Forestry plant regeneration cultivation intelligent analysis method and system

Abstract

The invention relates to the technical field of forestry intelligent management, in particular to a forestry plant regeneration cultivation intelligent analysis method and system. The method comprises the following steps: constructing a forestry digital twinborn model; according to the forestry digital twinborn model, carrying out plant individual matrix cultivation time sequence state analysis, and generating plant individual matrix cultivation time sequence state data; performing plant cultivation state comprehensive evaluation processing on the plant cultivation time sequence state characteristic data to generate plant cultivation state evaluation data; performing plant cultivation influence factor analysis based on the plant cultivation time sequence state characteristic data to generate plant cultivation influence factor data; performing plant cultivation state influence factor gain analysis on the plant cultivation state evaluation data and the plant cultivation influence factor data to generate plant cultivation state influence factor gain data; and designing a plant regeneration cultivation intelligent decision based on the plant cultivation state influence factor gain data. According to the invention, more intelligent and efficient forestry plant regeneration cultivation intelligent management is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of forestry intelligent management, and in particular to an intelligent analysis method and system for plant regeneration and cultivation in forestry. Background Art

[0002] As one of the most important ecosystems on Earth, forests not only provide rich biological resources and important ecological service functions, but also play a key role in global climate regulation, water resource circulation, soil conservation, etc. Forestry plant regeneration and cultivation has become one of the important means to restore forest resources and maintain ecological balance. Plant regeneration and cultivation rely on artificial sowing, afforestation and natural recovery, which are usually affected by the uncertainty of environmental factors, the limitation of climatic conditions and the lack of human management, resulting in a low success rate of plant regeneration, a long growth cycle, and the recovery effect is difficult to meet the needs of ecological restoration. The introduction of intelligent technology, such as the Internet of Things (IoT), remote sensing technology, artificial intelligence (AI) and big data analysis, provides intelligent technical means for forestry plant regeneration and cultivation, so that plant regeneration and cultivation can be managed more conveniently and efficiently. However, traditional forestry plant regeneration and cultivation analysis methods usually rely on plant cultivation experience and limited on-site monitoring data, which makes it difficult to achieve comprehensive control and refined management of complex and changeable ecological environments, resulting in low success rate of plant regeneration, long recovery cycle and low resource utilization efficiency, and unable to achieve efficient plant regeneration and cultivation management. Summary of the invention

[0003] Based on this, the present invention provides an intelligent analysis method and system for plant regeneration and cultivation in forestry to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a forestry plant regeneration cultivation intelligent analysis method comprises the following steps: Step S1: obtaining a forestry plant analysis area; performing forestry digital twin feature information analysis based on the forestry plant analysis area to construct a forestry digital twin model; Step S2: performing plant individual-based cultivation time series state analysis based on the forestry digital twin model to generate plant individual-based cultivation time series state data; performing local plant individual-based cultivation time series change analysis on the plant individual-based cultivation time series state data to generate local plant individual-based cultivation time series evolution data; performing plant cultivation time series evolution spatial heterogeneity feature analysis based on the local plant individual-based cultivation time series evolution data to generate plant cultivation time series evolution spatial heterogeneity feature data; Step S3: Based on the spatial heterogeneity characteristic data of plant cultivation temporal evolution, the plant cultivation temporal state characteristic data is subjected to a comprehensive analysis of the plant cultivation temporal state at different temporal scales to generate plant cultivation temporal comprehensive state data; the plant cultivation temporal comprehensive state data is subjected to a plant cultivation state evaluation process to generate plant cultivation state evaluation data; Step S4: performing a composite influencing factor analysis of plant cultivation based on the plant cultivation time series state characteristic data to generate plant cultivation influencing factor data; performing plant cultivation state evaluation and influencing factor association processing on the plant cultivation state evaluation data and the plant cultivation influencing factor data to generate plant cultivation state evaluation-influencing factor association data; performing plant cultivation state influencing factor gain analysis on the plant cultivation state evaluation-influencing factor association data to generate plant cultivation state influencing factor gain data; Step S5: Acquire forestry plant regeneration demand data; perform plant regeneration and cultivation digital decision analysis based on the forestry plant regeneration demand data and the forestry digital twin model to generate plant regeneration and cultivation digital decisions; optimize the plant regeneration and cultivation digital decisions according to the gain data of plant cultivation status influencing factors and the plant regeneration and cultivation digital decisions to generate optimized plant regeneration and cultivation digital decisions; perform intelligent adjustments on the plant regeneration and cultivation digital decisions with changes in influencing factors on the optimized plant regeneration and cultivation digital decisions to obtain plant regeneration and cultivation intelligent decisions; feed back the plant regeneration and cultivation intelligent decisions to the terminal to execute the forestry plant regeneration and cultivation intelligent cultivation operations.

[0005] The present invention obtains a specific forestry plant analysis area, clarifies the spatial scope of research and management, and ensures the pertinence and comprehensiveness of data collection. Based on the acquired area, the forestry digital twin feature information analysis can comprehensively integrate various types of data in the forestry ecosystem (such as meteorology, soil, vegetation status, terrain, etc.), and perform high-precision modeling, so that the digital twin model has a high degree of authenticity and dynamic reflection ability, so that the entire forestry ecosystem can be accurately reproduced in a virtual environment. Through the time series state analysis based on the digital twin model, the growth status of individual plants at different time series is accurately tracked and recorded, which helps to grasp the growth law of each individual plant and identify the key stages in the growth process. The local change analysis of the plant individual base cultivation time series state data is carried out to timely discover the abnormal movement of the plant during the growth process, such as the slowdown of growth rate or abnormal environmental response at a certain stage, to prevent the expansion of potential problems and ensure the smooth progress of the overall cultivation plan. By analyzing the spatial heterogeneity characteristics of plant individual cultivation time series evolution data, it is possible to reveal the growth differences of plants in different spatial locations and identify the spatial factors that affect plant growth, such as soil nutrient distribution and microclimate conditions, so as to guide the adoption of differentiated cultivation strategies in different regions. By comprehensively analyzing the plant cultivation time series state characteristic data at different time series scales, the full cycle state of plant growth is fully captured to ensure that all information from short-term fluctuations to long-term trends is effectively considered, accurately reflecting the performance of each stage in the plant growth process, and the generated plant cultivation time series comprehensive state data reflects the comprehensive characteristics of information at multiple time series scales, thereby reducing the amount of data and improving data processing efficiency. Plant cultivation state assessment data provides quantitative assessment results through the analysis and processing of comprehensive state data, identifying the overall health status and potential problems of current plant growth. The state assessment data promptly discovers abnormal conditions or potential risks in the growth process, thereby effectively avoiding cultivation failures or ecosystem imbalances and ensuring the healthy growth and regeneration efficiency of forestry plants. The composite influencing factor analysis of plant cultivation time series status characteristic data can identify various key factors affecting plant growth, including environmental conditions, soil characteristics, climate change, etc., and comprehensively consider the complex interactive relationship between different factors. The plant cultivation status assessment data and the plant cultivation influencing factor data are correlated to reveal the direct or indirect impact of each influencing factor on the plant growth status and understand the interaction between different factors. By performing gain analysis on the status assessment-influencing factor correlation data, the degree of influence of each factor on the plant growth status is quantified, the most influential factors are identified, key issues are prioritized, and the cultivation effect is maximized.By acquiring and analyzing the demand data of forestry plant regeneration, the goals and requirements of plant regeneration can be clarified. The digital decision analysis based on the demand can provide a targeted and effective cultivation plan to ensure that the regeneration cultivation work is more efficient and in line with the expected goals. The generated digital decision for plant regeneration cultivation can be combined with the precise simulation of the digital twin model to ensure the scientificity and effectiveness of the decision. Optimizing the digital decision according to the gain data of the influencing factors can ensure that the positive role of various influencing factors is maximized under the condition of limited resources. The optimized decision plan not only improves the efficiency of resource utilization, but also significantly improves the cultivation effect, ensuring that the plant regeneration process is smoother and more efficient. Intelligent adjustment of the optimized decision plan can respond to environmental changes, resource adjustments and other situations in real time, ensuring that the decision is always in the best state during the execution process, and reducing the cultivation failure caused by environmental mutations or other uncertain factors. Feeding back the final generated intelligent decision for plant regeneration cultivation to the terminal execution device realizes closed-loop management, and the whole process automation and intelligent management from data collection, analysis, decision-making to execution is realized.

[0006] The present specification provides a forestry plant regeneration cultivation intelligent analysis system for executing the forestry plant regeneration cultivation intelligent analysis method as described above. The forestry plant regeneration cultivation intelligent analysis system includes: A forestry digital twin model construction module is used to obtain forestry plant analysis areas; based on the forestry plant analysis areas, forestry digital twin feature information analysis is performed to construct a forestry digital twin model; The plant individual-based spatiotemporal feature analysis module is used to analyze the plant individual-based cultivation time series state according to the forestry digital twin model, and generate plant individual-based cultivation time series state data; perform local plant individual-based cultivation time series change analysis on the plant individual-based cultivation time series state data, and generate local plant individual-based cultivation time series evolution data; perform plant cultivation time series evolution spatial heterogeneity feature analysis based on local plant individual-based cultivation time series evolution data, and generate plant cultivation time series evolution spatial heterogeneity feature data; The plant cultivation state evaluation module is used to perform a comprehensive analysis of the plant cultivation time series state at different time series scales on the plant cultivation time series state characteristic data based on the spatial heterogeneity characteristic data of the plant cultivation time series evolution, and generate plant cultivation time series comprehensive state data; perform plant cultivation state evaluation processing on the plant cultivation time series comprehensive state data, and generate plant cultivation state evaluation data; The plant cultivation state influencing factor gain analysis module is used to analyze the composite influencing factors of plant cultivation based on the plant cultivation time series state characteristic data to generate plant cultivation influencing factor data; perform plant cultivation state evaluation and influencing factor association processing on the plant cultivation state evaluation data and the plant cultivation influencing factor data to generate plant cultivation state evaluation-influencing factor association data; perform plant cultivation state influencing factor gain analysis on the plant cultivation state evaluation-influencing factor association data to generate plant cultivation state influencing factor gain data; The plant regeneration and cultivation intelligent decision analysis module is used to obtain forestry plant regeneration demand data; perform plant regeneration and cultivation digital decision analysis based on forestry plant regeneration demand data and the forestry digital twin model to generate plant regeneration and cultivation digital decisions; optimize the plant regeneration and cultivation digital decisions according to the gain data of plant cultivation status influencing factors and the plant regeneration and cultivation digital decisions to generate optimized plant regeneration and cultivation digital decisions; intelligently adjust the plant regeneration and cultivation digital decisions with changes in influencing factors of the optimized plant regeneration and cultivation digital decisions to obtain plant regeneration and cultivation intelligent decisions; and feed back the plant regeneration and cultivation intelligent decisions to the terminal to execute the forestry plant regeneration and cultivation intelligent cultivation operations.

[0007] The beneficial effect of the present application lies in that the intelligent analysis method for plant regeneration and cultivation in forestry of the present invention introduces digital twin technology to comprehensively analyze the growth conditions of forestry plant regeneration and cultivation, overcomes the data analysis limitations of forestry plant regeneration and cultivation, analyzes the key influencing characteristics of complex and changeable ecological environment on plant regeneration and cultivation, reduces data latitude and ensures the amount of redundant data in plant regeneration and cultivation analysis, designs corresponding decisions on plant regeneration and cultivation more accurately and comprehensively, and considers the dynamic change characteristics of external factors in the process of plant regeneration and cultivation in plant regeneration and cultivation decisions, so as to intelligently adjust and change the decisions on plant regeneration and cultivation, ensure high plant regeneration success rate, short recovery cycle and high resource utilization efficiency in the process of plant regeneration and cultivation, and realize efficient intelligent management of plant regeneration and cultivation. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 A schematic diagram of the steps of an intelligent analysis method for plant regeneration and cultivation in forestry according to the present invention; Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart; Figure 3 for Figure 1 Detailed implementation steps of step S4 in FIG. Figure 4 for Figure 1 Detailed implementation steps of step S5; The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0009] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0010] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0011] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0012] To achieve this, please refer to Figures 1 to 4 The present invention provides a forestry plant regeneration cultivation intelligent analysis method, comprising the following steps: Step S1: obtaining a forestry plant analysis area; performing forestry digital twin feature information analysis based on the forestry plant analysis area to construct a forestry digital twin model; Step S2: performing plant individual-based cultivation time series state analysis based on the forestry digital twin model to generate plant individual-based cultivation time series state data; performing local plant individual-based cultivation time series change analysis on the plant individual-based cultivation time series state data to generate local plant individual-based cultivation time series evolution data; performing plant cultivation time series evolution spatial heterogeneity feature analysis based on the local plant individual-based cultivation time series evolution data to generate plant cultivation time series evolution spatial heterogeneity feature data; Step S3: Based on the spatial heterogeneity characteristic data of plant cultivation temporal evolution, the plant cultivation temporal state characteristic data is subjected to a comprehensive analysis of the plant cultivation temporal state at different temporal scales to generate plant cultivation temporal comprehensive state data; the plant cultivation temporal comprehensive state data is subjected to a plant cultivation state evaluation process to generate plant cultivation state evaluation data; Step S4: performing a composite influencing factor analysis of plant cultivation based on the plant cultivation time series state characteristic data to generate plant cultivation influencing factor data; performing plant cultivation state evaluation and influencing factor association processing on the plant cultivation state evaluation data and the plant cultivation influencing factor data to generate plant cultivation state evaluation-influencing factor association data; performing plant cultivation state influencing factor gain analysis on the plant cultivation state evaluation-influencing factor association data to generate plant cultivation state influencing factor gain data; Step S5: Acquire forestry plant regeneration demand data; perform plant regeneration and cultivation digital decision analysis based on the forestry plant regeneration demand data and the forestry digital twin model to generate plant regeneration and cultivation digital decisions; optimize the plant regeneration and cultivation digital decisions according to the gain data of plant cultivation status influencing factors and the plant regeneration and cultivation digital decisions to generate optimized plant regeneration and cultivation digital decisions; perform intelligent adjustments on the plant regeneration and cultivation digital decisions with changes in influencing factors on the optimized plant regeneration and cultivation digital decisions to obtain plant regeneration and cultivation intelligent decisions; feed back the plant regeneration and cultivation intelligent decisions to the terminal to execute the forestry plant regeneration and cultivation intelligent cultivation operations.

[0013] As an embodiment of the present invention, refer to Figure 1 The above is a schematic diagram of the steps of a forestry plant regeneration cultivation intelligent analysis method of the present invention. In this embodiment, the forestry plant regeneration cultivation intelligent analysis method includes the following steps: Step S1: obtaining a forestry plant analysis area; performing forestry digital twin feature information analysis based on the forestry plant analysis area to construct a forestry digital twin model; In an embodiment of the present invention, the geographical scope and ecological characteristics of the target forestry area are determined. Satellite remote sensing technology and drone aerial photography are used to collect high-resolution terrain and vegetation coverage images of the target area, which provide basic information such as the terrain, vegetation type, and soil conditions of the area. In the determined forestry analysis area, an Internet of Things sensor network is installed and deployed to monitor the environmental parameters in the area in real time, including temperature, humidity, light intensity, soil moisture, air quality, etc., and a detailed three-dimensional scan of the terrain and vegetation is performed using lidar technology to obtain accurate terrain and vegetation structure data. A forestry digital twin model is constructed using the collected environmental data, terrain data, and vegetation data, and these data are integrated and analyzed using big data analysis and machine learning algorithms to extract key ecological characteristics in the area, such as vegetation health, soil fertility distribution, microclimate conditions, etc. These characteristic information will be used as the basic data of the digital twin model to simulate and predict the growth of plants in the area. A forestry digital twin model is established based on the above-mentioned characteristic information. The model can reflect the ecological status in the target area in real time, and can perform growth simulation and prediction based on different input conditions (such as climate change and human intervention). It adopts high-performance computing technology to ensure that it can process large-scale, multi-dimensional data, and can be dynamically updated and optimized.

[0014] Step S2: performing plant individual-based cultivation time series state analysis based on the forestry digital twin model to generate plant individual-based cultivation time series state data; performing local plant individual-based cultivation time series change analysis on the plant individual-based cultivation time series state data to generate local plant individual-based cultivation time series evolution data; performing plant cultivation time series evolution spatial heterogeneity feature analysis based on the local plant individual-based cultivation time series evolution data to generate plant cultivation time series evolution spatial heterogeneity feature data; In the embodiment of the present invention, the constructed forestry digital twin model is used to analyze the cultivation time series state of individual plants in a specific area. By inputting real-time environmental data (such as light, temperature, humidity, etc.) and plant growth data, the growth state of individual plants in different growth periods is simulated. Based on these simulation results, plant individual-based cultivation time series state data is generated, and the growth of individual plants at various time points is described in detail. The generated plant individual-based cultivation time series state data is further analyzed, focusing on the changing trend of plant growth in a specific time period, and these data are mathematically modeled using ordinary differential equations to identify the dynamic characteristics of plant growth rate changes and health status fluctuations in different time periods, and generate local plant individual-based cultivation time series evolution data. Based on the time series evolution data of local plant individuals, the performance differences of these changes under different spatial conditions are further analyzed, and the plant growth data at different spatial locations are processed using a partial differential equation model to identify the specific impact of spatial heterogeneity on plant growth. The generated plant cultivation time series evolution spatial heterogeneity feature data will provide an important reference for subsequent cultivation management.

[0015] Step S3: Based on the spatial heterogeneity characteristic data of plant cultivation temporal evolution, the plant cultivation temporal state characteristic data is subjected to a comprehensive analysis of the plant cultivation temporal state at different temporal scales to generate plant cultivation temporal comprehensive state data; the plant cultivation temporal comprehensive state data is subjected to a plant cultivation state evaluation process to generate plant cultivation state evaluation data; In an embodiment of the present invention, the spatial heterogeneity characteristic data of plant cultivation temporal evolution is used to analyze the plant growth process at multiple time scales. Multi-scale analysis is performed based on short-term, medium-term and long-term growth data to identify the growth status of plants at different time stages and generate multi-scale plant cultivation status data. The plant cultivation status data of different time scales are comprehensively analyzed to form a unified plant cultivation temporal comprehensive status data, which integrates the growth information of each time period, provides a comprehensive description of the growth status, and provides data support for further status evaluation and management optimization. According to the preset plant cultivation status evaluation decision criteria, the plant cultivation temporal comprehensive status data is evaluated and processed, and the evaluation and processing includes quantitative evaluation of the growth status, risk identification, disease warning, etc., to generate plant cultivation status evaluation data and provide important information about the overall growth status of the plant.

[0016] Step S4: performing a composite influencing factor analysis of plant cultivation based on the plant cultivation time series state characteristic data to generate plant cultivation influencing factor data; performing plant cultivation state evaluation and influencing factor association processing on the plant cultivation state evaluation data and the plant cultivation influencing factor data to generate plant cultivation state evaluation-influencing factor association data; performing plant cultivation state influencing factor gain analysis on the plant cultivation state evaluation-influencing factor association data to generate plant cultivation state influencing factor gain data; In the embodiment of the present invention, the plant cultivation time series state characteristic data obtained in the early stage is used to comprehensively analyze the influence of different environmental and terrain factors on plant growth. Through the correlation analysis of multiple variables such as temperature, humidity, light, soil type, slope, etc., the influence degree of these factors on plant growth in different growth periods is identified, and a multivariate regression model or a machine learning algorithm is used for calculation to generate plant cultivation influencing factor data, and the influence of each factor on plant growth is described in detail. Combined with the plant cultivation state evaluation data and the plant cultivation influencing factor data, a detailed state evaluation and influencing factor correlation analysis are performed, and the factors that have a key influence on plant growth under different states are determined through correlation analysis, and these influencing factors are associated with specific plant growth performances. The generated plant cultivation state evaluation-influencing factor correlation data provides a basis for further management and decision-making. Using the plant cultivation state evaluation-influencing factor correlation data, the influencing factors are analyzed for gain through the gradient boosting tree algorithm, the factors that have the greatest influence on the plant growth state are identified, and the contribution of these factors is quantified. The generated plant cultivation state influencing factor gain data will provide an important basis for optimizing the plant growth management strategy.

[0017] Step S5: Acquire forestry plant regeneration demand data; perform plant regeneration and cultivation digital decision analysis based on the forestry plant regeneration demand data and the forestry digital twin model to generate plant regeneration and cultivation digital decisions; optimize the plant regeneration and cultivation digital decisions according to the gain data of plant cultivation status influencing factors and the plant regeneration and cultivation digital decisions to generate optimized plant regeneration and cultivation digital decisions; perform intelligent adjustments on the plant regeneration and cultivation digital decisions with changes in influencing factors on the optimized plant regeneration and cultivation digital decisions to obtain plant regeneration and cultivation intelligent decisions; feed back the plant regeneration and cultivation intelligent decisions to the terminal to execute the forestry plant regeneration and cultivation intelligent cultivation operations.

[0018] In the embodiment of the present invention, plant regeneration demand data provided by forestry managers and ecological restoration experts are collected and analyzed, including ecological restoration goals, target vegetation types, growth cycle requirements, and resource allocation, etc., to meet the expected ecological and economic benefit goals. Based on the obtained forestry plant regeneration demand data, combined with the forestry digital twin model that has been constructed, a detailed regeneration and cultivation digital decision analysis is performed, the effects of different cultivation schemes are simulated in the digital twin model, and the most demand-compliant and effective regeneration scheme is selected through data analysis. The generated plant regeneration and cultivation digital decision includes detailed operation steps, resource allocation suggestions, and time arrangements. Combined with the gain data of factors affecting plant cultivation status, the preliminary plant regeneration and cultivation digital decision is optimized, focusing on optimizing the key factors that have the greatest impact on plant growth. The generated optimized plant regeneration and cultivation digital decision provides a more complete implementation plan for the next step of operation. According to the optimized digital decision, further simulation analysis is performed in the digital twin model, and the performance of plant growth under different environmental conditions is predicted by simulating the regeneration and cultivation process, and plant regeneration and cultivation simulation data is generated. The simulation data will help further improve the decision and ensure that the best effect can be achieved during actual execution. Based on the plant regeneration and cultivation simulation data, the temporal growth trend of the plant regeneration process is analyzed. By analyzing the growth performance of each growth period, the growth trend of the plant in each future stage is predicted, and the temporal growth trend data of plant regeneration and cultivation is generated. These trend data will provide managers with predictions of future growth dynamics. Combined with the temporal growth trend data, the key influencing factors that need to be adjusted at different growth stages and the impact of the growth trend on the surrounding environment are identified. The optimized decision is intelligently adjusted to ensure that the regeneration and cultivation plan can flexibly respond to environmental changes and resource constraints, and the plant regeneration and cultivation influencing factor change data and the final intelligent decision are generated. The plant regeneration and cultivation intelligent decision is transmitted to the terminal device through the wireless network to guide the actual regeneration and cultivation operation. The intelligent decision ensures that all links of the cultivation operation can be executed according to the optimal plan to improve the cultivation efficiency and regeneration effect.

[0019] Preferably, step S1 comprises the following steps: Step S11: Acquire forestry plant analysis area; Step S12: using laser radar monitoring equipment to perform forestry area monitoring processing on the forestry analysis area to generate forestry area monitoring data; Step S13: collecting environmental distribution data of the forestry analysis area according to the IoT sensor to generate environmental distribution data; Step S14: Analyze forestry environment terrain characteristics of forestry monitoring area data using GIS technology to generate forestry environment terrain characteristic data; Step S15: performing forestry plant growth status monitoring processing on the forestry area monitoring data to generate forestry plant growth status monitoring data; Step S16: Establish a forestry digital twin model terrain framework based on the forestry environment terrain feature data, and map the forestry digital twin feature information by transmitting the forestry plant growth status monitoring data and environmental distribution data to the forestry digital twin model terrain framework to construct a forestry digital twin model.

[0020] By acquiring a specific forestry plant analysis area, the present invention can clarify the geographical scope and ecological goals of forestry management and plant regeneration cultivation, and provide clear spatial and ecological boundaries for subsequent data collection, analysis and model construction. Lidar technology can scan and monitor the forestry analysis area with high precision, accurately capture key information such as terrain, vegetation structure and vegetation height, and realize rapid monitoring and data collection of a large area, especially under complex terrain conditions, real-time monitoring and analysis of environmental changes in the area, such as dynamic changes in vegetation coverage, to help forestry managers discover abnormalities or potential risks in a timely manner, respond quickly, and ensure the stability of the regional ecological environment. By deploying IoT sensors in the forestry analysis area, real-time collection of environmental data including temperature, humidity, light, soil moisture, air quality, etc., provides comprehensive support for understanding the ecological conditions in the area, helps to build subsequent digital twin models, and ensures that the model can truly reflect the environmental characteristics in reality. GIS technology is used to conduct in-depth analysis of the data collected by Lidar and IoT sensors to generate terrain feature data in the area, including terrain undulations, slopes, orientations, watershed divisions, etc., which can provide accurate terrain background information for forestry management and plant regeneration. Analyze the monitoring data of forestry areas and track the growth status of plants in the area in real time, including growth rate, vegetation coverage, health status, etc. The plant growth status monitoring data provides accurate and timely decision-making basis for the management of plant regeneration. Through this data-driven management method, the scientificity and efficiency of the plant growth process are ensured, and the success rate of plant regeneration is maximized. By combining the terrain feature data of the forestry environment, the plant growth status monitoring data and the environmental distribution data, the forestry digital twin model can be accurately constructed, which can not only truly reflect the terrain characteristics in the area, but also dynamically simulate the whole process of plant growth, providing a scientific basis for regeneration cultivation. The construction of the digital twin model provides a high-precision data foundation for simulation, prediction and analysis in the virtual environment, tests and optimizes various cultivation strategies in the virtual environment, and maps various data (such as terrain, environment, plant status) to the digital twin model to generate a comprehensive and multi-dimensional virtual forestry environment, reflecting the complex dynamic process of the forestry ecosystem.

[0021] In an embodiment of the present invention, the geographical scope of the target forestry plant analysis area is determined, and satellite remote sensing technology and unmanned aerial photography systems are used to obtain high-resolution regional images. These image data include basic geographical information such as terrain undulations, vegetation coverage, soil type, rivers and roads. During the unmanned aerial photography process, multispectral cameras and high-precision positioning systems are used to ensure the accuracy and richness of image data. In the forestry analysis area, a laser radar (LiDAR) monitoring device is installed for comprehensive three-dimensional scanning. The LiDAR device emits laser pulses and receives reflected signals to generate high-precision three-dimensional point cloud data. These point cloud data can be used to finely describe the terrain, vegetation structure and forest canopy height of the forestry area, and generate forestry area monitoring data. The monitoring data can be updated in real time to provide continuous terrain and vegetation change information. An Internet of Things (IoT) sensor network is deployed in the forestry analysis area. These sensors include temperature sensors, humidity sensors, soil moisture sensors, light sensors, and air quality sensors. The sensors monitor and collect environmental data in the area in real time, such as temperature, humidity, precipitation, soil moisture, etc. Through wireless communication technology, these data are transmitted to the central data processing system to generate environmental distribution data for further analysis and model building, reflecting the environmental conditions of the forestry area in real time. The three-dimensional point cloud data and environmental distribution data generated by the lidar are processed and analyzed using geographic information system (GIS) technology. The terrain features are extracted through GIS software to generate a detailed terrain model, including the calculation and distribution analysis of terrain parameters such as slope, altitude, height difference, and orientation. Combined with the spatial analysis function of GIS, areas prone to soil erosion, sparse vegetation, or fragile environment are further identified to generate forestry environmental terrain feature data. By processing the monitoring data collected by the lidar and IoT sensors, the growth status of plants in the forestry area is monitored. The three-dimensional point cloud data generated by the lidar is analyzed using computer vision and machine learning algorithms to identify the growth height, canopy density, and health status of different plant species. At the same time, through the time series analysis of environmental distribution data, the impact of environmental factors on plant growth is evaluated, and forestry plant growth status monitoring data is generated. These monitoring data are used to track plant growth in real time and detect abnormal growth or disease threats. The basic terrain architecture of the digital twin model is constructed based on the terrain feature data of the forestry environment, and the GIS platform is used to combine three-dimensional terrain data and plant growth monitoring data to create a virtual digital twin model.The model can dynamically simulate the actual terrain features of the forestry area, provide a virtual environment to reflect the terrain changes in the area in real time, import forestry plant growth status monitoring data and environmental distribution data into the digital twin model to map the characteristic information, and construct a digital twin model that can reflect the ecological status of the forestry area in real time by combining the actual environmental data with the virtual terrain architecture. The model integrates all key data points and performs dynamic simulation and predictive analysis by inputting different environmental change conditions (such as climate change and human intervention measures).

[0022] Preferably, step S2 comprises the following steps: Step S21: performing plant individual-based cultivation time series state analysis according to the forestry digital twin model to generate plant individual-based cultivation time series state data; Step S22: performing local plant individual-based cultivation time series change analysis on the plant individual-based cultivation time series state data by using a preset ordinary differential equation algorithm to generate local plant individual-based cultivation time series evolution data; Step S23: performing individual-based temporal evolution spatial feature identification processing on the local plant individual-based cultivation temporal evolution data to generate spatially identified local plant individual-based cultivation temporal evolution data; Step S24: performing a spatial heterogeneity characteristic analysis of plant cultivation temporal evolution on the spatially identified local plant individual-based cultivation temporal evolution data through a preset partial differential equation to generate spatial heterogeneity characteristic data of plant cultivation temporal evolution.

[0023] The present invention uses the forestry digital twin model to analyze the time series state of individual plants, and tracks the state changes of each individual plant in different growth periods in real time. It can not only provide individualized growth curves, but also identify the health status and growth rate of each individual at a specific time point, provide basic data support for individualized management, and provide high-quality data sources for further time series analysis, change monitoring and growth trend prediction, ensuring that the dynamic tracking of individuals in the process of plant regeneration and cultivation is more accurate and comprehensive. The ordinary differential equation algorithm can perform refined mathematical modeling and analysis on the time series data of individual plants, so as to accurately capture the changing trend in the process of plant growth, and the generated local plant individual base cultivation time series evolution data reflects the growth changes of individual plants in a short time, which provides a specific time series basis for further optimizing the cultivation strategy. Through the digital twin model, the spatial feature analysis is carried out, and the growth environment of individual plants is analyzed in multiple dimensions, such as the spatial feature conditions such as the microclimate, soil characteristics, and light conditions of the individual, revealing the influence of the external environment of plant growth on its growth state, which helps to optimize the planting position and management strategy to support the formulation of individualized cultivation plans, thereby improving the success rate and growth quality of plant regeneration. Combining the temporal evolution data with spatial characteristics, a comprehensive data set containing temporal and spatial dimensions is generated for each plant individual, revealing the growth characteristics of plant individuals in different periods and different spatial environments, providing a more comprehensive description of the growth state, and the generated spatial identification data reflects the growth law of plant individuals in complex ecosystems. Spatial identification processing helps to identify and quantify the specific impact of different spatial regions on the growth of plant individuals, such as the reasons why plant individuals in a certain area grow faster or slower at a certain stage. By combining temporal and spatial information, we can better understand the comprehensive impact of different environmental conditions on plant growth. Partial differential equations can accurately describe and simulate the temporal evolution process of plant individual growth in complex spatial environments. Revealing the growth differences of plant individuals in different spatial environments and analyzing the impact of various types of plants on the spatial environment, identifying which areas have a positive or negative impact on plant growth, spatial heterogeneity feature analysis can enable managers to perform differentiated management in areas with obvious heterogeneity, thereby improving resource utilization efficiency and reducing unnecessary resource waste.

[0024] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed implementation step flow diagram of step S2 in the embodiment, step S2 in this embodiment includes: Step S21: performing plant individual-based cultivation time series state analysis according to the forestry digital twin model to generate plant individual-based cultivation time series state data; In the embodiment of the present invention, in the constructed forestry digital twin model, specific plant individuals are selected for detailed time series state analysis. The forestry digital twin model simulates the growth of plant individuals at different time points through integrated multi-source data (including environmental conditions, terrain characteristics, plant growth records, etc.). Use a deep learning algorithm (such as a recurrent neural network RNN) to process time series data, analyze the dynamic changes in plant growth, and generate detailed plant individual base cultivation time series state data. This data reflects the growth height, canopy density, health status, etc. of individual plants at different times.

[0025] Step S22: performing local plant individual-based cultivation time series change analysis on the plant individual-based cultivation time series state data by using a preset ordinary differential equation algorithm to generate local plant individual-based cultivation time series evolution data; In an embodiment of the present invention, the plant individual base cultivation time series state data is input into a preset ordinary differential equation model to perform a local plant individual base time series change analysis. Ordinary differential equations are used to describe the growth changes of plants in a short period of time, such as the increase or decrease in growth rate, fluctuations in health status, etc. By numerically solving these equations, the growth evolution of plant individuals in different time periods is analyzed, and local plant individual base cultivation time series evolution data is generated to identify key growth change points and provide a basis for further analysis.

[0026] Step S23: performing individual-based temporal evolution spatial feature identification processing on the local plant individual-based cultivation temporal evolution data to generate spatially identified local plant individual-based cultivation temporal evolution data; In an embodiment of the present invention, local plant individual-based cultivation time-series evolution data and plant individual-based cultivation spatial feature data are integrated, and plant individual time-series evolution data containing spatial information are generated by performing spatial feature identification processing on the data of each time point. By combining information in the time and space dimensions, the growth patterns of plants under different spatial conditions are identified, and spatially identified local plant individual-based cultivation time-series evolution data are generated, which helps to better understand the spatial heterogeneity of plant growth.

[0027] Step S24: performing a spatial heterogeneity characteristic analysis of plant cultivation temporal evolution on the spatially identified local plant individual-based cultivation temporal evolution data through a preset partial differential equation to generate spatial heterogeneity characteristic data of plant cultivation temporal evolution.

[0028] In the embodiment of the present invention, the local plant individual base cultivation time series evolution data of the spatial identification is collected and sorted, including the growth state information of the plant individual at different time series points, and combined with the specific spatial environmental characteristics of each time series point, such as soil moisture, light intensity, temperature, terrain slope, etc. The time series evolution data of the spatial identification is analyzed by partial differential equations, which are used to deal with complex spatial change problems, describe the growth dynamics of plants at different spatial positions, including the growth state of plants at position and time, as well as plant growth diffusion coefficients, plant impact spatial diffusion terms, plant growth impact reaction terms, plant growth impact reaction terms including environmental factors such as light, humidity, etc. The spatial heterogeneity characteristics of plant growth are identified, that is, the differences in plant growth performance in different regions. Using numerical analysis methods, such as finite difference method, finite element method, etc., the partial differential equations are solved to calculate the growth state of plants at different time and spatial positions, and the solution results will generate a growth state distribution map containing spatial and temporal dimensions. The obtained growth status data are analyzed to identify the growth differences between different spatial locations. These differences are manifested as plants growing faster in some areas and slower in other areas, or the health of plants in some areas is significantly better than in other areas. Spatial statistical analysis is performed on these data to identify the spatial heterogeneity characteristics of plant growth, which reflects how different environmental factors affect plant growth at different spatial scales. The analysis results are organized into spatial heterogeneity characteristic data, which describe in detail the differences in the characteristics of plant growth in different spatial regions, including quantitative indicators of each region's growth rate, health status, and impact on the surrounding environment, as well as the evolution of these indicators over time.

[0029] Preferably, step S21 includes the following steps: A plant cultivation simulation state analysis is performed according to the forestry digital twin model to generate plant cultivation simulation state data, wherein the plant cultivation simulation state data is the forestry plant growth state monitoring data of the forestry digital twin model and the corresponding environmental distribution data and forestry environment terrain characteristic data; a plant cultivation time series state characteristic analysis is performed according to the plant cultivation simulation state data to generate plant cultivation time series state characteristic data; a plant individual-based cultivation time series state analysis is performed according to the plant cultivation time series state characteristic data to generate plant individual-based cultivation time series state data.

[0030] The present invention uses a forestry digital twin model to perform plant cultivation simulation state analysis, accurately simulates the plant growth process in the real world in a virtual environment, and the simulation state data not only combines plant growth state monitoring data, but also integrates environmental distribution and terrain feature data, comprehensively and accurately reflecting the complexity and diversity of the ecosystem. Plant cultivation time series state feature analysis accurately captures the key time series characteristics of plants in the growth process through in-depth analysis of simulation state data, including growth rate, fluctuations in health status, key growth period, etc., which helps to improve the success rate and overall effect of plant regeneration cultivation. Further analysis of plant cultivation time series state feature data, refinement to individual level growth state analysis, individual base time series state analysis can generate exclusive growth data for each plant individual, revealing its performance and dynamic changes throughout the growth cycle, and the generated plant individual base cultivation time series state data provides accurate data support for individualized management, can flexibly respond to any changes in plant individuals in the growth process and provide a basis for the impact of associated growth factors, and avoid affecting the overall regeneration effect due to abnormal growth conditions of individual individuals.

[0031] In the embodiment of the present invention, the forestry digital twin model is used to simulate the cultivation state of the target plant. During the simulation process, real-time or preset environmental conditions (such as seasonal climate change, sudden weather events, etc.) are input, and the growth response of individual plants is simulated according to different terrain features and soil conditions. The generated plant cultivation simulation state data describes in detail the growth process of plants under given conditions. These data include information on the height, leaf area, root development, photosynthesis efficiency, etc. of the plant during the simulation process, which can reflect the dynamic changes of the plant throughout the growth cycle. The simulation state data is analyzed in time series to identify the key time series characteristics of the plant growth process. The various indicators of plant growth (such as height growth rate, leaf area expansion rate, photosynthesis efficiency, etc.) are segmented and counted using statistical algorithms to identify which time points or growth periods are the key stages of plant growth. For example, by analyzing the time series characteristics of the height growth of plants at different time series, it is helpful to understand the growth law of plants and provide important information for optimizing cultivation strategies. The generated plant cultivation time series state characteristic data provides managers with detailed growth characteristics of plants in different growth periods, including specific growth rates, health conditions, etc. According to the plant cultivation time series state characteristic data, a detailed time series state analysis is performed on each plant individual. By combining the growth characteristics of individual plants at different time points with their environment and terrain conditions, the specific performance of plants in each growth period can be analyzed. Nonlinear algorithms such as support vector machines or decision trees are used to analyze the differences in growth performance of individual plants in different periods. For example, by analyzing light and water conditions, we can understand how the growth response of individual plants changes under insufficient light or sufficient water conditions, identify the growth advantages and disadvantages of individual plants, and generate plant individual cultivation time series state data, including detailed growth status information of each individual plant at each time point.

[0032] Preferably, step S23 includes the following steps: According to the forestry digital twin model, the spatial characteristics of plant individual-based cultivation are analyzed to generate plant individual-based cultivation spatial characteristic data; according to the plant individual-based cultivation spatial characteristic data, the local plant individual-based cultivation time series evolution data are processed with individual-based time series evolution spatial characteristics identification to generate spatially identified local plant individual-based cultivation time series evolution data.

[0033] The present invention uses the forestry digital twin model to conduct a detailed analysis of the spatial characteristics of the environment where individual plants are located, including spatial variables such as terrain undulation, light distribution, soil moisture, and airflow, to fully understand the microenvironment of plant growth and identify key spatial factors that affect plant growth. The generated plant individual-based cultivation spatial feature data provides important spatial information for individualized management. Spatial feature analysis reveals the interaction between individual plants and their growth environment, understands the performance differences of different plants under different spatial conditions and the impact on spatial conditions. In addition, spatial feature data can provide higher accuracy for further growth predictions, and by combining time series data and spatial information, natural resources can be used to the maximum extent to improve the growth efficiency and health level of plants. The spatial feature data is combined with the time series evolution data of individual plants to generate local plant individual-based cultivation time series evolution data with spatial identification, and the growth law of plants under different time and space conditions is fully understood. Spatial identification processing embeds the growth process of individual plants more accurately into the spatial environment in which they are located, reveals the impact of spatial heterogeneity on plant growth, and enables managers to more accurately evaluate and optimize management measures in different regions. Through spatial identification processing, the analysis results of the time series evolution data can more accurately reflect the growth status of plants in a specific spatial environment. This processing helps to improve the accuracy of growth analysis and provide more intuitive and detailed growth status information. The generated spatial identification local plant individual-based cultivation time series evolution data can support more accurate growth predictions and be used to infer future growth trends and problems, so as to formulate countermeasures in advance and ensure the smooth progress of cultivation work.

[0034] In an embodiment of the present invention, a plurality of data sources including plant growth status data, terrain data, climate data and soil property data are integrated and analyzed through the forestry digital twin model that has been constructed. In the forestry digital twin model, the plant individuals to be analyzed are selected, and the spatial characteristics such as terrain slope, light distribution, soil moisture, air temperature, wind speed and the like of the environment in which they are located are combined to start spatial characteristic analysis. GIS (geographic information system) and spatial statistical analysis tools are used to perform a detailed spatial characteristic analysis of the environment in which the plant individuals are located. For example, the slope, orientation and elevation differences around the plant individuals are determined by terrain analysis tools; and the distribution of light in the region at different time periods is evaluated by light analysis. These spatial characteristics are associated with the growth status of the plant individuals to analyze the specific effects of different environmental factors on plant growth. For example, the difference in growth rate of plants on the south slope and the north slope is analyzed, or the comparison of plant growth health status in areas with different soil moisture levels is performed. The generated plant individual-based cultivation spatial characteristic data includes environmental information and plant growth characteristics in multiple dimensions. The spatial feature data of plant individual cultivation and the temporal evolution data of local plant individual cultivation are integrated. The integration process is completed through data alignment and feature mapping tools, so that the plant growth data at each time point are associated with its corresponding spatial feature data, ensuring that each growth state can reflect the spatial background conditions of its growth. The temporal evolution data of each plant individual is processed through the spatial feature identification algorithm, mainly by marking the plant growth data at different time points with their corresponding spatial feature information, so that each growth data point not only has the change of the time dimension, but also contains the characteristics of the spatial dimension. The identification process includes calculating and adding spatial feature data, such as adding terrain information, light intensity, humidity distribution and other characteristic parameters at each growth time point. Each time series data point has a spatial feature identification, which is convenient for subsequent analysis. After the spatial feature identification processing, the generated spatially identified local plant individual cultivation temporal evolution data not only records the growth state of the plant in each period, but also combines the environmental and spatial characteristics.

[0035] Preferably, step S3 comprises the following steps: Step S31: performing plant cultivation state analysis at different time series scales on the plant cultivation time series state characteristic data based on the spatial heterogeneity characteristic data of plant cultivation time series evolution to generate multi-scale plant cultivation state data; Step S32: performing a comprehensive analysis of the plant cultivation time series state according to the multi-scale plant cultivation state data to generate plant cultivation time series comprehensive state data; Step S33: performing plant cultivation state evaluation processing on the plant cultivation time series comprehensive state data according to the preset plant cultivation state evaluation decision to generate plant cultivation state evaluation data.

[0036] The present invention combines the spatial heterogeneity characteristic data of the plant cultivation time series evolution with the time series state characteristic data, and conducts in-depth analysis of the plant growth state at different time scales, which not only captures the long-term trend of plant growth, but also identifies the dynamic changes in the short term, which helps to fully understand the performance of plants in various growth periods, and the generated multi-scale plant cultivation state data provides a comprehensive perspective. The comprehensive analysis of the multi-scale plant cultivation state data integrates the growth state information at different time scales into a unified plant cultivation time series comprehensive state, provides a more comprehensive and accurate description of plant growth conditions, and reduces the amount of redundant data, so that the subsequent analysis is more efficient and more accurate, helping managers understand the overall trend and potential problems of plant growth at different time scales. Based on the preset plant cultivation state evaluation decision, the comprehensive state data is systematically evaluated and processed, the overall growth status of the plant is quantified, the risks and deficiencies that may exist in the cultivation process are identified, and a clear direction for improvement is provided. The generated plant cultivation state evaluation data provides an objective basis for subsequent decision optimization, helping managers to better adjust the cultivation strategy in actual operation, and ensure the continuous improvement of the success rate and quality of plant regeneration cultivation.

[0037] In an embodiment of the present invention, plant cultivation time series state characteristic data are analyzed at different time series scales based on plant cultivation time series evolution spatial heterogeneity characteristic data, the time series evolution data include plant growth state data at different time points, and the spatial heterogeneity characteristic data include spatial characteristic data related to terrain, environment and climate. Using these data, a multi-scale analysis model is established. The input of the model includes plant growth data on the time scale and environmental characteristic data on the spatial dimension. These data are input into the multi-scale analysis framework. In the multi-scale analysis model, different time scales are set, such as short-cycle scales and long-cycle scales, and the plant growth state is analyzed respectively. On the short-cycle scale, the response of plants to daytime environmental changes is analyzed; on the long-cycle scale, the long-term trend and periodic changes of plant growth are analyzed. Using time series analysis techniques, such as moving average, time series decomposition, Fourier transform, etc., the data of each time scale are processed to extract the main trend of plant growth, periodic changes and sudden events. The generated multi-scale plant cultivation state data includes growth rate, health status, environmental response characteristics, etc. at different time scales, reflecting the multi-dimensional change pattern of plant growth. The plant cultivation status data generated at different time scales are comprehensively analyzed. The growth data from different time scales are integrated through data fusion technology. The data at each time scale are merged into a unified state description using weighted average method or fusion technology based on Bayesian method. In the comprehensive analysis process, different weights are given to each time scale considering its different influence on the plant growth state. Short-term data may reflect the instantaneous impact of the environment, while long-term data can better reflect the trend change of plant growth. The integrated data retains the details and reflects the overall trend. The generated plant cultivation time series comprehensive state data includes the overall growth performance of plants in different time periods. According to the preset plant cultivation state evaluation standard, the evaluation parameters and thresholds of different states are set by combining expert knowledge and historical data. For example, different evaluation levels (such as excellent, good, medium, and poor) can be set according to indicators such as plant growth rate, health status, and disease resistance. When setting these standards, ensure that the evaluation standards can accurately reflect the actual situation of plant growth, and use supervised learning, expert knowledge, and historical data to establish a plant cultivation state evaluation model. The plant cultivation status assessment model is used to conduct a detailed assessment and processing of the comprehensive status data. By analyzing the growth performance of the plants in various time periods, the quantitative information of their current growth status is determined. In the assessment process, the influencing factors at different time scales are taken into account, and a comprehensive analysis of the plant growth status is conducted. Any abnormal conditions found, such as slow growth or disease threats, are marked and recorded in a timely manner. The generated plant cultivation status assessment data includes the assessment results of the growth status of each individual plant.

[0038] Preferably, step S4 comprises the following steps: Step S41: Analyze and process the plant cultivation environment influencing factors according to the plant cultivation time series comprehensive state data to generate plant cultivation environment influencing factor data; Step S42: Analyze and process the factors affecting plant cultivation terrain according to the plant cultivation time series comprehensive state data to generate plant cultivation terrain affecting factor data; Step S43: performing composite association processing of plant cultivation influencing factors according to the plant cultivation environment influencing factor data and the plant cultivation terrain influencing factor data to generate plant cultivation influencing factor data; Step S44: performing plant cultivation state evaluation and influencing factor association processing on the plant cultivation state evaluation data and the plant cultivation influencing factor data to generate plant cultivation state evaluation-influencing factor association data; Step S45: performing a gain analysis of the influencing factors of the plant cultivation state on the plant cultivation state evaluation-influencing factor association data according to a preset gradient boosting tree algorithm to generate plant cultivation state influencing factor gain data.

[0039] The present invention analyzes environmental influencing factors on plant cultivation time series comprehensive state data, comprehensively identifies and quantifies various environmental factors affecting plant growth, such as temperature, humidity, precipitation and light intensity, etc. The generated plant cultivation environmental influencing factor data provides detailed information on the impact of environmental conditions on plant growth, so that it can be accurately managed for different environmental conditions and optimize the effect of plant regeneration cultivation. By analyzing the terrain characteristics in the plant cultivation time series comprehensive state data, the specific impact of different terrain conditions (such as slope, altitude, orientation, etc.) on plant growth can be revealed. The generated plant cultivation terrain influencing factor data better understands the relationship between terrain characteristics and plant growth, so as to formulate more scientific cultivation strategies in areas with complex terrain, maximize the use of terrain advantages, and improve the growth quality of plants. By performing composite correlation processing on environmental influencing factors and terrain influencing factors, the comprehensive factors affecting plant growth and their interactions can be identified. The generated plant cultivation influencing factor data reflects the composite effects of various influencing factors, formulates a more optimized cultivation plan, and improves the comprehensive effect and stability of plant regeneration. The plant cultivation status assessment data is combined with the plant cultivation influencing factor data for correlation processing, and the specific contribution and influence of each influencing factor on the plant growth status are deeply analyzed. The generated plant cultivation status assessment-influencing factor correlation data provides accurate analysis results, enabling it to more effectively regulate the key factors in the cultivation process, thereby improving the success rate and management efficiency of plant regeneration. By using the gradient boosting tree algorithm to perform gain analysis on the plant cultivation status assessment-influencing factor correlation data, the contribution of each influencing factor to the plant growth status is quantified, and the most critical influencing factors are identified. The generated plant cultivation status influencing factor gain data provides managers with a clear direction for optimizing management, enabling them to concentrate resources and efforts on the most influential factors, thereby greatly improving the overall effect of plant regeneration cultivation and resource utilization efficiency.

[0040] As an embodiment of the present invention, refer to Figure 3 As shown, Figure 1 Detailed implementation step flow chart of step S4 in the embodiment, step S4 in this embodiment includes: Step S41: Analyze and process the plant cultivation environment influencing factors according to the plant cultivation time series comprehensive state data to generate plant cultivation environment influencing factor data; In an embodiment of the present invention, the plant cultivation time series comprehensive state data and the environmental data related to plant growth are integrated to perform association analysis, and the growth state of each individual plant is combined to analyze how environmental factors affect the growth performance of plants at different periods. Statistical analysis methods, such as multiple regression analysis or principal component analysis (PCA), are used to process environmental data to identify the most significant environmental factors that affect plant growth. For example, by analyzing the growth rate of plants under different temperature conditions, the key influencing points of temperature on plant growth are identified, or by analyzing the relationship between light and growth rate, the most suitable light conditions for plants are identified. The generated plant cultivation environment influencing factor data records in detail the specific degree of influence of each environmental variable on plant growth, providing data support for subsequent decision-making.

[0041] Step S42: Analyze and process the factors affecting plant cultivation terrain according to the plant cultivation time series comprehensive state data to generate plant cultivation terrain affecting factor data; In the embodiment of the present invention, the plant cultivation time series comprehensive state data and the corresponding terrain data are combined to analyze the influence of terrain factors on plant growth. For example, by analyzing the difference in plant growth in regions with different slopes, the influence of slope on plant water absorption and root development is identified. Using terrain analysis tools (such as DEM analysis, slope analysis, etc.), the terrain data is processed and analyzed in detail to identify the influence of terrain characteristics on plant growth. For example, the relationship between slope and water flow distribution is analyzed to determine how it affects plant water acquisition, or how the orientation affects plant light and temperature reception. The generated plant cultivation terrain influencing factor data records the influence of terrain characteristics on plant growth, providing a geographic reference for subsequent cultivation management.

[0042] Step S43: performing composite association processing of plant cultivation influencing factors according to the plant cultivation environment influencing factor data and the plant cultivation terrain influencing factor data to generate plant cultivation influencing factor data; In an embodiment of the present invention, data on plant cultivation environment influencing factors and data on plant cultivation terrain influencing factors are subjected to data composite association processing, the influencing factors corresponding to the plants are unified and integrated, data from different sources are integrated, the plant growth law under the joint action of multiple factors is identified, and machine learning algorithms such as multiple linear regression, decision trees or random forests are used to process environmental and terrain data to identify the effects of the interactions between various factors on plant growth. Through algorithm calculation, it is identified which combinations of environmental and terrain factors are most critical to plant growth. For example, the combination of slope and light intensity may significantly affect the photosynthesis efficiency of plants, or the combination of temperature and soil moisture has an important effect on the development of plant roots. The generated plant cultivation influencing factor data describes in detail the overall effects of the combination of various factors on plant growth, providing data support for optimizing cultivation strategies.

[0043] Step S44: performing plant cultivation state evaluation and influencing factor association processing on the plant cultivation state evaluation data and the plant cultivation influencing factor data to generate plant cultivation state evaluation-influencing factor association data; In an embodiment of the present invention, the plant cultivation status assessment data and the previously generated plant cultivation influencing factor data are subjected to correlation analysis. The purpose is to identify which factors play a key role in plant growth in different periods and under different spatial conditions by evaluating the contribution of each influencing factor to the plant growth state, and to further analyze the relationship between the influencing factors and the plant growth state using statistical methods such as correlation analysis and causal analysis. For example, through analysis, it is found that under certain specific environmental conditions, abnormal phenomena in plant growth may be related to specific terrain and environmental factors. The plant cultivation status assessment-influencing factor association data finally generated records in detail the correlation between the plant growth state and the influencing factors. This data set is used for further state optimization and decision support to ensure that managers can accurately identify and adjust the key factors in the cultivation strategy.

[0044] Step S45: performing a gain analysis of the influencing factors of the plant cultivation state on the plant cultivation state evaluation-influencing factor association data according to a preset gradient boosting tree algorithm to generate plant cultivation state influencing factor gain data.

[0045] In an embodiment of the present invention, the plant cultivation status assessment-influencing factor association data generated previously are collected and sorted. The data set includes the association information between various influencing factors (such as environment, topography, climate, etc.) and the growth status of plants, and the data is preprocessed, including data cleaning, missing value filling, standardization, etc., to ensure that each input variable is suitable for training the machine learning model. Gradient Boosting Decision Tree (GBDT) is used as the main analysis tool. GBDT is an integrated learning method that gradually improves the prediction performance of the model by constructing multiple weak learners (usually decision trees) and setting the key parameters of the GBDT model, such as learning rate, maximum tree depth, number of subtrees, and maximum number of features per tree. For example, the learning rate is set to 0.1, the maximum tree depth is 5, the number of trees is 100, etc. This parameter setting needs to be optimized by cross-validation or grid search method to obtain the best model effect. The pre-processed plant cultivation status evaluation-influencing factor association data is input into the GBDT model for training. During the training process, the model gradually learns the contribution of each influencing factor to the plant growth status. In each round of iteration, the model gradually optimizes the weight of each decision tree by fitting the residual, and continuously improves the accuracy of the overall model. After the model training is completed, the gain value of each input feature (influencing factor) is calculated using the model's built-in gain analysis function. The gain value is an indicator of the importance of a feature in the model, indicating the contribution of the feature to the final prediction result. The model traverses all tree nodes, calculates the information gain brought by each feature when splitting, and accumulates these gain values ​​to form the final feature gain ranking. According to the gain analysis results, the gain data of the influencing factors of plant cultivation status is generated. This data includes the gain value of each influencing factor and its ranking among all factors. The generated gain data provides a clear optimization direction. Through the gain data, we can clearly understand which factors are most important to plant growth, so that we can focus resources on optimizing these key factors. For example, if it is found that light intensity and soil moisture have the highest gain values ​​for plant growth, then these factors can be precisely managed, such as adjusting irrigation plans or taking shading measures. In addition, the gain analysis results can also be used to improve subsequent plant cultivation strategies and provide important reference for decision support systems.

[0046] Preferably, step S5 comprises the following steps: Step S51: Acquire forestry plant regeneration demand data; Step S52: performing plant regeneration and cultivation digital decision analysis based on forestry plant regeneration demand data and the forestry digital twin model to generate plant regeneration and cultivation digital decisions; Step S53: performing plant regeneration cultivation digital decision optimization processing according to the plant cultivation state influencing factor gain data and the plant regeneration cultivation digital decision, and generating an optimized plant regeneration cultivation digital decision; Step S54: performing plant regeneration and cultivation simulation analysis according to the optimized plant regeneration and cultivation digital decision to generate plant regeneration and cultivation simulation data; Step S55: performing plant regeneration and cultivation temporal growth trend analysis according to the plant regeneration and cultivation simulation data to generate plant regeneration and cultivation temporal growth trend data; Step S56: performing plant regeneration and cultivation influencing factor change analysis based on the plant regeneration and cultivation time series growth trend data, and generating plant regeneration and cultivation influencing factor change data; Step S57: intelligently adjusting the optimized plant regeneration and cultivation digital decision according to the plant regeneration and cultivation influencing factor change data to obtain the plant regeneration and cultivation intelligent decision; Step S58: Feedback the plant regeneration and cultivation intelligent decision to the terminal to execute the forestry plant regeneration and cultivation intelligent operation.

[0047] The present invention obtains forestry plant regeneration demand data to clarify current and future plant regeneration goals and requirements, provides a clear direction and basis for formulating scientific regeneration and cultivation plans, ensures that each step of regeneration and cultivation is closely centered on actual needs, avoids waste of resources, and improves the effectiveness and goal achievement of regeneration work. By combining forestry plant regeneration demand data with the forestry digital twin model, a scientific digital analysis of the regeneration and cultivation plan is performed, and a reasonable plant regeneration and cultivation digital decision is generated. The matching of regeneration demand and actual conditions is comprehensively considered to ensure the feasibility and scientificity of the decision-making plan. The generated digital decision provides managers with reliable guidelines to help them formulate more efficient cultivation strategies and achieve rapid recovery of the ecosystem. By combining the gain data of plant cultivation status influencing factors, the preliminary generated regeneration and cultivation digital decision is optimized, which can further improve the accuracy and effect of the decision. The optimized digital decision can be adjusted for the most critical influencing factors to ensure the optimal configuration of resources and management measures, thereby improving the success rate of plant regeneration and cultivation, reducing resource consumption, and accelerating the recovery process of the ecosystem. The optimized digital decision is simulated and analyzed to pre-verify the effect of the cultivation plan in the actual environment. The generated plant regeneration cultivation simulation data can reveal potential problems and risks, and can be adjusted and optimized before implementation to avoid unnecessary losses and waste of resources. This simulation analysis not only improves the reliability of decision-making, but also provides an important reference basis for actual operations to ensure the smooth progress of cultivation. The simulation data is analyzed for time-series growth trends to predict the performance and development trends of plants in different growth periods. The generated plant regeneration cultivation time-series growth trend data provides predictive information on future growth conditions, enabling them to formulate response strategies in advance, optimize management measures, and ensure the continuous and stable development of the plant regeneration cultivation process. Based on the plant regeneration cultivation time-series growth trend data, the plant regeneration cultivation influencing factor change analysis is carried out to identify and quantify the factors that have a greater impact on plant growth under different spatial conditions and in different growth periods. The generated influencing factor change data helps managers to promptly discover and adjust the key factors in the management strategy, ensuring that they can flexibly respond to environmental changes and changes in growth conditions during the cultivation process, thereby maintaining the efficiency and stability of plant regeneration cultivation. According to the change data of influencing factors, the optimized digital decision is intelligently adjusted to make the regeneration and cultivation plan more flexible and adaptive. The generated intelligent decision can respond to changes in the environment and growth conditions in real time, ensure that the cultivation strategy is always in the optimal state, and improve the success rate of regeneration work and resource utilization efficiency. By feeding back the intelligent decision to the terminal equipment, automated and intelligent cultivation operations can be achieved. Such a closed-loop feedback mechanism ensures the efficient implementation and real-time adjustment of decisions, making the plant regeneration and cultivation process more accurate, fast and efficient, and significantly improving the automation level and overall effect of management work.

[0048] As an embodiment of the present invention, refer to Figure 4 As shown, Figure 1 FIG. 5 is a flow chart of detailed implementation steps of step S5, in this embodiment, step S5 includes: Step S51: Acquire forestry plant regeneration demand data; In the embodiment of the present invention, a comprehensive regeneration demand survey is conducted on the target forest area to collect specific demand data for forestry plant regeneration, including ecological restoration goals, vegetation type selection, soil improvement requirements, climate adaptability, and forestry plant regeneration planting planning.

[0049] Step S52: performing plant regeneration and cultivation digital decision analysis based on forestry plant regeneration demand data and the forestry digital twin model to generate plant regeneration and cultivation digital decisions; In an embodiment of the present invention, the collected forestry plant regeneration demand data is input into the forestry digital twin model. The digital twin model has integrated various data such as the terrain, climate, soil, vegetation, etc. of the forest area, and can accurately simulate the plant growth process under different regeneration schemes. According to the input demand data, different regeneration and cultivation strategies are set in the digital twin model, including the selection of plant species, planting density, cultivation methods, irrigation plans, soil improvement measures, etc., to generate a preliminary plant regeneration and cultivation digital decision-making plan, which includes specific planting arrangements, management measures, and expected regeneration effects.

[0050] Step S53: performing plant regeneration cultivation digital decision optimization processing according to the plant cultivation state influencing factor gain data and the plant regeneration cultivation digital decision, and generating an optimized plant regeneration cultivation digital decision; In the embodiment of the present invention, the gain data of the factors affecting the plant cultivation state generated in the early stage are combined with the preliminary regeneration cultivation digital decision to further optimize the decision plan. The gain data indicates which environmental factors are most critical to plant growth, so the regeneration cultivation plan can be optimized by adjusting the management strategy of these key factors. For example, if the gain data indicates that light intensity is a key factor affecting plant growth, the planting position or shading measures of the plant can be adjusted to optimize the light conditions, and the final optimized plant regeneration cultivation digital decision is generated based on the optimized decision.

[0051] Step S54: performing plant regeneration and cultivation simulation analysis according to the optimized plant regeneration and cultivation digital decision to generate plant regeneration and cultivation simulation data; In the embodiment of the present invention, the optimized digital decision-making scheme for regeneration and cultivation is input into the forestry digital twin model for more detailed simulation analysis. Through model simulation, the effect of the optimization scheme in actual application is predicted, including the growth trend, health status, ecological recovery speed, etc. of the plants. Plant regeneration and cultivation simulation data is generated based on the simulation results, which provides a quantitative basis for further verification and adjustment of the decision, helping to ensure that the decision-making scheme can achieve the expected results in actual operation.

[0052] Step S55: performing plant regeneration and cultivation temporal growth trend analysis according to the plant regeneration and cultivation simulation data to generate plant regeneration and cultivation temporal growth trend data; In an embodiment of the present invention, the simulation data obtained from the plant regeneration and cultivation simulation is sorted and input into the analysis system. The simulation data includes key indicators of plant growth, such as growth height, leaf area, root expansion, photosynthesis efficiency, etc., covering the time series of the entire growth cycle. The cleaned simulation data is analyzed in detail using time series analysis technology, including moving average, exponential smoothing, ARIMA model (autoregressive integrated moving average model), etc. By analyzing the key time nodes in the plant growth process, its growth trend in different time periods is identified, and the generated plant regeneration and cultivation time series growth trend data describes in detail the trend changes of the plant throughout the growth cycle, and identifies the growth characteristics and potential risk points at different stages.

[0053] Step S56: performing plant regeneration and cultivation influencing factor change analysis based on the plant regeneration and cultivation time series growth trend data, and generating plant regeneration and cultivation influencing factor change data; In an embodiment of the present invention, the plant regeneration and cultivation time-series growth trend data is correlated with key environmental factors that affect plant growth, and the environmental factors include light, temperature, humidity, rainfall, soil fertility, etc. Methods such as multiple regression analysis and principal component analysis are used to quantify the correlation effects between various environmental factors and plant growth trends in different growth periods. For example, the influence of plants and the surrounding environment during the growth of regenerated plants is identified, and based on the results of the correlation analysis, the key environmental factors that need to be adjusted in a specific growth period are identified. For example, increase irrigation during high temperatures or adjust plant layout in the absence of sufficient light. The generated plant regeneration and cultivation influencing factor change data includes environmental parameters that need to be adjusted in each growth period and specific management measures recommendations, which help managers flexibly adjust cultivation strategies in actual operations to adapt to changing environmental conditions.

[0054] Step S57: intelligently adjusting the optimized plant regeneration and cultivation digital decision according to the plant regeneration and cultivation influencing factor change data to obtain the plant regeneration and cultivation intelligent decision; In an embodiment of the present invention, an intelligent adjustment model is constructed according to the change data of the influencing factors. The model integrates the current decision-making scheme of regeneration cultivation, and combines the real-time environmental data and change suggestions for dynamic adjustment. The model adopts a rule engine or an adaptive algorithm based on machine learning, and can automatically adjust the plant cultivation decision according to the input prediction data of the optimized plant regeneration cultivation digital decision and the change data of the plant regeneration cultivation influencing factors (such as meteorological data, soil moisture, etc.). For example, when it is found that the soil moisture is lower than the threshold, the intelligent adjustment model of the automatic adjustment irrigation strategy runs in real time during the actual cultivation process, continuously optimizes the regeneration cultivation decision according to the current environmental conditions and the growth status of the plant, and automatically adjusts the cultivation plan to ensure that the plant grows under the optimal conditions. The generated plant regeneration cultivation intelligent decision plan includes specific operation suggestions after dynamic adjustment. This intelligent decision plan can not only improve the success rate of plant regeneration cultivation, but also effectively reduce resource consumption and maximize ecological and economic benefits.

[0055] Step S58: Feedback the plant regeneration and cultivation intelligent decision to the terminal to execute the forestry plant regeneration and cultivation intelligent operation.

[0056] In an embodiment of the present invention, the intelligent decision is transmitted to the on-site operating terminal through the network system to guide the actual forestry plant regeneration and cultivation operations. The terminal equipment may include an intelligent irrigation system, an unmanned aerial vehicle monitoring system, an automated fertilization equipment, etc. During the actual operation process, the intelligent device automatically executes the cultivation task according to the decision plan and monitors the plant growth in real time. The monitoring data will be fed back to the central control system for further decision optimization.

[0057] Preferably, step S56 includes the following steps: Based on the spatial heterogeneity characteristic data of plant cultivation temporal evolution, the influencing factors of spatial heterogeneity of plant regeneration and cultivation are analyzed on the temporal growth trend data of plant regeneration and cultivation, and the data of influencing factors of spatial heterogeneity of plant regeneration and cultivation are generated; based on the data of influencing factors of spatial heterogeneity of plant regeneration and cultivation, the change analysis of influencing factors of plant regeneration and cultivation is carried out to generate the change data of influencing factors of plant regeneration and cultivation.

[0058] The present invention combines the spatial heterogeneity characteristic data of plant cultivation temporal evolution and the temporal growth trend data of plant regeneration cultivation, and can deeply analyze the impact of different spatial environments on plant regeneration growth. The spatial heterogeneity impact analysis identifies the key factors that may affect plant growth under specific spatial conditions, and reveals how environmental changes affect the long-term growth trend of plants. The generated plant regeneration cultivation spatial heterogeneity influencing factor data reflects comprehensive spatial environmental impact information, supports more accurate spatial differentiation management and optimization, and the scientificity and effect of regeneration cultivation work have been significantly improved. Based on the plant regeneration cultivation spatial heterogeneity influencing factor data, a more refined influencing factor change analysis is carried out to identify the key factors that need to be adjusted under different spatial conditions, accurately locate the spatial environment characteristics that have a positive or negative effect on plant growth, and help managers to adjust the cultivation strategy in a targeted manner. The generated plant regeneration cultivation influencing factor change data provides an important basis for subsequent intelligent decision-making, ensures the flexibility and adaptability of the cultivation plan, and thus improves the overall success rate of plant regeneration and the long-term stability of the ecosystem.

[0059] In an embodiment of the present invention, the spatial heterogeneity characteristic data of plant cultivation temporal evolution and the temporal growth trend data of plant regeneration cultivation generated in the early stage are collected and sorted. The spatial heterogeneity characteristic data of plant cultivation temporal evolution include the differences in growth performance of different plants in different spatial regions, such as light intensity, soil moisture, terrain height difference, etc.; the temporal growth trend data of plant regeneration cultivation reflects the growth changes of plants in different time periods. The spatial heterogeneity characteristic data of plant cultivation temporal evolution are used to analyze the impact of the regenerated plants corresponding to the temporal growth trend data of plant regeneration cultivation on the surrounding environment, and the spatial heterogeneity influencing factors of plant regeneration cultivation are analyzed through spatial autocorrelation analysis, hot spot analysis, Kriging interpolation, etc., including analyzing the changes and influences of spatial heterogeneity data such as temperature, humidity, and soil in the growth trend of different varieties of regenerated plants. The generated spatial heterogeneity influencing factor data of plant regeneration cultivation describes in detail the specific situation of the influence of spatial heterogeneity in the growth process of plants, including the affected areas, the intensity of the impact and the cause analysis. Based on the data of spatial heterogeneity influencing factors of plant regeneration and cultivation, the change characteristics of key factors affecting plant growth, such as uneven light distribution and insufficient soil moisture, are identified. Multivariate regression analysis, path analysis and other methods are used to quantify the contribution of spatial heterogeneity factors to plant growth, and the changes in the impact of these factors on plant growth in different time periods are analyzed. Combined with the analysis results, the influencing factors of plant regeneration are improved intelligently so that the influencing factors of plant regeneration are adjusted to the optimal state, such as adding supplementary lighting measures in areas with weak light, optimizing irrigation strategies in high-altitude areas, or adjusting the timing of fertilization to adapt to the characteristics of different soil types. The change data of factors affecting plant regeneration and cultivation are generated, including the abnormal status of factors affecting plant regeneration and cultivation, and the various management measures and environmental parameters that need to be adjusted are listed, including the specific change time and change method.

[0060] The present specification provides a forestry plant regeneration cultivation intelligent analysis system for executing the forestry plant regeneration cultivation intelligent analysis method as described above. The forestry plant regeneration cultivation intelligent analysis system includes: A forestry digital twin model construction module is used to obtain forestry plant analysis areas; based on the forestry plant analysis areas, forestry digital twin feature information analysis is performed to construct a forestry digital twin model; The plant individual-based spatiotemporal feature analysis module is used to analyze the plant individual-based cultivation time series state according to the forestry digital twin model, and generate plant individual-based cultivation time series state data; perform local plant individual-based cultivation time series change analysis on the plant individual-based cultivation time series state data, and generate local plant individual-based cultivation time series evolution data; perform plant cultivation time series evolution spatial heterogeneity feature analysis based on local plant individual-based cultivation time series evolution data, and generate plant cultivation time series evolution spatial heterogeneity feature data; The plant cultivation state evaluation module is used to perform a comprehensive analysis of the plant cultivation time series state at different time series scales on the plant cultivation time series state characteristic data based on the spatial heterogeneity characteristic data of the plant cultivation time series evolution, and generate plant cultivation time series comprehensive state data; perform plant cultivation state evaluation processing on the plant cultivation time series comprehensive state data, and generate plant cultivation state evaluation data; The plant cultivation state influencing factor gain analysis module is used to analyze the composite influencing factors of plant cultivation based on the plant cultivation time series state characteristic data to generate plant cultivation influencing factor data; perform plant cultivation state evaluation and influencing factor association processing on the plant cultivation state evaluation data and the plant cultivation influencing factor data to generate plant cultivation state evaluation-influencing factor association data; perform plant cultivation state influencing factor gain analysis on the plant cultivation state evaluation-influencing factor association data to generate plant cultivation state influencing factor gain data; The plant regeneration and cultivation intelligent decision analysis module is used to obtain forestry plant regeneration demand data; perform plant regeneration and cultivation digital decision analysis based on forestry plant regeneration demand data and the forestry digital twin model to generate plant regeneration and cultivation digital decisions; optimize the plant regeneration and cultivation digital decisions according to the gain data of plant cultivation status influencing factors and the plant regeneration and cultivation digital decisions to generate optimized plant regeneration and cultivation digital decisions; intelligently adjust the plant regeneration and cultivation digital decisions with changes in influencing factors of the optimized plant regeneration and cultivation digital decisions to obtain plant regeneration and cultivation intelligent decisions; and feed back the plant regeneration and cultivation intelligent decisions to the terminal to execute the forestry plant regeneration and cultivation intelligent cultivation operations.

[0061] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0062] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A forestry plant regeneration and cultivation intelligent analysis method, characterized in that: The following steps are involved: Step S1: obtaining a forestry plant analysis area; performing forestry digital twin feature information analysis based on the forestry plant analysis area to construct a forestry digital twin model; Step S2: performing plant individual-based cultivation time series state analysis based on the forestry digital twin model to generate plant individual-based cultivation time series state data; performing local plant individual-based cultivation time series change analysis on the plant individual-based cultivation time series state data to generate local plant individual-based cultivation time series evolution data; performing plant cultivation time series evolution spatial heterogeneity feature analysis based on the local plant individual-based cultivation time series evolution data to generate plant cultivation time series evolution spatial heterogeneity feature data; Step S3: Based on the spatial heterogeneity characteristic data of plant cultivation temporal evolution, the plant cultivation temporal state characteristic data is subjected to a comprehensive analysis of the plant cultivation temporal state at different temporal scales to generate plant cultivation temporal comprehensive state data; the plant cultivation temporal comprehensive state data is subjected to a plant cultivation state evaluation process to generate plant cultivation state evaluation data; Step S4: performing a composite influencing factor analysis of plant cultivation based on the plant cultivation time series state characteristic data to generate plant cultivation influencing factor data; performing plant cultivation state evaluation and influencing factor association processing on the plant cultivation state evaluation data and the plant cultivation influencing factor data to generate plant cultivation state evaluation-influencing factor association data; performing plant cultivation state influencing factor gain analysis on the plant cultivation state evaluation-influencing factor association data to generate plant cultivation state influencing factor gain data; Step S5: Acquire forestry plant regeneration demand data; perform plant regeneration and cultivation digital decision analysis based on the forestry plant regeneration demand data and the forestry digital twin model to generate plant regeneration and cultivation digital decisions; optimize the plant regeneration and cultivation digital decisions according to the gain data of plant cultivation status influencing factors and the plant regeneration and cultivation digital decisions to generate optimized plant regeneration and cultivation digital decisions; perform intelligent adjustments on the plant regeneration and cultivation digital decisions with changes in influencing factors on the optimized plant regeneration and cultivation digital decisions to obtain plant regeneration and cultivation intelligent decisions; feed back the plant regeneration and cultivation intelligent decisions to the terminal to execute the forestry plant regeneration and cultivation intelligent cultivation operations.

2. The intelligent analysis method for plant regeneration and cultivation in forestry according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Acquire forestry plant analysis area; Step S12: using laser radar monitoring equipment to perform forestry area monitoring processing on the forestry analysis area to generate forestry area monitoring data; Step S13: collecting environmental distribution data of the forestry analysis area according to the IoT sensor to generate environmental distribution data; Step S14: Analyze forestry environment terrain characteristics of forestry monitoring area data using GIS technology to generate forestry environment terrain characteristic data; Step S15: performing forestry plant growth status monitoring processing on the forestry area monitoring data to generate forestry plant growth status monitoring data; Step S16: Establish a forestry digital twin model terrain framework based on the forestry environment terrain feature data, and map the forestry digital twin feature information by transmitting the forestry plant growth status monitoring data and environmental distribution data to the forestry digital twin model terrain framework to construct a forestry digital twin model.

3. The intelligent analysis method for plant regeneration and cultivation in forestry according to claim 2, characterized in that: Step S2 includes the following steps: Step S21: performing plant individual-based cultivation time series state analysis according to the forestry digital twin model to generate plant individual-based cultivation time series state data; Step S22: performing local plant individual-based cultivation time series change analysis on the plant individual-based cultivation time series state data by using a preset ordinary differential equation algorithm to generate local plant individual-based cultivation time series evolution data; Step S23: performing individual-based temporal evolution spatial feature identification processing on the local plant individual-based cultivation temporal evolution data to generate spatially identified local plant individual-based cultivation temporal evolution data; Step S24: performing a spatial heterogeneity characteristic analysis of plant cultivation temporal evolution on the spatially identified local plant individual-based cultivation temporal evolution data through a preset partial differential equation to generate spatial heterogeneity characteristic data of plant cultivation temporal evolution.

4. The intelligent analysis method for plant regeneration and cultivation in forestry according to claim 3, characterized in that: Step S21 includes the following steps: A plant cultivation simulation state analysis is performed according to the forestry digital twin model to generate plant cultivation simulation state data, wherein the plant cultivation simulation state data is the forestry plant growth state monitoring data of the forestry digital twin model and the corresponding environmental distribution data and forestry environment terrain characteristic data; a plant cultivation time series state characteristic analysis is performed according to the plant cultivation simulation state data to generate plant cultivation time series state characteristic data; a plant individual-based cultivation time series state analysis is performed according to the plant cultivation time series state characteristic data to generate plant individual-based cultivation time series state data.

5. The intelligent analysis method for plant regeneration and cultivation in forestry according to claim 4, characterized in that: Step S23 includes the following steps: According to the forestry digital twin model, the spatial characteristics of plant individual-based cultivation are analyzed to generate plant individual-based cultivation spatial characteristic data; according to the plant individual-based cultivation spatial characteristic data, the local plant individual-based cultivation time series evolution data are processed with individual-based time series evolution spatial characteristics identification to generate spatially identified local plant individual-based cultivation time series evolution data.

6. The intelligent analysis method for plant regeneration and cultivation in forestry according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: performing plant cultivation state analysis at different time series scales on the plant cultivation time series state characteristic data based on the spatial heterogeneity characteristic data of plant cultivation time series evolution to generate multi-scale plant cultivation state data; Step S32: performing a comprehensive analysis of the plant cultivation time series state according to the multi-scale plant cultivation state data to generate plant cultivation time series comprehensive state data; Step S33: performing plant cultivation state evaluation processing on the plant cultivation time series comprehensive state data according to the preset plant cultivation state evaluation decision to generate plant cultivation state evaluation data.

7. The intelligent analysis method for plant regeneration and cultivation in forestry according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: Analyze and process the plant cultivation environment influencing factors according to the plant cultivation time series comprehensive state data to generate plant cultivation environment influencing factor data; Step S42: Analyze and process the factors affecting plant cultivation terrain according to the plant cultivation time series comprehensive state data to generate plant cultivation terrain affecting factor data; Step S43: performing composite association processing of plant cultivation influencing factors according to the plant cultivation environment influencing factor data and the plant cultivation terrain influencing factor data to generate plant cultivation influencing factor data; Step S44: performing plant cultivation state evaluation and influencing factor association processing on the plant cultivation state evaluation data and the plant cultivation influencing factor data to generate plant cultivation state evaluation-influencing factor association data; Step S45: performing a gain analysis of the influencing factors of the plant cultivation state on the plant cultivation state evaluation-influencing factor association data according to a preset gradient boosting tree algorithm to generate plant cultivation state influencing factor gain data.

8. The intelligent analysis method for plant regeneration and cultivation in forestry according to claim 3, characterized in that: Step S5 includes the following steps: Step S51: Acquire forestry plant regeneration demand data; Step S52: performing plant regeneration and cultivation digital decision analysis based on forestry plant regeneration demand data and the forestry digital twin model to generate plant regeneration and cultivation digital decisions; Step S53: performing plant regeneration cultivation digital decision optimization processing according to the plant cultivation state influencing factor gain data and the plant regeneration cultivation digital decision, and generating an optimized plant regeneration cultivation digital decision; Step S54: performing plant regeneration and cultivation simulation analysis according to the optimized plant regeneration and cultivation digital decision to generate plant regeneration and cultivation simulation data; Step S55: performing plant regeneration and cultivation temporal growth trend analysis according to the plant regeneration and cultivation simulation data to generate plant regeneration and cultivation temporal growth trend data; Step S56: performing plant regeneration and cultivation influencing factor change analysis based on the plant regeneration and cultivation time series growth trend data, and generating plant regeneration and cultivation influencing factor change data; Step S57: intelligently adjusting the optimized plant regeneration and cultivation digital decision according to the plant regeneration and cultivation influencing factor change data to obtain the plant regeneration and cultivation intelligent decision; Step S58: Feedback the plant regeneration and cultivation intelligent decision to the terminal to execute the forestry plant regeneration and cultivation intelligent operation.

9. The intelligent analysis method for plant regeneration and cultivation in forestry according to claim 8, characterized in that: Step S56 includes the following steps: Based on the spatial heterogeneity characteristic data of plant cultivation temporal evolution, the influencing factors of spatial heterogeneity of plant regeneration and cultivation are analyzed on the temporal growth trend data of plant regeneration and cultivation, and the data of influencing factors of spatial heterogeneity of plant regeneration and cultivation are generated; based on the data of influencing factors of spatial heterogeneity of plant regeneration and cultivation, the change analysis of influencing factors of plant regeneration and cultivation is carried out to generate the change data of influencing factors of plant regeneration and cultivation.

10. A forestry plant regeneration and cultivation intelligent analysis system, characterized in that: The method for executing the intelligent analysis method for plant regeneration and cultivation in forestry as claimed in claim 1, wherein the intelligent analysis system for plant regeneration and cultivation in forestry comprises: A forestry digital twin model construction module is used to obtain forestry plant analysis areas; based on the forestry plant analysis areas, forestry digital twin feature information analysis is performed to construct a forestry digital twin model; The plant individual-based spatiotemporal feature analysis module is used to analyze the plant individual-based cultivation time series state according to the forestry digital twin model, and generate plant individual-based cultivation time series state data; perform local plant individual-based cultivation time series change analysis on the plant individual-based cultivation time series state data, and generate local plant individual-based cultivation time series evolution data; perform plant cultivation time series evolution spatial heterogeneity feature analysis based on local plant individual-based cultivation time series evolution data, and generate plant cultivation time series evolution spatial heterogeneity feature data; The plant cultivation state evaluation module is used to perform a comprehensive analysis of the plant cultivation time series state at different time series scales on the plant cultivation time series state characteristic data based on the spatial heterogeneity characteristic data of the plant cultivation time series evolution, and generate plant cultivation time series comprehensive state data; perform plant cultivation state evaluation processing on the plant cultivation time series comprehensive state data, and generate plant cultivation state evaluation data; The plant cultivation state influencing factor gain analysis module is used to analyze the composite influencing factors of plant cultivation based on the plant cultivation time series state characteristic data to generate plant cultivation influencing factor data; perform plant cultivation state evaluation and influencing factor association processing on the plant cultivation state evaluation data and the plant cultivation influencing factor data to generate plant cultivation state evaluation-influencing factor association data; perform plant cultivation state influencing factor gain analysis on the plant cultivation state evaluation-influencing factor association data to generate plant cultivation state influencing factor gain data; The plant regeneration and cultivation intelligent decision analysis module is used to obtain forestry plant regeneration demand data; perform plant regeneration and cultivation digital decision analysis based on forestry plant regeneration demand data and the forestry digital twin model to generate plant regeneration and cultivation digital decisions; optimize the plant regeneration and cultivation digital decisions according to the gain data of plant cultivation status influencing factors and the plant regeneration and cultivation digital decisions to generate optimized plant regeneration and cultivation digital decisions; intelligently adjust the plant regeneration and cultivation digital decisions with changes in influencing factors of the optimized plant regeneration and cultivation digital decisions to obtain plant regeneration and cultivation intelligent decisions; and feed back the plant regeneration and cultivation intelligent decisions to the terminal to execute the forestry plant regeneration and cultivation intelligent cultivation operations.

Images