A Spatial Optimization-Based Method and System for Transforming Inefficient Camellia oleifera Forests

Abstract

This invention discloses a method and system for transforming inefficient Camellia oleifera forests based on spatial optimization. The method includes: collecting data from standard Camellia oleifera forests to construct a standard production database; collecting stand layout data and individual plant data of the inefficient Camellia oleifera forests to be transformed to construct a twin digital forest; based on the data in the standard production database, constructing a predictive model for the transformation of inefficient Camellia oleifera forests with the objectives of maximizing the expected total stand yield and minimizing the complexity of transformation implementation; inputting the data from the twin digital forest into the model for optimization calculations to generate a production optimization scheme containing optimal plant layout and individual plant transformation suggestions; generating a visual construction drawing or AR-guided instructions based on the optimization scheme to guide the transformation construction; and collecting output data after transformation to verify the effect. This invention, through digital modeling and multi-objective spatial optimization, achieves refined, intelligent, and scientific decision-making in the transformation of inefficient Camellia oleifera forests, effectively improving overall output efficiency.

Description

Technical Field

[0001] This invention belongs to the field of smart forestry technology, and in particular relates to a method and system for transforming inefficient Camellia oleifera forests based on spatial optimization. Background Technology

[0002] Camellia oleifera is a perennial economic forest tree that can sustain seed harvesting for decades. However, in the long run, improper initial planting density, unreasonable variety configuration, or extensive management can easily lead to an imbalance in forest structure, canopy closure, and intensified competition for light, eventually resulting in low-efficiency forests.

[0003] Specifically, there are significant genetic differences in flowering phenology, pollination compatibility, and fruit setting ability among camellia oleifera varieties. Inappropriate variety pairings can easily lead to pollination and fertilization obstacles, thus affecting yield. Furthermore, global climate change has exacerbated abiotic stresses such as high temperatures and drought, placing higher demands on the resilience of existing camellia oleifera varieties. Rapid advancements in biotechnology have facilitated the successful breeding of a number of new high-yield, high-oil-content varieties with specific functional components, providing a solid foundation for variety renewal. Simultaneously, with the continuous rise in rural labor costs and the promotion of mechanized farming, traditional varieties, due to their tree structure and crown shape, are unsuitable for mechanized operations and urgently need to be replaced by new, resilient, and mechanization-friendly varieties to reduce labor resource consumption and improve production efficiency.

[0004] On the other hand, traditional low-efficiency forest transformation relies heavily on human experience and judgment, adopting conventional thinning and reclamation measures. It lacks precise quantitative analysis of individual tree growth status, canopy structure, spatial distribution and resource competition relationship. The transformation process is highly subjective and lacks specificity, making it difficult to achieve stand spatial optimization and efficient resource utilization, as well as cost reduction and efficiency improvement.

[0005] Therefore, there is an urgent need for a transformation method that can accurately assess the growth status of individual Camellia oleifera trees, scientifically optimize forest stand structure, and achieve differentiated management, so as to break through the technical bottlenecks in the current transformation of low-yield and inefficient Camellia oleifera forests and improve the overall production efficiency and resource utilization efficiency of the Camellia oleifera industry. Summary of the Invention

[0006] To address these issues, this invention provides a spatially optimized method and system for transforming inefficient Camellia oleifera forests, thereby resolving the aforementioned problems.

[0007] In a first aspect, the present invention provides a method for transforming inefficient Camellia oleifera forests based on spatial optimization, comprising:

[0008] Collect stand layout and production data of standard Camellia oleifera forests to construct a standard Camellia oleifera production database;

[0009] Collect stand layout data and individual plant data of the low-efficiency Camellia oleifera forest to be transformed, and construct a twin digital forest of the low-efficiency Camellia oleifera forest based on the stand layout data and the individual plant data.

[0010] Based on the data in the Camellia oleifera standard production database, a prediction model for the transformation of inefficient Camellia oleifera forests is constructed. The data in the twin digital forest is input into the prediction model for the transformation of inefficient Camellia oleifera forests. Referring to the data in the Camellia oleifera standard production database, the prediction model for the transformation of inefficient Camellia oleifera forests is used for optimization calculation to generate a production optimization scheme that includes the best plant layout and individual plant transformation suggestions.

[0011] Based on the aforementioned production optimization plan, the low-efficiency camellia oleifera forest will undergo renovation construction.

[0012] After the transformation, the transformation effect of the transformed camellia oleifera forest is verified. The output data of the transformed camellia oleifera forest is compared with the output data of camellia oleifera forest in the camellia oleifera standard production database. If the output data of the transformed camellia oleifera forest is equal to or better than the output data of camellia oleifera forest in the camellia oleifera standard production database, then the original inefficient camellia oleifera forest has been successfully transformed.

[0013] Secondly, the present invention provides a spatially optimized system for transforming inefficient Camellia oleifera forests, comprising:

[0014] The Camellia oleifera database management module is configured to collect stand layout data and production data of standard Camellia oleifera forests and construct a standard Camellia oleifera production database.

[0015] The stand and individual tree data acquisition module is configured to collect stand layout data and individual tree data of the low-efficiency Camellia oleifera forest to be transformed, and to construct a twin digital forest of the low-efficiency Camellia oleifera forest based on the stand layout data and the individual tree data.

[0016] The model building and decision-making module is configured to build a prediction model for the transformation of inefficient Camellia oleifera forests based on the data in the Camellia oleifera standard production database, and input the data in the twin digital forest into the prediction model for the transformation of inefficient Camellia oleifera forests. Referring to the data in the Camellia oleifera standard production database, the prediction model for the transformation of inefficient Camellia oleifera forests is used to perform optimization calculations and generate a production optimization scheme that includes the best plant layout and individual plant transformation suggestions.

[0017] The execution guidance module is configured to generate a visual construction drawing or augmented reality (AR) guidance instruction from the production optimization plan to guide construction personnel to perform specified modification operations on plants with specified numbers.

[0018] The transformation effect verification module is configured to verify the transformation effect of the transformed camellia oleifera forest after transformation. The output data of the transformed camellia oleifera forest is compared with the output data of camellia oleifera forest in the camellia oleifera standard production database. If the output data of the transformed camellia oleifera forest is equal to or better than the output data of camellia oleifera forest in the camellia oleifera standard production database, then the original inefficient camellia oleifera forest has been successfully transformed.

[0019] Thirdly, an electronic device is provided, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the steps of the space-optimized camellia oleifera inefficient forest transformation method according to any embodiment of the present invention.

[0020] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor performs the steps of the space-optimized method for transforming inefficient Camellia oleifera forests according to any embodiment of the present invention.

[0021] The spatial optimization-based method and system for transforming inefficient Camellia oleifera forests proposed in this application have the following specific beneficial effects:

[0022] 1) Refinement and intelligence: By constructing a twin digital forest and identifying each plant, high-precision digital management of forest stand resources has been achieved, providing a solid data foundation for scientific decision-making and elevating the transformation from relying on experience to a data-driven and model-optimized intelligent level.

[0023] 2) Scientific decision-making and optimization: By establishing a multi-objective optimization function (maximizing yield and minimizing the complexity of transformation implementation) and comprehensively considering multiple constraints such as plant density, transformation complexity, plant variety matching, and light competition, the Pareto optimal solution can be automatically calculated. This makes the transformation solution not only optimize the physical space but also optimize the configuration at the reproductive biology level, achieving the optimal balance between technical efficiency and ecological benefits, and avoiding the blindness of human decision-making. Attached Figure Description

[0024] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 A flowchart illustrating a spatial optimization-based method for transforming inefficient Camellia oleifera forests, as provided in an embodiment of the present invention;

[0026] Figure 2 A structural block diagram of a space-optimized inefficient camellia oleifera forest transformation system provided in an embodiment of the present invention;

[0027] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0028] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0029] Please see Figure 1 The diagram shows a flowchart of a spatial optimization-based method for transforming inefficient Camellia oleifera forests according to this application.

[0030] In one embodiment, a 10-mu (approximately 1.65 acres) low-yield camellia oleifera forest located in a hilly area of ​​Jiangxi Province, China, is used as the target for transformation. The spatial optimization-based method for transforming low-efficiency camellia oleifera forests provided by this invention is applied.

[0031] Step S1: Collect stand layout data and production data of standard Camellia oleifera forests and construct a standard Camellia oleifera production database;

[0032] Specifically, the Camellia oleifera standard production database includes: standard forest stand structure data, yield efficiency benchmark data, and transformation implementation complexity data.

[0033] In this step, before implementing the transformation, it is necessary to first establish a standard production database for Camellia oleifera. The core data source for this database is the long-term monitoring and measured data of high-standard Camellia oleifera demonstration forests constructed by local forestry authorities and research institutes (such as provincial and municipal forestry research institutes / technology extension stations). It also integrates historical production data from the region and other areas with similar climatic conditions over many years to ensure the database's authority and regional applicability, serving as a benchmark reference for this transformation method. The database specifically includes the following data subsets:

[0034] Standard stand structure data includes the standard planting density range widely adopted in high-yield camellia oleifera forests, the ideal crown size and canopy closure range of camellia oleifera forests of different ages, and the spatial configuration and layout patterns of varieties that have been verified in practice and can effectively promote cross-pollination.

[0035] Yield performance benchmark data: This includes the standard annual average yield range of different varieties and canopy size grades of Camellia oleifera plants in high-yield Camellia oleifera forests.

[0036] Data on the complexity of transformation implementation: including the complexity rating of different transformation measures such as grafting and replacement, and the expected increase in production.

[0037] Step S2: Collect stand layout data and individual plant data of the low-efficiency Camellia oleifera forest to be transformed, and construct a twin digital forest of the low-efficiency Camellia oleifera forest based on the stand layout data and the individual plant data.

[0038] Specifically, constructing the digital twin forest of the low-efficiency Camellia oleifera forest includes:

[0039] S21. High-resolution multispectral images and laser point cloud data of the low-efficiency Camellia oleifera forest are collected by UAV aerial surveying. The forest stand layout data is obtained through data processing. The forest stand layout data includes at least plant distribution point data, canopy height model data, and digital elevation model data.

[0040] S22. Collect individual plant data of the low-efficiency camellia forest through manual field measurement. The individual plant data shall include at least the precise geographical information of the planting point, the variety information of the individual plant, the diameter at root, the growth status, and the historical data of the number of flowers and fruits. This individual plant data cannot be obtained by drone aerial survey and is an important supplement to the forest stand layout data collected by drone.

[0041] S23. By spatial location association, the plant distribution point data is coupled with the corresponding single plant data, and combined with the canopy height model data and digital elevation model data, the twin digital forest containing stand spatial structure and single plant attribute information is constructed.

[0042] In this step, aerial data acquisition is used to collect stand layout data of the low-efficiency camellia oleifera forest to be transformed. During implementation, a DJI Matrice 350 RTK drone is used as the flight platform, equipped with a Zenmuse P1 aerial survey camera, a Zenmuse H20N multispectral camera, and a Zenmuse L2 LiDAR module. Before flight, at least three RTK ground control points are deployed for accurate data correction later. The drone is set to a flight altitude of 100 meters, with a forward overlap of 80% and a lateral overlap of 70%, to perform automated flight scanning of the target forest stand, acquiring high-resolution multispectral imagery and LiDAR point cloud data.

[0043] After data acquisition, preliminary processing is performed. The acquired laser point cloud data is imported into professional data processing software (such as LiDAR360 or TerraSolid). After denoising, classification (separating ground points and vegetation points), and other processing, a high-precision digital elevation model (DEM) and digital surface model (DSM) are generated. By calculating the difference between the DSM and the DEM, a canopy height model (CHM) that accurately reflects the height of the top of the forest canopy is obtained. Using a single-tree segmentation algorithm, the location of individual trees (plant distribution points) can be identified from the CHM.

[0044] Simultaneously, workers entered the forest to count and number all the camellia oleifera plants. Each plant was assigned a weather-resistant plastic tag (containing an RFID chip, with the chip ID linked to the plant number). High-precision GPS devices (such as Trimble R2) were used to record the precise coordinates of each plant (geographic information of the individual planting location). Detailed parameters of the sample plants were manually measured and recorded, including: plant variety, flower quantity, fruit quantity, east / west / north / south crown diameter, and tree height. This individual plant data is crucial for constructing a precise digital twin forest and for subsequent optimization decisions.

[0045] Finally, data coupling and the construction of a digital twin forest are performed. Through spatial location matching (e.g., registering manually measured GPS coordinates of individual trees with plant distribution points identified by UAV aerial surveys), detailed individual tree attribute data (variety, diameter at breast height, growth status, etc.) for each Camellia oleifera tree are associated and coupled one-to-one with its spatial entity in the digital twin forest (represented by plant distribution points, CHM, etc.). By integrating all UAV aerial survey data (multispectral imagery, DEM, DSM, CHM) and the coupled individual tree data, a high-precision, information-fusion-based digital twin forest is constructed, incorporating information such as topography, individual tree location, tree height, canopy volume, and individual tree attributes.

[0046] Step S3: Based on the data in the Camellia oleifera standard production database, construct a prediction model for the transformation of inefficient Camellia oleifera forests, and input the data in the twin digital forest into the prediction model. Referring to the data in the Camellia oleifera standard production database, perform optimization calculations through the prediction model to generate a production optimization scheme that includes the best plant layout and individual plant transformation suggestions.

[0047] Specifically, the construction of a predictive model for the transformation of inefficient Camellia oleifera forests includes:

[0048] Step S31: Establish a multi-objective optimization function with the objectives of maximizing the expected total yield of the forest stand and minimizing the complexity of the transformation implementation, subject to constraints.

[0049] Step S32: Define decision variables, where the decision variables are the modification operations performed on each plant.

[0050] Step S33: Define constraints, including total stand density constraints, complexity constraints of different modification methods, plant variety matching constraints, and light competition constraints among plants based on the twin digital forest.

[0051] Step S34: Use a multi-objective optimization algorithm to solve the multi-objective optimization function, obtain the Pareto optimal solution set, and select the final production optimization scheme from the solution set.

[0052] Furthermore, the plant variety matching constraint is used to ensure that among the optimized and retained camellia oleifera plants, the proportion of variety combinations that guarantee flowering period coincidence and high pollination compatibility is not less than a preset variety compatibility threshold, thereby avoiding pollination and fertilization obstacles.

[0053] Furthermore, the light competition constraint between plants is achieved by analyzing the canopy light distribution in the twin digital forest to ensure that, in the optimized plant layout, the canopies of any two adjacent plants do not overlap on the projection plane, or the overlapping area is less than a set canopy overlap threshold.

[0054] In this step, the prediction model is modified into a mathematical model with the goal of maximizing the expected yield of the forest stand and minimizing the implementation complexity; the parameters and constraints are defined below.

[0055] The maximum total output is: ,

[0056] In the formula, The total number of all plants in the forest; These are decision variables, including four operations on the plant: 0-retain, 1-remove, 2-graft replacement; For the first Predicted yield per plant after specific modification measures The value is calculated with reference to the Camellia oleifera standard production database: First, based on the variety of the plant and its current crown volume provided by the twin digital forest. In the "Yield Efficiency Benchmark Data" subset of the Camellia oleifera standard production database, query the standard yield range for the corresponding variety and canopy size grade. Then, based on the modification operations selected for this plant... In the "Transformation Implementation Complexity Data" subset of the Camellia oleifera standard production database, query the expected yield increase coefficient corresponding to this operation. (like: =1.0 (retained)). Finally, the predicted yield of this plant is calculated as follows:

[0057] .

[0058] Minimize the implementation complexity as follows: ,

[0059] In the formula, This is the baseline complexity value, which is the baseline complexity of the same type of modification defined in the Camellia oleifera standard production database. In this embodiment, the baseline complexity value is set to 1. This represents the technical complexity of performing modification operations on the corresponding plant. The technical complexity of retention is set to 0, the technical complexity of removal is set to 0.5, and the technical complexity of grafting replacement is set to 1. It is the expected output gain coefficient. It is the ratio of the total yield of the low-efficiency forest after transformation to the total yield of the low-efficiency forest before transformation.

[0060] at the same time, The maximum implementation complexity is less than or equal to the maximum implementation complexity. The maximum implementation complexity is set according to the complexity distribution of historical modification cases in the Camellia oleifera standard production database. In this embodiment, the 75th percentile value is taken.

[0061] The decision variable is the set of modification operations for all Camellia oleifera plants. .

[0062] The plant density constraint is set at a longitudinal spacing of 3 meters and a lateral spacing of 4 meters between each plant.

[0063] Plant variety matching constraints: The complete definition of this constraint relies on the standard production database of Camellia oleifera, while subsequent model solving and scheme generation depend on the precise geographic coordinates and variety information of each plant provided by the twin digital forest. This ensures that for any variety ultimately retained... The plant, at its effective pollination distance Within a 30-meter radius, there must be at least one plant whose flowering period coincides with that of another plant and which is compatible for pollination. Other varieties (variety affinity threshold) The plants are selected to ensure that the optimized stand will not experience pollination problems due to improper plant variety matching.

[0064] in, For pollination affinity matrix Matrix elements, pollination affinity matrix The "variety pollination compatibility data" subset stored in the Camellia oleifera standard production database; variety compatibility threshold. (In this embodiment, it is set to 0.6) This is a reasonable value set based on historical data and expert experience in the Camellia oleifera standard production database, ensuring the biological effectiveness of the constraint.

[0065] Light competition constraints: Based on twin digital forests, it is ensured that the proportion of insufficient light-receiving area of ​​the canopy of any retained plant after optimization is less than the canopy overlap threshold. In this embodiment, the canopy overlap threshold is 10%, meaning that in the optimized layout, the area within the canopy projection surface of any retained plant where the cumulative light intensity received is lower than 60% of its light saturation point must not exceed 10% of its total projected area. The light saturation point is taken from the photosynthetic characteristics research data of different Camellia oleifera varieties in the Camellia oleifera standard production database; the canopy overlap threshold is an empirical value calculated by back-calculating the canopy closure of high-yield forests in the "Standard Forest Structure Data" of the Camellia oleifera standard production database, ensuring the rationality of the spatial structure.

[0066] After defining the above parameters and constraints, the model is solved and the solution is generated.

[0067] Using the Python programming language, the NSGA-II algorithm from the pymoo library (a multi-objective optimization library) is used to solve the above problem. The algorithm is set with a population size of 100 and a maximum number of generations of evolution of 200. Each iteration of the algorithm generates a large number of candidate solutions, and each solution is rapidly simulated and validated in a twin forest "digital sandbox" using spatial and lighting conditions to evaluate its feasibility.

[0068] After the algorithm runs, it yields a Pareto optimal solution set containing multiple non-dominated solutions (i.e., no objective can be improved without harming another objective), and the output and modification implementation complexity of these non-dominated solutions both meet or exceed the benchmark values ​​of the camellia oil standard production database. For example, solution A has high output but high modification implementation complexity, while solution B has moderate output but low modification implementation complexity.

[0069] The system provides all Pareto solutions for users to choose from. Users can select the most suitable solution based on their objectives and requirements for the rational layout of varieties. In this embodiment, a high-yield solution is adopted, with a yield weight of 0.7 and a modification implementation complexity weight of 0.3. All solutions in the Pareto optimal solution set are weighted and scored, and the solution with the highest comprehensive score is selected as the final production optimization solution. The final production optimization solution will specify the operations to be performed for each numbered plant (e.g., removing plants numbered #012 and #078; grafting replacements for plants numbered #103 and #155, etc.).

[0070] Step S4: Based on the production optimization plan, carry out the transformation construction on the low-efficiency camellia forest;

[0071] Specifically, the production optimization plan is used to generate visual construction drawings or augmented reality (AR) guidance instructions to guide construction personnel to perform specified modification operations on plants with designated numbers.

[0072] In this step, the planting density of the low-efficiency forest is first modified. The planting density is set to a longitudinal spacing of 3 meters and a transverse spacing of 4 meters between each plant. Then, AR guidance is used to optimize the planting varieties.

[0073] After the plant density adjustment is completed, the final production optimization plan is imported into a custom-developed mobile AR application. Construction workers then enter the woodland using handheld devices. The application uses the camera to identify the plant identification tags (or uses GPS positioning overlaid with AR spatial anchors), and virtual operation command icons are displayed on the screen in real time overlaid on the video feed. (For example, a red "×" appears on plants to be removed, and a yellow "scissors" icon appears on plants to be grafted, along with the grafting variety code). Based on this WYSIWYG visual guidance, construction workers complete the work efficiently and accurately, greatly reducing the risk of errors.

[0074] Step S5: After the transformation, the transformation effect of the transformed camellia oleifera forest is verified. The output data of the transformed camellia oleifera forest is compared with the output data of the camellia oleifera forest in the camellia oleifera standard production database. If the output data of the transformed camellia oleifera forest is equal to or better than the output data of the camellia oleifera forest in the camellia oleifera standard production database, then the original inefficient camellia oleifera forest has been successfully transformed.

[0075] In this step, after the transformation is completed, the same UAV aerial survey method is used again in the next production season to scan the transformed camellia oleifera forest stands. Changes in canopy structure parameters (such as leaf area index LAI and canopy opening) before and after the transformation are compared to objectively verify the improvement in light competition. Actual yield is recorded through manual harvesting and weighing, and compared with the average yield of the three years before the transformation to calculate the yield increase of the transformed camellia oleifera forest. Simultaneously, the output data of the transformed camellia oleifera forest is compared with the output data of camellia oleifera forests in the camellia oleifera standard production database. If the output data of the transformed camellia oleifera forest is equal to or better than the output data of camellia oleifera forests in the camellia oleifera standard production database, then the transformation of the previously described low-efficiency camellia oleifera forest is successful. The "input data-operation plan-result data" from this transformation are used as a new data sample and added to the training database of the machine learning model for iterative optimization of the model, making its future predictions and suggestions more accurate.

[0076] The above description is merely a preferred embodiment of the present invention. Through these specific embodiments, a digital, intelligent, and mass-producible method for transforming inefficient camellia oleifera forests is clearly demonstrated. Those skilled in the art, based on the above description, can implement the solution described in this invention without any creative effort and achieve the expected beneficial effects.

[0077] Please see Figure 2 The diagram shows a structural block diagram of a spatially optimized camellia oleifera inefficient forest transformation system according to this application.

[0078] like Figure 2 As shown, the modules are: Camellia oleifera database management module 200, stand and individual tree data acquisition module 201, model building and decision-making module 202, execution guidance module 203, and transformation effect verification module 204.

[0079] Among them, the Camellia oleifera database management module 200 is configured to collect stand layout data and production data of standard Camellia oleifera forests and construct a standard Camellia oleifera production database;

[0080] The stand and individual tree data acquisition module 201 is configured to collect stand layout data and individual tree data of the low-efficiency Camellia oleifera forest to be transformed, and to construct a twin digital forest of the low-efficiency Camellia oleifera forest based on the stand layout data and the individual tree data.

[0081] The model building and decision-making module 202 is configured to build a prediction model for the transformation of inefficient Camellia oleifera forests based on the data in the Camellia oleifera standard production database, and input the data in the twin digital forest into the prediction model for the transformation of inefficient Camellia oleifera forests. Referring to the data in the Camellia oleifera standard production database, the prediction model for the transformation of inefficient Camellia oleifera forests is used to perform optimization calculations and generate a production optimization scheme that includes the best plant layout and single plant transformation suggestions.

[0082] The execution guidance module 203 is configured to generate a visual construction drawing or augmented reality (AR) guidance instruction from the production optimization plan to guide construction personnel to perform specified modification operations on plants with specified numbers.

[0083] The transformation effect verification module 204 is configured to verify the transformation effect of the transformed camellia oleifera forest after transformation. The output data of the transformed camellia oleifera forest is compared with the output data of camellia oleifera forest in the camellia oleifera standard production database. If the output data of the transformed camellia oleifera forest is equal to or better than the output data of camellia oleifera forest in the camellia oleifera standard production database, then the original inefficient camellia oleifera forest has been successfully transformed.

[0084] It should be understood that Figure 2 The modules and references described in the document Figure 1 The steps described in the text correspond to those in the method described above. Therefore, the operations, features, and corresponding technical effects described above also apply to the method described in the text. Figure 2 The various modules in the document will not be described in detail here.

[0085] In other embodiments, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor performs the space-optimized method for transforming inefficient Camellia oleifera forests as described in any of the above method embodiments:

[0086] Collect stand layout and production data of standard Camellia oleifera forests to construct a standard Camellia oleifera production database;

[0087] Collect stand layout data and individual plant data of the low-efficiency Camellia oleifera forest to be transformed, and construct a twin digital forest of the low-efficiency Camellia oleifera forest based on the stand layout data and the individual plant data.

[0088] Based on the data in the Camellia oleifera standard production database, a prediction model for the transformation of inefficient Camellia oleifera forests is constructed. The data in the twin digital forest is input into the prediction model for the transformation of inefficient Camellia oleifera forests. The prediction model for the transformation of inefficient Camellia oleifera forests is used for optimization calculation to generate a production optimization scheme that includes the best plant layout and individual plant transformation suggestions.

[0089] Based on the aforementioned production optimization plan, the low-efficiency camellia oleifera forest will undergo renovation construction.

[0090] After the transformation, the transformation effect of the transformed camellia oleifera forest is verified. The output data of the transformed camellia oleifera forest is compared with the output data of camellia oleifera forest in the camellia oleifera standard production database. If the output data of the transformed camellia oleifera forest is equal to or better than the output data of camellia oleifera forest in the camellia oleifera standard production database, then the original inefficient camellia oleifera forest has been successfully transformed.

[0091] Computer-readable storage media may include a stored program area and a stored data area, wherein the stored program area may store an operating system and an application program required for at least one function; the stored data area may store data created based on the use of the space-optimized camellia oleifera inefficient forest transformation system, etc. Furthermore, the computer-readable storage medium may include high-speed random access memory, and may also include memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer-readable storage medium may optionally include memory remotely configured relative to a processor, which can be connected to the space-optimized camellia oleifera inefficient forest transformation system via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0092] Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiment of the present invention, such as... Figure 3 As shown, the device includes a processor 310 and a memory 320. The electronic device may also include an input device 330 and an output device 340. The processor 310, memory 320, input device 330, and output device 340 can be connected via a bus or other means. Figure 3Taking a bus connection as an example, the memory 320 is the computer-readable storage medium described above. The processor 310 executes various server functions and data processing by running non-volatile software programs, instructions, and modules stored in the memory 320, thereby realizing the space-optimized camellia oleifera inefficient forest transformation method described in the above embodiment. The input device 330 can receive input digital or character information and generate key signal inputs related to user settings and function control of the space-optimized camellia oleifera inefficient forest transformation system. The output device 340 may include a display screen or other display device.

[0093] The aforementioned electronic device can execute the method provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in this embodiment can be found in the method provided in the embodiments of the present invention.

[0094] In one implementation, the above-described electronic device is applied in a space-optimized camellia oleifera low-efficiency forest transformation system, serving as a client, and includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to:

[0095] Collect stand layout and production data of standard Camellia oleifera forests to construct a standard Camellia oleifera production database;

[0096] Collect stand layout data and individual plant data of the low-efficiency Camellia oleifera forest to be transformed, and construct a twin digital forest of the low-efficiency Camellia oleifera forest based on the stand layout data and the individual plant data.

[0097] Based on the data in the Camellia oleifera standard production database, a prediction model for the transformation of inefficient Camellia oleifera forests is constructed. The data in the twin digital forest is input into the prediction model for the transformation of inefficient Camellia oleifera forests. The prediction model for the transformation of inefficient Camellia oleifera forests is used for optimization calculation to generate a production optimization scheme that includes the best plant layout and individual plant transformation suggestions.

[0098] Based on the aforementioned production optimization plan, the low-efficiency camellia oleifera forest will undergo renovation construction.

[0099] After the transformation, the transformation effect of the transformed camellia oleifera forest is verified. The output data of the transformed camellia oleifera forest is compared with the output data of camellia oleifera forest in the camellia oleifera standard production database. If the output data of the transformed camellia oleifera forest is equal to or better than the output data of camellia oleifera forest in the camellia oleifera standard production database, then the original inefficient camellia oleifera forest has been successfully transformed.

[0100] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.

[0101] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for transforming inefficient Camellia oleifera forests based on spatial optimization, characterized in that, include: Collect stand layout data and production data of standard Camellia oleifera forests, and construct a standard Camellia oleifera production database. The standard Camellia oleifera production database includes standard stand structure data, yield efficiency benchmark data, and transformation implementation complexity data. Collect stand layout data and individual plant data of the low-efficiency Camellia oleifera forest to be transformed, and construct a twin digital forest of the low-efficiency Camellia oleifera forest based on the stand layout data and the individual plant data; the stand layout data is obtained by collecting high-resolution multispectral images and laser point cloud data and processing them, and the stand layout data includes at least plant distribution point data, canopy height model data, and digital elevation model data; Based on the data in the Camellia oleifera standard production database, a prediction model for the transformation of inefficient Camellia oleifera forests is constructed with the objectives of maximizing the expected total yield of the stand and minimizing the complexity of the transformation implementation. This model is constrained by the total plant density of the stand, the complexity of different transformation methods, the plant variety matching, and the light competition among plants based on the twin digital forest. The data from the twin digital forest is input into the prediction model for the transformation of inefficient Camellia oleifera forests. The model is then used for optimization calculations to generate a production optimization scheme that includes the optimal plant layout and individual plant transformation suggestions. Based on the production optimization plan, a visual construction drawing or augmented reality (AR) guidance instruction is generated to guide construction personnel in carrying out the transformation construction of the low-efficiency camellia oleifera forest. After the transformation, the transformation effect of the transformed camellia oleifera forest is verified. The output data of the transformed camellia oleifera forest is compared with the output data of camellia oleifera forest in the camellia oleifera standard production database. If the output data of the transformed camellia oleifera forest is equal to or better than the output data of camellia oleifera forest in the camellia oleifera standard production database, then the original inefficient camellia oleifera forest has been successfully transformed.

2. The method for transforming inefficient Camellia oleifera forests based on spatial optimization according to claim 1, characterized in that, Constructing the digital twin forest of the aforementioned low-efficiency camellia oleifera forest also includes: Data on individual plants in the low-efficiency camellia forest were collected through manual field measurements. The data on individual plants included at least the geographical information of the planting site, the variety information of the individual plant, the diameter at root and growth status. By associating spatial locations, the data of plant distribution points are coupled with the corresponding data of individual plants, and combined with the canopy height model data and digital elevation model data, a twin digital forest containing stand spatial structure and individual plant attribute information is constructed.

3. The method for transforming inefficient Camellia oleifera forests based on spatial optimization according to claim 1, characterized in that, The construction of a predictive model for the transformation of inefficient Camellia oleifera forests also includes: Define decision variables, which are the modification operations performed on each plant; A multi-objective optimization algorithm is used to solve the multi-objective optimization function to obtain the Pareto optimal solution set, and the final production optimization scheme is selected from the solution set.

4. The method for transforming inefficient Camellia oleifera forests based on spatial optimization according to claim 3, characterized in that, The plant variety pairing constraints are used to ensure that among the optimized and retained Camellia oleifera plants, the proportion of variety combinations with overlapping flowering periods and high pollination compatibility is not less than the preset variety compatibility threshold. The light competition constraint between plants is achieved by analyzing the canopy light distribution in the twin digital forest to ensure that, in the optimized plant layout, the canopies of any two adjacent plants do not overlap on the projection plane, or the overlapping area is less than a set canopy overlap threshold.

5. A method for transforming inefficient Camellia oleifera forests based on spatial optimization according to claim 3, characterized in that, Selecting the final optimized solution from the solution set includes: Based on preset output weights and complexity weights, the Pareto optimal solution set is weighted and scored, and the solution with the highest comprehensive score is selected as the final solution.

6. A spatially optimized system for transforming inefficient Camellia oleifera forests, characterized in that, include: The Camellia oleifera database management module is configured to collect stand layout data and production data of standard Camellia oleifera forests and construct a standard Camellia oleifera production database. The standard Camellia oleifera production database includes standard stand structure data, yield efficiency benchmark data, and transformation implementation complexity data. The stand and individual tree data acquisition module is configured to collect stand layout data and individual tree data of the low-efficiency Camellia oleifera forest to be transformed, and to construct a twin digital forest of the low-efficiency Camellia oleifera forest based on the stand layout data and the individual tree data; the stand layout data is obtained by acquiring high-resolution multispectral images and laser point cloud data and processing them, and the stand layout data includes at least plant distribution point data, canopy height model data, and digital elevation model data; The model construction and decision-making module is configured to construct a prediction model for the transformation of inefficient Camellia oleifera forests based on data from the standard production database of Camellia oleifera. This model aims to maximize the expected total yield of the forest stand and minimize the complexity of the transformation implementation, and is constrained by the total plant density of the stand, the complexity of different transformation methods, plant variety matching constraints, and light competition constraints among plants based on the twin digital forest. Data from the twin digital forest is input into the prediction model for the transformation of inefficient Camellia oleifera forests. The model is then used for optimization calculations to generate a production optimization scheme that includes the optimal plant layout and individual plant transformation suggestions. The execution guidance module is configured to generate visual construction drawings or augmented reality (AR) guidance instructions based on the production optimization scheme to guide construction personnel in carrying out the transformation construction of the low-efficiency camellia oleifera forest. The transformation effect verification module is configured to verify the transformation effect of the transformed camellia oleifera forest after transformation. The output data of the transformed camellia oleifera forest is compared with the output data of camellia oleifera forest in the camellia oleifera standard production database. If the output data of the transformed camellia oleifera forest is equal to or better than the output data of camellia oleifera forest in the camellia oleifera standard production database, then the original inefficient camellia oleifera forest has been successfully transformed.

7. An electronic device, characterized in that, include: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method described in any one of claims 1 to 5.

Images