A neural network-based aquatic ecological restoration plant community management method and system

Abstract

The application discloses a kind of water ecological restoration plant community management method and system based on neural network, method includes: based on SOFM neural network, water body stratification detection is carried out to target water area, and stratification result is obtained;According to stratification result, dynamic hydrological data sampling is carried out to each water layer using water body monitoring equipment, and the sampling result of each water layer is obtained;According to aquatic plant distribution data and aquatic animal distribution data, corresponding biological information and water layer natural ecological environment data are called to construct target database;Based on BP neural network, according to target database, determine the dynamic change rule of target water area within a predetermined time;Judge whether the dynamic change rule meets the preset restoration target, according to the judgment result, based on ecological restoration principle, calculate the plant species and corresponding quantity required for each water layer, and obtain the calculation result;According to the calculation result, the plant community of target water area is managed using plant management equipment.

Description

Technical Field

[0001] This invention belongs to the field of aquatic ecological restoration technology, specifically relating to a method and system for managing aquatic ecological restoration plant communities based on neural networks. Background Technology

[0002] One of the main causes of black and odorous water bodies is oxygen deficiency, which is further exacerbated by water stratification. However, traditional water ecological restoration methods can only achieve horizontal circulation of surface water and cannot improve the vertical stratification of water bodies, making it difficult to carry out in-depth water ecological restoration of deep water bodies.

[0003] To address the problems of traditional aquatic ecological restoration methods, existing technologies propose a matching method based on aquatic ecological restoration plant communities. This method involves analyzing natural data of the target water area and selecting appropriate aquatic plant communities for its treatment. However, existing aquatic ecological restoration technologies only consider the ecological restoration effect of aquatic plants on stratified water bodies, without considering the impact of aquatic animals on aquatic plants in the target water area, or the continuous impact of aquatic animals on the ecological environment of the target water area. Summary of the Invention

[0004] In view of this, the purpose of this invention is to provide a method and system for managing aquatic ecological restoration plant communities based on neural networks, in order to solve the above-mentioned technical problems.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] A neural network-based method for managing aquatic ecosystem restoration plant communities includes:

[0007] The SOFM neural network is used to perform water stratification detection on the target water area and obtain the stratification results.

[0008] Based on the stratification results, dynamic hydrological data were sampled for each water layer using water monitoring equipment to obtain the sampling results for each water layer; the sampling results include data on the distribution of aquatic plants, aquatic animals, and the natural ecological environment of the water layer;

[0009] Based on the distribution data of aquatic plants and aquatic animals, the target database is constructed by calling the corresponding biological information and natural ecological environment data of the water body layer;

[0010] Based on a BP neural network, the dynamic change pattern of the target water area within a preset time period is determined according to the target database;

[0011] Determine whether the dynamic change pattern meets the preset restoration target. Based on the determination result and the principle of ecological restoration, calculate the required plant species and corresponding quantities for each water layer to obtain the calculation results.

[0012] Based on the calculation results, plant management equipment was used to manage the plant community in the target water area.

[0013] Furthermore, based on the SOFM neural network, water stratification detection was performed on the target water area to obtain stratification results, including:

[0014] The controller controls the lifting motor to carry the water monitoring equipment to the target water area for adaptive data acquisition, obtaining an initial natural dataset; the initial natural dataset is preprocessed to obtain a training dataset; the initial natural data includes dissolved oxygen data, temperature data, and water pH value;

[0015] Initialize the SOFM neural network, and iteratively train the initialized SOFM neural network according to the training dataset until the number of iterations meets the preset conditions, and the target SOFM neural network is obtained.

[0016] The topology of the target SOFM neural network in the output layer is obtained, the topology is analyzed, and water stratification detection of the target water area is realized to obtain the stratification results.

[0017] The topology is used to reflect the relationships between training data in the training dataset;

[0018] When analyzing the topology, each group of neurons in the output layer of the target SOFM neural network represents a water body layer of the target water area, and its corresponding weight vector represents the initial natural data of the current water body layer.

[0019] Furthermore, based on the stratification results, dynamic hydrological data were sampled for each water layer using water monitoring equipment to obtain the sampling results for each water layer, including:

[0020] Based on the stratification results, multiple water layers in the target water area are identified;

[0021] Based on random sampling methods, multiple sampling areas are set for each water layer of the target water area;

[0022] Dynamic hydrological data were sampled for each sampling area using water monitoring equipment, resulting in multiple dynamic hydrological sampling results for each water layer.

[0023] Multiple dynamic hydrological sampling results for each water body layer are integrated to obtain a unique sampling result for each water body layer; the sampling result includes aquatic plant distribution data, aquatic animal distribution data, and natural ecological environment data for each water body layer;

[0024] Aquatic plant distribution data includes aquatic plant category distribution data and aquatic plant quantity distribution data;

[0025] The aquatic animal distribution data includes data on the distribution of aquatic animal categories and data on the distribution of aquatic animal populations;

[0026] The natural ecological environment data of the aquatic layer includes dissolved oxygen data, temperature data, and water pH value.

[0027] Furthermore, based on aquatic plant and aquatic animal distribution data, a target database is constructed by calling corresponding biological information and natural ecological environment data of the aquatic layer, including:

[0028] Obtain aquatic plant category data from the aquatic plant distribution data;

[0029] Obtain aquatic animal category data from the aquatic animal distribution data;

[0030] Based on data on aquatic plant categories and aquatic animal categories, and using network communication methods, a target database is constructed by calling corresponding biological information and natural ecological environment data of the water body layer.

[0031] The corresponding biological information includes information on aquatic plants and aquatic animals;

[0032] Information on aquatic plants includes plant species, suitable water depth, suitable water temperature, suitable water pH value, and dissolved oxygen growth rate;

[0033] Information on aquatic animals includes animal species, suitable water depth, suitable water temperature, suitable water pH, oxygen consumption rate, types of plants they graze on, and the efficiency of plant grazing.

[0034] Furthermore, based on a BP neural network, the dynamic change patterns of the target water area within a preset time period are determined according to the target database, including:

[0035] Historical dynamic hydrological data of several water bodies were acquired to construct a training dataset. The dynamic hydrological data included aquatic plant data, aquatic animal data, and natural ecological environment data of each water layer at different time scales.

[0036] Aquatic plant data includes aquatic plant distribution data and aquatic plant information;

[0037] Aquatic animal data includes aquatic animal distribution data and aquatic animal information;

[0038] Based on the training dataset, a BP neural network is used to simulate the response patterns of aquatic plants and animals in different water layers at various time scales to changes in the natural ecological environment data of each water layer under the condition of no human interference, and a BP neural network prediction model is generated.

[0039] Information from the target database is used as input data and fed into the BP neural network prediction model. The output reveals the dynamic changes among aquatic plant data, aquatic animal data, and natural ecological environment data in the target water area.

[0040] Furthermore, determine whether the dynamic change pattern meets the preset repair target, including:

[0041] To obtain the dynamic change patterns among aquatic plant data, aquatic animal data, and aquatic natural ecological environment data in the target water area;

[0042] Obtain the target time scale, and determine the target time nodes in the dynamic change pattern based on the target time scale;

[0043] Based on the target time points, obtain the target natural ecological environment data corresponding to the dynamic change patterns;

[0044] Determine whether the target natural ecological environment meets the preset restoration goals and generate the determination result;

[0045] The judgment result is that the target natural ecological environment meets the preset restoration target;

[0046] Alternatively, the target natural ecological environment may not meet the preset restoration goals.

[0047] Furthermore, based on the assessment results and the principles of ecological restoration, the required plant species and quantities for each water layer were calculated, yielding the following results:

[0048] If the judgment result indicates that the target natural ecological environment does not meet the preset restoration target, obtain the ecological restoration principles:

[0049]

[0050] in, For the preset remediation target of the j-th water layer, Let be the number of aquatic plant species in the j-th water layer. Let be the matching coefficient of the i-th aquatic plant in the j-th water layer. The total dissolved oxygen growth rate of the i-th aquatic plant in the target water area per unit time. Let be the average growth efficiency of the i-th aquatic plant per unit time. Let be the average phytophagy efficiency of the k-th aquatic animal on the i-th aquatic plant per unit time. The total oxygen consumption rate of the k-th aquatic animal in the target water area per unit time;

[0051]

[0052] when When, it indicates that the matching relationship between the i-th aquatic plant and the j-th water layer is a match, when When, it indicates that the matching relationship between the i-th aquatic plant and the j-th water layer is not a match. This indicates that the suitable water depth, suitable water temperature, and suitable water pH value of the i-th aquatic plant are matched with the temperature data and water pH value of the j-th water layer.

[0053] Calculate the required plant species and quantities for each water layer to ensure that the left and right equations of the ecological restoration principle are equal, and obtain the calculation results.

[0054] Furthermore, based on the calculation results, plant management equipment is used to manage the plant community in the target water area, including:

[0055] Obtain the required plant species and quantities for each water layer included in the calculation results;

[0056] Based on the different water layers, the corresponding plant management equipment is activated;

[0057] Control the corresponding plant management equipment to load the required plant species and quantities for the corresponding water layer, and then proceed to the corresponding location in the target water area to deploy the plants.

[0058] In the process of obtaining the required plant species and corresponding quantities for each water layer, The corresponding distribution location of the i-th aquatic plant is determined, and the corresponding aquatic plant harvesting system is invoked to cut and recycle the i-th aquatic plant.

[0059] Furthermore, a neural network-based approach to aquatic ecosystem restoration plant community management also includes:

[0060] The starting point is the moment when the plant management equipment manages the plant community in the target water area and the management ends.

[0061] Acquire historical dissolved oxygen data and historical biological content information of different water layers in the target water area after a preset second time point from the starting time point;

[0062] Analyze historical dissolved oxygen data to obtain the historical dissolved oxygen change rate of different water layers for each unit of time.

[0063] Analyzing historical biomass information yields historical biomass information for each organism in different water layers within each unit of time.

[0064] Obtain information on the rate of change of dissolved oxygen and the biomass content of different water layers after a unit of time has elapsed at the current moment.

[0065] To obtain dynamic change patterns and extract standard biological content information of different water layers after a unit of time has elapsed at the current moment;

[0066] The water ecological restoration detection score of the current target water area is calculated based on the historical dissolved oxygen change rate, historical biological content information, dissolved oxygen change rate, biological content information, and standard biological content information. The water ecological restoration detection score and preset threshold are used to determine whether the current water ecological restoration progress meets the preset restoration progress.

[0067] A neural network-based aquatic ecosystem restoration plant community management system includes:

[0068] The water stratification detection module is used to perform water stratification detection on the target water area based on the SOFM neural network and obtain the stratification results.

[0069] The hydrological data sampling module is used to dynamically sample hydrological data for each water layer using water monitoring equipment based on the stratification results, and obtain the sampling results for each water layer. The sampling results include aquatic plant distribution data, aquatic animal distribution data, and natural ecological environment data of the water layer.

[0070] The database module is used to construct the target database by calling corresponding biological information and natural ecological environment data of the water body layer based on the distribution data of aquatic plants and aquatic animals.

[0071] The water area data dynamic change monitoring module is used to determine the dynamic change pattern of the target water area within a preset time period based on the target database using a BP neural network.

[0072] The plant community restoration calculation module is used to determine whether the dynamic change pattern meets the preset restoration target. Based on the judgment result and the principle of ecological restoration, it calculates the required plant species and corresponding quantities for each water layer and obtains the calculation results.

[0073] The plant community management module is used to manage the plant community in the target water area using plant management equipment based on the calculation results.

[0074] The beneficial effects of this invention are as follows:

[0075] This invention proposes a neural network-based method for managing aquatic ecological restoration plant communities. It employs a SOFM neural network to accurately stratify target water bodies based on pollution levels at different water layers, improving the efficiency of subsequent aquatic ecological restoration. Furthermore, during the restoration process, a BP neural network is used to predict the dynamic changes in the interdependence between flora, fauna, and natural data. This dynamic change pattern enables dynamic restoration of the aquatic ecological environment, enhancing the reliability of ecological restoration in the target water body. Ultimately, this method achieves ecological self-circulation restoration for different water layers, thus fulfilling the goal of aquatic ecological restoration.

[0076] Other advantages, objectives, and features of the invention will be set forth in the following description and will be apparent to those skilled in the art in some respects, or may be learned by practice of the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings.

[0077] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0078] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0079] Figure 1 This is a flowchart of a method and system for managing aquatic ecological restoration plant communities based on neural networks, as described in an embodiment of the present invention.

[0080] Figure 2 This is a flowchart illustrating the sampling process of the water layer in a water ecological restoration plant community management method and system based on neural networks, as described in an embodiment of the present invention.

[0081] Figure 3 This is a schematic diagram of the system modules of a water ecological restoration plant community management method and system based on neural networks in an embodiment of the present invention. Detailed Implementation

[0082] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0083] Please see Figure 1 This invention proposes a method for managing aquatic ecological restoration plant communities based on neural networks, comprising:

[0084] S101. Based on the SOFM neural network, water stratification detection is performed on the target water area to obtain the stratification results;

[0085] S102. Based on the stratification results, dynamic hydrological data are sampled for each water layer using water body monitoring equipment to obtain the sampling results for each water layer; among which, the sampling results include aquatic plant distribution data, aquatic animal distribution data, and natural ecological environment data of the water layer;

[0086] S103. Based on the distribution data of aquatic plants and aquatic animals, construct a target database by calling the corresponding biological information and natural ecological environment data of the water body layer;

[0087] S104. Based on the BP neural network, determine the dynamic change pattern of the target water area within a preset time according to the target database;

[0088] S105. Determine whether the dynamic change pattern meets the preset restoration target. Based on the judgment result and the principle of ecological restoration, calculate the required plant species and corresponding quantities for each water layer and obtain the calculation results.

[0089] S106. Based on the calculation results, use plant management equipment to manage the plant community in the target water area;

[0090] The working principle of the above technical solution is as follows: In the actual aquatic ecological environment, when an area can complete a perfect ecological self-circulation, it must meet the ecological cycle system of animals and plants. However, the existing water ecological restoration technology only uses plants to perform stratified ecological restoration of water bodies, without combining the actual aquatic ecological environment for dynamic restoration. Therefore, this invention proposes a water ecological restoration plant community management method based on neural networks to solve the above problems.

[0091] First, SOFM neural network is used to perform cluster analysis on hydrological data to detect water stratification in the target water area, delineating regions with obvious eco-hydrological characteristics and obtaining stratification results. Existing water stratification methods include surface layer, thermocline, isothermal layer, bottom layer, and sedimentary layer. Compared with existing conventional water stratification methods, this method can perform cluster analysis based on the eco-hydrological characteristics of polluted water bodies and accurately stratify water bodies based on specific pollution data, which facilitates the subsequent arrangement of appropriate quantities and types of plants for precise remediation of the water body stratification. The polluted water body mainly described in this paper is a black and odorous water body formed due to water hypoxia.

[0092] After obtaining the test results, dynamic hydrological data are sampled for each water layer using water monitoring equipment to obtain the sampling results for each water layer, i.e., the dynamic hydrological data for each water layer; among which, the sampling results include aquatic plant distribution data, aquatic animal distribution data, and natural ecological environment data of the water layer;

[0093] The distribution data of aquatic plants and aquatic animals are the distribution density and distribution location of different plants and animals in each water layer. It is worth noting that it is preferable to divide each water layer into zones according to the species of plants or animals, and then calculate the distribution density of the corresponding plants or animals based on the zoning results, while determining the distribution location.

[0094] Natural ecological environment data of the water body includes, but is not limited to, dissolved oxygen data, temperature data, water flow direction data, pH value and other natural direction data of the water body;

[0095] Then, based on the distribution data of aquatic plants and aquatic animals, the basic data of each individual in the corresponding biological information is called up using the network or other feasible links, and the natural ecological environment data of all water layers are used to construct the target database. This step is beneficial for individual monitoring of all groups in the target water area, which facilitates the subsequent controllable management of the plant community in the target water area.

[0096] Then, using a BP neural network, the dynamic change pattern of the target water area within a preset time period is determined based on the target database, that is, the change pattern of oxygen content in the target water area under the condition of no human interference in the subsequent time period is predicted.

[0097] It also determines whether the dynamic change pattern meets the preset restoration target. Based on the judgment result and the principle of ecological restoration, it calculates the required plant species and corresponding quantities for each water layer and obtains the calculation results.

[0098] Based on the calculation results, plant management equipment is used to manage the plant community in the target water area; management includes, but is not limited to, various methods such as harvesting, planting and relocation;

[0099] The beneficial effects of the above technical solution are as follows: By using the above technical solution to accurately stratify the target water area according to the pollution status of different water layers, it is beneficial to improve the efficiency of subsequent water ecological restoration. At the same time, in the process of water ecological restoration, the dynamic change law of the dependence relationship between animals, plants and natural data is predicted by using the BP neural network. The dynamic change law is used to realize the dynamic restoration of the water ecological environment, which is beneficial to improve the reliability of ecological environment restoration of the target water area. Ultimately, it can achieve ecological self-circulation restoration for different water layers and achieve the purpose of water ecological restoration.

[0100] In one embodiment, water stratification detection of the target water area is performed based on a SOFM neural network to obtain stratification results, including:

[0101] The controller controls the lifting motor to carry the water monitoring equipment to the target water area for adaptive data acquisition, and obtains the initial natural dataset; the initial natural dataset is preprocessed to obtain the training dataset; the initial natural data includes dissolved oxygen data, temperature data and water pH value;

[0102] Initialize the SOFM neural network, and iteratively train the initialized SOFM neural network according to the training dataset until the number of iterations meets the preset conditions, and the target SOFM neural network is obtained.

[0103] The topology of the target SOFM neural network in the output layer is obtained, the topology is analyzed, and water stratification detection of the target water area is realized to obtain the stratification results.

[0104] The topology is used to reflect the relationships between training data in the training dataset;

[0105] When analyzing the topology, each group of neurons in the output layer of the target SOFM neural network represents a water body layer of the target water area, and its corresponding weight vector represents the initial natural data of the current water body layer.

[0106] The working principle of the above technical solution is as follows: Before carrying out aquatic ecological restoration of the target water area, the controller first uses a lifting motor to carry water monitoring equipment to adaptively collect data in the target water area, obtaining an initial natural dataset; the initial natural dataset is preprocessed to obtain a training dataset; the initial natural data includes, but is not limited to, dissolved oxygen data, temperature data, and water pH value, and depending on the specific ecological restoration standards, also includes various measurement data such as flow velocity and water turbidity; the collected data needs to be preprocessed to ensure that it is suitable for input into the SOFM network, and the preprocessing includes, but is not limited to, data cleaning, normalization, and outlier removal; the SOFM neural network is initialized, in which each neuron or node is associated with a weight vector, and the SOFM neural network is initialized so that these weight vectors are randomly assigned in the initial stage; then, the initialized SOFM neural network is iteratively trained according to the training dataset until the number of iterations meets the preset conditions, and the target data is obtained. SOFM neural network; During the iteration process, the SOFM neural network learns the inherent structure of the training dataset. In each iteration, the SOFM neural network compares the initial natural data with the weight vector of each neuron, finds the neuron that best matches it, and adjusts its weights to better match the input initial natural data. At the same time, the weights of neurons around the successfully matched neuron are also adjusted. When the number of iterations meets the preset conditions, the SOFM neural network can map similar initial natural data to adjacent neurons, thus forming a topology in the output layer. At this time, the topology formed by the target SOFM neural network in the output layer is obtained, and the topology is analyzed to realize the water body layer detection of the target water area and obtain the layer results. Since the topology is used to reflect the relationship between the training data in the training dataset; When analyzing the topology, each group of neurons in the output layer of the target SOFM neural network represents a water body layer of the target water area, and its corresponding weight vector represents the initial natural data of the current water body layer.

[0107] The beneficial effects of the above technical solution are as follows: By using the above technical solution to accurately stratify the target water area according to the pollution status of different water layers, it is beneficial to improve the efficiency of subsequent water ecological restoration and achieve efficient treatment of different water layers in the target water area.

[0108] Please see Figure 2In one embodiment, based on the stratification results, dynamic hydrological data is sampled for each water layer using water monitoring equipment to obtain the sampling results for each water layer, including:

[0109] S201. Based on the stratification results, determine multiple water layers in the target water area;

[0110] It is worth noting that when determining the water layers, it is also necessary to determine the water depth range of each water layer to facilitate subsequent management of aquatic plants.

[0111] S202. Based on the random sampling method, multiple sampling areas are set for each water layer of the target water area;

[0112] When conducting random sampling, the number and extent of the sampling area depend on the size of the target body of water; the larger the target body of water, the larger the number and extent of the sampling area.

[0113] S203. Use water body monitoring equipment to sample dynamic hydrological data for each sampling area to obtain multiple dynamic hydrological sampling results for each water body layer.

[0114] Dynamic hydrological data sampling includes collecting information on aquatic plants, aquatic animals, and the natural ecological environment;

[0115] S204. Integrate multiple dynamic hydrological sampling results for each water body layer to obtain a unique sampling result for each water body layer; the sampling result includes aquatic plant distribution data, aquatic animal distribution data, and natural ecological environment data for each water body layer;

[0116] The preferred integration operation is to integrate the aquatic plant distribution data and aquatic animal distribution data without duplication, statistically integrate their distribution data, and calculate and integrate the average value of the natural ecological environment data of the water body layer.

[0117] Aquatic plant distribution data includes aquatic plant category distribution data and aquatic plant quantity distribution data;

[0118] The aquatic animal distribution data includes data on the distribution of aquatic animal categories and data on the distribution of aquatic animal populations;

[0119] The natural ecological environment data of the aquatic layer includes dissolved oxygen data, temperature data, and water pH value;

[0120] The beneficial effects of the above technical solution are as follows: by using the above technical solution, biological and natural data of each water layer can be collected, which is beneficial to improving the reliability of subsequent water ecological restoration.

[0121] In one embodiment, a target database is constructed by calling corresponding biological information and natural ecological environment data of the aquatic layer based on aquatic plant distribution data and aquatic animal distribution data, including:

[0122] Obtain aquatic plant category data from the aquatic plant distribution data;

[0123] Obtain aquatic animal category data from the aquatic animal distribution data;

[0124] Based on data on aquatic plant categories and aquatic animal categories, and using network communication methods, a target database is constructed by calling corresponding biological information and natural ecological environment data of the water body layer.

[0125] The target database includes natural ecological environment data, aquatic plant distribution data, aquatic animal distribution data, and corresponding biological information for each water layer;

[0126] The corresponding biological information includes information on aquatic plants and aquatic animals;

[0127] Information on aquatic plants includes, but is not limited to, plant species, suitable water depth, suitable water temperature, suitable water pH value, and dissolved oxygen growth rate.

[0128] The dissolved oxygen growth rate is obtained by calling the corresponding data in the existing target database, or by detecting the dissolved oxygen concentration at different times with an instrument, calculating and storing the data in the target database, and then calling it from the target database.

[0129] Information on aquatic animals includes, but is not limited to, animal species, suitable water depth, suitable water temperature, suitable water pH, oxygen consumption rate, types of plants they graze on, and plant grazing efficiency.

[0130] The beneficial effects of the above technical solution are as follows: By using the above technical solution, a corresponding target ecological database can be established for the target water area, thereby improving the comprehensive understanding of the target water area ecosystem and providing reliable data support for subsequent water ecological governance and water area management.

[0131] In one embodiment, based on a BP neural network, determining the dynamic change pattern of a target water area within a preset time period according to a target database includes:

[0132] Historical dynamic hydrological data of several water bodies were acquired to construct a training dataset. The dynamic hydrological data included aquatic plant data, aquatic animal data, and natural ecological environment data of each water layer at different time scales.

[0133] Aquatic plant data includes aquatic plant distribution data and aquatic plant information;

[0134] Aquatic plant distribution data includes the water layer in which they are distributed and the corresponding quantity;

[0135] Aquatic animal data includes aquatic animal distribution data and aquatic animal information;

[0136] Aquatic animal distribution data includes the water layers in which they are distributed and their corresponding numbers;

[0137] Based on the training dataset, a BP neural network is used to simulate the response patterns of aquatic plants and animals in different water layers at various time scales to changes in the natural ecological environment data of each water layer under the condition of no human interference, and a BP neural network prediction model is generated.

[0138] Information from the target database is used as input data and fed into the BP neural network prediction model. The output shows the dynamic change patterns among aquatic plant data, aquatic animal data, and natural ecological environment data in the target water area.

[0139] The working principle of the above technical solution is as follows: Dynamic hydrological data of different water layers in several water bodies under undisturbed conditions are acquired, including aquatic plant data, aquatic animal data, and natural ecological environment data of each water layer at different time scales, such as plant and animal species, quantities, and water quality parameters, to construct a training dataset. Preprocessing the collected training dataset improves the training efficiency and prediction accuracy of the model. Then, a backpropagation (BP) neural network structure is designed. Based on the training dataset, the BP neural network simulates the response patterns of aquatic plants and animals in different water layers at various time scales to changes in the natural ecological environment data of each water layer under undisturbed conditions, generating a BP neural network prediction model. Preferably, the BP neural network... The number of nodes in the input layer of the network is matched with the number of features of the corresponding aquatic plant data, aquatic animal data, and natural ecological environment data of each water body layer. The number of nodes in the output layer is matched with the corresponding response pattern. The specific simulation method is preferably based on the application of BP neural network in the lag response of desert rodent communities to climate change, which will not be elaborated here. Then, the information in the target database is obtained as input data and input into the BP neural network prediction model. The output shows the dynamic change pattern among the aquatic plant data, aquatic animal data, and natural ecological environment data of the target water body. It is worth noting that curves can also be generated based on the dynamic change pattern, which is beneficial for managers to intuitively feel the changing trend among the three.

[0140] Furthermore, in addition to using BP neural networks to determine the dynamic changes among aquatic plant data, aquatic animal data, and aquatic natural ecological environment data in the target water area, it is also possible to generate a water oxygen content curve change graph per unit time by statistically analyzing the oxygenation efficiency of aquatic plant data, the oxygen consumption efficiency of aquatic animals, and the original oxygen content in the aquatic natural ecological environment data of each layer in the target water area. This graph can be used to determine the dynamic changes among aquatic plant data, aquatic animal data, and aquatic natural ecological environment data in the target water area.

[0141] The beneficial effects of the above technical solution are as follows: By using the above technical solution, the dynamic change law of the dependence relationship between plants and animals and natural data is predicted by using the BP neural network, and the dynamic change law is used to realize the dynamic restoration of the aquatic ecological environment, which is beneficial to improving the reliability of ecological environment restoration of the target water area.

[0142] In one embodiment, determining whether the dynamic change pattern meets a preset repair target includes:

[0143] To obtain the dynamic change patterns among aquatic plant data, aquatic animal data, and aquatic natural ecological environment data in the target water area;

[0144] Obtain the target time scale, and determine the target time nodes in the dynamic change pattern based on the target time scale;

[0145] The target time scale is a time period set by the user. The target time node in the dynamic change pattern is determined based on the target time scale, that is, the last time node of the time period is determined as the target time node.

[0146] Based on the target time node, obtain the target natural ecological environment data corresponding to the dynamic change pattern, that is, obtain the natural ecological environment data at the target time node in the curve generated by the dynamic change pattern, and use it as the target natural ecological environment data.

[0147] Determine whether the target natural ecological environment meets the preset restoration goals and generate the determination result;

[0148] The preset remediation target is preferably the oxygen content threshold of each water layer in the water body;

[0149] The judgment result is that the target natural ecological environment meets the preset restoration target;

[0150] Alternatively, the target natural ecological environment may not meet the preset restoration goals.

[0151] In one embodiment, based on the judgment result and the principle of ecological restoration, the required plant species and corresponding quantities for each water layer are calculated to obtain the calculation results, including:

[0152] If the judgment result indicates that the target natural ecological environment does not meet the preset restoration target, obtain the ecological restoration principles:

[0153]

[0154] in, For the preset remediation target of the j-th water layer, Let be the number of aquatic plant species in the j-th water layer. Let be the matching coefficient of the i-th aquatic plant in the j-th water layer. The total dissolved oxygen growth rate of the i-th aquatic plant in the target water area per unit time. Let be the average growth efficiency of the i-th aquatic plant per unit time. Let be the average phytophagy efficiency of the k-th aquatic animal on the i-th aquatic plant per unit time. The total oxygen consumption rate of the k-th aquatic animal in the target water area per unit time;

[0155]

[0156] when When, it indicates that the matching relationship between the i-th aquatic plant and the j-th water layer is a match, when When, it indicates that the matching relationship between the i-th aquatic plant and the j-th water layer is not a match. This indicates that the suitable water depth, suitable water temperature, and suitable water pH value for the i-th aquatic plant are matched with the temperature data and water pH value of the j-th water layer; the suitable water depth is matched with the corresponding water layer.

[0157] Calculate the required plant species and corresponding quantities for each water layer, ensuring that the left and right sides of the ecological restoration principle are equal, or that the result on the left side is greater than that on the right side. Calculate the corresponding number and species of plants that need to be added. It is worth noting that there are no restrictions on the types and quantities of plants that need to be added, as long as the preset restoration goals can be met.

[0158] The beneficial effects of the above technical solution are: it provides reliable data support for plant management in the target water area.

[0159] In one embodiment, based on calculation results, the plant community of the target water area is managed using plant management equipment, including:

[0160] Obtain the required plant species and quantities for each water layer included in the calculation results;

[0161] Based on the different water layers, the corresponding plant management equipment is activated;

[0162] Since aquatic plants are generally divided into floating plants, emergent plants and submerged plants, different aquatic plants need to be planted for different water layers. Therefore, it is necessary to use the corresponding plant management equipment to plant and manage aquatic plants according to the differences in water layers.

[0163] Control the corresponding plant management equipment to load the required plant species and quantities for the corresponding water layer, and then proceed to the corresponding location in the target water area to deploy the plants.

[0164] Simultaneously, during the calculation process of obtaining the plant species and corresponding quantities required for each water layer, The corresponding distribution location of the i-th aquatic plant is used to call the corresponding aquatic plant harvesting system to cut and recycle the i-th aquatic plant;

[0165] Since the i-th type of aquatic plant is not suitable for growing in the corresponding water layer, its growth trend in that water layer is relatively slow, and it will also affect other aquatic plants in that water layer, such as blocking sunlight, thus affecting the ecological restoration efficiency of that water layer. Therefore, choosing to cut and recycle it is beneficial to improve the standardization of plant management.

[0166] Furthermore, aquatic plants can be regulated and managed to grow in a suitable water layer.

[0167] The beneficial effects of the above technical solution are: to achieve the management of plant communities through the above technical solution.

[0168] In one embodiment, a neural network-based management method for aquatic ecosystem restoration plant communities further includes:

[0169] The starting point is the moment when the plant management equipment manages the plant community in the target water area and the management ends.

[0170] Acquire historical dissolved oxygen data and historical biological content information of different water layers in the target water area after a preset second time point from the starting time point;

[0171] Analyze historical dissolved oxygen data to obtain the historical dissolved oxygen change rate of different water layers for each unit of time.

[0172] Analyzing historical biomass information yields historical biomass information for each organism in different water layers within each unit of time.

[0173] After a unit of time has elapsed since the current moment, the dissolved oxygen change rate and biological content information of different water layers within the current detection period are obtained.

[0174] To obtain dynamic change patterns and extract standard biological content information of different water layers after a unit of time has elapsed at the current moment;

[0175] The standard biological content information is preferably determined based on a curve generated by dynamic change patterns, or it can be directly based on the standard biological content information preset by the management personnel.

[0176] The water ecological restoration detection score of the current target water area is calculated based on the historical dissolved oxygen change rate, historical biological content information, dissolved oxygen change rate, biological content information and standard biological content information. The water ecological restoration detection score and preset threshold are used to determine whether the current water ecological restoration progress meets the preset restoration progress.

[0177] The preferred calculation formula is:

[0178]

[0179]

[0180]

[0181] Where F represents the current water ecological restoration monitoring score for the target water area. This represents the water ecological restoration detection score for the j-th water layer in the current target water area;

[0182] and To preset weights, This indicates the dissolved oxygen test score for water ecological restoration. This indicates the bioinformatics score for water ecosystem restoration. This represents the dissolved oxygen detection score for the water ecological restoration of the j-th water layer. This represents the bioinformatics detection score for the water ecological restoration of the j-th water layer;

[0183] The unit of time is divided into multiple time periods according to a preset time standard. This indicates the number of moments that have passed when the current time has elapsed within a unit of time. The number of moments is determined by the length of the unit of time, and once the length of the unit of time is determined, the number of moments is fixed. This represents the number of moments during the detection of the j-th water layer;

[0184] Each test within a unit of time is considered a test cycle. Indicates the first detection cycle. The rate of change of dissolved oxygen at each time point. This indicates the number of historical testing cycles. This indicates the c-th historical detection period. Historical dissolved oxygen change rate at each point in time; This indicates that the j-th water layer is in the current detection cycle. The rate of change of dissolved oxygen at each time point. This represents the number of historical monitoring cycles for the j-th water layer. Typically, the number of historical monitoring cycles is the same for all water layers. This indicates that the j-th water layer is in the c-th historical monitoring period. Historical dissolved oxygen change rate at each point in time;

[0185] This indicates the number of species of aquatic plants and animals in the target water area. Indicates the first detection cycle. The biomass information of the b-th organism in the detection information at time point b. This indicates the standard biomass content information for organism b. This indicates the c-th historical detection period. The historical biomass content information of the b-th organism in the detection information at each moment; This represents the number of aquatic plant and animal species in the j-th water layer of the target water area. This indicates the current detection period of the j-th water layer. The biomass information of the b-th organism in the detection information at time point b. This represents the standard biomass content information of species b in the j-th water layer. This indicates the first historical detection cycle of the j-th water layer. The historical biomass content information of the b-th organism in the detection information at each moment;

[0186] If the water ecological restoration detection score is less than the preset threshold, it is determined that the current water ecological restoration progress does not meet the preset restoration progress, and an alarm signal is sent to the management personnel to facilitate the management personnel to conduct surveys of the target water area.

[0187] The beneficial effects of the above technical solution are as follows: Through the above technical solution, the ecological restoration progress of the target water area can be further automated. Compared with the existing technology of treating the target water area once and then letting it develop, this solution is beneficial to improving the reliability of water ecological restoration.

[0188] Please see Figure 3 A neural network-based aquatic ecosystem restoration plant community management system includes:

[0189] The water stratification detection module is used to perform water stratification detection on the target water area based on the SOFM neural network and obtain the stratification results.

[0190] The hydrological data sampling module is used to dynamically sample hydrological data for each water layer using water monitoring equipment based on the stratification results, and obtain the sampling results for each water layer. The sampling results include aquatic plant distribution data, aquatic animal distribution data, and natural ecological environment data of the water layer.

[0191] The database module is used to construct the target database by calling corresponding biological information and natural ecological environment data of the water body layer based on the distribution data of aquatic plants and aquatic animals.

[0192] The water area data dynamic change monitoring module is used to determine the dynamic change pattern of the target water area within a preset time period based on the target database using a BP neural network.

[0193] The plant community restoration calculation module is used to determine whether the dynamic change pattern meets the preset restoration target. Based on the judgment result and the principle of ecological restoration, it calculates the required plant species and corresponding quantities for each water layer and obtains the calculation results.

[0194] The plant community management module is used to manage the plant community in the target water area using plant management equipment based on the calculation results.

[0195] The working principle and beneficial effects of the above technical solution have been explained in the methodology summary, and will not be repeated here.

[0196] Finally, it should be noted that the above preferred embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail through the above preferred embodiments, those skilled in the art should understand that various changes can be made to it in form and detail without departing from the scope defined by the claims of the present invention.

Claims

1. A method for managing aquatic ecological restoration plant communities based on neural networks, characterized in that, include: The SOFM neural network is used to perform water stratification detection on the target water area and obtain the stratification results. Based on the stratification results, dynamic hydrological data were sampled for each water layer using water monitoring equipment to obtain the sampling results for each water layer; the sampling results include data on the distribution of aquatic plants, aquatic animals, and the natural ecological environment of the water layer; Based on the distribution data of aquatic plants and aquatic animals, the target database is constructed by calling the corresponding biological information and natural ecological environment data of the water body layer; Based on a BP neural network, the dynamic change pattern of the target water area within a preset time period is determined according to the target database; Determine whether the dynamic change pattern meets the preset restoration target. Based on the determination result and the principle of ecological restoration, calculate the required plant species and corresponding quantities for each water layer to obtain the calculation results. Based on the calculation results, plant management equipment was used to manage the plant community in the target water area; Based on the assessment results and the principles of ecological restoration, the required plant species and quantities for each water layer were calculated, yielding the following results: If the judgment result indicates that the target natural ecological environment does not meet the preset restoration target, obtain the ecological restoration principles: in, For the preset remediation target of the j-th water layer, Let be the number of aquatic plant species in the j-th water layer. Let be the matching coefficient of the i-th aquatic plant in the j-th water layer. The total dissolved oxygen growth rate of the i-th aquatic plant in the target water area per unit time. Let be the average growth efficiency of the i-th aquatic plant per unit time. Let be the average phytophagy efficiency of the k-th aquatic animal on the i-th aquatic plant per unit time. The total oxygen consumption rate of the k-th aquatic animal in the target water area per unit time; when When, it indicates that the matching relationship between the i-th aquatic plant and the j-th water layer is a match, when When, it indicates that the matching relationship between the i-th aquatic plant and the j-th water layer is not a match. This indicates that the suitable water depth, suitable water temperature, and suitable water pH value of the i-th aquatic plant are matched with the temperature data and water pH value of the j-th water layer; Calculate the required plant species and quantities for each water layer to ensure that the left and right equations of the ecological restoration principle are equal, and obtain the calculation results.

2. The method for managing aquatic ecological restoration plant communities based on neural networks according to claim 1, characterized in that, Based on the SOFM neural network, water stratification detection is performed on the target water area to obtain stratification results, including: The controller controls the lifting motor to carry the water monitoring equipment to the target water area for adaptive data acquisition, and obtains the initial natural dataset; the initial natural dataset is preprocessed to obtain the training dataset; the initial natural data includes dissolved oxygen data, temperature data and pH value. Initialize the SOFM neural network, and iteratively train the initialized SOFM neural network according to the training dataset until the number of iterations meets the preset conditions, and the target SOFM neural network is obtained. The topology of the target SOFM neural network in the output layer is obtained, the topology is analyzed, and water stratification detection of the target water area is realized to obtain the stratification results. The topology is used to reflect the relationships between training data in the training dataset; When analyzing the topology, each group of neurons in the output layer of the target SOFM neural network represents a water body layer of the target water area, and its corresponding weight vector represents the initial natural data of the current water body layer.

3. The method for managing aquatic ecological restoration plant communities based on neural networks according to claim 1, characterized in that, Based on the stratification results, dynamic hydrological data were sampled for each water layer using water monitoring equipment to obtain the sampling results for each water layer, including: Based on the stratification results, multiple water layers in the target water area are identified; Based on random sampling methods, multiple sampling areas are set for each water layer of the target water area; Dynamic hydrological data were sampled for each sampling area using water monitoring equipment, resulting in multiple dynamic hydrological sampling results for each water layer. Multiple dynamic hydrological sampling results for each water body layer are integrated to obtain a unique sampling result for each water body layer; the sampling result includes aquatic plant distribution data, aquatic animal distribution data, and natural ecological environment data for each water body layer; Aquatic plant distribution data includes aquatic plant category distribution data and aquatic plant quantity distribution data; The aquatic animal distribution data includes data on the distribution of aquatic animal categories and data on the distribution of aquatic animal populations; The natural ecological environment data of the aquatic layer includes dissolved oxygen data, temperature data, and pH value of the water.

4. The method for managing aquatic ecological restoration plant communities based on neural networks according to claim 1, characterized in that, Based on aquatic plant and aquatic animal distribution data, a target database is constructed by calling corresponding biological information and natural ecological environment data of the aquatic layer, including: Obtain aquatic plant category data from the aquatic plant distribution data; Obtain aquatic animal category data from the aquatic animal distribution data; Based on data on aquatic plant categories and aquatic animal categories, and using network communication methods, a target database is constructed by calling corresponding biological information and natural ecological environment data of the water body layer. The corresponding biological information includes information on aquatic plants and aquatic animals; Information on aquatic plants includes plant species, suitable water depth, suitable water temperature, suitable pH value, and dissolved oxygen growth rate; Information on aquatic animals includes animal species, suitable water depth, suitable water temperature, suitable water pH, oxygen consumption rate, types of plants they graze on, and the efficiency of plant grazing.

5. The method for managing aquatic ecological restoration plant communities based on neural networks according to claim 1, characterized in that, Based on a backpropagation neural network, the dynamic change patterns of the target water area within a preset time period are determined according to the target database, including: Historical dynamic hydrological data of several water bodies were acquired to construct a training dataset. The dynamic hydrological data included aquatic plant data, aquatic animal data, and natural ecological environment data of each water layer at different time scales. Aquatic plant data includes aquatic plant distribution data and aquatic plant information; Aquatic animal data includes aquatic animal distribution data and aquatic animal information; Based on the training dataset, a BP neural network is used to simulate the response patterns of aquatic plants and animals in different water layers at various time scales to changes in the natural ecological environment data of each water layer under the condition of no human interference, and a BP neural network prediction model is generated. Information from the target database is used as input data and fed into the BP neural network prediction model. The output reveals the dynamic changes among aquatic plant data, aquatic animal data, and natural ecological environment data in the target water area.

6. The method for managing aquatic ecological restoration plant communities based on neural networks according to claim 1, characterized in that, Determining whether the dynamic change pattern meets the preset repair target includes: To obtain the dynamic change patterns among aquatic plant data, aquatic animal data, and aquatic natural ecological environment data in the target water area; Obtain the target time scale, and determine the target time nodes in the dynamic change pattern based on the target time scale; Based on the target time points, obtain the target natural ecological environment data corresponding to the dynamic change patterns; Determine whether the target natural ecological environment meets the preset restoration goals and generate the determination result; The judgment result is that the target natural ecological environment meets the preset restoration target; Alternatively, the target natural ecological environment may not meet the preset restoration goals.

7. The method for managing aquatic ecological restoration plant communities based on neural networks according to claim 1, characterized in that, Based on the calculation results, plant management equipment is used to manage the plant community in the target water area, including: Obtain the required plant species and quantities for each water layer included in the calculation results; Based on the different water layers, the corresponding plant management equipment is activated; Control the corresponding plant management equipment to load the required plant species and quantities for the corresponding water layer, and then proceed to the corresponding location in the target water area to deploy the plants. In the process of obtaining the required plant species and corresponding quantities for each water layer, The corresponding distribution location of the i-th aquatic plant is determined, and the corresponding aquatic plant harvesting system is invoked to cut and recycle the i-th aquatic plant.

8. The method for managing aquatic ecological restoration plant communities based on neural networks according to claim 1, characterized in that, Also includes: The starting point is the moment when the plant management equipment manages the plant community in the target water area and the management ends. Acquire historical dissolved oxygen data and historical biological content information of different water layers in the target water area after a preset second time point from the starting time point; Analyze historical dissolved oxygen data to obtain the historical dissolved oxygen change rate of different water layers for each unit of time. Analyzing historical biomass information yields historical biomass information for each organism in different water layers within each unit of time. Obtain information on the rate of change of dissolved oxygen and the biomass content of different water layers after a unit of time has elapsed at the current moment. To obtain dynamic change patterns and extract standard biological content information of different water layers after a unit of time has elapsed at the current moment; The water ecological restoration detection score of the current target water area is calculated based on the historical dissolved oxygen change rate, historical biological content information, dissolved oxygen change rate, biological content information, and standard biological content information. The water ecological restoration detection score and preset threshold are used to determine whether the current water ecological restoration progress meets the preset restoration progress.

9. A water ecological restoration plant community management system based on neural networks, characterized in that, include: The water stratification detection module is used to perform water stratification detection on the target water area based on the SOFM neural network and obtain the stratification results. The hydrological data sampling module is used to dynamically sample hydrological data for each water layer using water monitoring equipment based on the stratification results, and obtain the sampling results for each water layer. The sampling results include aquatic plant distribution data, aquatic animal distribution data, and natural ecological environment data of the water layer. The database module is used to construct the target database by calling corresponding biological information and natural ecological environment data of the water body layer based on the distribution data of aquatic plants and aquatic animals. The water area data dynamic change monitoring module is used to determine the dynamic change pattern of the target water area within a preset time period based on the target database using a BP neural network. The plant community restoration calculation module is used to determine whether the dynamic change pattern meets the preset restoration target. Based on the judgment result and the principle of ecological restoration, it calculates the required plant species and corresponding quantities for each water layer and obtains the calculation result. The plant community management module is used to manage the plant community of the target water area using plant management equipment based on the calculation result. Based on the assessment results and the principles of ecological restoration, the required plant species and quantities for each water layer were calculated, yielding the following results: If the judgment result indicates that the target natural ecological environment does not meet the preset restoration target, obtain the ecological restoration principles: in, For the preset remediation target of the j-th water layer, Let be the number of aquatic plant species in the j-th water layer. Let be the matching coefficient of the i-th aquatic plant in the j-th water layer. The total dissolved oxygen growth rate of the i-th aquatic plant in the target water area per unit time. Let be the average growth efficiency of the i-th aquatic plant per unit time. Let be the average phytophagy efficiency of the k-th aquatic animal on the i-th aquatic plant per unit time. The total oxygen consumption rate of the k-th aquatic animal in the target water area per unit time; when When, it indicates that the matching relationship between the i-th aquatic plant and the j-th water layer is a match, when When, it indicates that the matching relationship between the i-th aquatic plant and the j-th water layer is not a match. This indicates that the suitable water depth, suitable water temperature, and suitable water pH value of the i-th aquatic plant are matched with the temperature data and water pH value of the j-th water layer; Calculate the required plant species and quantities for each water layer to ensure that the left and right equations of the ecological restoration principle are equal, and obtain the calculation results.

Images