Forest ecological product value accounting method

Abstract

The invention discloses a forest ecological product value accounting method, and relates to the technical field of ecological value accounting, and the method comprises the specific steps: S100, data collection: employing a novel sensor technology and an unmanned aerial vehicle remote sensing technology, carrying out the data collection of a forest ecological system, and combining the data of a conventional fixed monitoring point, and obtaining the value of a forest ecological product; forming a data set of multi-source data fusion; by utilizing a novel sensor technology and an unmanned aerial vehicle remote sensing technology, the method realizes high-frequency and high-precision data acquisition of a forest ecological system, and the technologies not only cover key information such as vegetation growth conditions, soil humidity and animal activities of the forest, but also are combined with traditional fixed monitoring point data, so that the forest ecological system is more accurate. A multi-source data fusion monitoring system is formed, the innovative data acquisition mode greatly enriches data dimensions, the comprehensiveness and accuracy of data are improved, and a solid data basis is provided for subsequent value accounting of forest ecological products.

Description

Technical Field

[0001] The present invention relates to the technical field of ecological value accounting, and in particular to a method for calculating the value of forest ecological products. Background Art

[0002] The calculation of the value of forest ecological products involves many complex factors, including vegetation growth conditions, soil moisture, animal activities, and changes in forest ecological functions in different seasons. These factors make it difficult for traditional accounting methods to fully and accurately reflect the actual value of forest ecosystems.

[0003] In the traditional accounting of the value of forest ecological products, data collection mainly relies on fixed monitoring point data. Although these data have certain reference value, due to the low collection frequency and limited accuracy, it is often difficult to fully reflect the dynamic changes of forest ecosystems. Especially in the fusion of multi-source data, traditional methods lack efficient data integration and processing technology, resulting in difficulty in achieving seamless connection and effective utilization of data from different sources. In addition, in terms of dynamic monitoring, traditional methods are often based on static data models for accounting, ignoring the changing characteristics of forest ecosystems in different seasons and growth stages, resulting in a large deviation between the accounting results and the actual value.

[0004] Specifically, in terms of data collection technology innovation, traditional technology mainly relies on ground monitoring equipment, such as soil moisture meters and thermometers. Although these devices can provide certain data support, they are limited by the number of equipment, distribution range and data collection frequency, and it is often difficult to achieve comprehensive monitoring of forest ecosystems. At the same time, in terms of data fusion and processing, traditional methods often lack efficient data integration technology, resulting in weak correlation between data and difficulty in forming a complete monitoring system. In addition, in terms of dynamic data model construction, traditional methods are often based on simple statistical models for prediction and calculation, ignoring the complexity and dynamics of forest ecosystems, thereby limiting the accuracy and practicality of the calculation results.

[0005] Therefore, developing a method for calculating the value of forest ecological products can comprehensively and accurately reflect the actual value changes of forest ecosystems and provide a strong scientific basis for the management and utilization of forest resources. Summary of the invention

[0006] The purpose of the present invention is to make up for the shortcomings of the existing technology and provide a method for calculating the value of forest ecological products. The method integrates new sensor technology, unmanned aerial vehicle remote sensing technology and traditional fixed monitoring point data, constructs a monitoring system with multi-source data fusion, and provides a comprehensive and accurate data basis for value accounting. Through dynamic model construction, linear regression and multivariate nonlinear regression methods are used, combined with time series data, to achieve real-time dynamic evaluation of the value of forest ecological products. This method not only takes into account the growth and renewal of forest resources, but also makes adjustments according to changes in forest ecological functions in different seasons, so that the calculation results can better reflect the actual value changes of the forest ecosystem.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for calculating the value of forest ecological products, the specific steps of which are: S100, data collection: using new sensor technology and drone remote sensing technology to collect data on forest ecosystems, combined with traditional fixed monitoring point data to form a multi-source data fusion data set; S200, data preprocessing: use statistical methods combined with data visualization technology to detect outliers in the data, take targeted measures such as correction, deletion and marking according to the causes of outliers, use interpolation to fill in missing values ​​in the data, divide the data into different categories according to its type and characteristics, classify and code the filled data, assign a unique code to each category, format the data, convert it into a common format, and store the processed data; S300, dynamic model construction: linear regression method is used to analyze the trend of time series data, and the regression equation is set as: ,in For the value of forest ecological products, For time, and is the regression coefficient, is the dynamic adjustment coefficient, For time-based The complex dynamic function is calculated as follows: ,in For a time period, the regression coefficient is estimated by the least squares method, the seasonal index method is used for seasonal analysis, and the moving average trend value is calculated. ,in For time series data The moving average trend value at each time point is calculated using the weighted moving average method, and the formula is: ,in is a dynamic weight coefficient, whose value is dynamically calculated based on the seasonal characteristics of the data to calculate the seasonal ratio ,in ,in Based on time point The dynamic adjustment factor is calculated as follows: , where n is the seasonal period, calculate the seasonal index ,in Based on the season number The dynamic adjustment coefficient is selected according to the results of time series data analysis, and the multivariate nonlinear regression model is selected to establish a dynamic evaluation model. The formula is: ,in, For the value of forest ecological products, is the intercept term, is the regression coefficient, is the interaction term coefficient, is the error term, and the historical data is used to train and verify the model; S400, value calculation: input the preprocessed data into the dynamic evaluation model, calculate the value of all data points, and obtain a preliminary forest ecological product value set , the formula for calculating the average value is: , the total value formula is: ; S500, result output: Output the value accounting results of forest ecological products, including the total value and the specific values ​​of various value indicators, present the results in a visual way, and provide a detailed report to explain the method, process and results of value accounting.

[0008] Furthermore, the S100, a new sensor technology in data collection, installs vegetation growth sensors in the forest to monitor the growth status parameters of vegetation height, coverage, and leaf area index of different tree species in the forest in real time. The soil moisture sensor measures the moisture conditions of the soil at different depths. The temperature sensor continuously monitors soil temperature changes. The micro motion sensor collects data on the activities of small animals in the forest.

[0009] Furthermore, in the S100, during data collection, the installation height of the vegetation growth sensor is set according to a certain ratio of the average heights of different tree species. When determining the installation height, the different tree species in the forest are first classified and counted, and the average height of each tree species is measured. The installation height of the vegetation growth sensor is calculated according to a certain ratio. For taller tree species, the sensor installation height is set at two-thirds of the average height, and for shorter tree species, the installation height is set at half of the average height.

[0010] Furthermore, the S100, the UAV remote sensing technology in data collection, uses high-performance UAVs equipped with high-resolution cameras and multi-spectral sensors to conduct large-scale aerial photography of forests. The high-resolution camera can capture clear images of forest vegetation distribution, identify different tree species, the health status of vegetation, and open spaces and damaged areas in the forest. The multi-spectral sensor obtains the reflection information of the forest in different spectral bands, which is used to analyze the physiological indicators of the forest's chlorophyll content and water content.

[0011] Furthermore, in S100, the flight route of the UAV is optimized during data collection, the terrain and vegetation distribution of the forest are analyzed in detail, a three-dimensional map of the forest is drawn using geographic information system technology, the boundaries and main terrain features of the forest are determined, and the flight route of the UAV is planned using an optimization algorithm based on the performance parameters of the UAV and the area and shape of the forest. On the premise of covering the entire forest ecosystem, the flight distance and number of turns of the UAV are reduced, and the flight time and energy consumption are reduced.

[0012] Furthermore, in the S300, the implementation steps of building a dynamic evaluation model in the dynamic model building are as follows: (1) Based on the results of time series data analysis, a new multivariate nonlinear regression model is used to establish a dynamic evaluation model. The formula is: ; (2) Determine the influencing factors of the model, including vegetation growth, soil moisture, and animal activities; (3) Estimation of model parameters , and , achieved by minimizing the objective function; (4) Use optimization algorithms to solve the objective function and obtain the optimal values ​​of the model parameters.

[0013] Furthermore, in the S300, during the establishment of the multivariate nonlinear regression model in the dynamic model construction, for the adjustment of model parameters, the historical data is divided into a training set and a validation set, the training set data is used to estimate the parameters of the dynamic evaluation model to obtain preliminary model parameters, the model is validated using the validation set data, the prediction error of the model on the validation set is calculated, the training set and validation set are randomly divided multiple times, cross-validation is performed, the average prediction error is obtained, and the model parameters are adjusted according to the results of the cross-validation.

[0014] Furthermore, in the S400, the seasonality of the value is adjusted according to the seasonality analysis result in the time series data analysis in the value calculation, and the seasonal index is set. It indicates that the value of forest ecological products in a certain season is relatively high. The value calculation result of this season is multiplied by the corresponding seasonal adjustment coefficient. Suppose the seasonal adjustment coefficient is , for the season The adjusted value of the data point is: ,in, is the original value, is the adjusted value.

[0015] Furthermore, in the S400, the value calculation is dynamically adjusted according to the growth and renewal of forest resources and the changes in forest ecological functions in different seasons. The dynamic adjustment coefficient is set to , at the time point The adjusted value of the data point is: ,in is the seasonally adjusted value, The dynamically adjusted value.

[0016] Compared with the existing technology, this method of calculating the value of forest ecological products has the following beneficial effects: 1. The present invention utilizes new sensor technology and UAV remote sensing technology to achieve high-frequency and high-precision data collection of forest ecosystems. These technologies not only cover the key information of forest vegetation growth, soil moisture, and animal activities, but also combine with traditional fixed monitoring point data to form a multi-source data fusion monitoring system. This innovative data collection method greatly enriches the data dimension, improves the comprehensiveness and accuracy of the data, and provides a solid data foundation for the subsequent forest ecological product value accounting. At the same time, the fusion of multi-source data can also effectively reduce the errors that may be caused by a single data source, further improving the reliability of the accounting results.

[0017] 2. The present invention constructs a dynamic evaluation model for the value of forest ecological products based on time series data. This model can dynamically calculate the value of forest ecological products in real time according to the changes in forest ecological functions in different seasons and the growth and renewal of forest resources. This dynamic calculation method not only improves the timeliness of the calculation, but also makes the calculation results more scientific and practical, which helps decision makers to more accurately evaluate the economic value and social benefits of forest ecosystems, thereby formulating more reasonable protection and management strategies.

[0018] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 This is a flow chart of a method for calculating the value of forest ecological products; Figure 2 Flowchart of steps for building a dynamic model. DETAILED DESCRIPTION

[0021] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Example

[0022] Calculation of the value of forest ecological products in mountainous areas: The forest area in a certain mountainous area is vast, containing a variety of tree species, complex terrain, and changeable climate. The forest has important ecological functions, such as maintaining soil and water, conserving water resources, and providing habitats. It also produces a certain amount of timber and forest products.

[0023] In the data collection stage (S100), vegetation growth sensors are installed at different altitudes and in different tree species distribution areas in the forest. For example, sensors are installed in coniferous forest areas and broad-leaved forest areas to monitor the vegetation height, coverage and leaf area index of different tree species. Soil moisture sensors are installed in different terrain locations in valleys and hillsides to measure the moisture conditions of soil at different depths. Temperature sensors are installed in some key locations to continuously monitor soil temperature changes. At the same time, multiple micro motion sensors are installed in the forest to monitor the activities of small animals, such as the activity tracks of squirrels and hares. High-performance drones are equipped with high-resolution cameras and multi-spectral sensors for aerial photography. According to the area and terrain of the mountain forest, the flight route of the drone is planned to ensure coverage of the entire forest area. Forest vegetation distribution images are captured by high-resolution cameras to clearly identify the distribution range, health status and forest status of different tree species. In the open spaces and damaged areas in the forest, multispectral sensors are used to obtain the reflectance information of the forest in different spectral bands, analyze the physiological indicators of the forest's chlorophyll content and water content, understand the growth status of the forest, set up multiple fixed monitoring points in the forest, including setting up monitoring points next to some representative trees, regularly measuring the growth parameters of the tree diameter and height, setting up monitoring points near different water sources, collecting soil samples, analyzing the physical and chemical properties of the soil, such as soil fertility and pH, and recording the types, number and activities of animals, such as observing the habitats and migration of birds, integrating the data collected by sensors, drone remote sensing data and traditional fixed monitoring point data, converting the format and coordinate system of data from different sources so that they can be analyzed and processed in the same spatial coordinate system, and at the same time, synchronizing the data in time to ensure the time consistency of the data.

[0024] In the data preprocessing stage (S200), statistical methods are used to calculate the mean and standard deviation statistics of the data. For vegetation growth data, if it is found that the vegetation height data collected by a certain sensor deviates significantly from the mean and is found to be caused by sensor failure after inspection, the data is corrected. For soil moisture data, if abnormally high or low values ​​appear, combined with field investigations, it is judged to be caused by local environmental factors, and then it is marked and explained. The missing values ​​in the data are checked. For the missing time periods in the vegetation growth data, the interpolation method is used to fill in the missing values. For example, if the leaf area index data of a certain tree is missing for two days in a week, the linear interpolation method is used to fill in the missing values ​​based on the data of adjacent dates. For areas with more missing soil moisture data, the data reconstruction method is considered for processing. The filled data is classified and encoded according to the type and characteristics of the data, such as encoding vegetation growth data into the "VG" series, soil moisture data into the "SH" series, and animal activity data into the "AA" series. After assigning a unique code to each category, the data is formatted, converted into a common CSV format, and stored in the database.

[0025] In the dynamic model construction stage (S300), the collected time series data are subjected to trend analysis. For example, the changing trend of forest ecological product value over time is analyzed with a one-year cycle. The linear regression method is used, and the regression equation is set as ,in For the value of forest ecological products, For time, and is the regression coefficient, is the dynamic adjustment coefficient, ( The regression coefficient is estimated by the least square method to analyze the long-term trend of value, such as the regression coefficient If it is positive, it means that the value of forest ecological products is on an upward trend in the long term. This is due to the growth of forest vegetation and the enhancement of ecological functions. Seasonal analysis is performed and the moving average trend value is calculated. ,in For time series data The moving average trend value at each time point is calculated using the weighted moving average method. The weight coefficient is dynamically calculated according to the seasonal characteristics of the data. The formula is: For example, in spring and summer, vegetation grows rapidly, which has a greater impact on value, and the corresponding weight coefficient is higher. The seasonal ratio is calculated ,in , ( , representing four seasons), and finally calculate the seasonal index ,in , Based on the season number The dynamic adjustment coefficient of seasonal analysis shows that the ecological service value of forests is higher in summer, and the windbreak effect of forests in winter makes an important contribution to the value.

[0026] According to the results of time series data analysis, a multivariate nonlinear regression model is selected to establish a dynamic evaluation model, assuming that the value of forest ecological products is , influencing factors include vegetation growth conditions ( ), soil moisture( )、Animal Activities( ), the model formula is: , estimate the model parameters , and First, divide the historical data into a training set and a validation set, for example, in a ratio of 70% and 30%, and use the training set data to estimate the parameters of the dynamic evaluation model by minimizing the objective function: To achieve this, the gradient descent method is used as the optimization algorithm, and the model parameters are continuously adjusted to converge to the optimal value. The training set and validation set are randomly divided multiple times, and cross-validation is performed to obtain the average prediction error. According to the results of cross-validation, the model parameters are further adjusted to improve the accuracy and generalization ability of the model.

[0027] In the value calculation stage (S400), the pre-processed data is input into the dynamic evaluation model to calculate the value of all data points. For example, for a data point at a certain moment, the corresponding vegetation growth status, soil moisture and animal activity data are A quantitative value indicating how well the vegetation grows. A quantitative value indicating moderate soil moisture. The quantitative value representing the activity level of animals is substituted into the dynamic evaluation model: The forest ecological product value at that moment is calculated The value of is seasonally adjusted according to the seasonal analysis results. For the summer data points, its adjusted value is: , according to the growth and renewal of forest resources, dynamic adjustment is carried out. For example, if the forest vegetation grows rapidly in a certain year, the dynamic adjustment coefficient is determined as At the point in time The adjusted value of the data point is: .

[0028] In the result output stage (S500), the forest ecological product value accounting results are output, including the total value and the specific values ​​of various value indicators, and the results are presented in a visual way, such as drawing a line graph of the change of forest ecological product value over time, in which the horizontal axis is time and the vertical axis is value. The value changes in different seasons and the value fluctuations caused by seasonal adjustment and dynamic adjustment are clearly marked in the graph, and a detailed report is provided to explain the method, process and results of value accounting. The report details the location, method and time of data collection, the method and steps of data preprocessing, the principle and process of dynamic model construction, and the specific formula and adjustment method of value accounting. At the same time, the changing trend and influencing factors of the value of forest ecological products are analyzed to provide support for the management and decision-making of forest resources.

[0029] To sum up: the mountain forest accounting collects data through multiple technologies, preprocesses and builds dynamic models, takes into account multiple factors and seasonal and dynamic adjustments to derive the value. This method integrates multi-source data, scientifically processes and models, and can accurately reflect the value of mountain forest ecological products, providing a scientific basis for their management and decision-making, reflecting the effectiveness and practicality of this accounting method in complex mountain forest environments. Example

[0030] Calculation of the value of forest ecological products in mountainous areas The mountain area is rich in forest vegetation, including coniferous and broad-leaved forests. The terrain is undulating and the altitude difference is obvious. The forest has important ecological functions such as conserving water resources, maintaining water and soil, and providing biological habitats. It also produces a small amount of timber and forest products.

[0031] In the data collection stage (S100), vegetation growth sensors are installed in coniferous and broad-leaved forests at different altitudes to monitor tree height, crown width, and leaf area index. Soil moisture sensors are installed in valleys and hillsides to measure soil moisture at different depths. Temperature sensors are set up in the forest to monitor temperature changes, and micro motion sensors are used to capture animal activity trajectories. High-performance drones are equipped with high-resolution cameras and multispectral sensors. The cameras capture the distribution, health status, and damaged areas of forest vegetation. Multispectral sensors obtain chlorophyll and water content information. Routes are planned to cover the entire mountain forest. Monitoring points are set up next to representative trees and near water sources to measure tree diameter and height growth parameters. Soil samples are collected to analyze fertility and pH, and animal species and numbers are recorded. The data collected by the above sensors are combined to form a multi-source data fusion data set.

[0032] In the data preprocessing stage (S200), statistical methods are used to calculate the mean and standard deviation of the data. For vegetation growth data, if the data collected by a certain sensor deviates significantly from the mean and is found to be caused by sensor failure, the data is corrected. For soil moisture data, if abnormally high or low values ​​appear, combined with field investigations, it is judged to be caused by local environmental factors, and then it is marked and explained. The missing values ​​in the data are checked. For the missing time periods in the vegetation growth data, the interpolation method is used to fill them. The data point of the missing value is set to , and the data points around it are set to , and the interpolation method is used to fill them. For areas with more missing soil moisture data, the data reconstruction method is used to process them. The filled data is classified and encoded according to the type and characteristics of the data, such as encoding vegetation growth data into the "VG" series, soil moisture data into the "SH" series, and animal activity data into the "AA" series. After assigning a unique code to each category, the data is formatted, converted into a common CSV format, and stored in the database.

[0033] In the dynamic model building phase (S300), the collected time series data is subjected to trend analysis, with a period of one year (assuming In order to analyze the changing trend of forest ecological product value over time, the linear regression method was used, and the regression equation was set as ,in For the value of forest ecological products, For time, and is the regression coefficient, is the dynamic adjustment coefficient, , estimate the regression coefficient by the least squares method, perform seasonal analysis, and calculate the moving average trend value ,in For time series data The moving average trend value at each time point is calculated using the weighted moving average method. The formula is: ,in is a dynamic weight coefficient, whose value is dynamically calculated based on the seasonal characteristics of the data to calculate the seasonal ratio ,in , (set up , representing four seasons), calculate the seasonal index ,in , Based on the season number According to the seasonal analysis results, it is found that the ecological service value of forests in summer (such as cooling effect) is higher, and the windbreak effect of forests in winter makes an important contribution to the value. According to the results of time series data analysis, the multivariate nonlinear regression model is selected to establish a dynamic evaluation model. The forest ecological product value is set as , the influencing factors include vegetation growth conditions (set as ), soil moisture (set to ), Animal Activities (set to ), the model formula is: , estimate the model parameters , and , divide the historical data into training set and validation set, for example, according to the ratio of 70% and 30%, and set the training set data as , the number of validation sets is , use the training set data to estimate the parameters of the dynamic evaluation model by minimizing the objective function, and use the gradient descent method as the optimization algorithm to continuously adjust the model parameters so that they converge to the optimal value. By randomly dividing the training set and the validation set multiple times, cross-validation is performed to obtain the average prediction error. According to the results of cross-validation, the model parameters are further adjusted to improve the accuracy and generalization ability of the model.

[0034] In the value calculation stage (S400), the pre-processed data is input into the dynamic evaluation model to calculate the value of all data points. For example, for a data point at a certain moment, the corresponding vegetation growth status, soil moisture and animal activity data are A quantitative value indicating how well the vegetation grows. A quantitative value indicating moderate soil moisture. The quantitative value representing the activity level of animals is substituted into the dynamic evaluation model: , calculate the value of forest ecological products at that moment The seasonal adjustment is performed based on the seasonal analysis results. For the data points in the moving season, the adjusted value is , according to the growth and renewal of forest resources, dynamic adjustment is carried out. For example, if the forest vegetation grows rapidly in a certain year, the dynamic adjustment coefficient is determined as At the point in time The adjusted value of the data point is: .

[0035] In the result output stage (S500), the forest ecological product value accounting results are output, including the total value and the specific values ​​of each value indicator, and the results are presented in a visual way, such as drawing a heat map of the forest ecological product value in different regions (such as different altitudes and different tree species distribution areas), showing the spatial distribution differences of the value, and providing a detailed report to explain the method, process and results of the value accounting. The report details the location, method and time of data collection, the method and steps of data preprocessing, the principle and process of dynamic model construction, and the specific formula and adjustment method of value accounting. At the same time, the changing trend and influencing factors of the forest ecological product value are analyzed to provide a scientific basis for the management and decision-making of forest resources.

[0036] In summary, this embodiment calculates the value of ecological products for mountain forests. In the data collection stage, a variety of technologies are used to collect data covering vegetation, soil, and animals. During data preprocessing, outliers and missing values ​​are scientifically processed, and classified, coded, and stored. The dynamic model is constructed through time series analysis and multivariate nonlinear regression, taking into account various factors and seasonal and dynamic adjustments. The value accounting stage calculates and adjusts the value based on the model, and the final output results are presented in an intuitive way, providing a scientific basis for mountain forest management decisions and demonstrating the effectiveness and comprehensiveness of the accounting method in complex mountain environments.

[0037] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A method for calculating the value of forest ecological products, characterized in that: The specific steps of this calculation method are: S100, data collection: using new sensor technology and drone remote sensing technology to collect data on forest ecosystems, combined with traditional fixed monitoring point data to form a multi-source data fusion data set; S200, data preprocessing: use statistical methods combined with data visualization technology to detect outliers in the data, take targeted measures such as correction, deletion and marking according to the causes of outliers, use interpolation to fill in missing values ​​in the data, divide the data into different categories according to its type and characteristics, classify and code the filled data, assign a unique code to each category, format the data, convert it into a common format, and store the processed data; S300, dynamic model construction: linear regression method is used to analyze the trend of time series data, and the regression equation is set as: ,in For the value of forest ecological products, For time, and is the regression coefficient, is the dynamic adjustment coefficient, For time-based The complex dynamic function is calculated as follows: ,in For a time period, the regression coefficient is estimated by the least squares method, the seasonal index method is used for seasonal analysis, and the moving average trend value is calculated. ,in For time series data The moving average trend value at each time point is calculated using the weighted moving average method, and the formula is: ,in is a dynamic weight coefficient, whose value is dynamically calculated based on the seasonal characteristics of the data to calculate the seasonal ratio ,in ,in Based on time point The dynamic adjustment factor is calculated as follows: , where n is the seasonal period, calculate the seasonal index ,in Based on the season number The dynamic adjustment coefficient is selected according to the results of time series data analysis, and the dynamic evaluation model is established by selecting the multivariate nonlinear regression model. The formula is: ,in, For the value of forest ecological products, is the intercept term, is the regression coefficient, is the interaction coefficient, is the error term, and the historical data is used to train and verify the model; S400, value calculation: input the preprocessed data into the dynamic evaluation model, calculate the value of all data points, and obtain a preliminary forest ecological product value set , the formula for calculating the average value is: , the total value formula is: ; S500, result output: Output the value accounting results of forest ecological products, including the total value and the specific values ​​of various value indicators, present the results in a visual way, and provide a detailed report to explain the method, process and results of value accounting.

2. A method for calculating the value of forest ecological products according to claim 1, characterized in that: The S100 is a new sensor technology for data collection. It installs vegetation growth sensors in the forest to monitor the growth parameters of vegetation height, coverage, and leaf area index of different tree species in the forest in real time. The soil moisture sensor measures the moisture of the soil at different depths. The temperature sensor continuously monitors soil temperature changes. The micro motion sensor collects data on the activities of small animals in the forest.

3. A method for calculating the value of forest ecological products according to claim 1, characterized in that: In the S100, during data collection, the installation height of the vegetation growth sensor is set according to a certain ratio of the average heights of different tree species. When determining the installation height, the different tree species in the forest are first classified and counted, and the average height of each tree species is measured. The installation height of the vegetation growth sensor is calculated according to a certain ratio. For taller tree species, the sensor installation height is set at two-thirds of the average height, and for shorter tree species, the installation height is set at half of the average height.

4. A method for calculating the value of forest ecological products according to claim 1, characterized in that: The S100, the UAV remote sensing technology in data collection, uses high-performance UAVs equipped with high-resolution cameras and multispectral sensors to conduct large-scale aerial photography of forests. The high-resolution camera can capture clear images of forest vegetation distribution, identify different tree species, the health status of vegetation, and open spaces and damaged areas in the forest. The multispectral sensor obtains the reflectance information of the forest in different spectral bands, which is used to analyze the physiological indicators of the forest's chlorophyll content and water content.

5. A method for calculating the value of forest ecological products according to claim 1, characterized in that: In the S100, the flight route of the UAV is optimized during data collection, the terrain and vegetation distribution of the forest are analyzed in detail, a three-dimensional map of the forest is drawn using geographic information system technology, the boundaries and main terrain features of the forest are determined, and the flight route of the UAV is planned using an optimization algorithm based on the performance parameters of the UAV and the area and shape of the forest. On the premise of covering the entire forest ecosystem, the flight distance and number of turns of the UAV are reduced, and the flight time and energy consumption are reduced.

6. A method for calculating the value of forest ecological products according to claim 1, characterized in that: In S300, the implementation steps of building a dynamic evaluation model in the dynamic model building are as follows: (1) Based on the results of time series data analysis, a new multivariate nonlinear regression model is used to establish a dynamic evaluation model. The formula is: ; (2) Determine the influencing factors of the model, including vegetation growth, soil moisture, and animal activities; (3) Estimation of model parameters , and , achieved by minimizing the objective function; (4) Use optimization algorithms to solve the objective function and obtain the optimal values ​​of the model parameters.

7. A method for calculating the value of forest ecological products according to claim 1, characterized in that: In the process of establishing the multivariate nonlinear regression model in the dynamic model construction, S300 adjusts the model parameters by dividing the historical data into a training set and a validation set, using the training set data to estimate the parameters of the dynamic evaluation model to obtain preliminary model parameters, using the validation set data to validate the model, calculating the prediction error of the model on the validation set, performing cross-validation by randomly dividing the training set and the validation set multiple times, obtaining an average prediction error, and adjusting the model parameters according to the cross-validation results.

8. A method for calculating the value of forest ecological products according to claim 1, characterized in that: In the above S400, in the value calculation, seasonal adjustment is performed on the value according to the seasonal analysis result in the time series data analysis, and a seasonal index is set. It indicates that the value of forest ecological products in a certain season is relatively high. The value calculation result of this season is multiplied by the corresponding seasonal adjustment coefficient. Suppose the seasonal adjustment coefficient is , for the season The adjusted value of the data point is: ,in, is the original value, is the adjusted value.

9. A method for calculating the value of forest ecological products according to claim 1, characterized in that: In the S400, the value calculation is dynamically adjusted according to the growth and renewal of forest resources and the changes in forest ecological functions in different seasons. The dynamic adjustment coefficient is set as , at the time point The adjusted value of the data point is: ,in is the seasonally adjusted value, The dynamically adjusted value.

Images