental load assessment point, F p Expressed as the value of the pth water quality sensitivity factor, G q It is expressed as the area of ​​the qth water quality sensitivity assessment point, H r Expressed as the value of the rth ecological risk factor, I s It is represented as the area of ​​the sth ecological risk assessment point, and c is the assessment time range.

10. The method for inactivating organisms onshore in ballast water according to claim 1, characterized in that: Step S6 includes the following steps: Step S61: discharging ballast water according to the ballast water discharge range optimization data, and recording the discharge time to obtain a first discharge time; performing onshore biological population statistics according to the first discharge time to generate first onshore biological population statistics; Step S62: Conduct a second onshore biological population statistic on the first onshore biological population statistic at a preset time interval to generate a second onshore biological population statistic; conduct actual inactivation statistics based on the first onshore biological population statistic and the second onshore biological population statistic to generate a biological inactivation statistics report.

Images