Self-adaptive forest resource survey factor generation method

Abstract

The invention relates to the technical field of adaptive measurement, in particular to an adaptive forest resource survey factor generation method. The method comprises the following steps: acquiring and processing forest resources in a survey area range by using a space remote sensing image technology to obtain forest resource survey data; performing noise reduction processing on the forest resource survey data by using a forest resource noise reduction algorithm to obtain forest resource survey noise reduction data; performing feature extraction processing on the forest resource survey noise reduction data by using a feature extraction technology to obtain forest resource survey data features; performing classification processing on the forest resource survey data features according to a preset forest resource classification model to obtain forest resource survey type data; and analyzing and processing the forest resource survey type data by using a factor analysis technology to generate a forest resource state factor. According to the method, the factor parameters are automatically adjusted by utilizing the remote sensing data and using the adaptive algorithm, so that the accuracy and efficiency of forest resource investigation are improved.

Description

Technical Field

[0001] The present invention relates to the field of adaptive measurement technology, in particular to an adaptive forest resource survey factor generation method. Background Art

[0002] Forests are one of Earth's most important natural resources, playing a vital role in the balance of global ecosystems and the sustainable development of human society and economy. Therefore, forest protection and management have become a global concern. Forest resource surveys are the foundation of forest protection and management, and forest survey factors are important indicators for measuring forest resources and are crucial for formulating forest protection and management policies.

[0003] Traditional forest survey methods, primarily based on manual measurement, suffer from low efficiency, limited accuracy, and high costs, making them inadequate for large-scale forest surveys. In recent years, with the continuous development and widespread adoption of satellite remote sensing technology, methods for generating forest survey factors based on remote sensing data have become a research hotspot and have been widely implemented. However, traditional methods for generating forest survey factors based on remote sensing data typically employ fixed parameter settings and have low model complexity. These methods fail to fully utilize the rich information contained in remote sensing data, making it difficult to improve the accuracy and efficiency of forest surveys. Summary of the Invention

[0004] Based on this, it is necessary for the present invention to provide an adaptive forest resource survey factor generation method to solve at least one of the above technical problems.

[0005] To achieve the above purpose, an adaptive forest resource survey factor generation method is provided, which includes the following steps:

[0006] Step S1: using spatial remote sensing imaging technology to collect and process forest resources within the survey area to obtain forest resource survey data; using a forest resource noise reduction algorithm to perform noise reduction on the forest resource survey data to obtain forest resource survey noise reduction data;

[0007] Step S2: Using feature extraction technology to perform feature extraction processing on the forest resource survey noise reduction data to obtain forest resource survey data features; classifying the forest resource survey data features according to a preset forest resource classification model to obtain forest resource survey type data;

[0008] Step S3: Analyze and process the forest resource survey type data using factor analysis technology to generate forest resource status factors;

[0009] Step S4: real-time monitoring and evaluation of the forest resource status factor is performed using an adaptive evaluation algorithm to obtain a forest resource adaptive status factor; and the weight of the forest resource adaptive status factor is dynamically adjusted using a weight adjustment algorithm that introduces a factor weight mechanism to generate a forest resource adjustment status factor.

[0010] Step S5: Use hierarchical assessment technology to conduct a comprehensive assessment of the forest resource adjustment status factors to generate forest resource survey factors; formulate a forest resource survey report based on the forest resource survey factors to implement the corresponding adaptive forest resource survey strategy.

[0011] The present invention can quickly obtain forest resource survey data over a large area by using spatial remote sensing imaging technology. The forest resource denoising algorithm is used to perform denoising processing on the forest resource survey data obtained by spatial remote sensing imaging technology. This can effectively reduce the noise source of the forest resource survey data and avoid the influence of noise sources and interference signals in the forest resource survey data on the subsequent generation process of forest resource survey factors, thereby improving the accuracy and reliability of the forest resource survey data, thereby providing clear and accurate basic data for subsequent forest resource classification tasks and forest resource survey factor generation processes, and providing data support for forest resource protection and management. By selecting a suitable feature extraction technology to extract features from the forest resource survey denoised data and constructing an appropriate forest resource classification model for classification processing, the obtained complex forest resource survey data can be converted into processable forest resource survey type data, providing a data processing basis for the subsequent factor analysis generation process, thereby achieving refined management and protection of forest resources. Then, the obtained forest resource survey data is analyzed and processed using factor analysis technology, and key factors affecting forest resource health and ecosystems can be extracted from the perspective of data dimensions, providing a basis for subsequent adaptive evaluation and adjustment, thereby improving the feasibility and effectiveness of forest resource management and protection. By setting up an appropriate adaptive assessment algorithm to monitor and evaluate forest resource status factors in real time and introducing adjustment factor weights for dynamic adjustment, it is possible to monitor and adjust forest resource status factors in real time, and promptly address abnormal forest resource conditions, thereby better protecting forest resources and reducing resource waste and loss. Finally, by setting up an appropriate hierarchical assessment technology to comprehensively evaluate the adjusted forest resource adjustment status factors to generate forest resource survey factors, it is possible to comprehensively analyze the status of forest resources from multiple dimensions, thereby improving the effectiveness and accuracy of forest resource surveys, further clarifying key issues and measures for forest resource protection and management, and providing a basis and support for managers to formulate scientific and feasible forest resource management strategies.

[0012] Preferably, step S1 includes the following steps:

[0013] Step S11: using space remote sensing imaging technology to collect and process images of forest resources within the survey area to obtain a forest resource survey image;

[0014] Step S12: performing data format conversion processing on the forest resource survey image using image format conversion technology to obtain initial forest resource survey data;

[0015] Step S13: pre-processing the initial data of the forest resource survey to obtain forest resource survey data;

[0016] Step S14: using a forest resource noise reduction algorithm to perform noise reduction processing on the forest resource survey data to obtain forest resource survey noise reduction data.

[0017] The present invention uses space remote sensing imaging technology to collect and process images of forest resources within the survey area. This space remote sensing imaging technology can realize accurate and rapid remote sensing monitoring and quantitative analysis of forest resources and their surrounding environment, and can obtain large-area, high-precision data at the same time, providing sufficient basic data for subsequent data preprocessing, noise reduction and other steps. By converting the forest resource survey image into the required data format through image format conversion technology, it can facilitate data processing and analysis in subsequent steps, reduce data storage space, and improve data transmission efficiency, thereby providing basic data normalization for subsequent processing and analysis of forest resource surveys. Then, by performing data preprocessing on the initial data of the forest resource survey after format conversion, interference factors that affect the accuracy and reliability of the data can be removed, and systematic errors in the data can be corrected and compensated, thereby improving the quantitative analysis capability and accuracy of the forest resource survey data, and providing a data basis for subsequent noise reduction processing. Finally, using the forest resource noise reduction algorithm to denoise the forest resource survey data can reduce the impact of interference signals on data quality and signal-to-noise ratio, improve the reliability and accuracy of forest resource survey data, and provide accurate data support for subsequent forest resource classification tasks and survey factor generation processes, thereby promoting the protection and sustainable utilization of forest resources.

[0018] Preferably, step S14 includes the following steps:

[0019] Step S141: Calculate the noise value of the forest resource survey data using a forest resource noise reduction algorithm to obtain a forest resource noise value;

[0020] Among them, the forest resource noise reduction algorithm function is as follows:

[0021]

[0022] Where, e(X) is the forest resource noise value, X is the forest resource survey data sample point dataset, n is the number of forest resource survey data sample points, Xl is the lth sample point to be denoised in the forest resource survey data sample point dataset, w(X,X l ) is the noise weight function, s(X,X l ) is the noise power density function, Y l is the observation value of the lth sample point to be denoised in the forest resources survey data sample point dataset, f(X l ) is the noise source kernel function, α is the noise adjustment coefficient, ΔX is the weight increment, β is the weight adjustment parameter, and μ is the correction value of the forest resource noise value;

[0023] The present invention constructs a functional formula for a forest resource noise reduction algorithm. In order to eliminate the impact of noise sources in forest resource survey data on subsequent forest resource classification tasks and forest resource survey factor generation processes, it is necessary to perform noise reduction processing on the forest resource survey data to obtain cleaner and more accurate forest resource survey data. The forest resource noise reduction algorithm can effectively remove noise and interference data in the forest resource survey data. After noise reduction processing, the forest resource survey data is more consistent with the actual situation, which can improve the practicality and reliability of the forest resource survey data, thereby improving the quality and accuracy of the forest resource survey data and providing a reliable data foundation for subsequent survey factor generation work. In addition, the forest resource noise reduction algorithm calculates the noise value of each sample point in the forest resource survey data by using a noise weight function and a noise power density function, thereby obtaining a forest resource noise value. The algorithm function formula fully considers the forest resource survey data sample point dataset X, the number of forest resource survey data sample points n, and the lth sample point to be noise-reduced in the forest resource survey data sample point dataset X. l , noise weight function w(X,X l ), noise power density function s(X,X l ), the observation value Y of the lth sample point to be denoised in the forest resources survey data sample point dataset l , noise source kernel function f(X l ), noise adjustment coefficient α, where the forest resource survey data sample point dataset X, the lth sample point to be denoised in the forest resource survey data sample point dataset X l The mutual correlation between the weight increment ΔX and the weight adjustment parameter β constitutes the noise weight function w(X,X l )relation According to the relationship between the forest resource noise value e(X) and the above parameters, a functional relationship is formed: This formula realizes the noise reduction of forest resource survey data. At the same time, by introducing the correction value μ of the forest resource noise value, it can be adjusted according to special circumstances that occur during the noise reduction process, thereby improving the applicability and stability of the forest resource noise reduction algorithm.

[0024] Step S142: judging the forest resource noise value according to a preset forest resource noise threshold; if the forest resource noise value is greater than or equal to the preset forest resource noise threshold, then eliminating the forest resource survey data corresponding to the forest resource noise value to obtain forest resource survey noise-reduced data;

[0025] Step S143: judging the forest resource noise value according to a preset forest resource noise threshold; if the forest resource noise value is less than the preset forest resource noise threshold, defining the forest resource survey data corresponding to the forest resource noise value as forest resource survey noise reduction data.

[0026] The present invention calculates the noise value of forest resource survey data by setting a suitable forest resource noise reduction algorithm, which can identify and measure the noise and interference signals present in the forest resource survey data, remove the noise signal from the source, enhance the signal-to-noise ratio of the forest resource survey data, and thus improve the accuracy and reliability of the forest resource survey data. The forest resource noise reduction algorithm can more accurately calculate the noise value by combining the noise power density function and the noise weight function, and is particularly suitable for processing data with high mutual noise. Then, according to specific data processing requirements and quality standards, setting a suitable forest resource noise threshold can better meet actual needs. The calculated forest resource noise value is judged according to the preset forest resource noise threshold, which can effectively eliminate forest resource survey data with large forest resource noise values, avoid the influence of these forest resource survey data with large noise sources on the overall data, help to further improve the data quality of forest resource survey data, remove interference with subsequent classification tasks, and ensure the accuracy and reliability of forest resource survey data. Finally, the forest resource noise value is judged using the preset forest resource noise threshold, and the forest resource survey data with smaller forest resource noise value is defined as forest resource survey noise reduction data. This can obtain more accurate and reliable forest resource survey data, which is less affected by noise and can provide a more stable data basis for subsequent forest resource classification models.

[0027] Preferably, step S2 includes the following steps:

[0028] Step S21: standardizing the forest resource survey noise reduction data to obtain forest resource survey standard data;

[0029] Step S22: using feature extraction technology to perform feature extraction processing on the forest resource survey standard data to obtain forest resource survey data features;

[0030] Step S23: using a preset forest resource classification model based on random forest to classify the forest resource survey data features to obtain forest resource survey type data.

[0031] By standardizing the obtained forest resource survey noise reduction data, the present invention can normalize data differences between different variables in the forest resource survey noise reduction data, remove some data dimensions and outliers, and thus obtain more stable and accurate forest resource survey standard data, which helps improve the accuracy and reliability of subsequent feature extraction and classification tasks. Feature extraction techniques are then used to extract features from the standardized forest resource survey standard data, extracting the most representative feature information from the forest resource survey standard data for subsequent classification tasks based on the random forest algorithm. Different feature extraction methods have different effects, so it is necessary to select an appropriate feature extraction method based on the task characteristics to improve the performance of the classification model. Finally, a preset random forest-based forest resource classification model is used to classify the forest resource survey data features. This forest resource classification model can quickly and accurately classify the extracted feature data and obtain forest resource survey type data. Compared with other classification algorithms, random forests have advantages such as greater robustness, scalability, and applicability to large-scale data sets, making this model more suitable for forest resource classification tasks. Furthermore, classification and prediction using this forest resource classification model make forest resource classification tasks more stable and reliable.

[0032] Preferably, step S23 includes the following steps:

[0033] Step S231: performing data collection and processing on the forest resource survey data characteristics to obtain a forest resource survey characteristic data set;

[0034] Step S232: dividing the forest resource survey feature dataset into a training dataset, a validation dataset, and a test dataset according to a preset division rule;

[0035] Step S233: constructing a forest resource classification model based on random forest, wherein the forest resource classification model includes model training, model validation and model evaluation;

[0036] Step S234: inputting the training data set into the forest resource classification model based on random forest to perform model training, and optimizing the model parameters through the cross-validation method to obtain a verification model; inputting the verification data set into the verification model to perform model verification to obtain a test model;

[0037] Step S235: Input the test data set into the test model after parameter optimization for model evaluation to obtain an optimized forest resource classification model; and re-input the forest resource survey feature data set into the optimized forest resource classification model for classification processing to obtain forest resource survey type data.

[0038] By performing data collection and processing on extracted forest resource survey data features, the present invention can extract useful feature datasets from the data for subsequent model construction and classification, helping to reduce the complexity of unprocessed data and clarify the objectives of forest resource classification tasks. By partitioning the collected forest resource survey feature dataset, model overfitting can be effectively avoided and the model's stability and generalization ability can be evaluated. By dividing the forest resource survey feature dataset into training, validation, and test datasets, managers can better determine the model's performance and reliability. Subsequently, a random forest-based forest resource classification model is constructed. This forest resource classification model, utilizing the random forest algorithm, offers efficient and accurate classification capabilities. Compared to other classification algorithms, random forests offer advantages such as greater robustness, scalability, and suitability for large datasets, making this forest resource classification model more suitable for forest resource classification tasks. Model training and cross-validation methods can optimize model parameters and improve the accuracy of the forest resource classification model. The cross-validation method can avoid variance issues associated with forest resource classification models, resulting in a forest resource classification model with higher predictive power. The performance of the forest resource classification model is evaluated using validation and test datasets to ensure its generalization and reliability. Model evaluation can be performed on the optimized forest resource classification model, helping to determine the validity and reliability of the model's classification capabilities and providing decision support for subsequent forest resource surveys and management. Finally, by applying the optimized forest resource classification model to the forest resource survey feature dataset, forest resources can be accurately classified into different categories, providing managers with more accurate forest resource information.

[0039] Preferably, step S3 includes the following steps:

[0040] Step S31: Analyze and process the forest resource survey type data using factor analysis technology, wherein the factor analysis technology includes factor collection technology, factor loading algorithm and factor rotation technology;

[0041] Step S32: using factor collection technology to perform factor collection processing on forest resource survey type data to obtain forest resource factor data;

[0042] Step S33: performing a related load operation on the forest resource factor data using a factor load algorithm to obtain a forest resource factor load value;

[0043] Step S34: Using factor rotation technology to perform correlation attenuation processing on the forest resource factor loading value to generate a forest resource status factor.

[0044] This invention utilizes factor analysis techniques to extract key factors or elements from complex forest resource survey data, enabling better understanding and interpretation of complex data sets. Factor analysis compresses multiple variables into a smaller number of factors, enabling better understanding and analysis of data, thereby helping forest resource managers gain a more accurate understanding of forest resource status. This factor analysis technique includes factor collection, factor loading, and factor rotation. Factor collection extracts factors related to forest resources, which can represent a large number of variables in forest resource survey data. Through factor collection, managers can more accurately assess forest resource status and implement targeted management. The factor loading algorithm calculates the correlation between each factor and the original variables and assigns weights to each factor, enabling a more accurate assessment of forest resource status. This allows managers to gain a more comprehensive understanding of forest resource status and implement more scientific management. Factor rotation reduces correlations between factors, making forest resource status factors more independent. This helps forest resource managers gain a more accurate understanding of forest resource status and better guide forest resource survey and management strategies.

[0045] Preferably, the factor loading algorithm function formula in step S33 is specifically:

[0046]

[0047] Where h(θ) is the forest resource factor load value, θ is the variable in the forest resource factor data, N is the number of variables in the forest resource factor data, p is the number of factors in the forest resource factor data, L is the load calculation interval range threshold of the forest resource factor data, ω(θ) is the load contribution weight function, r ij is the correlation coefficient between the i-th variable and the j-th factor in the forest resource factor data, s ij is the load harmonic smoothing parameter between the i-th variable and the j-th factor in the forest resource factor data, and ε is the correction value of the forest resource factor loading value.

[0048] The present invention constructs a formula for a factor load algorithm function, which is used to perform relevant load operations on forest resource factor data and calculate the load value of the forest resource factor, which is then used to generate a forest resource status factor. The factor load algorithm involves multiple parameters, including a load operation interval range threshold, a load contribution weight function, and a load harmonic smoothing parameter. The load contribution weight function determines the contribution degree of each variable to the factor, and the correlation coefficient between the variable and the factor and the load harmonic smoothing parameter are combined to calculate the forest resource factor load value, thereby overcoming the influence of the correlation between different variables and improving the reliability and effectiveness of obtaining the forest resource status factor. The algorithm function formula fully considers the variable θ in the forest resource factor data, the number of variables N in the forest resource factor data, the number of factors p in the forest resource factor data, the load operation interval range threshold L of the forest resource factor data, the load contribution weight function ω(θ), the correlation coefficient r between the i-th variable and the j-th factor in the forest resource factor data ij , the load harmonic smoothing parameter s between the i-th variable and the j-th factor in the forest resource factor data ij According to the correlation between the forest resource factor load value h(θ) and the above parameters, a functional relationship is formed: The correlation load calculation of forest resource factor data is realized. At the same time, the introduction of the correction value ε of the forest resource factor loading value can be adjusted according to the actual situation, thereby improving the adaptability and accuracy of the factor loading algorithm.

[0049] Preferably, step S4 includes the following steps:

[0050] Step S41: performing real-time monitoring and evaluation processing on the forest resource status factor through an adaptive evaluation algorithm to obtain a forest resource adaptive status factor;

[0051] Among them, the adaptive evaluation algorithm function is as follows:

[0052]

[0053] Where S(R,t) is the adaptive state factor of forest resources at the current time variable t and regional range position R, c R is the amount of forest resources flowing through the regional range position R per unit time, Ω is the adaptive assessment monitoring area, γ(R,t;τ) is the adaptive adjustment parameter function, τ is the time difference with the current time variable t, is the risk factor contribution index function, x is the horizontal position within the region, y is the vertical position within the region, H(R,x,y,τ) is the spatiotemporal cross-weight function, is the revised value of the adaptive state factor of forest resources;

[0054] The present invention constructs a formula for an adaptive assessment algorithm function for real-time monitoring and assessment of forest resource status factors. The adaptive assessment algorithm calculates an accurate forest resource adaptive status factor by comprehensively considering factors such as the amount of forest resources within the regional scope, setting appropriate adaptive adjustment parameter functions, risk factor contribution index functions, and spatiotemporal cross-weight functions, providing data support for the subsequent adaptive adjustment factor weighting process. The algorithm function formula fully considers the current time variable t, the regional scope location R, and the amount of forest resources c flowing through the regional scope location R per unit time. R , adaptive assessment monitoring area Ω, adaptive adjustment parameter function γ(R,t;τ), time difference τ with the current time variable t, risk factor contribution index function The horizontal position x within the regional range, the vertical position y within the regional range, the spatiotemporal cross-weight function H(R,x,y,τ), and the mutual correlation between the forest resource adaptive state factor S(R,t) and the above parameters form a functional relationship This formula realizes the real-time monitoring and evaluation of forest resource status factors. At the same time, the correction value of the forest resource adaptive status factor in the algorithm function formula is Adjustments can be made according to actual conditions to improve the accuracy and applicability of the adaptive evaluation algorithm.

[0055] Step S42: adding an adjustment factor weight to the forest resource adaptive state factor by introducing a factor weight mechanism, and calculating an adjustment weight value of the adjustment factor weight of the forest resource adaptive state factor using a weight adjustment algorithm to obtain a weight adjustment value;

[0056] Step S43: The weight adjustment value is judged according to a preset adjustment threshold. If the weight adjustment value is greater than or equal to the preset adjustment threshold, the forest resource adaptive state factor corresponding to the weight adjustment value is dynamically adjusted to generate a forest resource adjustment state factor.

[0057] Step S44: The weight adjustment value is judged according to the preset adjustment threshold. If the weight adjustment value is less than the preset adjustment threshold, the forest resource adaptive state factor corresponding to the weight adjustment value is re-iteratively adjusted until the weight adjustment value is greater than or equal to the preset adjustment threshold.

[0058] The present invention implements a suitable adaptive assessment algorithm for real-time monitoring and assessment of forest resource status factors, enabling rapid understanding of the current state of forest resources and timely response to abnormal situations. The adaptive assessment algorithm can calculate in real time based on current monitoring data to obtain a relatively accurate forest resource adaptive status factor, thereby providing a solid basis for targeted forest management and facilitating the sustainable utilization and protection of forest resources. Then, by introducing a factor weighting mechanism, adjustment factor weights are added to the forest resource adaptive status factor, enabling weighted processing based on the importance of different factors, resulting in a more accurate calculation of the forest resource adaptive status factor. Finally, the weight adjustment value calculated by the weight adjustment algorithm is evaluated against a preset adjustment threshold, enabling better control of the adjustment range of the factor weights and ensuring the stability and accuracy of forest resource adjustment. If the weight adjustment value is greater than or equal to the preset adjustment threshold, dynamic adjustment of the current factor weights is required. This dynamic adjustment generates a forest resource adjustment status factor to ensure the timeliness and effectiveness of forest resource adjustment. However, if the weight adjustment value is less than the preset adjustment threshold, the current factor weights are very close to the expected values, and the forest resource adaptive status factor corresponding to these factor weights does not require real-time adjustment, allowing monitoring and assessment to resume in the next time period. If adjustments are still needed, the factor weights can be iteratively adjusted again until the weight adjustment value reaches the preset adjustment threshold, thereby providing a more scientific basis for subsequent forest resource adjustments.

[0059] Preferably, the weight adjustment algorithm function formula in step S42 is specifically:

[0060]

[0061] Where Δω is the weight adjustment value, Σ is the forest resource survey area, T1 is the initial time of the weight adjustment process, T2 is the end time of the weight adjustment process, and x ′ is the horizontal position of the forest resource adaptive state factor within the survey area, y ′ is the vertical position of the forest resource adaptive state factor within the survey area, T is the time variable of the weight adjustment process, G(x ′ ,y ′ , T) is the adjustment factor weight of the forest resource adaptive state factor, A(x ′ ,y ′ , T) is the weight of the adjustment factor to be adjusted, B(x ′ ,y ′ ,T) is the control adjustment factor of the adjustment factor weight, C(x ′ ,y ′ ,T) is the degree of adjustment factor weight, D(x ′ ,y′ ,T) is the normalization coefficient of the weight adjustment process, and ∈ is the correction value of the weight adjustment value.

[0062] The present invention constructs a formula for a weight adjustment algorithm function, which is used to calculate the adjustment weights of the adjustment factor of the forest resource adaptive state factor. The weight adjustment algorithm introduces a factor weight mechanism into the forest resource adaptive state factor to calculate the weight adjustment value. Then, according to a preset adjustment threshold, the forest resource adaptive state factor is dynamically adjusted or the adjustment factor weight is re-iterated to achieve the purpose of real-time assessment of forest resource status and corresponding adjustments. In the weight adjustment algorithm, the control adjustment factor is one of the important parameters. By limiting the range of variation of the adjustment factor weight of the adaptive state factor, it achieves control and stability of the weight adjustment and avoids unnecessary losses caused by over-adjustment. At the same time, the introduction of the degree coefficient and the normalization coefficient helps to ensure the effectiveness and reliability of the weight adjustment process, making the evaluation results more accurate and reliable. The algorithm function formula fully considers the forest resource survey range area Σ, the initial time T1 of the weight adjustment process, the end time T2 of the weight adjustment process, and the horizontal position x of the forest resource adaptive state factor within the survey range. ′ , the vertical position y of the forest resource adaptive state factor within the survey area ′ , the time variable T of the weight adjustment process, the adjustment factor weight G(x ′ ,y ′ ,T), the adjustment factor weight to be adjusted A(x ′ ,y ′ ,T), the control adjustment factor B(x ′ ,y ′ ,T), the degree of adjustment factor weight coefficient C(x ′ ,y ′ ,T), the normalization coefficient D(x ′ ,y ′ ,T), a functional relationship is formed according to the relationship between the weight adjustment value Δω and the above parameters The calculation of the adjustment weight of the adjustment factor weight of the forest resource adaptive state factor is realized. At the same time, the introduction of the correction value ∈ of the weight adjustment value can be adjusted according to the actual situation, thereby improving the adaptability and accuracy of the weight adjustment algorithm.

[0063] Preferably, step S5 includes the following steps:

[0064] Step S51: using a hierarchical assessment technique to comprehensively assess the forest resource adjustment status factors to generate forest resource survey factors;

[0065] Step S52: Perform real-time monitoring, analysis, and processing on forest resource survey factors to obtain forest resource survey information;

[0066] Step S53: Formulate a forest resource survey report based on the forest resource survey information, and use the forest resource survey report to implement a corresponding adaptive forest resource survey strategy for the forest resources within the survey area.

[0067] The present invention utilizes hierarchical assessment technology to perform comprehensive assessment processing, which can help divide different levels and classify and layer adjustment status factors, facilitating a more comprehensive understanding of the status of forest resources and the effective management and protection of forest resources. Furthermore, through comprehensive assessment processing, important factors affecting forest resources can be identified, providing guidance for subsequent investigations and monitoring. Then, by performing real-time monitoring and analysis on the generated forest resource survey factors, the current status of forest resources can be quickly understood, allowing for timely responses to abnormal situations. Simultaneously, real-time monitoring can also provide long-term monitoring data, providing a solid basis for targeted forest management and facilitating the sustainable utilization and protection of forest resources. Finally, based on the forest resource survey report, a corresponding adaptive forest resource survey strategy can be formulated. Based on the survey results, specific protection and management measures can be planned to prevent and avoid the damage to forest resources caused by abnormal factors, improve the efficiency of forest resource utilization, and protect the sustainable development of the ecosystem. Furthermore, based on the results of the forest resource survey report, relevant policies can be revised and improved to improve the effectiveness and level of forest resource management. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0069] Figure 1 Schematic diagram of the process flow of the adaptive forest resource survey factor generation method of the present invention;

[0070] Figure 2 for Figure 1 Detailed step flow diagram of step S1;

[0071] Figure 3 for Figure 2 Detailed step flow diagram of step S14;

[0072] Figure 4 for Figure 1 Detailed step flow diagram of step S2;

[0073] Figure 5 for Figure 4 Detailed step flow diagram of step S23 in FIG. DETAILED DESCRIPTION

[0074] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the embodiments described 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 those skilled in the art without making any creative work are within the scope of protection of the present invention.

[0075] In addition, the accompanying drawings are merely schematic illustrations of the present invention and are not necessarily drawn to scale. Identical reference numerals in the figures denote identical or similar parts, and thus repetitive descriptions thereof will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically separate entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor and / or microcontroller approaches.

[0076] It should be understood that although the terms "first," "second," and the like may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used solely to distinguish one element from another. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element, without departing from the scope of the exemplary embodiments. The term "and / or" as used herein includes any and all combinations of one or more of the listed associated items.

[0077] To achieve this, please refer to Figures 1 to 5 The present invention provides an adaptive forest resource survey factor generation method, which comprises the following steps:

[0078] Step S1: using spatial remote sensing imaging technology to collect and process forest resources within the survey area to obtain forest resource survey data; using a forest resource noise reduction algorithm to perform noise reduction on the forest resource survey data to obtain forest resource survey noise reduction data;

[0079] Step S2: Using feature extraction technology to perform feature extraction processing on the forest resource survey noise reduction data to obtain forest resource survey data features; classifying the forest resource survey data features according to a preset forest resource classification model to obtain forest resource survey type data;

[0080] Step S3: Analyze and process the forest resource survey type data using factor analysis technology to generate forest resource status factors;

[0081] Step S4: real-time monitoring and evaluation of the forest resource status factor is performed using an adaptive evaluation algorithm to obtain a forest resource adaptive status factor; and the weight of the forest resource adaptive status factor is dynamically adjusted using a weight adjustment algorithm that introduces a factor weight mechanism to generate a forest resource adjustment status factor.

[0082] Step S5: Use hierarchical assessment technology to conduct a comprehensive assessment of the forest resource adjustment status factors to generate forest resource survey factors; formulate a forest resource survey report based on the forest resource survey factors to implement the corresponding adaptive forest resource survey strategy.

[0083] In the embodiment of the present invention, please refer to Figure 1 FIG. 1 is a flow chart showing the steps of the adaptive forest resource survey factor generation method of the present invention. In this example, the steps of the adaptive forest resource survey factor generation method include:

[0084] Step S1: using spatial remote sensing imaging technology to collect and process forest resources within the survey area to obtain forest resource survey data; using a forest resource noise reduction algorithm to perform noise reduction on the forest resource survey data to obtain forest resource survey noise reduction data;

[0085] The present invention uses remote sensing satellites to acquire high-resolution remote sensing images of the forest resource survey area. Space-based remote sensing imaging technology is then used to collect and process the high-resolution remote sensing images of each area to obtain forest resource survey data. Then, an appropriate forest resource noise reduction algorithm is constructed by setting appropriate parameters, including a noise weight function, a noise power density function, a noise source kernel function, a noise adjustment coefficient, a weight adjustment parameter, a weight increment, and a correction value. The algorithm is used to eliminate the effects of noise sources in the forest resource survey data, ultimately obtaining noise-reduced forest resource survey data.

[0086] Step S2: Using feature extraction technology to perform feature extraction processing on the forest resource survey noise reduction data to obtain forest resource survey data features; classifying the forest resource survey data features according to a preset forest resource classification model to obtain forest resource survey type data;

[0087] This embodiment of the present invention uses feature extraction technology to process forest resource survey noise reduction data, extracting data features related to forest resource anomalies to obtain forest resource survey data features. Then, a suitable forest resource classification model is constructed using the random forest algorithm. The extracted forest resource survey data features are used as input to the forest resource classification model to classify different forest resource types, ultimately obtaining forest resource survey type data.

[0088] Step S3: Analyze and process the forest resource survey type data using factor analysis technology to generate forest resource status factors;

[0089] The embodiment of the present invention analyzes and processes forest resource survey type data by integrating factor collection technology, factor loading algorithm and factor rotation technology, compresses the forest resource survey type data into factors, and finally generates forest resource status factors. The factor collection technology extracts factors related to abnormal forest resource conditions by extracting and screening factors from the forest resource survey type data. The factor loading algorithm determines the factor loading value corresponding to each factor by calculating the correlation between each collected factor and the variables in the forest resource survey type data. The factor rotation technology reduces the correlation between each factor to make each factor independent.

[0090] Step S4: real-time monitoring and evaluation of the forest resource status factor is performed using an adaptive evaluation algorithm to obtain a forest resource adaptive status factor; and the weight of the forest resource adaptive status factor is dynamically adjusted using a weight adjustment algorithm that introduces a factor weight mechanism to generate a forest resource adjustment status factor.

[0091] The present invention provides a suitable adaptive assessment algorithm and uses it to monitor and assess forest resource status factors in real time to obtain forest resource adaptive status factors. Then, an adjustment factor weight is added to each forest resource adaptive status factor by introducing a factor weight mechanism, and an initial value for each adjustment factor weight is determined. An appropriate weight adjustment algorithm is constructed using relevant parameters, and the constructed weight adjustment algorithm is used to dynamically adjust the adjustment factor weights of the forest resource adaptive status factors. The results determine whether the corresponding forest resource adaptive status factors need to be adjusted, ultimately generating the forest resource adjustment status factors.

[0092] Step S5: Use hierarchical assessment technology to conduct a comprehensive assessment of the forest resource adjustment status factors to generate forest resource survey factors; formulate a forest resource survey report based on the forest resource survey factors to implement the corresponding adaptive forest resource survey strategy.

[0093] This embodiment of the present invention uses a hierarchical assessment technique to classify forest resource adjustment status factors into different levels, establishes a corresponding evaluation index system and criteria, and then performs a categorized and hierarchical assessment of the forest resource survey adjustment status factors. The scores for each evaluation index are calculated, and a comprehensive assessment of the forest resource status is conducted to generate forest resource survey factors. A forest resource survey report is then prepared based on the generated forest resource survey factors, and the report is used to implement the corresponding adaptive forest resource survey strategy for the forest resources within the survey area.

[0094] The present invention can quickly obtain forest resource survey data over a large area by using spatial remote sensing imaging technology. The forest resource denoising algorithm is used to perform denoising processing on the forest resource survey data obtained by spatial remote sensing imaging technology. This can effectively reduce the noise source of the forest resource survey data and avoid the influence of noise sources and interference signals in the forest resource survey data on the subsequent generation process of forest resource survey factors, thereby improving the accuracy and reliability of the forest resource survey data, thereby providing clear and accurate basic data for subsequent forest resource classification tasks and forest resource survey factor generation processes, and providing data support for forest resource protection and management. By selecting a suitable feature extraction technology to extract features from the forest resource survey denoised data and constructing an appropriate forest resource classification model for classification processing, the obtained complex forest resource survey data can be converted into processable forest resource survey type data, providing a data processing basis for the subsequent factor analysis generation process, thereby achieving refined management and protection of forest resources. Then, the obtained forest resource survey data is analyzed and processed using factor analysis technology, and key factors affecting forest resource health and ecosystems can be extracted from the perspective of data dimensions, providing a basis for subsequent adaptive evaluation and adjustment, thereby improving the feasibility and effectiveness of forest resource management and protection. By setting up an appropriate adaptive assessment algorithm to monitor and evaluate forest resource status factors in real time and introducing adjustment factor weights for dynamic adjustment, it is possible to monitor and adjust forest resource status factors in real time, and promptly address abnormal forest resource conditions, thereby better protecting forest resources and reducing resource waste and loss. Finally, by setting up an appropriate hierarchical assessment technology to comprehensively evaluate the adjusted forest resource adjustment status factors to generate forest resource survey factors, it is possible to comprehensively analyze the status of forest resources from multiple dimensions, thereby improving the effectiveness and accuracy of forest resource surveys, further clarifying key issues and measures for forest resource protection and management, and providing a basis and support for managers to formulate scientific and feasible forest resource management strategies.

[0095] Preferably, step S1 includes the following steps:

[0096] Step S11: using space remote sensing imaging technology to collect and process images of forest resources within the survey area to obtain a forest resource survey image;

[0097] Step S12: performing data format conversion processing on the forest resource survey image using image format conversion technology to obtain initial forest resource survey data;

[0098] Step S13: pre-processing the initial data of the forest resource survey to obtain forest resource survey data;

[0099] Step S14: denoising the forest resource survey data using a forest resource denoising algorithm to obtain forest resource survey denoised data.

[0100] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed step flow diagram of step S1 in FIG. 1 , in this embodiment, step S1 includes the following steps:

[0101] Step S11: using space remote sensing imaging technology to collect and process images of forest resources within the survey area to obtain a forest resource survey image;

[0102] The embodiment of the present invention obtains high-resolution remote sensing image data within the forest resource survey area by using remote sensing satellites, and preprocesses the obtained high-resolution remote sensing image data through radiation correction to improve image quality. Then, the processed high-resolution remote sensing image data is divided into regions, and image processing and feature extraction are performed on the image data of each region using space remote sensing imaging technology to finally obtain a forest resource survey image.

[0103] Step S12: performing data format conversion processing on the forest resource survey image using image format conversion technology to obtain initial forest resource survey data;

[0104] The embodiment of the present invention selects an appropriate image format conversion technology to perform data format conversion on a forest resource survey image, converts the forest resource survey image into a required data format, and finally obtains initial forest resource survey data.

[0105] Step S13: pre-processing the initial data of the forest resource survey to obtain forest resource survey data;

[0106] The embodiment of the present invention performs processing such as filling missing values, removing duplicate values, abnormal values, invalid values, and normalization on the converted initial forest resource survey data to finally obtain forest resource survey data.

[0107] Step S14: denoising the forest resource survey data using a forest resource denoising algorithm to obtain forest resource survey denoised data.

[0108] The embodiment of the present invention constructs an appropriate forest resource noise reduction algorithm by setting appropriate parameters such as noise weight function, noise power density function, noise source kernel function, noise adjustment coefficient, weight adjustment parameter, weight increment and correction value, and uses the constructed forest resource noise reduction algorithm to eliminate the influence of noise sources in forest resource survey data, and finally obtain forest resource survey noise reduction data.

[0109] The present invention uses space remote sensing imaging technology to collect and process images of forest resources within the survey area. This space remote sensing imaging technology can realize accurate and rapid remote sensing monitoring and quantitative analysis of forest resources and their surrounding environment, and can obtain large-area, high-precision data at the same time, providing sufficient basic data for subsequent data preprocessing, noise reduction and other steps. By converting the forest resource survey image into the required data format through image format conversion technology, it can facilitate data processing and analysis in subsequent steps, reduce data storage space, and improve data transmission efficiency, thereby providing basic data normalization for subsequent processing and analysis of forest resource surveys. Then, by performing data preprocessing on the initial data of the forest resource survey after format conversion, interference factors that affect the accuracy and reliability of the data can be removed, and systematic errors in the data can be corrected and compensated, thereby improving the quantitative analysis capability and accuracy of the forest resource survey data, and providing a data basis for subsequent noise reduction processing. Finally, using the forest resource noise reduction algorithm to denoise the forest resource survey data can reduce the impact of interference signals on data quality and signal-to-noise ratio, improve the reliability and accuracy of forest resource survey data, and provide accurate data support for subsequent forest resource classification tasks and survey factor generation processes, thereby promoting the protection and sustainable utilization of forest resources.

[0110] Preferably, step S14 includes the following steps:

[0111] Step S141: Calculate the noise value of the forest resource survey data using a forest resource noise reduction algorithm to obtain a forest resource noise value;

[0112] Among them, the forest resource noise reduction algorithm function is as follows:

[0113]

[0114] Where, e(X) is the forest resource noise value, X is the forest resource survey data sample point dataset, n is the number of forest resource survey data sample points, X l is the lth sample point to be denoised in the forest resource survey data sample point dataset, w(X,X l ) is the noise weight function, s(X,X l ) is the noise power density function, Y l is the observation value of the lth sample point to be denoised in the forest resources survey data sample point dataset, f(X l ) is the noise source kernel function, α is the noise adjustment coefficient, ΔX is the weight increment, β is the weight adjustment parameter, and μ is the correction value of the forest resource noise value;

[0115] Step S142: judging the forest resource noise value according to a preset forest resource noise threshold; if the forest resource noise value is greater than or equal to the preset forest resource noise threshold, then eliminating the forest resource survey data corresponding to the forest resource noise value to obtain forest resource survey noise-reduced data;

[0116] Step S143: judging the forest resource noise value according to a preset forest resource noise threshold; if the forest resource noise value is less than the preset forest resource noise threshold, defining the forest resource survey data corresponding to the forest resource noise value as forest resource survey noise reduction data.

[0117] As an embodiment of the present invention, refer to Figure 3 As shown, Figure 2 Detailed step flow diagram of step S14 in the embodiment, step S14 includes the following steps:

[0118] Step S141: Calculate the noise value of the forest resource survey data using a forest resource noise reduction algorithm to obtain a forest resource noise value;

[0119] The embodiment of the present invention constructs an appropriate forest resource noise reduction algorithm by setting appropriate parameters such as noise weight function, noise power density function, noise source kernel function, noise adjustment coefficient, weight adjustment parameter, weight increment and correction value, and adjusts the parameters according to the actual situation in the noise reduction process, so that the constructed forest resource noise reduction algorithm is more accurate. The noise value of each sample point in the forest resource survey data is calculated through the constructed forest resource noise reduction algorithm, and finally the forest resource noise value is obtained.

[0120] Among them, the forest resource noise reduction algorithm function is as follows:

[0121]

[0122] Where, e(X) is the forest resource noise value, X is the forest resource survey data sample point dataset, n is the number of forest resource survey data sample points, X l is the lth sample point to be denoised in the forest resource survey data sample point dataset, w(X,X l ) is the noise weight function, s(X,X l ) is the noise power density function, Y l is the observation value of the lth sample point to be denoised in the forest resources survey data sample point dataset, f(X l ) is the noise source kernel function, α is the noise adjustment coefficient, ΔX is the weight increment, β is the weight adjustment parameter, and μ is the correction value of the forest resource noise value;

[0123] The present invention constructs a functional formula for a forest resource noise reduction algorithm. In order to eliminate the impact of noise sources in forest resource survey data on subsequent forest resource classification tasks and forest resource survey factor generation processes, it is necessary to perform noise reduction processing on the forest resource survey data to obtain cleaner and more accurate forest resource survey data. The forest resource noise reduction algorithm can effectively remove noise and interference data in the forest resource survey data. After noise reduction processing, the forest resource survey data is more consistent with the actual situation, which can improve the practicality and reliability of the forest resource survey data, thereby improving the quality and accuracy of the forest resource survey data and providing a reliable data foundation for subsequent survey factor generation work. In addition, the forest resource noise reduction algorithm calculates the noise value of each sample point in the forest resource survey data by using a noise weight function and a noise power density function, thereby obtaining a forest resource noise value. The algorithm function formula fully considers the forest resource survey data sample point dataset X, the number of forest resource survey data sample points n, and the lth sample point to be noise-reduced in the forest resource survey data sample point dataset X. l , noise weight function w(X,X l ), noise power density function s(X,X l ), the observation value Y of the lth sample point to be denoised in the forest resources survey data sample point dataset l , noise source kernel function f(X l ), noise adjustment coefficient α, where the forest resource survey data sample point dataset X, the lth sample point to be denoised in the forest resource survey data sample point dataset X l The mutual correlation between the weight increment ΔX and the weight adjustment parameter β constitutes the noise weight function w(X,X l )relation According to the relationship between the forest resource noise value e(X) and the above parameters, a functional relationship is formed: This formula realizes the noise reduction of forest resource survey data. At the same time, by introducing the correction value μ of the forest resource noise value, it can be adjusted according to special circumstances that occur during the noise reduction process, thereby improving the applicability and stability of the forest resource noise reduction algorithm.

[0124] Step S142: judging the forest resource noise value according to a preset forest resource noise threshold; if the forest resource noise value is greater than or equal to the preset forest resource noise threshold, then eliminating the forest resource survey data corresponding to the forest resource noise value to obtain forest resource survey noise-reduced data;

[0125] The embodiment of the present invention determines whether the calculated forest resource noise value exceeds the preset forest resource noise threshold based on the preset forest resource noise threshold. When the forest resource noise value is greater than or equal to the preset forest resource noise threshold, it indicates that the interference effect of the noise source in the forest resource survey data corresponding to the forest resource noise value is large. In this case, the forest resource survey data corresponding to the forest resource noise value is eliminated, and finally the forest resource survey noise-reduced data is obtained.

[0126] Step S143: judging the forest resource noise value according to a preset forest resource noise threshold; if the forest resource noise value is less than the preset forest resource noise threshold, defining the forest resource survey data corresponding to the forest resource noise value as forest resource survey noise reduction data.

[0127] In an embodiment of the present invention, a calculated forest resource noise value is determined to be greater than a preset forest resource noise threshold value based on the preset forest resource noise threshold value. When the forest resource noise value is less than the preset forest resource noise threshold value, it indicates that the interference effect of the noise source in the forest resource survey data corresponding to the forest resource noise value is relatively small. In this case, the forest resource survey data corresponding to the forest resource noise value is directly defined as forest resource survey noise reduction data.

[0128] The present invention calculates the noise value of forest resource survey data by setting a suitable forest resource noise reduction algorithm, which can identify and measure the noise and interference signals present in the forest resource survey data, remove the noise signal from the source, enhance the signal-to-noise ratio of the forest resource survey data, and thus improve the accuracy and reliability of the forest resource survey data. The forest resource noise reduction algorithm can more accurately calculate the noise value by combining the noise power density function and the noise weight function, and is particularly suitable for processing data with high mutual noise. Then, according to specific data processing requirements and quality standards, setting a suitable forest resource noise threshold can better meet actual needs. The calculated forest resource noise value is judged according to the preset forest resource noise threshold, which can effectively eliminate forest resource survey data with large forest resource noise values, avoid the influence of these forest resource survey data with large noise sources on the overall data, help to further improve the data quality of forest resource survey data, remove interference with subsequent classification tasks, and ensure the accuracy and reliability of forest resource survey data. Finally, the forest resource noise value is judged using the preset forest resource noise threshold, and the forest resource survey data with smaller forest resource noise value is defined as forest resource survey noise reduction data. This can obtain more accurate and reliable forest resource survey data, which is less affected by noise and can provide a more stable data basis for subsequent forest resource classification models.

[0129] Preferably, step S2 includes the following steps:

[0130] Step S21: standardizing the forest resource survey noise reduction data to obtain forest resource survey standard data;

[0131] Step S22: using feature extraction technology to perform feature extraction processing on the forest resource survey standard data to obtain forest resource survey data features;

[0132] Step S23: using a preset forest resource classification model based on random forest to classify the forest resource survey data features to obtain forest resource survey type data.

[0133] As an embodiment of the present invention, refer to Figure 4 As shown, Figure 1 Detailed step flow diagram of step S2 in the embodiment, step S2 includes the following steps:

[0134] Step S21: standardizing the forest resource survey noise reduction data to obtain forest resource survey standard data;

[0135] The embodiment of the present invention first deduplicates the forest resource survey noise reduction data to remove duplicate data to ensure the uniqueness of the forest resource survey noise reduction data, then normalizes the deduplicated forest resource survey noise reduction data, and unifies the unit, resolution, accuracy, etc. of the forest resource survey noise reduction data within a certain standard range to ensure the consistency of the forest resource survey noise reduction data, and finally obtains the forest resource survey standard data.

[0136] Step S22: using feature extraction technology to perform feature extraction processing on the forest resource survey standard data to obtain forest resource survey data features;

[0137] The embodiment of the present invention processes the standardized forest resource survey standard data by using feature extraction technology, extracts data features related to abnormal forest resource conditions, and finally obtains forest resource survey data features.

[0138] Step S23: using a preset forest resource classification model based on random forest to classify the forest resource survey data features to obtain forest resource survey type data.

[0139] The embodiment of the present invention constructs an appropriate forest resource classification model through a random forest algorithm, takes the forest resource survey data features as the input of the forest resource classification model to classify different forest resource types, and finally obtains forest resource survey type data.

[0140] By standardizing the obtained forest resource survey noise reduction data, the present invention can normalize data differences between different variables in the forest resource survey noise reduction data, remove some data dimensions and outliers, and thus obtain more stable and accurate forest resource survey standard data, which helps improve the accuracy and reliability of subsequent feature extraction and classification tasks. Feature extraction techniques are then used to extract features from the standardized forest resource survey standard data, extracting the most representative feature information from the forest resource survey standard data for subsequent classification tasks based on the random forest algorithm. Different feature extraction methods have different effects, so it is necessary to select an appropriate feature extraction method based on the task characteristics to improve the performance of the classification model. Finally, a preset random forest-based forest resource classification model is used to classify the forest resource survey data features. This forest resource classification model can quickly and accurately classify the extracted feature data and obtain forest resource survey type data. Compared with other classification algorithms, random forests have advantages such as greater robustness, scalability, and applicability to large-scale data sets, making this model more suitable for forest resource classification tasks. Furthermore, classification and prediction using this forest resource classification model make forest resource classification tasks more stable and reliable.

[0141] Preferably, step S23 includes the following steps:

[0142] Step S231: performing data collection and processing on the forest resource survey data characteristics to obtain a forest resource survey characteristic data set;

[0143] Step S232: dividing the forest resource survey feature dataset into a training dataset, a validation dataset, and a test dataset according to a preset division rule;

[0144] Step S233: constructing a forest resource classification model based on random forest, wherein the forest resource classification model includes model training, model validation and model evaluation;

[0145] Step S234: inputting the training data set into the forest resource classification model based on random forest to perform model training, and optimizing the model parameters through the cross-validation method to obtain a verification model; inputting the verification data set into the verification model to perform model verification to obtain a test model;

[0146] Step S235: Input the test data set into the test model after parameter optimization for model evaluation to obtain an optimized forest resource classification model; and re-input the forest resource survey feature data set into the optimized forest resource classification model for classification processing to obtain forest resource survey type data.

[0147] As an embodiment of the present invention, refer to Figure 5 As shown, Figure 4 Detailed step flow diagram of step S23 in the embodiment, step S23 includes the following steps:

[0148] Step S231: performing data collection and processing on the forest resource survey data characteristics to obtain a forest resource survey characteristic data set;

[0149] The embodiment of the present invention collects data on forest resource adjustment data features, extracts feature data related to forest resource survey from forest resource survey data features, and finally obtains a forest resource survey feature data set.

[0150] Step S232: dividing the forest resource survey feature dataset into a training dataset, a validation dataset, and a test dataset according to a preset division rule;

[0151] The embodiment of the present invention divides the forest resource survey feature data set into a training data set, a verification data set and a test data set according to a certain division ratio, and divides the forest resource survey feature data set into 70% training data set, 20% verification data set and 10% test data set according to a preset division ratio of 7:2:1.

[0152] Step S233: constructing a forest resource classification model based on random forest, wherein the forest resource classification model includes model training, model validation and model evaluation;

[0153] According to actual conditions, the embodiment of the present invention uses a random forest algorithm to construct a forest resource classification model. The forest resource classification model includes model training, model verification and model evaluation. The forest resource classification model is trained using a training data set, and the forest resource classification model is verified using a verification data set. At the same time, the forest resource classification model is evaluated using a test data set to improve the generalization performance and robustness of the forest resource classification model.

[0154] Step S234: inputting the training data set into the forest resource classification model based on random forest to perform model training, and optimizing the model parameters through the cross-validation method to obtain a verification model; inputting the verification data set into the verification model to perform model verification to obtain a test model;

[0155] The embodiment of the present invention performs model training by inputting the divided training data set into the constructed forest resource classification model, and optimizes the model parameters by selecting an appropriate cross-validation method. First, the training data set is randomly divided into K mutually non-overlapping subsets, where K is usually 5 or 10. K-1 subsets are randomly used as training data for the model, and the remaining 1 subset is used as verification data to evaluate the performance of the model. After repeating the above process K times, a different subset is used as verification data each time to evaluate the model, and K different evaluation results are obtained. Then, the average of the K evaluation results is calculated to obtain the evaluation result of the verification model. Finally, the verification model is used to perform model verification on the divided verification data set to obtain the final test model.

[0156] Step S235: Input the test data set into the test model after parameter optimization for model evaluation to obtain an optimized forest resource classification model; and re-input the forest resource survey feature data set into the optimized forest resource classification model for classification processing to obtain forest resource survey type data.

[0157] The embodiment of the present invention evaluates the model by inputting the divided test data set into the test model after parameter optimization, further checks and optimizes the model parameters by calculating the accuracy, recall rate, F1 value and other indicators of the model, and obtains a more efficient and accurate optimized forest resource classification model. At the same time, the forest resource survey feature data set is re-input into the optimized forest resource classification model for classification processing, and finally the forest resource survey type data is obtained.

[0158] By performing data collection and processing on extracted forest resource survey data features, the present invention can extract useful feature datasets from the data for subsequent model construction and classification, helping to reduce the complexity of unprocessed data and clarify the objectives of forest resource classification tasks. By partitioning the collected forest resource survey feature dataset, model overfitting can be effectively avoided and the model's stability and generalization ability can be evaluated. By dividing the forest resource survey feature dataset into training, validation, and test datasets, managers can better determine the model's performance and reliability. Subsequently, a random forest-based forest resource classification model is constructed. This forest resource classification model, utilizing the random forest algorithm, offers efficient and accurate classification capabilities. Compared to other classification algorithms, random forests offer advantages such as greater robustness, scalability, and suitability for large datasets, making this forest resource classification model more suitable for forest resource classification tasks. Model training and cross-validation methods can optimize model parameters and improve the accuracy of the forest resource classification model. The cross-validation method can avoid variance issues associated with forest resource classification models, resulting in a forest resource classification model with higher predictive power. The performance of the forest resource classification model is evaluated using validation and test datasets to ensure its generalization and reliability. Model evaluation can be performed on the optimized forest resource classification model, helping to determine the validity and reliability of the model's classification capabilities and providing decision support for subsequent forest resource surveys and management. Finally, by applying the optimized forest resource classification model to the forest resource survey feature dataset, forest resources can be accurately classified into different categories, providing managers with more accurate forest resource information.

[0159] Preferably, step S3 includes the following steps:

[0160] Step S31: Analyze and process the forest resource survey type data using factor analysis technology, wherein the factor analysis technology includes factor collection technology, factor loading algorithm and factor rotation technology;

[0161] The embodiment of the present invention analyzes and processes forest resource survey type data by integrating factor collection technology, factor loading algorithm and factor rotation technology, and compresses forest resource survey type data into forest resource status factors. The factor collection technology extracts factors related to abnormal forest resource conditions by extracting and screening factors from forest resource survey type data. The factor loading algorithm determines the factor loading value corresponding to each factor by calculating the correlation between each collected factor and the variables in the forest resource survey type data. The factor rotation technology reduces the correlation between each factor to make each factor independent.

[0162] Step S32: using factor collection technology to perform factor collection processing on forest resource survey type data to obtain forest resource factor data;

[0163] The embodiment of the present invention performs factor extraction and screening processing on forest resource survey type data through a factor collection technology based on a principal component analysis method, and finally obtains forest resource factor data.

[0164] Step S33: performing a related load operation on the forest resource factor data using a factor load algorithm to obtain a forest resource factor load value;

[0165] In an embodiment of the present invention, a correlation load operation is performed on the extracted forest resource factor data using a factor load algorithm composed of a load operation interval range threshold, a load contribution weight function, and a load harmonic smoothing parameter. The load contribution weight function is used to determine the contribution degree of each variable in the forest resource factor data to the factor, and the correlation coefficient between the variable and the factor and the load harmonic smoothing parameter are combined for calculation to finally obtain the forest resource factor load value.

[0166] Step S34: Using factor rotation technology to perform correlation attenuation processing on the forest resource factor loading value to generate a forest resource status factor.

[0167] The embodiment of the present invention performs correlation attenuation processing on the calculated forest resource factor load values through a factor rotation technology based on an orthogonal rotation method, thereby reducing the correlation between each factor and ultimately generating a more independent forest resource status factor.

[0168] This invention utilizes factor analysis techniques to extract key factors or elements from complex forest resource survey data, enabling better understanding and interpretation of complex data sets. Factor analysis compresses multiple variables into a smaller number of factors, enabling better understanding and analysis of data, thereby helping forest resource managers gain a more accurate understanding of forest resource status. This factor analysis technique includes factor collection, factor loading, and factor rotation. Factor collection extracts factors related to forest resources, which can represent a large number of variables in forest resource survey data. Through factor collection, managers can more accurately assess forest resource status and implement targeted management. The factor loading algorithm calculates the correlation between each factor and the original variables and assigns weights to each factor, enabling a more accurate assessment of forest resource status. This allows managers to gain a more comprehensive understanding of forest resource status and implement more scientific management. Factor rotation reduces correlations between factors, making forest resource status factors more independent. This helps forest resource managers gain a more accurate understanding of forest resource status and better guide forest resource survey and management strategies.

[0169] Preferably, the factor loading algorithm function formula in step S33 is specifically:

[0170]

[0171] Where h(θ) is the forest resource factor load value, θ is the variable in the forest resource factor data, N is the number of variables in the forest resource factor data, p is the number of factors in the forest resource factor data, L is the load calculation interval range threshold of the forest resource factor data, ω(θ) is the load contribution weight function, r ij is the correlation coefficient between the i-th variable and the j-th factor in the forest resource factor data, s ij is the load harmonic smoothing parameter between the i-th variable and the j-th factor in the forest resource factor data, and ε is the correction value of the forest resource factor loading value.

[0172] The present invention constructs a formula for a factor load algorithm function, which is used to perform relevant load operations on forest resource factor data and calculate the load value of the forest resource factor, which is then used to generate a forest resource status factor. The factor load algorithm involves multiple parameters, including a load operation interval range threshold, a load contribution weight function, and a load harmonic smoothing parameter. The load contribution weight function determines the contribution degree of each variable to the factor, and the correlation coefficient between the variable and the factor and the load harmonic smoothing parameter are combined to calculate the forest resource factor load value, thereby overcoming the influence of the correlation between different variables and improving the reliability and effectiveness of obtaining the forest resource status factor. The algorithm function formula fully considers the variable θ in the forest resource factor data, the number of variables N in the forest resource factor data, the number of factors p in the forest resource factor data, the load operation interval range threshold L of the forest resource factor data, the load contribution weight function ω(θ), the correlation coefficient r between the i-th variable and the j-th factor in the forest resource factor data ij , the load harmonic smoothing parameter s between the i-th variable and the j-th factor in the forest resource factor data ij According to the correlation between the forest resource factor load value h(θ) and the above parameters, a functional relationship is formed: The correlation load calculation of forest resource factor data is realized. At the same time, the introduction of the correction value ε of the forest resource factor loading value can be adjusted according to the actual situation, thereby improving the adaptability and accuracy of the factor loading algorithm.

[0173] Preferably, step S4 includes the following steps:

[0174] Step S41: performing real-time monitoring and evaluation processing on the forest resource status factor through an adaptive evaluation algorithm to obtain a forest resource adaptive status factor;

[0175] The embodiment of the present invention constructs an appropriate adaptive assessment algorithm by setting appropriate adaptive adjustment parameter functions, risk factor contribution index functions, spatiotemporal cross weight functions and other factors and related parameters, and uses the set adaptive assessment algorithm to perform real-time monitoring and assessment processing on the forest resource status factor, and finally obtains the forest resource adaptive status factor.

[0176] Among them, the adaptive evaluation algorithm function is as follows:

[0177]

[0178] Where S(R,t) is the adaptive state factor of forest resources at the current time variable t and regional range position R, c Ris the amount of forest resources flowing through the regional range position R per unit time, Ω is the adaptive assessment monitoring area, γ(R,t;τ) is the adaptive adjustment parameter function, τ is the time difference with the current time variable t, is the risk factor contribution index function, x is the horizontal position within the region, y is the vertical position within the region, H(R,x,y,τ) is the spatiotemporal cross-weight function, is the revised value of the adaptive state factor of forest resources;

[0179] The present invention constructs a formula for an adaptive assessment algorithm function for real-time monitoring and assessment of forest resource status factors. The adaptive assessment algorithm calculates an accurate forest resource adaptive status factor by comprehensively considering factors such as the amount of forest resources within the regional scope, setting appropriate adaptive adjustment parameter functions, risk factor contribution index functions, and spatiotemporal cross-weight functions, providing data support for the subsequent adaptive adjustment factor weighting process. The algorithm function formula fully considers the current time variable t, the regional scope location R, and the amount of forest resources c flowing through the regional scope location R per unit time. R , adaptive assessment monitoring area Ω, adaptive adjustment parameter function γ(R,t;τ), time difference τ with the current time variable t, risk factor contribution index function The horizontal position x within the regional range, the vertical position y within the regional range, the spatiotemporal cross-weight function H(R,x,y,τ), and the mutual correlation between the forest resource adaptive state factor S(R,t) and the above parameters form a functional relationship This formula realizes the real-time monitoring and evaluation of forest resource status factors. At the same time, the correction value of the forest resource adaptive status factor in the algorithm function formula is Adjustments can be made according to actual conditions to improve the accuracy and applicability of the adaptive evaluation algorithm.

[0180] Step S42: adding an adjustment factor weight to the forest resource adaptive state factor by introducing a factor weight mechanism, and calculating an adjustment weight value of the adjustment factor weight of the forest resource adaptive state factor using a weight adjustment algorithm to obtain a weight adjustment value;

[0181] The embodiment of the present invention introduces a factor weight mechanism to add an adjustment factor weight to each forest resource adaptive state factor, determines the initial value of each adjustment factor weight, and constructs an appropriate weight adjustment algorithm by selecting appropriate control adjustment factors, measurement degree coefficients, normalization coefficients and related parameters. The constructed weight adjustment algorithm is used to calculate the adjustment weights of the adjustment factor weights of the forest resource adaptive state factors, and the calculation results are used to determine whether the corresponding forest resource adaptive state factors need to be adjusted, and finally obtain the weight adjustment value.

[0182] Step S43: The weight adjustment value is judged according to a preset adjustment threshold. If the weight adjustment value is greater than or equal to the preset adjustment threshold, the forest resource adaptive state factor corresponding to the weight adjustment value is dynamically adjusted to generate a forest resource adjustment state factor.

[0183] The embodiment of the present invention determines whether the calculated weight adjustment value exceeds the preset adjustment threshold based on the preset adjustment threshold. When the weight adjustment value is greater than or equal to the preset adjustment threshold, it means that the adjustment factor weight of the forest resource adaptive state factor corresponding to the weight adjustment value has a large impact, and the forest resource adaptive state factor needs to be dynamically adjusted to finally generate the forest resource adjustment state factor.

[0184] Step S44: The weight adjustment value is judged according to the preset adjustment threshold. If the weight adjustment value is less than the preset adjustment threshold, the forest resource adaptive state factor corresponding to the weight adjustment value is re-iteratively adjusted until the weight adjustment value is greater than or equal to the preset adjustment threshold.

[0185] The embodiment of the present invention determines whether the calculated weight adjustment value exceeds the preset adjustment threshold based on the preset adjustment threshold. When the weight adjustment value is less than the preset adjustment threshold, it means that the adjustment factor weight of the forest resource adaptive state factor corresponding to the weight adjustment value has little effect, and the current forest resource adaptive state factor is close to the expected value. In this case, the forest resource adaptive state factor corresponding to the weight adjustment value does not need to be dynamically adjusted, and the monitoring and adjustment processing is restarted in the next period, and the adjustment factor weight is re-iterated until the calculated weight adjustment value is greater than or equal to the preset adjustment threshold.

[0186] The present invention implements a suitable adaptive assessment algorithm for real-time monitoring and assessment of forest resource status factors, enabling rapid understanding of the current state of forest resources and timely response to abnormal situations. The adaptive assessment algorithm can calculate in real time based on current monitoring data to obtain a relatively accurate forest resource adaptive status factor, thereby providing a solid basis for targeted forest management and facilitating the sustainable utilization and protection of forest resources. Then, by introducing a factor weighting mechanism, adjustment factor weights are added to the forest resource adaptive status factor, enabling weighted processing based on the importance of different factors, resulting in a more accurate calculation of the forest resource adaptive status factor. Finally, the weight adjustment value calculated by the weight adjustment algorithm is evaluated against a preset adjustment threshold, enabling better control of the adjustment range of the factor weights and ensuring the stability and accuracy of forest resource adjustment. If the weight adjustment value is greater than or equal to the preset adjustment threshold, dynamic adjustment of the current factor weights is required. This dynamic adjustment generates a forest resource adjustment status factor to ensure the timeliness and effectiveness of forest resource adjustment. However, if the weight adjustment value is less than the preset adjustment threshold, the current factor weights are very close to the expected values, and the forest resource adaptive status factor corresponding to these factor weights does not require real-time adjustment, allowing monitoring and assessment to resume in the next time period. If adjustments are still needed, the factor weights can be iteratively adjusted again until the weight adjustment value reaches the preset adjustment threshold, thereby providing a more scientific basis for subsequent forest resource adjustments.

[0187] Preferably, the weight adjustment algorithm function formula in step S42 is specifically:

[0188]

[0189] Where Δω is the weight adjustment value, Σ is the forest resource survey area, T1 is the initial time of the weight adjustment process, T2 is the end time of the weight adjustment process, and x ′ is the horizontal position of the forest resource adaptive state factor within the survey area, y ′ is the vertical position of the forest resource adaptive state factor within the survey area, T is the time variable of the weight adjustment process, G(x ′ ,y ′ , T) is the adjustment factor weight of the forest resource adaptive state factor, A(x ′ ,y ′ , T) is the weight of the adjustment factor to be adjusted, B(x ′ ,y ′ ,T) is the control adjustment factor of the adjustment factor weight, C(x ′ ,y ′ ,T) is the degree of adjustment factor weight, D(x ′ ,y′ ,T) is the normalization coefficient of the weight adjustment process, and ∈ is the correction value of the weight adjustment value.

[0190] The present invention constructs a formula for a weight adjustment algorithm function, which is used to calculate the adjustment weights of the adjustment factor of the forest resource adaptive state factor. The weight adjustment algorithm introduces a factor weight mechanism into the forest resource adaptive state factor to calculate the weight adjustment value. Then, according to a preset adjustment threshold, the forest resource adaptive state factor is dynamically adjusted or the adjustment factor weight is re-iterated to achieve the purpose of real-time assessment of forest resource status and corresponding adjustments. In the weight adjustment algorithm, the control adjustment factor is one of the important parameters. By limiting the range of variation of the adjustment factor weight of the adaptive state factor, it achieves control and stability of the weight adjustment and avoids unnecessary losses caused by over-adjustment. At the same time, the introduction of the degree coefficient and the normalization coefficient helps to ensure the effectiveness and reliability of the weight adjustment process, making the evaluation results more accurate and reliable. The algorithm function formula fully considers the forest resource survey range area Σ, the initial time T1 of the weight adjustment process, the end time T2 of the weight adjustment process, and the horizontal position x of the forest resource adaptive state factor within the survey range. ′ , the vertical position y of the forest resource adaptive state factor within the survey area ′ , the time variable T of the weight adjustment process, the adjustment factor weight G(x ′ ,y ′ ,T), the adjustment factor weight to be adjusted A(x ′ ,t ′ ,T), the control adjustment factor B(x ′ ,y ′ ,T), the degree of adjustment factor weight coefficient C(x ′ ,y ′ ,T), the normalization coefficient D(x ′ ,y ′ ,T), a functional relationship is formed according to the relationship between the weight adjustment value Δω and the above parameters The calculation of the adjustment weight of the adjustment factor weight of the forest resource adaptive state factor is realized. At the same time, the introduction of the correction value ∈ of the weight adjustment value can be adjusted according to the actual situation, thereby improving the adaptability and accuracy of the weight adjustment algorithm.

[0191] Preferably, step S5 includes the following steps:

[0192] Step S51: using a hierarchical assessment technique to comprehensively assess the forest resource adjustment status factors to generate forest resource survey factors;

[0193] The present invention utilizes a hierarchical assessment technique to classify forest resource adjustment status factors into different levels. First, forest resource adjustment status factor assessment indicators are determined. These indicators are used to measure and describe the characteristics and properties of the assessment object during the assessment process. Appropriate assessment indicators can be selected based on the nature and characteristics of the assessment object. These indicators may include forest coverage, forest growth status, tree species and number, and land use patterns. Corresponding assessment standards and assessment grading are then established. Assessment standards are defined based on the assessment indicators and used for assessment, judgment, and classification. Assessment standards are developed based on the actual conditions of the assessment object. Assessment grading involves classifying the assessment object into several levels based on its nature and characteristics, and then aligning the assessment object with the assessment standards during the assessment. Based on the assessment indicators and assessment standards, the assessment object is graded. Then, the forest resource survey adjustment status factors are classified and graded to assess whether they meet the corresponding assessment standards at that assessment level, and the scores of each forest resource adjustment status factor assessment indicator are calculated. Finally, the scores of the forest resource adjustment status factors are comprehensively evaluated and calculated using a weighted average to ultimately generate the forest resource survey factor.

[0194] Step S52: Perform real-time monitoring, analysis, and processing on forest resource survey factors to obtain forest resource survey information;

[0195] The embodiment of the present invention monitors forest resource survey factors in real time, inputs the monitoring data into a computer for analysis and processing, and interprets and judges the analysis results to ultimately obtain forest resource survey information.

[0196] Step S53: Formulate a forest resource survey report based on the forest resource survey information, and use the forest resource survey report to implement a corresponding adaptive forest resource survey strategy for the forest resources within the survey area.

[0197] An embodiment of the present invention formulates a forest resource survey report based on the generated forest resource survey information. The forest resource survey report includes the current status of forest resources, existing problems and possible risks, statistical analysis and evaluation of the survey data, and governance suggestions and countermeasures for these problems and risks. The forest resource survey report is used to implement corresponding adaptive forest resource survey strategies for forest resources within the survey area.

[0198] The present invention utilizes hierarchical assessment technology to perform comprehensive assessment processing, which can help divide different levels and classify and layer adjustment status factors, facilitating a more comprehensive understanding of the status of forest resources and the effective management and protection of forest resources. Furthermore, through comprehensive assessment processing, important factors affecting forest resources can be identified, providing guidance for subsequent investigations and monitoring. Then, by performing real-time monitoring and analysis on the generated forest resource survey factors, the current status of forest resources can be quickly understood, allowing for timely responses to abnormal situations. Simultaneously, real-time monitoring can also provide long-term monitoring data, providing a solid basis for targeted forest management and facilitating the sustainable utilization and protection of forest resources. Finally, based on the forest resource survey report, a corresponding adaptive forest resource survey strategy can be formulated. Based on the survey results, specific protection and management measures can be planned to prevent and avoid the damage to forest resources caused by abnormal factors, improve the efficiency of forest resource utilization, and protect the sustainable development of the ecosystem. Furthermore, based on the results of the forest resource survey report, relevant policies can be revised and improved to improve the effectiveness and level of forest resource management.

[0199] The present invention is therefore intended to be illustrative and non-restrictive in all respects, with the scope of the invention being defined by the appended claims rather than the foregoing description, and all changes that come within the meaning and range of equivalents of the application documents are intended to be embraced therein.

[0200] The foregoing description is intended only to provide specific embodiments of the present invention, which will enable those skilled in the art to understand and implement the present invention. Various modifications to these embodiments will be readily 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 is not intended to be limited to the embodiments shown herein, but is to be construed in the widest possible manner consistent with the principles and novel features disclosed herein.

Claims

1. An adaptive forest resource survey factor generation method, characterized in that: The following steps are involved: Step S1: using spatial remote sensing imaging technology to collect and process forest resources within the survey area to obtain forest resource survey data; using a forest resource noise reduction algorithm to perform noise reduction on the forest resource survey data to obtain forest resource survey noise reduction data; Step S2: Using feature extraction technology to perform feature extraction processing on the forest resource survey noise reduction data to obtain forest resource survey data features; classifying the forest resource survey data features according to a preset forest resource classification model to obtain forest resource survey type data; Step S3: Analyze and process the forest resource survey type data using factor analysis technology to generate forest resource status factors; Step S4: real-time monitoring and evaluation of the forest resource status factor is performed using an adaptive evaluation algorithm to obtain a forest resource adaptive status factor; and the weight of the forest resource adaptive status factor is dynamically adjusted using a weight adjustment algorithm that introduces a factor weight mechanism to generate a forest resource adjustment status factor. Step S5: Use hierarchical assessment technology to conduct a comprehensive assessment of the forest resource adjustment status factors to generate forest resource survey factors; formulate a forest resource survey report based on the forest resource survey factors to implement the corresponding adaptive forest resource survey strategy.

2. The adaptive forest resource survey factor generation method according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: using space remote sensing imaging technology to collect and process images of forest resources within the survey area to obtain a forest resource survey image; Step S12: performing data format conversion processing on the forest resource survey image using image format conversion technology to obtain initial forest resource survey data; Step S13: pre-processing the initial data of the forest resource survey to obtain forest resource survey data; Step S14: using a forest resource noise reduction algorithm to perform noise reduction processing on the forest resource survey data to obtain forest resource survey noise reduction data.

3. The adaptive forest resource survey factor generation method according to claim 2, characterized in that: Step S14 includes the following steps: Step S141: Calculate the noise value of the forest resource survey data using a forest resource noise reduction algorithm to obtain a forest resource noise value; Among them, the forest resource noise reduction algorithm function is as follows: Where, e(X) is the forest resource noise value, X is the forest resource survey data sample point dataset, n is the number of forest resource survey data sample points, X l is the lth sample point to be denoised in the forest resource survey data sample point dataset, w(X,X l ) is the noise weight function, s(X,X l ) is the noise power density function, Y l is the observation value of the lth sample point to be denoised in the forest resources survey data sample point dataset, f(X l ) is the noise source kernel function, α is the noise adjustment coefficient, ΔX is the weight increment, β is the weight adjustment parameter, and μ is the correction value of the forest resource noise value; Step S142: judging the forest resource noise value according to a preset forest resource noise threshold; if the forest resource noise value is greater than or equal to the preset forest resource noise threshold, then eliminating the forest resource survey data corresponding to the forest resource noise value to obtain forest resource survey noise-reduced data; Step S143: judging the forest resource noise value according to a preset forest resource noise threshold; if the forest resource noise value is less than the preset forest resource noise threshold, defining the forest resource survey data corresponding to the forest resource noise value as forest resource survey noise reduction data.

4. The adaptive forest resource survey factor generation method according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: standardizing the forest resource survey noise reduction data to obtain forest resource survey standard data; Step S22: using feature extraction technology to perform feature extraction processing on the forest resource survey standard data to obtain forest resource survey data features; Step S23: using a preset forest resource classification model based on random forest to classify the forest resource survey data features to obtain forest resource survey type data.

5. The adaptive forest resource survey factor generation method according to claim 4, characterized in that: Step S23 includes the following steps: Step S231: performing data collection and processing on the forest resource survey data characteristics to obtain a forest resource survey characteristic data set; Step S232: dividing the forest resource survey feature dataset into a training dataset, a validation dataset, and a test dataset according to a preset division rule; Step S233: constructing a forest resource classification model based on random forest, wherein the forest resource classification model includes model training, model validation and model evaluation; Step S234: inputting the training data set into the forest resource classification model based on random forest to perform model training, and optimizing the model parameters through the cross-validation method to obtain a verification model; inputting the verification data set into the verification model to perform model verification to obtain a test model; Step S235: Input the test data set into the test model after parameter optimization for model evaluation to obtain an optimized forest resource classification model; and re-input the forest resource survey feature data set into the optimized forest resource classification model for classification processing to obtain forest resource survey type data.

6. The adaptive forest resource survey factor generation method according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: Analyze and process the forest resource survey type data using factor analysis technology, wherein the factor analysis technology includes factor collection technology, factor loading algorithm and factor rotation technology; Step S32: using factor collection technology to perform factor collection processing on forest resource survey type data to obtain forest resource factor data; Step S33: performing a related load operation on the forest resource factor data using a factor load algorithm to obtain a forest resource factor load value; Step S34: Using factor rotation technology to perform correlation attenuation processing on the forest resource factor loading value to generate a forest resource status factor.

7. The adaptive forest resource survey factor generation method according to claim 6, characterized in that: The factor loading algorithm function formula in step S33 is specifically: Where h(θ) is the forest resource factor load value, θ is the variable in the forest resource factor data, N is the number of variables in the forest resource factor data, p is the number of factors in the forest resource factor data, L is the load calculation interval range threshold of the forest resource factor data, ω(θ) is the load contribution weight function, r ij is the correlation coefficient between the i-th variable and the j-th factor in the forest resource factor data, s ij is the load harmonic smoothing parameter between the i-th variable and the j-th factor in the forest resource factor data, and ε is the correction value of the forest resource factor loading value.

8. The adaptive forest resource survey factor generation method according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: performing real-time monitoring and evaluation processing on the forest resource status factor through an adaptive evaluation algorithm to obtain a forest resource adaptive status factor; Among them, the adaptive evaluation algorithm function is as follows: Where S(R,t) is the adaptive state factor of forest resources at the current time variable t and regional range position R, c R is the amount of forest resources flowing through the regional range position R per unit time, Ω is the adaptive assessment monitoring area, γ(R,t;τ) is the adaptive adjustment parameter function, τ is the time difference with the current time variable t, is the risk factor contribution index function, x is the horizontal position within the region, y is the vertical position within the region, H(R, x, y, τ) is the spatiotemporal cross-weight function, and θ is the correction value of the forest resource adaptive state factor; Step S42: adding an adjustment factor weight to the forest resource adaptive state factor by introducing a factor weight mechanism, and calculating an adjustment weight value of the adjustment factor weight of the forest resource adaptive state factor using a weight adjustment algorithm to obtain a weight adjustment value; Step S43: The weight adjustment value is judged according to a preset adjustment threshold. If the weight adjustment value is greater than or equal to the preset adjustment threshold, the forest resource adaptive state factor corresponding to the weight adjustment value is dynamically adjusted to generate a forest resource adjustment state factor. Step S44: The weight adjustment value is judged according to the preset adjustment threshold. If the weight adjustment value is less than the preset adjustment threshold, the forest resource adaptive state factor corresponding to the weight adjustment value is re-iteratively adjusted until the weight adjustment value is greater than or equal to the preset adjustment threshold.

9. The adaptive forest resource survey factor generation method according to claim 8, characterized in that: The weight adjustment algorithm function formula in step S42 is specifically: where Δω is the weight adjustment value, Σ is the forest resource survey area, T1 is the initial time of the weight adjustment process, T2 is the end time of the weight adjustment process, x′ is the horizontal position of the forest resource adaptive state factor within the survey area, y′ is the vertical position of the forest resource adaptive state factor within the survey area, T is the time variable of the weight adjustment process, G(x′, y′, T) is the adjustment factor weight of the forest resource adaptive state factor, A(x′, y′, T) is the adjustment factor weight to be adjusted, B(x′, y′, T) is the control adjustment factor of the adjustment factor weight, C(x′, y′, T) is the measurement degree coefficient of the adjustment factor weight, D(x′, t′, T) is the normalization coefficient of the weight adjustment process, and ∈ is the correction value of the weight adjustment value.

10. The adaptive forest resource survey factor generation method according to claim 1, characterized in that: Step S5 includes the following steps: Step S51: using a hierarchical assessment technique to comprehensively assess the forest resource adjustment status factors to generate forest resource survey factors; Step S52: Perform real-time monitoring, analysis, and processing on forest resource survey factors to obtain forest resource survey information; Step S53: Formulate a forest resource survey report based on the forest resource survey information, and use the forest resource survey report to implement a corresponding adaptive forest resource survey strategy for the forest resources within the survey area.

Images