Methods and devices for ecoacoustic monitoring of macrobenthic animals in mangrove areas

Abstract

This invention relates to a method and apparatus for ecoacoustic monitoring of macrobenthic animals in mangrove areas, belonging to the field of ecological monitoring technology. Based on acoustic propagation characteristic data in mangrove areas, this invention deploys acoustic equipment to monitor and identify functional groups of macrobenthic animals, statistically analyzes the relative abundance of these functional groups, and finally assesses the acoustic diversity of macrobenthic animals based on the analysis results. By optimizing the deployment of acoustic sensors, developing efficient acoustic signal processing algorithms, and integrating environmental parameter monitoring, this invention achieves long-term, continuous, and non-invasive monitoring of macrobenthic animals in mangrove areas, providing scientific basis and technical support for the health assessment of mangrove ecosystems and biodiversity conservation.

Description

Technical Field

[0001] This invention relates to the field of ecological monitoring technology, and in particular to a method and device for ecological acoustic monitoring of large benthic animals in mangrove areas. Background Technology

[0002] Mangroves are vital ecosystems in tropical and subtropical coastal areas, possessing extremely high biodiversity and ecosystem services. Macrobenthic animals (such as crabs, shellfish, and polychaetes) in mangrove areas are an important component of the ecosystem, playing a crucial role in material cycling, energy flow, and habitat construction. However, due to the complexity and dynamic nature of the mangrove environment, traditional macrobenthic animal monitoring methods (such as quadrat sampling and trapping) have the following limitations: 1) High invasiveness: Traditional methods usually require direct disturbance to the habitat of macrobenthic animals, which may lead to changes in animal behavior or habitat destruction, affecting the accuracy of monitoring results; 2) Low efficiency: Mangrove areas have complex topography and frequent tidal changes, making traditional methods time-consuming and labor-intensive, and difficult to achieve large-scale, long-term continuous monitoring; 3) Data limitations: Traditional methods usually only acquire data within a specific time and spatial range, making it difficult to comprehensively reflect the ecological characteristics and dynamic changes of macrobenthic animals. In recent years, acoustic monitoring technology has been widely used in aquatic ecosystem research. Acoustic monitoring has the advantages of being non-invasive, continuous, and having high spatiotemporal resolution, effectively compensating for the shortcomings of traditional methods. However, existing acoustic monitoring technologies mainly target fish and marine mammals, and research on acoustic monitoring of large benthic animals in mangrove areas remains lacking. The acoustic environment of mangrove areas is complex, and the acoustic signals of large benthic animals are weak and easily interfered with by environmental noise. Therefore, it is necessary to develop acoustic monitoring methods and devices specifically suitable for mangrove areas.

[0003] The purpose of this invention is to provide a method and device for ecological acoustic monitoring of macrobenthic animals in mangrove areas. By optimizing the deployment of acoustic sensors, developing efficient acoustic signal processing algorithms, and integrating environmental parameter monitoring, long-term, continuous, and non-invasive monitoring of macrobenthic animals in mangrove areas can be achieved, providing scientific basis and technical support for the health assessment of mangrove ecosystems and the protection of biodiversity. Summary of the Invention

[0004] This invention overcomes the shortcomings of the prior art and provides a method and device for ecoacoustic monitoring of large benthic animals in mangrove areas.

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

[0006] This invention provides a method for ecoacoustic monitoring of macrobenthic animals in mangrove areas, comprising the following steps:

[0007] Acoustic propagation characteristic data under various environmental characteristics are obtained through big data, and an acoustic propagation characteristic data prediction model is constructed based on the acoustic propagation characteristic data under various environmental characteristics.

[0008] Based on the acoustic propagation characteristic data prediction model, acoustic characteristic data in the mangrove area are predicted, and acoustic equipment in the mangrove area is arranged according to the acoustic propagation characteristic data in the mangrove area.

[0009] Acoustic feature data of mangrove areas are acquired using acoustic equipment, and the functional groups of macrobenthic animals in mangrove areas are monitored and identified based on the acoustic feature data of mangrove areas, and the relative abundance of macrobenthic animal functional groups is statistically analyzed.

[0010] The relative abundance of each functional group of the macrobenthic animals was analyzed, the analysis results were obtained, and the acoustic diversity of macrobenthic animals was assessed based on the analysis results.

[0011] Furthermore, in the method for ecological acoustic monitoring of macrobenthic animals in mangrove areas, an acoustic propagation characteristic data prediction model is constructed based on the acoustic propagation characteristic data under the aforementioned environmental characteristics, specifically as follows:

[0012] An acoustic propagation feature data prediction model is constructed based on a deep neural network. A graph neural network is introduced, and the acoustic propagation feature data under each environmental feature is input into the graph neural network. The acoustic propagation feature data features are used as the first node of the graph neural network.

[0013] Using acoustic propagation feature data as the second node of a graph neural network, a directed descriptive relationship is constructed. Based on the directed descriptive relationship, the first node and the second node are connected so that the first node points to the second node, thus constructing a topology graph.

[0014] Based on the topology graph, an adjacency matrix is ​​obtained. The adjacency matrix is ​​then input into the acoustic propagation feature data prediction model for training. It is then determined whether the acoustic propagation feature data prediction model meets the training termination condition during the training process.

[0015] When the acoustic propagation feature data prediction model meets the training termination condition during the training process, the model parameters of the acoustic propagation feature data prediction model are saved, and the acoustic propagation feature data prediction model is output.

[0016] Furthermore, in the method for ecological acoustic monitoring of macrobenthic animals in mangrove areas, the prediction of acoustic propagation characteristic data in mangrove areas based on the aforementioned acoustic propagation characteristic data prediction model specifically includes:

[0017] The environmental characteristics and real-time acoustic characteristics of the current mangrove area are obtained, and the environmental characteristics and real-time acoustic characteristics of the current mangrove area are input into the acoustic propagation characteristic data prediction model for prediction.

[0018] The acoustic propagation characteristics data in the mangrove area are obtained through prediction, and the acoustic propagation characteristics data in the mangrove area are output.

[0019] Furthermore, in the method for ecological acoustic monitoring of macrobenthic animals in mangrove areas, acoustic equipment in the mangrove area is deployed based on acoustic propagation characteristic data, specifically as follows:

[0020] Obtain the sensing range area of ​​each acoustic device type under different acoustic propagation characteristic data, and obtain the acoustic device type whose sensing range area is larger than the preset sensing range area;

[0021] The acoustic device type corresponding to the sensing range area being larger than the preset sensing range area is used as the acoustic device type for data acquisition. The sensing range area of ​​the acoustic device type for data acquisition is obtained based on the sensing range area of ​​each acoustic device type under different acoustic propagation characteristic data and the acoustic propagation characteristic data in the mangrove area.

[0022] The arrangement location and quantity of acoustic devices for initializing the data acquisition are determined, and the estimated sensing range area is calculated based on the sensing range area of ​​the acoustic device type, the arrangement location, and the quantity of the acoustic device.

[0023] When the estimated sensing range is not greater than the preset range information, adjust the arrangement position and number of acoustic devices for data acquisition until it exceeds the preset range information.

[0024] Furthermore, in the method for ecological acoustic monitoring of macrobenthic animals in mangrove areas, acoustic characteristic data of the mangrove area are acquired through acoustic equipment, and the functional groups of macrobenthic animals in the mangrove area are monitored and identified based on the acoustic characteristic data, and the relative abundance of macrobenthic animal functional groups is statistically analyzed, specifically including:

[0025] Acoustic feature data in mangrove areas are acquired using acoustic devices, and large benthic animal functional groups related to each acoustic feature data are obtained through big data. A large benthic animal knowledge graph is constructed based on the large benthic animal functional groups related to each acoustic feature data.

[0026] The acoustic feature data of the mangrove area is input into the macrobenthic animal knowledge graph for identification, to obtain macrobenthic animal type feature data in the mangrove area, and to statistically analyze the macrobenthic animal functional group feature data in the mangrove area to obtain the relative abundance of macrobenthic animal functional groups.

[0027] Furthermore, in the method for ecoacoustic monitoring of macrobenthic animals in mangrove areas, the relative abundance of each functional group of macrobenthic animals is analyzed, the analysis results are obtained, and the acoustic landscape diversity of macrobenthic animals is assessed based on the analysis results, specifically including:

[0028] Set a relative abundance characteristic threshold for macrobenthic functional groups, and determine whether the relative abundance of each macrobenthic functional group is greater than the relative abundance characteristic threshold of the macrobenthic functional group.

[0029] When the relative abundance of each functional group of macrobenthic animals is greater than the relative abundance characteristic threshold of the macrobenthic animal functional group, the analysis results are generated and the relative abundance of each functional group of macrobenthic animals is output.

[0030] A second aspect of the present invention provides an eco-acoustic monitoring device for macrobenthic animals in mangrove areas, comprising a memory and a processor. The memory includes a program for eco-acoustic monitoring of macrobenthic animals in mangrove areas. When the program for eco-acoustic monitoring of macrobenthic animals in mangrove areas is executed by the processor, it implements the steps of any of the methods for eco-acoustic monitoring of macrobenthic animals in mangrove areas.

[0031] A third aspect of the present invention provides a computer-readable storage medium including a program for a method of monitoring the ecoacoustic ecology of macrobenthic animals in mangrove areas, wherein when the program is executed by a processor, it implements the steps of any of the methods for monitoring the ecoacoustic ecology of macrobenthic animals in mangrove areas.

[0032] This invention addresses the shortcomings of the prior art and has the following beneficial effects:

[0033] This invention acquires acoustic propagation characteristic data under various environmental conditions through big data, constructs an acoustic propagation characteristic data prediction model based on the acoustic propagation characteristic data under these environmental conditions, predicts acoustic characteristic data in mangrove areas based on the acoustic propagation characteristic data prediction model, and deploys acoustic devices in mangrove areas according to the acoustic propagation characteristic data in the mangrove areas. The acoustic devices then acquire acoustic characteristic data in the mangrove areas, monitor and identify macrobenthic functional groups in the mangrove areas based on the acoustic characteristic data, statistically analyze the relative abundance of macrobenthic functional groups, and finally analyze the relative abundance of each macrobenthic functional group to obtain the analysis results. Based on the analysis results, the acoustic landscape diversity of macrobenthic animals is assessed. The purpose of this invention is to provide a method and device for ecological acoustic monitoring of macrobenthic animals in mangrove areas. By optimizing the deployment of acoustic sensors, developing efficient acoustic signal processing algorithms, and integrating environmental parameter monitoring, long-term, continuous, and non-invasive monitoring of macrobenthic animals in mangrove areas can be achieved, providing scientific basis and technical support for the health assessment of mangrove ecosystems and the protection of biodiversity. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other embodiments can be obtained from these drawings without creative effort.

[0035] Figure 1 An overall flowchart of the ecoacoustic monitoring method for macrobenthic animals in mangrove areas is shown;

[0036] Figure 2 A partial flowchart of an ecoacoustic monitoring method for macrobenthic animals in mangrove areas is shown.

[0037] Figure 3 A block diagram of a large benthic animal ecoacoustic monitoring device for use in mangrove areas is shown.

[0038] Figure 4 A schematic diagram of the acoustic monitoring equipment is shown. Detailed Implementation

[0039] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0040] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0041] like Figure 1 As shown, this invention provides a method for ecoacoustic monitoring of macrobenthic animals in mangrove areas, comprising the following steps:

[0042] S102: Acquire acoustic propagation characteristic data under various environmental characteristics through big data, and construct an acoustic propagation characteristic data prediction model based on the acoustic propagation characteristic data under various environmental characteristics.

[0043] S104: Predict acoustic characteristic data in the mangrove area based on the acoustic propagation characteristic data prediction model, and arrange acoustic equipment in the mangrove area according to the acoustic propagation characteristic data in the mangrove area;

[0044] S106: Acoustic feature data of mangrove areas are acquired through acoustic devices, and macrobenthic functional groups of mangrove areas are monitored and identified based on the acoustic feature data of mangrove areas, and the relative abundance of macrobenthic functional groups is calculated.

[0045] S108: Analyze the relative abundance of each functional group of the macrobenthic animals, obtain the analysis results, and assess the acoustic diversity of macrobenthic animals based on the analysis results.

[0046] It should be noted that the purpose of this invention is to provide a method and device for ecological acoustic monitoring of macrobenthic animals in mangrove areas. By optimizing the deployment of acoustic sensors, developing efficient acoustic signal processing algorithms, and integrating environmental parameter monitoring, long-term, continuous, and non-invasive monitoring of macrobenthic animals in mangrove areas can be achieved, providing scientific basis and technical support for the health assessment of mangrove ecosystems and the protection of biodiversity.

[0047] Furthermore, in the method for ecological acoustic monitoring of macrobenthic animals in mangrove areas, an acoustic propagation characteristic data prediction model is constructed based on the acoustic propagation characteristic data under the aforementioned environmental characteristics, specifically as follows:

[0048] An acoustic propagation feature data prediction model is constructed based on a deep neural network. A graph neural network is introduced, and the acoustic propagation feature data under each environmental feature is input into the graph neural network, with the acoustic propagation feature data as the first node of the graph neural network.

[0049] Using acoustic propagation feature data as the second node of a graph neural network, a directed descriptive relationship is constructed. Based on the directed descriptive relationship, the first node and the second node are connected so that the first node points to the second node, thus constructing a topology graph.

[0050] Based on the topology graph, an adjacency matrix is ​​obtained. The adjacency matrix is ​​then input into the acoustic propagation feature data prediction model for training. It is then determined whether the acoustic propagation feature data prediction model meets the training termination condition during the training process.

[0051] When the acoustic propagation feature data prediction model meets the training termination condition during the training process, the model parameters of the acoustic propagation feature data prediction model are saved, and the acoustic propagation feature data prediction model is output.

[0052] It should be noted that acoustic propagation characteristic data includes data such as sound propagation loss per unit time, sound propagation speed per unit time, and sound propagation quality. Since different environments (such as temperature environment, humidity environment, soil environment, and seabed sediment environment) will have different acoustic propagation characteristics, this method can construct an acoustic propagation characteristic data prediction model to predict acoustic propagation characteristic data.

[0053] Furthermore, in the method for ecological acoustic monitoring of macrobenthic animals in mangrove areas, the prediction of acoustic propagation characteristic data in mangrove areas based on the aforementioned acoustic propagation characteristic data prediction model specifically includes:

[0054] The environmental characteristics and real-time acoustic characteristics of the current mangrove area are obtained, and the environmental characteristics and real-time acoustic characteristics of the current mangrove area are input into the acoustic propagation characteristic data prediction model for prediction.

[0055] The acoustic propagation characteristics data in the mangrove area are obtained through prediction, and the acoustic propagation characteristics data in the mangrove area are output.

[0056] like Figure 2 As shown, further, in the method for ecological acoustic monitoring of macrobenthic animals in mangrove areas, the acoustic equipment in the mangrove area is arranged according to the acoustic propagation characteristic data in the mangrove area, specifically as follows:

[0057] S202: Obtain the sensing range area of ​​each acoustic device type under different acoustic propagation characteristic data, and obtain the acoustic device type whose sensing range area is larger than the preset sensing range area;

[0058] S204: The acoustic device type corresponding to the sensing range area being larger than the preset sensing range area is taken as the acoustic device type for data acquisition, and the sensing range area of ​​the acoustic device type for data acquisition is obtained according to the sensing range area of ​​each acoustic device type under different acoustic propagation characteristic data and the acoustic propagation characteristic data in the mangrove area.

[0059] S206: Initialize the arrangement location and quantity of acoustic devices for collecting data, and calculate the estimated sensing range area based on the sensing range area of ​​the acoustic device type, the arrangement location and quantity of the acoustic device type for collecting data.

[0060] S208: When the estimated sensing range area is not greater than the preset range information, adjust the arrangement position and number of acoustic devices for collecting data until it is greater than the preset range information.

[0061] It should be noted that different types of acoustic equipment have different sound propagation capabilities. Failure to select an appropriate type of acoustic equipment can lead to data acquisition failures or anomalies, hindering data analysis and noise processing, and ultimately causing data distortion. This method estimates the sensing range of each acoustic equipment type based on its sensing range under different acoustic propagation characteristics and in mangrove forests. This optimization optimizes the placement of acoustic equipment, resulting in better data acquisition and improved accuracy and rationality of acoustic data acquisition, thereby enhancing the monitoring accuracy of large benthic animals.

[0062] Specifically, acoustic feature data of mangrove areas are acquired using acoustic equipment, and the functional groups of macrobenthic animals in the mangrove areas are monitored and identified based on the acoustic feature data. The relative abundance of macrobenthic animal functional groups is then calculated.

[0063] Acoustic feature data in mangrove areas are acquired using acoustic devices, and large benthic animal functional groups related to each acoustic feature data are obtained through big data. A large benthic animal knowledge graph is constructed based on the large benthic animal functional groups related to each acoustic feature data.

[0064] The acoustic feature data of the mangrove area is input into the macrobenthic animal knowledge graph for identification, to obtain macrobenthic animal type feature data in the mangrove area, and to statistically analyze the macrobenthic animal functional group feature data in the mangrove area to obtain the relative abundance of macrobenthic animal functional groups.

[0065] It should be noted that, in this method, after acquiring the acoustic feature data in the mangrove area, the process may also include noise processing of the acoustic data, signal amplification of the acoustic data (sound wave type, sound wave frequency, etc.), noise reduction processing of the acoustic signal using digital signal processing technology, and preservation of the characteristic frequencies of biological sounds, etc., and is not limited to the content of this embodiment. The acoustic feature data includes biological sounds, geophysical sounds, artificial sounds, etc.

[0066] Furthermore, in the method for ecoacoustic monitoring of macrobenthic animals in mangrove areas, the relative abundance of each functional group of macrobenthic animals is analyzed, the analysis results are obtained, and the acoustic landscape diversity of macrobenthic animals is assessed based on the analysis results, specifically including:

[0067] Set a relative abundance characteristic threshold for macrobenthic functional groups, and determine whether the relative abundance of each macrobenthic functional group is greater than the relative abundance characteristic threshold of the macrobenthic functional group.

[0068] When the relative abundance of each functional group of macrobenthic animals is greater than the relative abundance characteristic threshold of the macrobenthic animal functional group, the analysis results are generated and the relative abundance of each functional group of macrobenthic animals is output.

[0069] It should be noted that this method can better monitor large benthic animals in mangrove areas, achieving unmanned monitoring.

[0070] Figure 4 A schematic diagram of the acoustic monitoring equipment is shown.

[0071] In addition, this method also includes:

[0072] Acquire water environment characteristic data of each area of ​​the current mangrove forest, initialize the acoustic wave operating parameters of the acoustic device according to the water environment characteristic data of each area of ​​the current mangrove forest, and acquire environmental noise data under the acoustic wave operating parameters of the acoustic device;

[0073] A particle swarm optimization algorithm is introduced, and the number of iterations is set based on the particle swarm optimization algorithm to determine whether the environmental noise data under the acoustic operating parameters of the acoustic device is greater than a preset noise data threshold.

[0074] When the ambient noise data under the acoustic wave operating parameters of the acoustic device is greater than the preset noise data threshold, the acoustic wave operating parameters of the acoustic device are readjusted based on the number of iterations until the ambient noise data under the acoustic wave operating parameters of the acoustic device is not greater than the preset noise data threshold.

[0075] When the ambient noise data under the acoustic operating parameters of the acoustic device is not greater than the preset noise data threshold, the acoustic operating parameters of the acoustic device are output and controlled according to the acoustic operating parameters of the acoustic device.

[0076] It should be noted that by introducing an adaptive algorithm, the acoustic parameters can be automatically adjusted according to environmental noise or water conditions (e.g., by dynamically adjusting the output intensity using a power amplifier), thereby improving monitoring accuracy.

[0077] In addition, this method also includes:

[0078] Through continuous iteration, environmental noise data of the current acoustic equipment under the maximum acoustic wave operating parameters is obtained;

[0079] Determine whether the ambient noise data of the current acoustic device under the maximum acoustic wave operating parameters is greater than the preset noise data threshold.

[0080] When the ambient noise data of the current acoustic device under the maximum acoustic wave operating parameters is greater than the preset noise data threshold, the current acoustic device is controlled to stop working and an early warning is issued.

[0081] When the ambient noise data of the current acoustic device under the maximum acoustic wave operating parameters is not greater than the preset noise data threshold, the current acoustic device is controlled to continue working.

[0082] It should be noted that when the ambient noise data of the current acoustic device under the maximum acoustic wave operating parameters is greater than the preset noise data threshold, it means that no matter how it is adjusted, the requirements cannot be met. At this time, controlling the current acoustic device to stop working can save energy, reduce monitoring costs, and improve the rationality of monitoring.

[0083] like Figure 3 As shown, a second aspect of the present invention provides an acoustic monitoring device 4 for macrobenthic animals in mangrove areas, including a memory 41 and a processor 42. The memory 41 includes a program for an acoustic monitoring method 42 for macrobenthic animals in mangrove areas. When the program for an acoustic monitoring method for macrobenthic animals in mangrove areas is executed by the processor 42, the following steps are implemented:

[0084] Acoustic propagation characteristic data under various environmental characteristics are obtained through big data, and an acoustic propagation characteristic data prediction model is constructed based on the acoustic propagation characteristic data under various environmental characteristics.

[0085] Based on the acoustic propagation characteristic data prediction model, acoustic characteristic data in the mangrove area are predicted, and acoustic equipment in the mangrove area is arranged according to the acoustic propagation characteristic data in the mangrove area.

[0086] Acoustic feature data of mangrove areas are acquired using acoustic equipment, and the functional groups of macrobenthic animals in mangrove areas are monitored and identified based on the acoustic feature data of mangrove areas, and the relative abundance of macrobenthic animal functional groups is statistically analyzed.

[0087] The relative abundance of each functional group of the macrobenthic animals was analyzed, the analysis results were obtained, and the acoustic diversity of macrobenthic animals was assessed based on the analysis results.

[0088] Furthermore, in the method for ecological acoustic monitoring of macrobenthic animals in mangrove areas, an acoustic propagation characteristic data prediction model is constructed based on the acoustic propagation characteristic data under the aforementioned environmental characteristics, specifically as follows:

[0089] An acoustic propagation feature data prediction model is constructed based on a deep neural network. A graph neural network is introduced, and the acoustic propagation feature data under each environmental feature is input into the graph neural network. The acoustic propagation feature data features are used as the first node of the graph neural network.

[0090] Using acoustic propagation feature data as the second node of a graph neural network, a directed descriptive relationship is constructed. Based on the directed descriptive relationship, the first node and the second node are connected so that the first node points to the second node, thus constructing a topology graph.

[0091] Based on the topology graph, an adjacency matrix is ​​obtained. The adjacency matrix is ​​then input into the acoustic propagation feature data prediction model for training. It is then determined whether the acoustic propagation feature data prediction model meets the training termination condition during the training process.

[0092] When the acoustic propagation feature data prediction model meets the training termination condition during the training process, the model parameters of the acoustic propagation feature data prediction model are saved, and the acoustic propagation feature data prediction model is output.

[0093] Furthermore, in the method for ecological acoustic monitoring of macrobenthic animals in mangrove areas, the prediction of acoustic propagation characteristic data in mangrove areas based on the aforementioned acoustic propagation characteristic data prediction model specifically includes:

[0094] The environmental characteristics and real-time acoustic characteristics of the current mangrove area are obtained, and the environmental characteristics and real-time acoustic characteristics of the current mangrove area are input into the acoustic propagation characteristic data prediction model for prediction.

[0095] The acoustic propagation characteristics data in the mangrove area are obtained through prediction, and the acoustic propagation characteristics data in the mangrove area are output.

[0096] Furthermore, in the method for ecological acoustic monitoring of macrobenthic animals in mangrove areas, acoustic equipment in the mangrove area is deployed based on acoustic propagation characteristic data, specifically as follows:

[0097] Obtain the sensing range area of ​​each acoustic device type under different acoustic propagation characteristic data, and obtain the acoustic device type whose sensing range area is larger than the preset sensing range area;

[0098] The acoustic device type corresponding to the sensing range area being larger than the preset sensing range area is used as the acoustic device type for data acquisition. The sensing range area of ​​the acoustic device type for data acquisition is obtained based on the sensing range area of ​​each acoustic device type under different acoustic propagation characteristic data and the acoustic propagation characteristic data in the mangrove area.

[0099] The arrangement location and quantity of acoustic devices for initializing the data acquisition are determined, and the estimated sensing range area is calculated based on the sensing range area of ​​the acoustic device type, the arrangement location, and the quantity of the acoustic device.

[0100] When the estimated sensing range is not greater than the preset range information, adjust the arrangement position and number of acoustic devices for data acquisition until it exceeds the preset range information.

[0101] Furthermore, in the method for ecological acoustic monitoring of macrobenthic animals in mangrove areas, acoustic characteristic data of the mangrove area are acquired through acoustic equipment, and the functional groups of macrobenthic animals in the mangrove area are monitored and identified based on the acoustic characteristic data, and the relative abundance of macrobenthic animal functional groups is statistically analyzed, specifically including:

[0102] Acoustic feature data in mangrove areas are acquired using acoustic devices, and large benthic animal functional groups related to each acoustic feature data are obtained through big data. A large benthic animal knowledge graph is constructed based on the large benthic animal functional groups related to each acoustic feature data.

[0103] The acoustic feature data of the mangrove area is input into the macrobenthic animal knowledge graph for identification, to obtain macrobenthic animal type feature data in the mangrove area, and to statistically analyze the macrobenthic animal functional group feature data in the mangrove area to obtain the relative abundance of macrobenthic animal functional groups.

[0104] Furthermore, in the method for ecoacoustic monitoring of macrobenthic animals in mangrove areas, the relative abundance of each functional group of macrobenthic animals is analyzed, the analysis results are obtained, and the acoustic landscape diversity of macrobenthic animals is assessed based on the analysis results, specifically including:

[0105] Set a relative abundance characteristic threshold for macrobenthic functional groups, and determine whether the relative abundance of each macrobenthic functional group is greater than the relative abundance characteristic threshold of the macrobenthic functional group.

[0106] When the relative abundance of each functional group of macrobenthic animals is greater than the relative abundance characteristic threshold of the macrobenthic animal functional group, the analysis results are generated and the relative abundance of each functional group of macrobenthic animals is output.

[0107] A second aspect of the present invention provides an eco-acoustic monitoring device for macrobenthic animals in mangrove areas, comprising a memory and a processor. The memory includes a program for eco-acoustic monitoring of macrobenthic animals in mangrove areas. When the program for eco-acoustic monitoring of macrobenthic animals in mangrove areas is executed by the processor, it implements the steps of any of the methods for eco-acoustic monitoring of macrobenthic animals in mangrove areas.

[0108] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods, such as: multiple units or components may be combined, or integrated into another device, or some features may be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the various components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0109] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units. They may be located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0110] In addition, in the various embodiments of the present invention, each functional unit can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0111] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0112] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, ROM, RAM, magnetic disks, or optical disks.

[0113] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for ecoacoustic monitoring of large benthic animals in mangrove areas, characterized in that, Includes the following steps: Acoustic propagation characteristic data under various environmental characteristics are obtained through big data, and an acoustic propagation characteristic data prediction model is constructed based on the acoustic propagation characteristic data under various environmental characteristics. Based on the acoustic propagation characteristic data prediction model, acoustic characteristic data in the mangrove area are predicted, and acoustic equipment in the mangrove area is arranged according to the acoustic propagation characteristic data in the mangrove area. Acoustic feature data of mangrove areas are acquired using acoustic equipment, and the functional groups of macrobenthic animals in mangrove areas are monitored and identified based on the acoustic feature data of mangrove areas, and the relative abundance of macrobenthic animal functional groups is statistically analyzed. The relative abundance of each functional group of the macrobenthic animals was analyzed, the analysis results were obtained, and the acoustic diversity of macrobenthic animals was assessed based on the analysis results. Based on the acoustic propagation characteristic data under the aforementioned environmental characteristics, an acoustic propagation characteristic data prediction model is constructed, specifically as follows: An acoustic propagation feature data prediction model is constructed based on a deep neural network. A graph neural network is introduced, and the acoustic propagation feature data under each environmental feature is input into the graph neural network, with the environmental feature as the first node of the graph neural network. Using acoustic propagation feature data as the second node of a graph neural network, a directed descriptive relationship is constructed. Based on the directed descriptive relationship, the first node and the second node are connected so that the first node points to the second node, thus constructing a topology graph. Based on the topology graph, an adjacency matrix is ​​obtained. The adjacency matrix is ​​then input into the acoustic propagation feature data prediction model for training. It is then determined whether the acoustic propagation feature data prediction model meets the training termination condition during the training process. When the acoustic propagation feature data prediction model meets the training termination condition during the training process, the model parameters of the acoustic propagation feature data prediction model are saved, and the acoustic propagation feature data prediction model is output.

2. The method for ecoacoustic monitoring of macrobenthic animals in mangrove areas according to claim 1, characterized in that, The acoustic propagation characteristic data prediction model predicts acoustic propagation characteristic data in mangrove areas, specifically including: The environmental characteristics and real-time acoustic characteristics of the current mangrove area are obtained, and the environmental characteristics and real-time acoustic characteristics of the current mangrove area are input into the acoustic propagation characteristic data prediction model for prediction. The acoustic propagation characteristics data in the mangrove area are obtained through prediction, and the acoustic propagation characteristics data in the mangrove area are output.

3. The method for ecoacoustic monitoring of macrobenthic animals in mangrove areas according to claim 1, characterized in that, Based on the acoustic propagation characteristic data of the mangrove area, acoustic equipment is deployed in the mangrove area, specifically as follows: Obtain the sensing range area of ​​each acoustic device type under different acoustic propagation characteristic data, and obtain the acoustic device type whose sensing range area is larger than the preset sensing range area. The acoustic device type corresponding to the sensing range area being larger than the preset sensing range area is used as the acoustic device type for data acquisition. The sensing range area of ​​the acoustic device type for data acquisition is obtained based on the sensing range area of ​​each acoustic device type under different acoustic propagation characteristic data and the acoustic propagation characteristic data in the mangrove area. The arrangement location and quantity of acoustic devices for initializing the data acquisition are determined, and the estimated sensing range area is calculated based on the sensing range area of ​​the acoustic device type, the arrangement location, and the quantity of the acoustic device. When the estimated sensing range is not greater than the preset range information, adjust the arrangement position and number of acoustic devices for data acquisition until it exceeds the preset range information.

4. The method for ecoacoustic monitoring of macrobenthic animals in mangrove areas according to claim 1, characterized in that, Acoustic characteristic data of mangrove areas are acquired using acoustic equipment, and the functional groups of macrobenthic animals in the mangrove areas are monitored and identified based on the acoustic characteristic data. The relative abundance of macrobenthic animal functional groups is statistically analyzed, specifically including: Acoustic feature data in mangrove areas are acquired using acoustic devices, and large benthic animal functional groups related to each acoustic feature data are obtained through big data. A large benthic animal knowledge graph is constructed based on the large benthic animal functional groups related to each acoustic feature data. The acoustic feature data of the mangrove area is input into the macrobenthic animal knowledge graph for identification, to obtain macrobenthic animal type feature data in the mangrove area, and to statistically analyze the macrobenthic animal functional group feature data in the mangrove area to obtain the relative abundance of macrobenthic animal functional groups.

5. The method for ecoacoustic monitoring of macrobenthic animals in mangrove areas according to claim 1, characterized in that, The relative abundance of each functional group of the macrobenthic animals was analyzed, the results were obtained, and the acoustic landscape diversity of macrobenthic animals was assessed based on the results, specifically including: Set a relative abundance characteristic threshold for macrobenthic functional groups, and determine whether the relative abundance of each macrobenthic functional group is greater than the relative abundance characteristic threshold of the macrobenthic functional group. When the relative abundance of each functional group of macrobenthic animals is greater than the relative abundance characteristic threshold of the macrobenthic animal functional group, the analysis results are generated and the relative abundance of each functional group of macrobenthic animals is output.

6. An acoustic monitoring device for large benthic animals in mangrove areas, characterized in that, The device includes a memory and a processor. The memory includes a program for a method of monitoring the ecoacoustic ecology of macrobenthic animals in mangrove areas. When the program is executed by the processor, it implements the steps of the method for monitoring the ecoacoustic ecology of macrobenthic animals in mangrove areas as described in any one of claims 1-5.

7. A computer-readable storage medium, characterized in that, The method includes a program for monitoring the ecoacoustic ecology of macrobenthic animals in mangrove areas. When the program is executed by a processor, it implements the steps of the method for monitoring the ecoacoustic ecology of macrobenthic animals in mangrove areas as described in any one of claims 1-5.

Images