Method for planting mangrove in oyster reef region, electronic device, and medium

Abstract

The application discloses an oyster reef region mangrove planting method, an electronic device and a medium, and the method comprises the following steps: constructing a root system topology model based on a preset CT scan result of a mangrove plant; based on three-dimensional grid data of the root system topology model and a plurality of matrix matching parameters, predicting the shear resistance corresponding to each matrix matching parameter through a graph neural network, and each target matrix material corresponding to each matrix matching parameter comprises oyster shell powder, biochar and filamentous fungal hyphae; 3D printing is used to manufacture a honeycomb-shaped biomimetic matrix corresponding to the target matrix matching parameter that meets the target condition, and the honeycomb-shaped biomimetic matrix is used for mangrove planting. The application combines the oyster shell powder, the biochar and the filamentous fungal hyphae based on the degradable material, and the target matrix matching parameter that meets the target condition is obtained through the graph neural network prediction, and the honeycomb-shaped biomimetic matrix is constructed. Compared with a simple mixed matrix obtained by relying on an experience matching parameter in the prior art, the application can effectively improve the lodging resistance of the mangrove.

Description

Technical Field

[0001] This application relates to, but is not limited to, the field of ecological technology, and in particular to a method, electronic equipment, and medium for planting mangroves in oyster reef areas. Background Technology

[0002] The substrate for planting mangroves is the fundamental environment upon which mangrove plants depend for survival. Traditional substrate formulations rely on empirical methods (such as pure silt or simple mixed substrates), lacking a scientific match between root mechanical properties and substrate shear resistance. This is particularly problematic in oyster reef areas, affecting mangrove root anchorage. Consequently, substrates prepared using traditional formulations suffer from poor aeration and drainage, impacting root development and erosion resistance. Mangroves planted in such substrates are insufficiently resistant to wind and waves and prone to lodging. Summary of the Invention

[0003] This application provides a method, electronic device, and medium for planting mangroves in oyster reef areas, which can effectively improve the lodging resistance of mangroves.

[0004] In a first aspect, embodiments of this application provide a method for planting mangroves in oyster reef areas, including:

[0005] CT scans were performed on the pre-defined mangrove plants, and a root topology model was constructed based on the CT scan results;

[0006] Based on the three-dimensional mesh data of the root system topology model and multiple matrix ratio parameters, the shear resistance corresponding to each matrix ratio parameter is predicted by a graph neural network. The target matrix materials corresponding to all the matrix ratio parameters are of the same type, including oyster shell powder, biochar and filamentous fungal mycelium.

[0007] The matrix ratio parameter corresponding to the shear resistance that meets the target conditions is determined as the target matrix ratio parameter, and the honeycomb biomimetic matrix corresponding to the target matrix ratio parameter is made by 3D printing technology.

[0008] Mangrove planting was carried out using the aforementioned honeycomb-shaped biomimetic matrix.

[0009] In some embodiments, a CT scan is performed on a preset mangrove plant, and a root topology model is constructed based on the CT scan results, including:

[0010] The mangrove plants were fixed using low-temperature fixation technology or epoxy resin embedding technology;

[0011] Gradient ethanol dehydration treatment was carried out on the saline soil of the fixed mangrove plants;

[0012] The target sample was obtained by soaking dehydrated mangrove plants in sodium iodide for a preset time.

[0013] The target sample is scanned using a micro-CT device to obtain the CT scan results, and the root system topology model is constructed based on the CT scan results after noise correction and geometric calibration.

[0014] In some embodiments, the CT scan results include a three-dimensional grayscale image of the root system, and a root system topology model is constructed based on the CT scan results, including:

[0015] Calculate the image histogram of the three-dimensional grayscale image of the root system, and segment the root system and soil of the mangrove plant based on the image histogram and a preset density threshold to obtain the segmentation result, wherein the segmentation result includes the initial root system data of the mangrove plant;

[0016] The target root system data is obtained by enhancing the bifurcation region features of the initial root system data based on the preset Mask R-CNN model.

[0017] Extract the root skeleton features from the target root system data;

[0018] The root system topology model is constructed based on the root system skeleton features.

[0019] In some embodiments, based on three-dimensional mesh data of a root system topology model and multiple matrix ratio parameters, a graph neural network is used to predict the shear resistance corresponding to each of the matrix ratio parameters, including:

[0020] The graph neural network is constructed based on the three-dimensional mesh data;

[0021] Each of the matrix ratio parameters is sequentially input into the graph neural network to obtain each of the shear resistances, wherein any of the shear resistances includes the sub-shear resistances of each node in the corresponding graph neural network.

[0022] In some embodiments, the target condition is greater than the reference shear strength. The matrix ratio parameter corresponding to the shear strength that satisfies the target condition is determined as the target matrix ratio parameter, including:

[0023] Based on the parent-child relationship of the root topology corresponding to the graph neural network, the path from the root node to the leaf node of the graph neural network is recursively traversed to obtain the overall shear resistance. In the process of recursively calculating the reference shear resistance, for any branch node in the path, the first shear resistance obtained by accumulating the sub-shear resistance of the child nodes corresponding to the branch node is taken as the target shear resistance of the branch node. For any continuous segment node in the path, the sub-shear resistance with the smallest value in the target continuous segment corresponding to the continuous segment node is taken as the target shear resistance of the target continuous segment. The overall shear resistance is determined based on all the target shear resistances.

[0024] The matrix ratio parameter corresponding to the overall shear strength that is greater than the reference shear strength is determined as the target matrix ratio parameter.

[0025] In some embodiments, a honeycomb-shaped biomimetic matrix corresponding to the target matrix ratio parameters is fabricated using 3D printing technology, including:

[0026] Obtain the oyster shell powder, the biochar, and the filamentous fungal mycelium corresponding to the target matrix ratio parameters;

[0027] The oyster shell powder and the biochar were ground in a ball mill to obtain a mixed powder;

[0028] The filamentous fungal mycelium was subjected to sterilization treatment and pre-cultured in liquid culture medium for a preset time to obtain a mycelial suspension;

[0029] The mixed powder and the mycelium suspension are mixed in a preset ratio, and sodium alginate is added and stirred to obtain a printable slurry;

[0030] A random cellular topology is generated based on the CT scan results, and a printing path for the 3D printer is constructed based on the random cellular topology.

[0031] Based on the printing path control, the 3D printer loaded with the printing paste and water-soluble support material performs 3D printing at a preset temperature to obtain the honeycomb-shaped biomimetic matrix.

[0032] In some embodiments, prior to planting mangroves using the honeycomb-shaped biomimetic substrate, the method further includes:

[0033] The honeycomb-shaped biomimetic substrate was placed in an environment with 95% humidity and 28°C for 72 hours.

[0034] The honeycomb-shaped biomimetic matrix was subjected to ultraviolet light curing treatment for 30 minutes;

[0035] Electrostatic spraying is performed on the honeycomb-shaped biomimetic matrix to uniformly deposit an oyster shell powder-chitosan composite coating on the surface of the honeycomb-shaped biomimetic matrix.

[0036] The honeycomb-shaped biomimetic matrix is ​​mechanically polished to remove any residue of the water-soluble support material on the honeycomb-shaped biomimetic matrix.

[0037] In some embodiments, the number of honeycomb-shaped biomimetic substrates is multiple, and mangrove planting using the honeycomb-shaped biomimetic substrates includes:

[0038] Determine the elevation data of the target tidal flat, and arrange each of the honeycomb-shaped biomimetic substrates in the target tidal flat with an elevation range of -0.5m to 1.2m. The target tidal flat is located in an oyster reef area, and the spacing between each of the honeycomb-shaped biomimetic substrates is 25cm×25cm.

[0039] Biodegradable anchor pins are embedded at the bottom of each of the aforementioned honeycomb-shaped biomimetic matrices;

[0040] Nutrient solution was injected into the pores of each of the honeycomb-shaped biomimetic substrates 72 hours before planting the mangrove plants.

[0041] The selected mangrove seedlings are inserted into the honeycomb channels of the corresponding honeycomb-shaped biomimetic substrate using a planting machine. The honeycomb channels are pre-filled with a mixture of oyster shell powder and peat moss.

[0042] Spray each of the aforementioned honeycomb-shaped biomimetic substrates with a suspension of mycorrhizal fungal spores.

[0043] Secondly, embodiments of this application provide an electronic device, including at least one control processor and a memory for communicatively connecting to the at least one control processor; the memory stores instructions executable by the at least one control processor, which, when executed by the at least one control processor, enable the at least one control processor to perform the mangrove planting method in the oyster reef region as described in the first aspect.

[0044] Thirdly, embodiments of this application also provide a computer-readable storage medium storing computer-executable instructions for performing the mangrove planting method in the oyster reef region as described in the first aspect.

[0045] This application provides a method for planting mangroves in oyster reef areas. The method includes: performing CT scans on pre-selected mangrove plants and constructing a root topology model based on the CT scan results; predicting the shear resistance corresponding to each of the matrix ratio parameters using a graph neural network based on the three-dimensional mesh data of the root topology model and multiple matrix ratio parameters, wherein all the matrix ratio parameters correspond to the same type of target matrix material, including oyster shell powder, biochar, and filamentous fungal mycelium; determining the matrix ratio parameter corresponding to the shear resistance that meets the target conditions as the target matrix ratio parameter; fabricating a honeycomb-shaped biomimetic matrix corresponding to the target matrix ratio parameter using 3D printing technology; and planting mangroves using the honeycomb-shaped biomimetic matrix. According to the solution provided in this application, a honeycomb-shaped biomimetic matrix is ​​constructed based on the target matrix ratio parameters that meet the target conditions, using biodegradable materials such as oyster shell powder, biochar, and filamentous fungal mycelium, combined with the target matrix ratio parameters predicted by a graph neural network. Compared with the traditional simple mixed matrix obtained by relying on empirical ratio parameters, this method can effectively improve the lodging resistance of mangroves. Attached Figure Description

[0046] Figure 1 This is a flowchart of the steps of a mangrove planting method in an oyster reef area provided in one embodiment of this application;

[0047] Figure 2 This is a structural diagram of an electronic device provided in another embodiment of this application. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0049] It is understandable that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, or the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0050] The substrate for planting mangroves is the fundamental environment upon which mangrove plants depend for survival. Traditional substrate formulations rely on empirical methods (such as pure silt or simple mixed substrates), lacking a scientific match between root mechanical properties and substrate shear resistance. This is particularly problematic in oyster reef areas, affecting mangrove root anchorage. Consequently, substrates prepared using traditional formulations suffer from poor aeration and drainage, impacting root development and erosion resistance. Mangroves planted in such substrates are insufficiently resistant to wind and waves and prone to lodging.

[0051] To address the aforementioned problems, this application provides a method for planting mangroves in oyster reef areas. The method includes: performing CT scans on pre-selected mangrove plants and constructing a root system topology model based on the CT scan results; predicting the shear resistance corresponding to each of the matrix ratio parameters using a graph neural network based on the three-dimensional mesh data of the root system topology model and multiple matrix ratio parameters, wherein all the matrix ratio parameters correspond to the same type of target matrix material, including oyster shell powder, biochar, and filamentous fungal mycelium; determining the matrix ratio parameter corresponding to the shear resistance that meets the target conditions as the target matrix ratio parameter; fabricating a honeycomb-shaped biomimetic matrix corresponding to the target matrix ratio parameter using 3D printing technology; and planting mangroves using the honeycomb-shaped biomimetic matrix. According to the solution provided in this application, a honeycomb-shaped biomimetic matrix is ​​constructed based on the target matrix ratio parameters that meet the target conditions, using biodegradable materials such as oyster shell powder, biochar, and filamentous fungal mycelium, combined with the target matrix ratio parameters predicted by a graph neural network. Compared to the traditional simple mixed matrix obtained by relying on empirical ratio parameters, this method can effectively improve the lodging resistance of mangroves.

[0052] The embodiments of this application will be further described below with reference to the accompanying drawings.

[0053] refer to Figure 1 , Figure 1 This is a flowchart illustrating the steps of a mangrove planting method in an oyster reef region according to an embodiment of this application. This embodiment of the application provides a mangrove planting method in an oyster reef region, which includes, but is not limited to, the following steps:

[0054] Step S10: Perform CT scans on the preset mangrove plants and construct a root topology model based on the CT scan results.

[0055] Specifically, in some embodiments, Figure 1 Step S10 includes, but is not limited to, the following steps:

[0056] Step S11: Fix mangrove plants using low-temperature fixation technology or epoxy resin embedding technology;

[0057] Step S12: The saline soil of the fixed mangrove plants is subjected to gradient ethanol dehydration treatment.

[0058] Step S13: The target sample is obtained by soaking mangrove plants in sodium iodide solution for a preset time to obtain the dehydrated mangrove plants.

[0059] Step S14: Perform a CT scan on the target sample using a micro-CT device to obtain the CT scan results, and construct a root topology model based on the CT scan results after noise correction and geometric calibration.

[0060] Specifically, the mangrove plants in this embodiment can be Kandelia candel or Avicennia marina, which can be determined by those skilled in the art according to actual needs.

[0061] Specifically, in this embodiment, the temperature corresponding to fixing mangrove plants using low-temperature fixation technology is -20℃.

[0062] It should be noted that, in this embodiment, before using low-temperature fixation technology or epoxy resin embedding technology to fix the mangrove plants, in-situ sampling technology is first used to sample the mangrove plant roots along with the surrounding 30cm. 3 The original soil should be excavated as a whole to avoid breaking the fine roots.

[0063] Understandably, in this embodiment, the mangrove plants sampled in situ are fixed using low-temperature fixation technology or epoxy resin embedding technology, and the saline soil of the fixed mangrove plants is subjected to gradient ethanol dehydration treatment (from 30% ethanol concentration to 100% ethanol concentration) to optimize the medium and reduce scanning noise during subsequent CT scan operations. Then, the dehydrated mangrove plants are soaked in sodium iodide for a preset time (the preset soaking time in this embodiment is 48 hours) to obtain the target sample, which can improve the X-ray penetration efficiency during subsequent CT scan operations.

[0064] It should be noted that the micro-CT device in this embodiment is a submicron-level micro-CT device with a resolution of 10μm, which can ensure clear imaging of root hair-level structures. Before performing CT scanning using the micro-CT device, the X-ray source parameters of the micro-CT device are adjusted to: voltage 120kV, current 150μA, and exposure time 1.5s / frame, so as to balance the signal-to-noise ratio and the risk of radiation damage. The scanning path of the micro-CT device is set to spiral scanning + 360° rotation, with a step angle of 0.3°, and 5000 to 8000 projection images are acquired per sample. The detector pixel matrix of the micro-CT device is set to 4096×4096, slice thickness 5μm, and overlap rate 40%, which can ensure the continuity of three-dimensional data.

[0065] It is understandable that, in obtaining the CT scan results, this embodiment simultaneously acquires dark field (no X-ray) and bright field (no sample) images while scanning to obtain the CT scan results. This can correct and eliminate detector response differences, and use a tungsten alloy calibration ball to verify the geometric accuracy of the system and control errors, so as to ensure the accuracy of the CT scan results and thus ensure the accuracy of the root system topology model.

[0066] Specifically, in some embodiments, the CT scan results include three-dimensional grayscale images of the root system. Figure 1 Step S10, which involves constructing a root system topology model based on CT scan results, includes, but is not limited to, the following steps:

[0067] Step S15: Calculate the image histogram of the three-dimensional grayscale image of the root system, and segment the root system and soil of the mangrove plants based on the image histogram and a preset density threshold to obtain the segmentation result, wherein the segmentation result includes the initial root data of the mangrove plants.

[0068] Step S16: Enhance the bifurcation region features of the initial root system data based on the preset Mask R-CNN model to obtain the target root system data;

[0069] Step S17: Extract the root skeleton features of the target root system data;

[0070] Step S18: Construct a root system topology model based on root system skeleton features.

[0071] Specifically, the CT scan results include a three-dimensional grayscale image of the root system. Different scanning energies are used for different regions of the target sample. For example, dual-energy scanning (low energy 30kV + high energy 100kV) is used for high-salt samples of the target sample to effectively eliminate salt crystallization artifacts.

[0072] Specifically, the Mask R-CNN model in this embodiment adds a CBAM attention module that can enhance the features of the bifurcation region.

[0073] It is understandable that the specific steps of constructing the root topology model based on CT scan results in this embodiment include: (1) using the density threshold method to perform multi-level segmentation in order to accurately separate the root system of mangrove plants from the soil / sediment, ensuring that the main root positioning error is ≤1.2%. The specific steps of multi-level segmentation are as follows: calculate the image histogram of the three-dimensional grayscale image of the root system, and determine the root system (density >1.8g / cm³). 3 ) and soil (density < 1.3 g / cm³) 3The density threshold is dynamically optimized using the Otsu algorithm. Based on the image histogram and density threshold, the root system and soil of mangrove plants are segmented to obtain the segmentation result, which includes the initial root data of mangrove plants. Error correction is achieved through manual review. (2) The bifurcation region features of the initial root data are enhanced based on the preset Mask R-CNN model to obtain the target root data. Specifically, a labeled dataset containing 2000 sets of mangrove root bifurcation points is constructed (e.g., including 1200 sets of Kandelia candel and 800 sets of Sangharama spp.). The labeled dataset is randomly rotated in the range of -15° to 15°, and the brightness is adjusted in the range of -20% to 20%. The labeled dataset is enhanced with Gaussian noise with a standard deviation of σ = 0.01. (3) The initial Mask R-CNN model is trained using the labeled dataset with 500 iterations and a preset loss function to obtain the trained Mask R-CNN model. Based on the trained Mask R-CNN model, the initial Mask R-CNN model is trained. The R-CNN model enhances the bifurcation region features of the initial root data to obtain the target root data; (4) The improved MAT midline transformation method is used to perform binarization, pruning of short branches and topological repair on the target root data in sequence, and neighborhood connectivity detection is realized to repair the broken skeleton (maximum repair spacing 0.2mm) and obtain the root skeleton features. Among them, the root skeleton features include root length density L, fractal dimension D and specific surface area S. Root length density L = ∑(number of skeleton pixels × resolution) / volume. Root length density L can characterize the root extension capacity per unit volume. Fractal dimension D = lim(lnN(ε) / ln(1 / ε)). Fractal dimension D can characterize the spatial complexity of the root system. Among them, N(ε) represents the minimum number of boxes required to cover the fractal with a small box with a side length of ε. Specific surface area S = root surface area / biomass dry weight. Specific surface area S can characterize the material exchange efficiency. (4) A root system topology model was constructed based on the root system skeleton characteristics. Specifically, the root system skeleton characteristics were converted into a pore network model using Avizo software. Then, key parameters of the pore network model were obtained, including the pore throat diameter distribution (ranging from 2 μm to 50 μm) and path tortuosity T (ranging from 1.6 to 2.4). Path tortuosity T = actual diffusion path / straight-line distance. Based on the oxygen diffusion equation and sediment holding capacity model, combined with the above key parameters, multiphysics coupling processing was performed to construct the root system topology model. The expression corresponding to the oxygen diffusion equation is as follows:

[0074]

[0075] Where Deff is the effective diffusion coefficient and Rroot is the root oxygen consumption rate. The Laplace operator is the oxygen concentration; the expression for the sediment holding capacity model is as follows:

[0076] F max =0.87·e 0.32D ·ρ 1.5 ;

[0077] Where D is the fractal dimension and ρ is the root density.

[0078] Step S20: Based on the three-dimensional mesh data of the root system topology model and multiple matrix ratio parameters, the shear resistance corresponding to each matrix ratio parameter is predicted by a graph neural network. Among them, all matrix ratio parameters correspond to the same type of target matrix material, which includes oyster shell powder, biochar and filamentous fungal mycelium.

[0079] Specifically, in some embodiments, Figure 1 Step S20 includes, but is not limited to, the following steps:

[0080] Step S21: Construct a graph neural network based on the 3D mesh data;

[0081] Step S22: Input each matrix ratio parameter into the graph neural network in sequence to obtain each shear resistance, wherein any shear resistance includes the sub-shear resistance of each node in the corresponding graph neural network.

[0082] It is understood that the matrix materials selected in this invention (including oyster shell powder, biochar, and filamentous fungal mycelium) are all biodegradable materials, and the absence of hard materials (such as concrete modules) can improve the disaster resistance of mangroves while effectively avoiding the damage of hard materials to the ecological balance of the tidal flats, increasing the abundance of microorganisms, and ensuring that the ecological compatibility standards are met.

[0083] It is understood that this embodiment sets multiple matrix ratio parameters. Different matrix ratio parameters correspond to different mixing ratios of oyster shell powder, biochar, and filamentous fungal mycelium. The shear resistance of the matrix under different mixing ratios is predicted by a graph neural network. Specifically, a graph neural network is constructed based on three-dimensional mesh data. Each matrix ratio parameter is sequentially input into the graph neural network to obtain each shear resistance. Each shear resistance includes the sub-shear resistance of each node in the corresponding graph neural network. This provides an effective data foundation for subsequently determining the target matrix ratio parameter corresponding to high shear resistance and manufacturing a biomimetic matrix with strong lodging resistance.

[0084] Step S30: The matrix ratio parameter corresponding to the shear strength that meets the target conditions is determined as the target matrix ratio parameter, and the honeycomb biomimetic matrix corresponding to the target matrix ratio parameter is made using 3D printing technology.

[0085] Specifically, in some embodiments, the target condition is greater than the reference shear resistance. Figure 1Step S30, which determines the matrix ratio parameter corresponding to the shear strength that satisfies the target condition, as the target matrix ratio parameter, includes, but is not limited to, the following steps:

[0086] Step S31: Based on the parent-child relationship of the root topology corresponding to the graph neural network, recursively traverse the path from the root node to the leaf node of the graph neural network to obtain the overall shear resistance. In the process of recursively calculating the reference shear resistance, for any branch node in the path, the first shear resistance obtained by accumulating the sub-shear resistance of the child nodes corresponding to the branch node is used as the target shear resistance of the branch node. For any continuous segment node in the path, the sub-shear resistance with the smallest value in the target continuous segment corresponding to the continuous segment node is used as the target shear resistance of the target continuous segment. The overall shear resistance is determined based on all the target shear resistances.

[0087] Step S32: Determine the matrix ratio parameter corresponding to the overall shear strength that is greater than the reference shear strength as the target matrix ratio parameter.

[0088] It is understood that the steps in this embodiment to determine the matrix ratio parameter corresponding to the shear strength that meets the target condition as the target matrix ratio parameter include: based on the parent-child relationship of the root topology corresponding to the graph neural network, recursively traversing the path from the root node to the leaf node of the graph neural network to obtain the overall shear strength. In the process of recursively calculating the reference shear strength, for any branch node in the path, the first shear strength obtained by accumulating the sub-shear strength of the child nodes corresponding to the branch node is used as the target shear strength of the branch node. For any continuous segment node in the path, the sub-shear strength with the smallest value in the target continuous segment corresponding to the continuous segment node is used as the target shear strength of the target continuous segment. The overall shear strength is determined based on all the target shear strengths. In this way, the overall shear strength of planting mangroves corresponding to each matrix ratio parameter is obtained. Then, the matrix ratio parameter corresponding to the overall shear strength that is greater than the reference shear strength is determined as the target matrix ratio parameter. The graph neural network can realize the automatic prediction of the overall shear strength corresponding to each matrix ratio parameter. Compared with the traditional method of judging by expert experience, it can improve the screening efficiency of matrix ratio parameters and reduce experimental costs.

[0089] In addition, the substrate ratio parameters in this embodiment are dynamically optimized based on environmental factors such as tides and salinity, which can effectively reduce the interference of environmental variables and ensure the availability of the target substrate ratio parameters.

[0090] Additionally, in some embodiments... Figure 1 Step S30, which involves using 3D printing technology to create a honeycomb-shaped biomimetic matrix corresponding to the target matrix ratio parameters, includes, but is not limited to, the following steps:

[0091] Step S33: Obtain oyster shell powder, biochar, and filamentous fungal mycelium corresponding to the target matrix ratio parameters;

[0092] Step S34: Oyster shell powder and biochar are ground in a ball mill to obtain a mixed powder;

[0093] Step S35: The filamentous fungal mycelium is sterilized and pre-cultured in liquid culture medium for a preset time to obtain a mycelial suspension.

[0094] Step S36: Obtain oyster shell powder, biochar, and filamentous fungal mycelium corresponding to the target matrix ratio parameters;

[0095] Step S37: Mix the powder and mycelium suspension according to a preset ratio, add sodium alginate, and stir to obtain a printable slurry;

[0096] Step S38: Generate a random cellular topology based on the CT scan results, and construct the printing path of the 3D printer based on the random cellular topology;

[0097] Step S39: Based on the printing path control, the 3D printer loaded with printing paste and water-soluble support material performs 3D printing at a preset temperature to obtain a honeycomb-shaped biomimetic matrix.

[0098] Specifically, in this embodiment, the target matrix ratio for oyster shell powder, biochar, and filamentous fungal mycelium is 6:2.5:1.5.

[0099] Understandably, after determining the target matrix ratio parameters, raw material pretreatment is performed first to obtain oyster shell powder, biochar, and filamentous fungal mycelium corresponding to the target matrix ratio parameters. Then, oyster shell powder with a particle size less than or equal to 75 μm and biochar with a particle size less than or equal to 100 μm are mixed in a 6:2.5 ratio and ground in a ball mill to obtain a mixed powder. The grinding time is 2 hours to ensure uniform particle distribution. The filamentous fungal mycelium is then sterilized and pre-cultured in liquid culture medium for a preset time (48 hours in this embodiment) to obtain a mycelial suspension, which is used as a bio-binder. Next, slurry preparation is performed by mixing the mixed powder and the mycelial suspension in a preset ratio (8:2 in this embodiment) and adding... A 2% sodium alginate solution was stirred to obtain a printable slurry. Next, a biomimetic model was constructed. A random honeycomb topology was generated based on CT scan results, and the printing path of the 3D printer was constructed based on this random honeycomb topology. The surface porosity of the random honeycomb topology was 50%, with surface pore sizes ranging from 0.5 mm to 1.2 mm. The deep porosity was 30%, with deep pore sizes ranging from 0.3 mm to 0.6 mm, thus simulating the gradient pore distribution formed by tidal erosion. Furthermore, based on the printing path, the 3D printer, loaded with the printing slurry and water-soluble support material, was controlled to perform 3D printing at a preset temperature (25°C in this embodiment to prevent mycelial inactivation) to obtain a honeycomb-shaped biomimetic matrix.

[0100] Step S40: Mangrove planting is carried out using a honeycomb-shaped biomimetic substrate.

[0101] Additionally, in some embodiments, during execution Figure 1 Prior to step S40, the mangrove planting method in the oyster reef area of ​​this application embodiment also includes, but is not limited to, the following steps:

[0102] Step S51: Place the honeycomb-shaped biomimetic substrate in an environment with 95% humidity and 28°C for 72 hours.

[0103] Step S52: The honeycomb biomimetic matrix is ​​subjected to ultraviolet light curing treatment for 30 minutes;

[0104] Step S53: Electrostatic spraying is performed on the honeycomb biomimetic matrix to uniformly deposit an oyster shell powder-chitosan composite coating on the surface of the honeycomb biomimetic matrix.

[0105] Step S54: Mechanically polish the honeycomb biomimetic matrix to remove any residue of the water-soluble support material on the honeycomb biomimetic matrix.

[0106] Understandably, after the honeycomb-shaped biomimetic matrix is ​​printed, it is placed in an environment with 95% humidity and 28°C for 72 hours to allow the mycelium to form a three-dimensional network structure, thereby improving its shear strength. Next, the honeycomb-shaped biomimetic matrix is ​​subjected to ultraviolet light curing for 30 minutes to enhance its surface erosion resistance. Furthermore, the honeycomb-shaped biomimetic matrix is ​​electrostatically sprayed to uniformly deposit an oyster shell powder-chitosan composite coating on its surface. Mechanical polishing is then performed to remove any residue of the water-soluble support material, reducing fluid resistance and providing effective support for the subsequent planting of mangroves with strong lodging resistance.

[0107] Specifically, Figure 1 Step S40 includes, but is not limited to, the following steps:

[0108] Step S41: Determine the elevation data of the target tidal flat, and arrange each honeycomb biomimetic matrix in the target tidal flat with an elevation range of -0.5m to 1.2m. The target tidal flat is located in the oyster reef area, and the spacing between each honeycomb biomimetic matrix is ​​25cm×25cm.

[0109] Step S42: Embed biodegradable anchor pins at the bottom of each honeycomb-shaped biomimetic matrix;

[0110] Step S43: 72 hours before planting mangrove plants, inject nutrient solution into the pores of each honeycomb-shaped biomimetic substrate.

[0111] Step S44: The selected mangrove seedlings are inserted into the honeycomb channels of the corresponding honeycomb-shaped biomimetic substrate using a planting machine. The honeycomb channels are pre-filled with a mixture of oyster shell powder and peat moss.

[0112] Step S45: Spray a suspension of mycorrhizal fungal spores onto each honeycomb-shaped biomimetic substrate.

[0113] Understandably, the specific steps for planting mangroves using honeycomb-shaped biomimetic substrates in this embodiment include: determining the elevation data of the target tidal flat; arranging each honeycomb-shaped biomimetic substrate within an elevation range of -0.5m to 1.2m in the target tidal flat, located in an oyster reef area; the spacing between each honeycomb-shaped biomimetic substrate being 25cm × 25cm; embedding biodegradable anchors at the bottom of each honeycomb-shaped biomimetic substrate to enhance erosion resistance; then, injecting nutrient solution into the pores of each honeycomb-shaped biomimetic substrate 72 hours before planting mangrove plants to promote the symbiosis of mycelium and local microorganisms; inserting selected mangrove seedlings into the corresponding honeycomb-shaped biomimetic substrate's honeycomb channels using a planting machine, wherein the honeycomb channels are pre-filled with a mixture of oyster shell powder and peat moss; and promptly spraying each honeycomb-shaped biomimetic substrate with mycorrhizal fungal spore suspension after planting, resulting in a stable mangrove-colony-intertidal animal ecosystem after 20 days. This embodiment, through scientific optimization of root system model topology and substrate ratio, can effectively reduce substrate loss rate, which not only improves the planting effect of mangroves but also reduces subsequent maintenance costs, providing a strong guarantee for the ecological restoration and sustainable development of mangroves.

[0114] like Figure 2 As shown, Figure 2 This is a structural diagram of an electronic device provided in one embodiment of this application. The present invention also provides an electronic device 200, comprising:

[0115] The processor 210 can be implemented using a general-purpose central processing unit (CPU), microprocessor, application specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0116] The memory 220 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 220 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 220 and is called and executed by the processor 210 to implement the mangrove planting method in the oyster reef area of ​​this application embodiment.

[0117] Input / output interface 230 is used to implement information input and output;

[0118] The communication interface 240 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0119] Bus 250 transmits information between various components of the device (e.g., processor 210, memory 220, input / output interface 230, and communication interface 240);

[0120] The processor 210, memory 220, input / output interface 230 and communication interface 240 are connected to each other within the device via bus 250.

[0121] In addition, this application embodiment also provides a storage medium, which is a computer-readable storage medium, storing a computer program that, when executed by a processor, implements the above-described mangrove planting method in oyster reef areas.

[0122] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof. The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separate, and may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0123] It will be understood by those skilled in the art that all or some of the steps and systems in the methods disclosed above can be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components can be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, which can include computer storage media (or non-transitory media) and communication media (or transient media). As is known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, as is known to those skilled in the art, communication media typically include computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0124] The above provides a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of the present invention.

Claims

1. A method for planting mangroves in oyster reef areas, characterized in that, include: CT scans were performed on the pre-defined mangrove plants, and a root topology model was constructed based on the CT scan results; Based on the three-dimensional mesh data of the root system topology model and multiple matrix ratio parameters, the shear resistance corresponding to each matrix ratio parameter is predicted by a graph neural network. The target matrix materials corresponding to all the matrix ratio parameters are of the same type, including oyster shell powder, biochar and filamentous fungal mycelium. The matrix ratio parameter corresponding to the shear resistance that meets the target conditions is determined as the target matrix ratio parameter, and the honeycomb biomimetic matrix corresponding to the target matrix ratio parameter is made by 3D printing technology. Mangrove planting using the aforementioned honeycomb-shaped biomimetic matrix; The method involves predicting the shear resistance corresponding to each matrix ratio parameter using a graph neural network based on three-dimensional mesh data of the root system topology model and multiple matrix ratio parameters. This includes: constructing the graph neural network based on the three-dimensional mesh data; sequentially inputting each matrix ratio parameter into the graph neural network to obtain each shear resistance, wherein any shear resistance includes the sub-shear resistance of each node in the corresponding graph neural network. The target condition is greater than the reference shear strength. The matrix ratio parameter corresponding to the shear strength that satisfies the target condition is determined as the target matrix ratio parameter. This includes: recursively traversing the path from the root node to the leaf node of the graph neural network based on the parent-child relationship of the root topology corresponding to the graph neural network to obtain the overall shear strength. In the process of recursively calculating the reference shear strength, for any branch node in the path, the first shear strength obtained by accumulating the sub-shear strength of the child nodes corresponding to the branch node is used as the target shear strength of the branch node. For any continuous segment node in the path, the sub-shear strength with the smallest value in the target continuous segment corresponding to the continuous segment node is used as the target shear strength of the target continuous segment. The overall shear strength is determined based on all the target shear strengths. The matrix ratio parameter corresponding to the overall shear strength that is greater than the reference shear strength is determined as the target matrix ratio parameter.

2. The method for planting mangroves in oyster reef areas according to claim 1, characterized in that, CT scans were performed on the pre-defined mangrove plants, and a root topology model was constructed based on the CT scan results, including: The mangrove plants were fixed using low-temperature fixation technology or epoxy resin embedding technology; Gradient ethanol dehydration treatment was carried out on the saline soil of the fixed mangrove plants; The target sample was obtained by soaking dehydrated mangrove plants in sodium iodide for a preset time. The target sample is scanned using a micro-CT device to obtain the CT scan results, and the root system topology model is constructed based on the CT scan results after noise correction and geometric calibration.

3. The method for planting mangroves in oyster reef areas according to claim 1, characterized in that, The CT scan results include three-dimensional grayscale images of the root system. A root system topology model is constructed based on the CT scan results, including: Calculate the image histogram of the three-dimensional grayscale image of the root system, and segment the root system and soil of the mangrove plant based on the image histogram and a preset density threshold to obtain the segmentation result, wherein the segmentation result includes the initial root system data of the mangrove plant; The target root system data is obtained by enhancing the bifurcation region features of the initial root system data based on the preset Mask R-CNN model. Extract the root skeleton features from the target root system data; The root system topology model is constructed based on the root system skeleton features.

4. The method for planting mangroves in oyster reef areas according to claim 1, characterized in that, The honeycomb-shaped biomimetic matrix corresponding to the target matrix ratio parameters is fabricated using 3D printing technology, including: Obtain the oyster shell powder, the biochar, and the filamentous fungal mycelium corresponding to the target matrix ratio parameters; The oyster shell powder and the biochar were ground in a ball mill to obtain a mixed powder; The filamentous fungal mycelium was subjected to sterilization treatment and pre-cultured in liquid culture medium for a preset time to obtain a mycelial suspension; The mixed powder and the mycelium suspension are mixed in a preset ratio, and sodium alginate is added and stirred to obtain a printable slurry; A random cellular topology is generated based on the CT scan results, and a printing path for the 3D printer is constructed based on the random cellular topology. Based on the printing path control, the 3D printer loaded with the printing paste and water-soluble support material performs 3D printing at a preset temperature to obtain the honeycomb-shaped biomimetic matrix.

5. The method for planting mangroves in oyster reef areas according to claim 4, characterized in that, Before using the honeycomb-shaped biomimetic substrate for mangrove planting, the method further includes: The honeycomb-shaped biomimetic substrate was placed in an environment with 95% humidity and 28°C for 72 hours. The honeycomb-shaped biomimetic matrix was subjected to ultraviolet light curing treatment for 30 minutes; Electrostatic spraying is performed on the honeycomb-shaped biomimetic matrix to uniformly deposit an oyster shell powder-chitosan composite coating on the surface of the honeycomb-shaped biomimetic matrix. The honeycomb-shaped biomimetic matrix is ​​mechanically polished to remove any residue of the water-soluble support material on the honeycomb-shaped biomimetic matrix.

6. The method for planting mangroves in oyster reef areas according to claim 1, characterized in that, The honeycomb-shaped biomimetic substrate is multiple in number, and mangrove planting is carried out using the honeycomb-shaped biomimetic substrate, including: Determine the elevation data of the target tidal flat, and arrange each of the honeycomb-shaped biomimetic substrates in the target tidal flat with an elevation range of -0.5m to 1.2m. The target tidal flat is located in an oyster reef area, and the spacing between each of the honeycomb-shaped biomimetic substrates is 25cm×25cm. Biodegradable anchor pins are embedded at the bottom of each of the aforementioned honeycomb-shaped biomimetic matrices; Nutrient solution was injected into the pores of each of the honeycomb-shaped biomimetic substrates 72 hours before planting the mangrove plants. The selected mangrove seedlings are inserted into the honeycomb channels of the corresponding honeycomb-shaped biomimetic substrate using a planting machine. The honeycomb channels are pre-filled with a mixture of oyster shell powder and peat moss. Spray each of the aforementioned honeycomb-shaped biomimetic substrates with a suspension of mycorrhizal fungal spores.

7. An electronic device, characterized in that, It includes at least one control processor and a memory for communicatively connecting with the at least one control processor; The memory stores instructions that can be executed by the at least one control processor to enable the at least one control processor to perform the mangrove planting method in the oyster reef region as described in any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions for causing a computer to perform the mangrove planting method in the oyster reef region as described in any one of claims 1 to 6.

Images