Marine hormone pollution risk assessment method and system applied to swimming animals

Abstract

The invention discloses a marine hormone pollution risk assessment method and system applied to swimming animals, including: water quality sampling and hormone pollution detection, constructing a regional water hormone pollution status map; constructing a pollution change trend prediction model, and predicting the pollution change trend in combination with the regional water hormone pollution status map; analyzing the gathering place preference of swimming organisms in the target marine area, establishing a swimming organism food chain network in the target marine area based on population relationship data, and constructing an ecological simulation model; conducting biological sampling to analyze the biological hormone pollution status in the target marine area, and using the ecological simulation model to analyze the ecological response of the target marine area in the future time period; constructing a risk assessment model, and combining the ecological response analysis information to evaluate the hormone pollution risk of the target marine area in the future time period and provide early warning prompts. Improve the accuracy and comprehensiveness of marine hormone pollution risk assessment and protect the health and sustainability of the marine ecosystem.

Description

Technical Field

[0001] The present invention relates to the technical field of hormone pollution risk assessment, and in particular to a method and system for marine hormone pollution risk assessment applied to swimming animals. Background Art

[0002] Swimming animals, especially fish and marine mammals, may be exposed to these hormones through direct contact with contaminated water or indirect ingestion of contaminated prey. This exposure may not only lead to changes in physiological functions, such as reproductive disorders and growth retardation, but may also affect higher-level organisms through the food chain, thereby posing a threat to the entire ecosystem. Existing risk assessment methods usually use qualitative analysis or simple quantitative indicators, and lack a comprehensive understanding of the impact of hormone pollutants in complex ecosystems. Therefore, how to more effectively assess the potential risks of hormone pollution to swimming animals is an urgent problem to be solved. Summary of the invention

[0003] The present invention overcomes the defects of the prior art and provides a method and system for assessing the risk of marine hormone pollution applied to swimming animals. Its important purpose is to accurately assess the potential impact of hormone pollution on swimming animals and effectively protect the health and sustainability of the marine ecosystem.

[0004] To achieve the above-mentioned purpose, the present invention provides a method for assessing the risk of marine hormone pollution applied to swimming animals in a first aspect, comprising:

[0005] Divide the target marine area, obtain water quality samples from each sub-area and conduct hormone pollution detection to construct a regional water hormone pollution status map;

[0006] Constructing a pollution change trend prediction model, analyzing the water flow trend of the target ocean area and training the pollution change trend prediction model, and using the trained pollution change trend prediction model in combination with the hormone pollution status map of the water body in the area to predict the pollution change trend;

[0007] Analyze the gathering place preferences of swimming organisms in the target marine area, establish the food chain network of swimming organisms in the target marine area based on population relationship data, and construct an ecological simulation model of the target marine area;

[0008] Conduct biological sampling in the target marine area to analyze the bio-hormone pollution status in the target marine area, and use the ecological simulation model to analyze the ecological response of the target marine area in the future time period to obtain ecological response analysis information;

[0009] A risk assessment model is constructed, and the ecological response analysis information is input into the risk assessment model to analyze the hormone pollution risk of the target marine area in the future time period and provide early warning prompts.

[0010] In this scheme, the target ocean area is divided, water quality samples are obtained from each sub-area, hormone pollution detection is carried out, and a regional water hormone pollution status map is constructed, which specifically includes:

[0011] Divide the target ocean area into several sub-areas, and sample water quality in each sub-area based on the division results to obtain water quality sampling information;

[0012] Using high performance liquid chromatography technology to detect water hormone pollution according to the water quality sampling information, to obtain water hormone pollution detection information for each sub-area;

[0013] Obtain water environment parameter information of each sub-region, and generate a water hormone pollution status map of the target ocean area in combination with the water hormone pollution detection information of each sub-region;

[0014] The grid size is preset, and the hormone pollution status map of the water body is rasterized. The unknown grid cells are obtained according to the rasterization results, and the neighboring grid cells of the unknown grid cells are extracted. The interpolation interval is formed according to the hormone pollution data corresponding to the neighboring grid cells;

[0015] Interpolation processing is performed using linear interpolation method according to the interpolation interval to supplement the hormone pollution data of the unknown grid cells and generate a regional water hormone pollution status map.

[0016] In this solution, the pollution change trend prediction model is constructed, the water flow trend of the target ocean area is analyzed and the pollution change trend prediction model is trained, and the pollution change trend prediction is performed using the trained pollution change trend prediction model combined with the hormone pollution status map of the water body in the area, specifically including:

[0017] Acquire historical remote sensing monitoring images of the target ocean area and corresponding monitoring environment data based on big data retrieval, and perform image preprocessing on the historical remote sensing monitoring images to obtain preprocessed remote sensing images;

[0018] Extracting features from the preprocessed remote sensing image to obtain water flow characteristics in the target ocean area, and analyzing regional water flow trends using an ARIMA model to obtain regional water flow trend analysis information;

[0019] Preset the time step, combine the regional water flow trend analysis information to perform seasonal decomposition, analyze the seasonal water change law of the target ocean area, and associate the monitored environmental data as ancillary features to form a regional water change feature set;

[0020] Based on the regional water body change feature set, a regional water body change feature sequence is obtained, a Bayesian network is introduced, and the regional water body change feature sequence is input into the Bayesian network for calculation to obtain the water body flow state transition probability of the target ocean area;

[0021] A pollution change trend prediction model is constructed based on a deep neural network, the water flow state transition probability of the target ocean area is input into the pollution change trend prediction model for coding learning, and a training data set is constructed using the regional water body change feature set for model training;

[0022] Obtain the regional water hormone pollution status map, extract the regional water hormone pollution characteristics, set the pollution diffusion coefficient, and obtain the real-time monitoring environmental data of the target ocean area and input it into the pollution change trend prediction model after training to predict the pollution change trend and obtain the pollution change trend prediction information.

[0023] In this scheme, the analysis of the gathering place preferences of swimming organisms in the target marine area, the establishment of a swimming organism food chain network in the target marine area based on population relationship data, and the construction of an ecological simulation model of the target marine area specifically include:

[0024] Acquire swimming organism populations and population survival data in the target ocean area based on data retrieval, extract the adaptive characteristics of each swimming organism population based on the population survival data, and obtain adaptive characteristic information;

[0025] Acquire target ocean area environmental information, wherein the target ocean area environmental information includes regional terrain environmental information and regional water body environmental information; acquire a regional division result of the target ocean area, and associate each sub-area with a corresponding regional environmental feature in combination with the target ocean area environmental information to obtain first analysis information;

[0026] Calculating the similarity between the adaptation feature information and the first analysis information to obtain a similarity value, and sorting the sub-regions by swimming organism type according to the similarity value to obtain a sorting table of adaptation sub-regions for various types of swimming organisms;

[0027] Based on the ranking table of suitable sub-regions for various types of swimming organisms, the preferred gathering places of different types of swimming organisms in the target ocean area are analyzed to obtain gathering preference analysis information.

[0028] In this solution, the analysis of the gathering place preferences of swimming organisms in the target marine area, the establishment of a swimming organism food chain network in the target marine area based on population relationship data, and the construction of an ecological simulation model of the target marine area also include:

[0029] Obtain population relationship data according to the population categories of swimming organisms in the target ocean area, and construct a food chain network of swimming organisms in the target ocean area based on the population relationship data;

[0030] The energy flow model is combined with the constructed swimming organism food chain network to analyze the biomass and energy flow conditions of each food chain environment in the target marine area to obtain the second analysis information;

[0031] Extracting biological food chain characteristics of the target marine area based on the swimming biological food chain network, setting a number of experimental combinations according to the extracted biological food chain characteristics, evaluating the enrichment capacity of swimming animals and food sources for hormone pollutants through experimental results, and obtaining third analysis information;

[0032] The ecosystem dynamics control equation of the target ocean area is established in combination with the second analysis information and the third analysis information, and an ecological simulation model of the target ocean area is constructed according to the ecosystem dynamics control equation.

[0033] In this scheme, the biological sampling of the target marine area is used to analyze the bio-hormone pollution status in the target marine area, and the ecological simulation model is used to analyze the ecological response of the target marine area in the future time period, specifically including:

[0034] Conduct biological sampling in the target marine area, conduct regional bio-hormone pollution detection based on the biological samples obtained by sampling, and obtain regional bio-hormone pollution detection information;

[0035] Calculating the ratio of hormone pollutant concentrations in organisms at different trophic levels based on the regional biological hormone pollution detection information, and evaluating the enrichment of hormone pollutants in the food chain to obtain fourth analysis information;

[0036] Acquire pollution change trend prediction information, extract pollution change trend characteristics of the target ocean area in a future time period according to the pollution change trend prediction information, and obtain pollution change trend characteristic information;

[0037] Obtain the gathering place preference analysis information, combine the pollution change trend characteristic information, regional bio-hormone pollution detection information and the fourth analysis information, input them into the ecological simulation model for simulation, analyze the ecological response of the target ocean area in the future time period, and obtain ecological response analysis information.

[0038] In this scheme, the risk assessment model is constructed, the ecological response analysis information is input into the risk assessment model, the hormone pollution risk of the target marine area in the future time period is analyzed and early warning prompts are issued, specifically including:

[0039] Obtaining a marine hormone pollution risk assessment example, and extracting marine hormone pollution risk assessment indicators and historical assessment data of each assessment indicator according to the marine hormone pollution risk example;

[0040] Several risk level intervals are preset, risk assessment rules are constructed based on the acquired marine hormone pollution risk assessment indicators, and the risk assessment instance data set is constructed using the historical evaluation data of each evaluation indicator;

[0041] Constructing a risk assessment model according to the risk assessment rules, and training the risk assessment model using the risk assessment instance data set to obtain a risk assessment model that meets expectations;

[0042] Obtain ecological response analysis information, input the ecological response analysis information into the risk assessment model for analysis, output the hormone pollution risk assessment results for the target marine area in the future time period, and generate early warning information for early warning prompts.

[0043] The second aspect of the present invention provides a marine hormone pollution risk assessment system applied to swimming animals, the system comprising: a memory, a processor, the memory containing a marine hormone pollution risk assessment method program applied to swimming animals, the marine hormone pollution risk assessment method program applied to swimming animals when executed by the processor to implement the following steps:

[0044] Divide the target marine area, obtain water quality samples from each sub-area and conduct hormone pollution detection to construct a regional water hormone pollution status map;

[0045] Constructing a pollution change trend prediction model, analyzing the water flow trend of the target ocean area and training the pollution change trend prediction model, and using the trained pollution change trend prediction model in combination with the hormone pollution status map of the water body in the area to predict the pollution change trend;

[0046] Analyze the gathering place preferences of swimming organisms in the target marine area, establish the food chain network of swimming organisms in the target marine area based on population relationship data, and construct an ecological simulation model of the target marine area;

[0047] Conduct biological sampling in the target marine area to analyze the bio-hormone pollution status in the target marine area, and use the ecological simulation model to analyze the ecological response of the target marine area in the future time period to obtain ecological response analysis information;

[0048] A risk assessment model is constructed, and the ecological response analysis information is input into the risk assessment model to analyze the hormone pollution risk of the target marine area in the future time period and provide early warning prompts.

[0049] The invention discloses a marine hormone pollution risk assessment method and system applied to swimming animals, including: water quality sampling and hormone pollution detection, constructing a regional water hormone pollution status map; constructing a pollution change trend prediction model, and predicting the pollution change trend in combination with the regional water hormone pollution status map; analyzing the gathering place preference of swimming organisms in the target marine area, establishing a swimming organism food chain network in the target marine area based on population relationship data, and constructing an ecological simulation model; conducting biological sampling to analyze the biological hormone pollution status in the target marine area, and using the ecological simulation model to analyze the ecological response of the target marine area in the future time period; constructing a risk assessment model, and combining the ecological response analysis information to evaluate the hormone pollution risk of the target marine area in the future time period and provide early warning prompts. Improve the accuracy and comprehensiveness of marine hormone pollution risk assessment and protect the health and sustainability of the marine ecosystem. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments or exemplary embodiments of the present invention, the drawings required for use in the embodiments or exemplary descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained according to the drawings without paying creative work.

[0051] Figure 1 A flow chart of a method for assessing the risk of marine hormone pollution applied to swimming animals provided in one embodiment of the present invention;

[0052] Figure 2 A flow chart of a method for assessing the risk of marine hormone pollution in swimming animals provided by one embodiment of the present invention;

[0053] Figure 3 A block diagram of a marine hormone pollution risk assessment system for swimming animals provided by one embodiment of the present invention;

[0054] 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

[0055] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0056] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0057] Figure 1 A flow chart of a method for assessing the risk of marine hormone pollution applied to swimming animals provided in one embodiment of the present invention;

[0058] like Figure 1 As shown, the present invention provides a flow chart of a method for risk assessment of marine hormone pollution applied to swimming animals, comprising:

[0059] S102, dividing the target ocean area, obtaining water quality samples from each sub-area and conducting hormone pollution detection, and constructing a regional water hormone pollution status map;

[0060] S104, constructing a pollution change trend prediction model, analyzing the water flow trend of the target ocean area and training the pollution change trend prediction model, and using the trained pollution change trend prediction model in combination with the hormone pollution status map of the water body in the area to predict the pollution change trend;

[0061] S106, analyzing the gathering place preferences of swimming organisms in the target marine area, establishing a food chain network of swimming organisms in the target marine area based on population relationship data, and constructing an ecological simulation model of the target marine area;

[0062] S108, performing biological sampling on the target ocean area to analyze the bio-hormone pollution status in the target ocean area, and using the ecological simulation model to analyze the ecological response of the target ocean area in the future time period to obtain ecological response analysis information;

[0063] S110, constructing a risk assessment model, inputting the ecological response analysis information into the risk assessment model, analyzing the hormone pollution risk of the target marine area in the future time period and issuing early warning prompts.

[0064] It should be noted that the present invention provides a method and system for assessing the risk of marine hormone pollution applied to swimming animals, by sampling the water body in the target marine area, analyzing the hormone pollution status and constructing a regional water hormone pollution status map. By analyzing the water flow trend of the target marine area to form a training data set, the constructed pollution change trend prediction model is trained, and then the trained pollution change trend prediction model predicts the pollution change trend. Next, based on the adaptive habits of swimming animals, their gathering place preferences in the target marine area are analyzed, and then the swimming organism food chain network in the target marine area is established according to the population relationship data, and the ecological simulation model of the target marine area is further constructed. Subsequently, swimming organisms in the target area are sampled, biological hormone pollution detection is performed, and the ecological response of the target marine area in the future time period is analyzed using the ecological simulation model to obtain ecological response analysis information. Finally, a risk assessment model is constructed, the ecological response analysis information is input into the risk assessment model, the hormone pollution risk in the future time period of the target marine area is analyzed and early warning prompts are given, and the potential impact of hormone pollution on swimming animals is accurately assessed, thereby effectively protecting the health and sustainability of the marine ecosystem.

[0065] Furthermore, in a preferred embodiment of the present invention, the target ocean area is divided, water quality samples of each sub-area are obtained and hormone pollution detection is performed, and a regional water hormone pollution status map is constructed, which specifically includes:

[0066] Divide the target ocean area into several sub-areas, and sample water quality in each sub-area based on the division results to obtain water quality sampling information;

[0067] Using high performance liquid chromatography technology to detect water hormone pollution according to the water quality sampling information, to obtain water hormone pollution detection information for each sub-area;

[0068] Obtain water environment parameter information of each sub-region, and generate a water hormone pollution status map of the target ocean area in combination with the water hormone pollution detection information of each sub-region;

[0069] The grid size is preset, and the hormone pollution status map of the water body is rasterized. The unknown grid cells are obtained according to the rasterization results, and the neighboring grid cells of the unknown grid cells are extracted. The interpolation interval is formed according to the hormone pollution data corresponding to the neighboring grid cells;

[0070] Interpolation processing is performed using linear interpolation method according to the interpolation interval to supplement the hormone pollution data of the unknown grid cells and generate a regional water hormone pollution status map.

[0071] It should be noted that the target ocean area is divided into multiple sub-areas for water quality sampling and hormone pollution detection to generate a water hormone pollution status map of the target ocean area, that is, the macroscopic regional water hormone pollution status. Further rasterization is performed, and the unknown grids are interpolated and supplemented using linear interpolation to further generate a regional water hormone pollution status map, obtaining more abundant regional water hormone pollution status information, which provides a basis for subsequent analysis.

[0072] Further, in a preferred embodiment of the present invention, the pollution change trend prediction model is constructed, the water flow trend of the target ocean area is analyzed and the pollution change trend prediction model is trained, and the pollution change trend prediction is performed using the trained pollution change trend prediction model in combination with the hormone pollution status map of the regional water body, specifically including:

[0073] Acquire historical remote sensing monitoring images of the target ocean area and corresponding monitoring environment data based on big data retrieval, and perform image preprocessing on the historical remote sensing monitoring images to obtain preprocessed remote sensing images;

[0074] Extracting features from the preprocessed remote sensing image to obtain water flow characteristics in the target ocean area, and analyzing regional water flow trends using an ARIMA model to obtain regional water flow trend analysis information;

[0075] Preset the time step, combine the regional water flow trend analysis information to perform seasonal decomposition, analyze the seasonal water change law of the target ocean area, and associate the monitored environmental data as ancillary features to form a regional water change feature set;

[0076] Based on the regional water body change feature set, a regional water body change feature sequence is obtained, a Bayesian network is introduced, and the regional water body change feature sequence is input into the Bayesian network for calculation to obtain the water body flow state transition probability of the target ocean area;

[0077] A pollution change trend prediction model is constructed based on a deep neural network, the water flow state transition probability of the target ocean area is input into the pollution change trend prediction model for coding learning, and a training data set is constructed using the regional water body change feature set for model training;

[0078] Obtain the regional water hormone pollution status map, extract the regional water hormone pollution characteristics, set the pollution diffusion coefficient, and obtain the real-time monitoring environmental data of the target ocean area and input it into the pollution change trend prediction model after training to predict the pollution change trend and obtain the pollution change trend prediction information.

[0079] It should be noted that the historical remote sensing monitoring images and their corresponding environmental data are first obtained through big data retrieval technology. Next, the acquired remote sensing monitoring images are preprocessed to improve image quality and eliminate noise to ensure the accuracy of subsequent feature extraction. The preprocessed remote sensing images are used to extract the water flow characteristics of the target ocean area. The regional water flow trend analysis is performed by combining the autoregressive moving average (ARIMA) model to obtain the water flow trend information of the area. The regional water flow trend is seasonally decomposed by presetting the time step to reveal the seasonal water change law of the target ocean area. At the same time, the monitoring environmental data is used as an auxiliary feature to construct a regional water change feature set. Based on the constructed regional water change feature set, the water change feature sequence is extracted and input into the Bayesian network for calculation to obtain the water flow state transition probability of the target ocean area, reflecting the transition of water flow between different states. Subsequently, a pollution change trend prediction model is constructed based on a deep neural network, and the water flow state transition probability is input into the model for encoding learning. At the same time, the regional water change feature set is used to construct a training data set for model training. After the training is completed, the regional water hormone pollution status map is obtained, the pollution characteristics are extracted, and the pollution diffusion coefficient is set. The real-time monitoring environmental data of the target marine area is input into the trained pollution change trend prediction model to predict the pollution change trend of the real-time water hormone pollution in the target area.

[0080] Further, in a preferred embodiment of the present invention, the analysis of the gathering place preference of swimming organisms in the target marine area, the establishment of a swimming organism food chain network in the target marine area based on population relationship data, and the construction of an ecological simulation model of the target marine area specifically include:

[0081] Acquire swimming organism populations and population survival data in the target ocean area based on data retrieval, extract the adaptive characteristics of each swimming organism population based on the population survival data, and obtain adaptive characteristic information;

[0082] Acquire target ocean area environmental information, wherein the target ocean area environmental information includes regional terrain environmental information and regional water body environmental information; acquire a regional division result of the target ocean area, and associate each sub-area with a corresponding regional environmental feature in combination with the target ocean area environmental information to obtain first analysis information;

[0083] Calculating the similarity between the adaptation feature information and the first analysis information to obtain a similarity value, and sorting the sub-regions by swimming organism type according to the similarity value to obtain a sorting table of adaptation sub-regions for various types of swimming organisms;

[0084] Based on the ranking table of suitable sub-regions for various types of swimming organisms, the preferred gathering places of different types of swimming organisms in the target ocean area are analyzed to obtain gathering preference analysis information.

[0085] It should be noted that swimming organisms living in marine areas will gather in certain comfortable areas due to habits and environmental factors. This is called gathering preference. By analyzing the gathering preference, we can further understand the survival habits of swimming organisms in the target marine area, and then better analyze the impact of water hormone pollution on swimming organisms.

[0086] Further, in a preferred embodiment of the present invention, the analysis of the gathering place preference of swimming organisms in the target marine area, the establishment of a swimming organism food chain network in the target marine area based on population relationship data, and the construction of an ecological simulation model of the target marine area also include:

[0087] Obtain population relationship data according to the population categories of swimming organisms in the target ocean area, and construct a food chain network of swimming organisms in the target ocean area based on the population relationship data;

[0088] The energy flow model is combined with the constructed swimming organism food chain network to analyze the biomass and energy flow conditions of each food chain environment in the target marine area to obtain the second analysis information;

[0089] Extracting biological food chain characteristics of the target marine area based on the swimming biological food chain network, setting a number of experimental combinations according to the extracted biological food chain characteristics, evaluating the enrichment capacity of swimming animals and food sources for hormone pollutants through experimental results, and obtaining third analysis information;

[0090] The ecosystem dynamics control equation of the target ocean area is established in combination with the second analysis information and the third analysis information, and an ecological simulation model of the target ocean area is constructed according to the ecosystem dynamics control equation.

[0091] It should be noted that, firstly, the food chain network is constructed through the relationship data of different swimming organisms in the target marine area, covering the predation and prey relationship between various swimming organisms. After the swimming organism food chain network is established, the energy flow model is used to analyze each food chain in the network, evaluate the biomass and energy flow status in the target marine area, and obtain the second analysis information, revealing the role of different biological populations in the energy transfer process and its impact on the health of the ecosystem. Thus, key species and their functions in the food chain are identified, providing a scientific basis for ecological protection and management. Next, based on the constructed swimming organism food chain network, relevant biological food chain characteristics are extracted, and several experimental combinations are designed. The enrichment capacity of swimming animals and their food sources for hormone pollutants is evaluated through experimental results, and then the role of different organisms in the accumulation of hormone pollutants is quantified, providing important data support for pollution monitoring and ecological risk assessment. Finally, the ecosystem dynamics control equation of the target marine area is established by combining the second analysis information and the third analysis information, describing the interaction, energy flow and material cycle between various biological populations in the ecosystem, thereby providing a theoretical basis for understanding and predicting the dynamics of the ecosystem. According to the established control equation, an ecological simulation model of the target marine area is constructed to simulate the response of the ecosystem under different conditions.

[0092] Further, in a preferred embodiment of the present invention, the biological sampling of the target marine area to analyze the bio-hormone pollution status in the target marine area, and the use of the ecological simulation model to analyze the ecological response of the target marine area in the future time period specifically include:

[0093] Conduct biological sampling in the target marine area, conduct regional bio-hormone pollution detection based on the biological samples obtained by sampling, and obtain regional bio-hormone pollution detection information;

[0094] Calculating the ratio of hormone pollutant concentrations in organisms at different trophic levels based on the regional biological hormone pollution detection information, and evaluating the enrichment of hormone pollutants in the food chain to obtain fourth analysis information;

[0095] Acquire pollution change trend prediction information, extract pollution change trend characteristics of the target ocean area in a future time period according to the pollution change trend prediction information, and obtain pollution change trend characteristic information;

[0096] Obtain the gathering place preference analysis information, combine the pollution change trend characteristic information, regional bio-hormone pollution detection information and the fourth analysis information, input them into the ecological simulation model for simulation, analyze the ecological response of the target ocean area in the future time period, and obtain ecological response analysis information.

[0097] It should be noted that, first, biological sampling is carried out in the target marine area, representative biological samples are collected, and bio-hormone pollution detection is carried out to obtain regional bio-hormone pollution detection information. The ratio of hormone pollutant concentrations in organisms at different trophic levels is calculated to evaluate the degree of enrichment of hormone pollutants in the food chain. Next, by obtaining the pollution change trend prediction information, the pollution change trend characteristics in the future time period of the target marine area are extracted to obtain the pollution change trend characteristic information. Finally, the aggregation preference analysis information is combined with the pollution change trend characteristic information, the regional bio-hormone pollution detection information and the fourth analysis information, and input into the ecological simulation model for simulation, and the ecological response of the target marine area in the future time period is analyzed, so as to obtain the ecological response analysis information, understand the transmission and enrichment of pollutants in the food chain, and the response of organisms to pollutants.

[0098] Furthermore, in a preferred embodiment of the present invention, the risk assessment model is constructed, the ecological response analysis information is input into the risk assessment model, the hormone pollution risk of the target marine area in the future time period is analyzed and an early warning prompt is given, specifically including:

[0099] Obtaining a marine hormone pollution risk assessment example, and extracting marine hormone pollution risk assessment indicators and historical assessment data of each assessment indicator according to the marine hormone pollution risk example;

[0100] Several risk level intervals are preset, risk assessment rules are constructed based on the acquired marine hormone pollution risk assessment indicators, and the risk assessment instance data set is constructed using the historical evaluation data of each evaluation indicator;

[0101] Constructing a risk assessment model according to the risk assessment rules, and training the risk assessment model using the risk assessment instance data set to obtain a risk assessment model that meets expectations;

[0102] Obtain ecological response analysis information, input the ecological response analysis information into the risk assessment model for analysis, output the hormone pollution risk assessment results for the target marine area in the future time period, and generate early warning information for early warning prompts.

[0103] It should be noted that relevant risk assessment indicators and their historical evaluation data are extracted through examples of marine hormone pollution risks. On this basis, several risk level intervals are preset, and risk assessment rules are constructed based on the acquired marine hormone pollution risk assessment indicators. Then, the historical evaluation data of each evaluation indicator is used to construct a risk assessment instance data set. A risk assessment model is constructed using a random forest algorithm or a neural network, and the risk assessment model is trained using the risk assessment instance data set to obtain a risk assessment model that meets expectations. Finally, the ecological response analysis information is obtained and input into the trained risk assessment model for analysis, and the hormone pollution risk assessment results of the target marine area in the future time period are output and corresponding early warning information is generated to provide managers with early warning prompts to ensure that necessary management measures are taken in time to respond to potential pollution threats.

[0104] Figure 2 A flow chart of a method for assessing the risk of marine hormone pollution in swimming animals provided by one embodiment of the present invention;

[0105] like Figure 2 As shown, the present invention provides a flow chart of a method for assessing the risk of marine hormone pollution in swimming animals, comprising:

[0106] S202, dividing the target ocean area, collecting water quality samples from each sub-area to perform regional water hormone pollution detection, and generating a regional water hormone pollution status map;

[0107] S204, extracting water pollution characteristics based on the regional water hormone pollution status map, setting the pollution diffusion coefficient, and obtaining real-time monitoring environmental data to input into the pollution change trend prediction model to predict the pollution change trend;

[0108] S206, performing biological sampling on the target marine area to analyze the bio-hormone pollution status in the target marine area, and using the ecological simulation model to analyze the ecological response of the target marine area in the future time period;

[0109] S208, obtaining ecological response analysis information and inputting it into the risk assessment model, analyzing the hormone pollution risk of the target marine area in the future time period, and generating early warning information according to the risk assessment results.

[0110] In addition, in a marine hormone pollution risk assessment method applied to swimming animals provided by the present invention, the following steps are also included:

[0111] Obtain the marine hormone pollution risk assessment results of swimming animals in the target marine area, extract the marine hormone pollution risk levels of different types of swimming animals, and make judgments based on the preset thresholds;

[0112] If it is greater than the preset threshold, the corresponding species of swimming animals are defined as risk species, the hormone pollution characteristic information of risk species is obtained, and data retrieval is used to determine whether the risk species is an edible species;

[0113] If it is an edible species, the pollution control plan of the target marine area is obtained, and the pollution control efficiency characteristics are extracted according to the pollution control plan;

[0114] Analyze the hormone pollution change trend of the target risk species according to the pollution control efficiency characteristics and the hormone pollution characteristic information of the risk species, and generate a hormone pollution change trend graph of the risk species;

[0115] Preset a safety threshold, and build a change curve chart that associates the pollution change degree characteristic with the pollution change time characteristic based on the risk species hormone pollution change trend chart. Combined with the safety threshold, determine the consumption time for the target risk species hormone pollution to be remediated within the safety threshold, and obtain consumption time analysis information;

[0116] A prohibited time interval for prohibiting fishing of target risk species is generated based on the consumption time analysis information, and a fishing ban recommendation is made.

[0117] It should be noted that during the hormone pollution control process, the pollution control cannot be completed in a very short time due to the timeliness of the control plan. At the same time, due to the possibility of fishing activities in the marine area, the capture of swimming organisms with hormone pollution in the marine area may bring health risks to consumers. Therefore, the risk species in the marine area and the decline time of hormone pollution in the risk species are analyzed, and it is recommended to prohibit the capture of corresponding swimming animals during this period to ensure the health and safety of consumers.

[0118] Figure 3 A marine hormone pollution risk assessment system 3 applied to swimming animals is provided in one embodiment of the present invention. The system includes: a memory 31 and a processor 32. The memory 31 contains a marine hormone pollution risk assessment method program applied to swimming animals. When the marine hormone pollution risk assessment method program applied to swimming animals is executed by the processor 32, the following steps are implemented:

[0119] Divide the target marine area, obtain water quality samples from each sub-area and conduct hormone pollution detection to construct a regional water hormone pollution status map;

[0120] Constructing a pollution change trend prediction model, analyzing the water flow trend of the target ocean area and training the pollution change trend prediction model, and using the trained pollution change trend prediction model in combination with the hormone pollution status map of the water body in the area to predict the pollution change trend;

[0121] Analyze the gathering place preferences of swimming organisms in the target marine area, establish the food chain network of swimming organisms in the target marine area based on population relationship data, and construct an ecological simulation model of the target marine area;

[0122] Conduct biological sampling in the target marine area to analyze the bio-hormone pollution status in the target marine area, and use the ecological simulation model to analyze the ecological response of the target marine area in the future time period to obtain ecological response analysis information;

[0123] A risk assessment model is constructed, and the ecological response analysis information is input into the risk assessment model to analyze the hormone pollution risk of the target marine area in the future time period and provide early warning prompts.

[0124] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0125] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0126] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0127] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0128] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0129] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for assessing the risk of marine hormone pollution in swimming animals, characterized in that: include: Divide the target marine area, obtain water quality samples from each sub-area and conduct hormone pollution detection to construct a regional water hormone pollution status map; Constructing a pollution change trend prediction model, analyzing the water flow trend of the target ocean area and training the pollution change trend prediction model, and using the trained pollution change trend prediction model in combination with the hormone pollution status map of the water body in the area to predict the pollution change trend; Analyze the gathering place preferences of swimming organisms in the target marine area, establish the food chain network of swimming organisms in the target marine area based on population relationship data, and construct an ecological simulation model of the target marine area; Conduct biological sampling in the target marine area to analyze the bio-hormone pollution status in the target marine area, and use the ecological simulation model to analyze the ecological response of the target marine area in the future time period to obtain ecological response analysis information; Constructing a risk assessment model, inputting the ecological response analysis information into the risk assessment model, analyzing the hormone pollution risk of the target marine area in the future time period and providing early warning prompts; Obtain the marine hormone pollution risk assessment results of swimming animals in the target marine area, extract the marine hormone pollution risk levels of different types of swimming animals, and make judgments based on the preset thresholds; If it is greater than the preset threshold, the corresponding species of swimming animals are defined as risk species, the hormone pollution characteristic information of risk species is obtained, and data retrieval is used to determine whether the risk species is an edible species; If it is an edible species, the pollution control plan of the target marine area is obtained, and the pollution control efficiency characteristics are extracted according to the pollution control plan; Analyze the hormone pollution change trend of the target risk species according to the pollution control efficiency characteristics and the hormone pollution characteristic information of the risk species, and generate a hormone pollution change trend graph of the risk species; Preset a safety threshold, and build a change curve chart that associates the pollution change degree characteristic with the pollution change time characteristic based on the risk species hormone pollution change trend chart. Combined with the safety threshold, determine the consumption time for the target risk species hormone pollution to be remediated within the safety threshold, and obtain consumption time analysis information; Generate a prohibited time interval for prohibiting fishing of target risk species based on the consumption time analysis information, and make a fishing ban recommendation; The method of constructing a pollution change trend prediction model, analyzing the water flow trend of the target ocean area and training the pollution change trend prediction model, and using the trained pollution change trend prediction model in combination with the regional water hormone pollution status map to predict the pollution change trend, specifically includes: Acquire historical remote sensing monitoring images of the target ocean area and corresponding monitoring environment data based on big data retrieval, and perform image preprocessing on the historical remote sensing monitoring images to obtain preprocessed remote sensing images; Extracting features from the preprocessed remote sensing image to obtain water flow characteristics in the target ocean area, and analyzing regional water flow trends using an ARIMA model to obtain regional water flow trend analysis information; Preset the time step, combine the regional water flow trend analysis information to perform seasonal decomposition, analyze the seasonal water change law of the target ocean area, and associate the monitored environmental data as ancillary features to form a regional water change feature set; Based on the regional water body change feature set, a regional water body change feature sequence is obtained, a Bayesian network is introduced, and the regional water body change feature sequence is input into the Bayesian network for calculation to obtain the water body flow state transition probability of the target ocean area; A pollution change trend prediction model is constructed based on a deep neural network, the water flow state transition probability of the target ocean area is input into the pollution change trend prediction model for coding learning, and a training data set is constructed using the regional water body change feature set for model training; Obtain the regional water hormone pollution status map, extract the regional water hormone pollution characteristics, set the pollution diffusion coefficient, and obtain the real-time monitoring environmental data of the target ocean area and input it into the pollution change trend prediction model after training to predict the pollution change trend and obtain the pollution change trend prediction information.

2. A method for assessing marine hormone pollution risk for swimming animals according to claim 1, characterized in that: The target ocean area is divided, water quality samples are obtained from each sub-area, hormone pollution detection is performed, and a regional water hormone pollution status map is constructed, specifically including: Divide the target ocean area into several sub-areas, and sample water quality in each sub-area based on the division results to obtain water quality sampling information; Using high performance liquid chromatography technology to detect water hormone pollution based on the water quality sampling information, to obtain water hormone pollution detection information for each sub-area; Obtain water environment parameter information of each sub-region, and generate a water hormone pollution status map of the target ocean area in combination with the water hormone pollution detection information of each sub-region; The grid size is preset, and the hormone pollution status map of the water body is rasterized. The unknown grid cells are obtained according to the rasterization results, and the neighboring grid cells of the unknown grid cells are extracted. The interpolation interval is formed according to the hormone pollution data corresponding to the neighboring grid cells; Interpolation processing is performed using linear interpolation method according to the interpolation interval to supplement the hormone pollution data of the unknown grid cells and generate a regional water hormone pollution status map.

3. A method for assessing the risk of marine hormone pollution in swimming animals according to claim 1, characterized in that: The analysis of the gathering place preferences of swimming organisms in the target marine area, the establishment of a food chain network of swimming organisms in the target marine area based on population relationship data, and the construction of an ecological simulation model of the target marine area specifically include: Acquire swimming organism populations and population survival data in the target ocean area based on data retrieval, extract the adaptive characteristics of each swimming organism population based on the population survival data, and obtain adaptive characteristic information; Acquire target ocean area environmental information, wherein the target ocean area environmental information includes regional terrain environmental information and regional water body environmental information; acquire a regional division result of the target ocean area, and associate each sub-area with a corresponding regional environmental feature in combination with the target ocean area environmental information to obtain first analysis information; Calculating the similarity between the adaptation feature information and the first analysis information to obtain a similarity value, and sorting the sub-regions by swimming organism type according to the similarity value to obtain a sorting table of adaptation sub-regions for various types of swimming organisms; Based on the ranking table of suitable sub-regions for various types of swimming organisms, the preferred gathering places of different types of swimming organisms in the target ocean area are analyzed to obtain gathering preference analysis information.

4. The method for risk assessment of marine hormone pollution applied to swimming animals according to claim 1, characterized in that: The analysis of the gathering place preferences of swimming organisms in the target ocean area, establishing a food chain network of swimming organisms in the target ocean area based on population relationship data, and constructing an ecological simulation model of the target ocean area also includes: Obtain population relationship data according to the population categories of swimming organisms in the target ocean area, and construct a food chain network of swimming organisms in the target ocean area based on the population relationship data; The energy flow model is combined with the constructed swimming organism food chain network to analyze the biomass and energy flow conditions of each food chain environment in the target marine area to obtain the second analysis information; Extracting biological food chain characteristics of the target marine area based on the swimming biological food chain network, setting a number of experimental combinations according to the extracted biological food chain characteristics, evaluating the enrichment capacity of swimming animals and food sources for hormone pollutants through experimental results, and obtaining third analysis information; The ecosystem dynamics control equation of the target ocean area is established in combination with the second analysis information and the third analysis information, and an ecological simulation model of the target ocean area is constructed according to the ecosystem dynamics control equation.

5. The method for risk assessment of marine hormone pollution applied to swimming animals according to claim 1, characterized in that: The biological sampling of the target marine area is used to analyze the bio-hormone pollution status in the target marine area, and the ecological simulation model is used to analyze the ecological response of the target marine area in the future time period, specifically including: Conduct biological sampling in the target marine area, conduct regional bio-hormone pollution detection based on the biological samples obtained by sampling, and obtain regional bio-hormone pollution detection information; Calculating the ratio of hormone pollutant concentrations in organisms at different trophic levels based on the regional biological hormone pollution detection information, and evaluating the enrichment of hormone pollutants in the food chain to obtain fourth analysis information; Acquire pollution change trend prediction information, extract pollution change trend characteristics of the target ocean area in a future time period according to the pollution change trend prediction information, and obtain pollution change trend characteristic information; Obtain the gathering place preference analysis information, combine the pollution change trend characteristic information, regional bio-hormone pollution detection information and the fourth analysis information, input them into the ecological simulation model for simulation, analyze the ecological response of the target ocean area in the future time period, and obtain ecological response analysis information.

6. The method for risk assessment of marine hormone pollution applied to swimming animals according to claim 1, characterized in that: The risk assessment model is constructed, the ecological response analysis information is input into the risk assessment model, the hormone pollution risk of the target marine area in the future time period is analyzed and early warning prompts are issued, specifically including: Obtaining a marine hormone pollution risk assessment example, and extracting marine hormone pollution risk assessment indicators and historical assessment data of each assessment indicator according to the marine hormone pollution risk assessment example; Several risk level intervals are preset, risk assessment rules are constructed based on the acquired marine hormone pollution risk assessment indicators, and the risk assessment instance data set is constructed using the historical evaluation data of each evaluation indicator; Constructing a risk assessment model according to the risk assessment rules, and training the risk assessment model using the risk assessment instance data set to obtain a risk assessment model that meets expectations; Obtain ecological response analysis information, input the ecological response analysis information into the risk assessment model for analysis, output the hormone pollution risk assessment results for the target marine area in the future time period, and generate early warning information for early warning prompts.

7. A marine hormone pollution risk assessment system applied to swimming animals, characterized in that: The system includes: a memory and a processor, wherein the memory contains a marine hormone pollution risk assessment method program applied to swimming animals, and the marine hormone pollution risk assessment method program applied to swimming animals is executed by the processor as the steps of a marine hormone pollution risk assessment method applied to swimming animals as described in any one of claims 1-6.

Images