A method and system for dynamic assessment of carbon sink potential of natural resources

Abstract

The application relates to a natural resource carbon sink potential dynamic evaluation method and system, and relates to the technical field of carbon sink evaluation, which comprises the following steps: collecting monitoring data of a topography main body in a target region, performing slope fitting, obtaining a topography slope and a fitting factor, and processing to obtain a first dynamic coefficient; obtaining a historical topography slope, processing to obtain a second dynamic coefficient, combining the first dynamic coefficient to obtain a dynamic coefficient; adopting a carbon sink capacity prediction model to perform carbon sink capacity prediction, obtaining a carbon sink capacity parameter, performing confidence compensation according to the fitting factor to obtain a first compensation parameter; and performing dynamic compensation according to the dynamic coefficient to obtain a second compensation parameter as a dynamic evaluation result. The application solves the problem of low carbon sink evaluation accuracy in hilly areas, improves the evaluation accuracy and dynamic adaptability by considering the dynamic change of the topography, combining the slope dynamic rate and the prediction model, and provides a reliable scheme for accurate carbon sink potential evaluation.

Description

Technical Field

[0001] This application relates to the field of carbon sink assessment, and in particular to a method and system for dynamic assessment of the carbon sink potential of natural resources. Background Technology

[0002] With the intelligent development of carbon sequestration assessment technology, accurate assessment of hilly areas has become crucial for improving the efficiency of ecological protection. Currently, traditional carbon sequestration potential assessments mostly employ static model analysis, which suffers from insufficient dynamic adaptability and low assessment accuracy, making it difficult to meet the needs of dynamic assessment of carbon sequestration capacity in hilly areas due to topographic changes such as soil erosion.

[0003] Existing assessment methods rely solely on historical static data for analysis, resulting in insufficient response to dynamic changes in hilly terrain. This makes it difficult to accurately reflect real-time fluctuations in carbon sequestration capacity and to meet the dynamic and precise requirements of the intelligent transformation of carbon sequestration assessment. Summary of the Invention

[0004] To address the aforementioned technical issues, this application provides a method and system for dynamic assessment of carbon sequestration potential of natural resources. This method solves the problems of insufficient dynamic adaptability and low accuracy in assessing changes in hilly terrain in traditional assessments. It achieves dynamic compensation assessment based on the dynamic rate of terrain slope and a carbon sequestration capacity prediction model, thereby improving the accuracy and dynamic adaptability of carbon sequestration potential assessment.

[0005] The embodiments of this application disclose the following technical solutions:

[0006] In a first aspect, embodiments of this application provide a method for dynamic assessment of the carbon sink potential of natural resources, the method comprising:

[0007] Collect monitoring data of the main terrain features in the target area, fit the slope of the main terrain features to obtain the terrain slope and fitting factor, and process to obtain the first dynamic coefficient.

[0008] The historical terrain slope of the main terrain over a historical period is obtained, processed to obtain the second dynamic coefficient, and combined with the first dynamic coefficient to obtain the dynamic coefficient.

[0009] Based on the monitoring data of the main terrain, a carbon sequestration capacity prediction model is used to predict carbon sequestration capacity and obtain carbon sequestration capacity parameters. Based on the fitting factor, confidence compensation is performed on the predicted carbon sequestration capacity parameters to obtain the first compensated carbon sequestration capacity parameters.

[0010] Based on the dynamic coefficient, the first compensation carbon sink capacity parameter is dynamically compensated to obtain the second compensation carbon sink capacity parameter, which serves as the dynamic evaluation result.

[0011] Secondly, embodiments of this application provide a dynamic assessment system for the carbon sequestration potential of natural resources, the system comprising:

[0012] The terrain data processing module is used to collect monitoring data of the main terrain in the target area, perform slope fitting of the main terrain, obtain terrain slope and fitting factor, and process to obtain the first dynamic coefficient.

[0013] The dynamic coefficient calculation module is used to obtain the historical terrain slope of the main terrain over a historical period, process it to obtain the second dynamic coefficient, and combine it with the first dynamic coefficient to obtain the dynamic coefficient.

[0014] The carbon sequestration capacity prediction module is used to predict carbon sequestration capacity based on the monitoring data of the main terrain and the carbon sequestration capacity prediction model, obtain carbon sequestration capacity parameters, and perform confidence compensation on the predicted carbon sequestration capacity parameters according to the fitting factor to obtain the first compensated carbon sequestration capacity parameters.

[0015] The compensation assessment generation module is used to dynamically compensate the first compensation carbon sequestration capacity parameter based on the dynamic coefficient to obtain the second compensation carbon sequestration capacity parameter, which serves as the dynamic assessment result.

[0016] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0017] This application proposes a method and system for dynamic assessment of the carbon sequestration potential of natural resources. By collecting UAV imagery data of the target area's terrain and measured carbon sequestration capacity data, a carbon sequestration capacity prediction model is constructed using machine learning algorithms. Confidence compensation is performed based on fitting factors, and secondary correction is applied to the dynamic coefficients to achieve accurate dynamic assessment of carbon sequestration potential. This method effectively solves the problems of traditional assessments that fail to consider dynamic terrain changes and lack reliability in prediction results by calculating the inverse distribution of the dynamic coefficients to the training data, combined with iterative fitting of terrain slope and comparative analysis of historical data. Furthermore, through the steps of "data acquisition-model training-dual compensation," the adaptability of the assessment results to different terrain features and time periods is significantly improved, overcoming the shortcomings of inaccurate carbon sequestration capacity assessments and providing a scientific quantitative basis for calculating carbon sequestration capacity in carbon sequestration projects.

[0018] The technical solution of this application realizes the transformation of natural resource carbon sink potential from single indicator prediction to dynamic interval assessment through the synergistic effect of multi-source data fusion analysis, model iterative optimization and dual compensation mechanism. It avoids the assessment bias caused by ignoring the historical evolution trend of topographic slope and the uncertainty of the fitting process, and improves the scientificity and credibility of carbon sink potential assessment. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 A flowchart illustrating a method for dynamically assessing the carbon sequestration potential of natural resources, provided as an embodiment of this application;

[0021] Figure 2 This is a schematic diagram of the structure of a dynamic assessment system for carbon sequestration potential of natural resources, provided as an embodiment of this application.

[0022] The components represented by each number in the attached diagram are explained below:

[0023] Topographic data processing module 01, dynamic coefficient calculation module 02, carbon sequestration capacity prediction module 03, compensation assessment generation module 04. Detailed Implementation

[0024] This application provides a method and system for dynamic assessment of carbon sink potential of natural resources, which addresses the technical problems of insufficient dynamic adaptability, lagging response to topographic changes, and low accuracy of assessment in hilly areas in existing technologies.

[0025] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0026] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0027] In the description of this application, the term "for example" is used to mean "used as an example, illustration, or description." Any embodiment described as "for example" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use the invention. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be made without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0028] Example 1, as shown in the appendix Figure 1 As shown, this application provides a method for dynamic assessment of the carbon sink potential of natural resources, the method comprising the following steps:

[0029] S100: Collect monitoring data of the main terrain features within the target area, fit the slope of the main terrain features, obtain the terrain slope and fitting factor, and process to obtain the first dynamic coefficient.

[0030] In this embodiment of the application, in the process of dynamic assessment of natural resource carbon sequestration potential, in order to reflect the impact of dynamic changes in terrain such as soil erosion in hilly areas on carbon sequestration capacity, it is necessary to collect hilly images from the side by drone, extract the image edges and fit the slope to obtain terrain slope data.

[0031] Specifically, image data of the hilly area is first collected from the side using drones, and then an image sequence with geographic coordinate labels is generated.

[0032] Furthermore, the monitoring data (i.e., image data collected by the UAV) is processed to separate and extract the main terrain edges, resulting in terrain edge data containing multiple terrain edge coordinates. By randomly generating a first slope fitting line and coinciding with the coordinates of the highest point within the terrain edge data, the average distance between all terrain edge coordinates and this fitting line is calculated to obtain the first iterative fitting factor.

[0033] Subsequently, the slope fitting line is randomly used to iteratively fit the terrain edge data until the preset number of fittings is reached. The slope fitting line corresponding to the minimum iterative fitting factor is then output, thereby obtaining the terrain slope and fitting factor.

[0034] Finally, the terrain change classification table is called, the obtained terrain slope is input into the classification table, and the first dynamic coefficient is obtained from the classification output.

[0035] This process uses the logic of drone image acquisition and terrain edge fitting, combined with the positive correlation between terrain slope and dynamic coefficient, to provide basic dynamic parameters for dynamic assessment of carbon sink potential.

[0036] Step S100 in the method provided in this application embodiment includes:

[0037] Collect monitoring data on the main terrain features within the target area, including UAV data, with the main terrain feature being hills;

[0038] The edges of the main terrain features within the monitoring data are separated and extracted to obtain terrain edge data, wherein the terrain edge data includes multiple terrain edge coordinates;

[0039] A first slope fitting line is randomly generated, and the terrain edge data is fitted to obtain a first iterative fitting factor, wherein the first slope fitting line includes a first slope.

[0040] Continue to randomly select slope fitting lines to iteratively fit the terrain edge data until the preset number of fittings is reached, and output the slope fitting line corresponding to the smallest iterative fitting factor to obtain the terrain slope and fitting factor.

[0041] The first dynamic coefficient is obtained by processing the terrain slope.

[0042] In this embodiment of the application, in order to accurately obtain the slope characteristics of the main terrain, it is necessary to collect image data of the hilly area from the side using a drone to obtain the original monitoring information of the main terrain in the process of dynamic assessment of the carbon sink potential of natural resources.

[0043] Specifically, by calling the drone aerial photography API and setting shooting parameters (such as resolution, focal length, etc.), multi-angle image acquisition can be performed on the target hilly area, and the images can be stored as pixel image data in a preset format.

[0044] For example, if a target area is a hilly area, the image acquisition device takes a picture of the eastern slope of the hill at a resolution of 1920×1080 to generate pixel image data.

[0045] Furthermore, the monitoring data (i.e. image data) collected by the UAV is preprocessed, and the edges of the main terrain are separated and extracted by edge detection algorithms (such as the Canny operator) to obtain terrain edge data containing multiple pixel coordinates.

[0046] The coordinate data is based on the pixel coordinate system and records the horizontal and vertical coordinates of each edge point (e.g., pixel (1256, 892)).

[0047] The method provided in this application embodiment includes the step of "randomly generating a first slope fitting line, performing fitting processing on the terrain edge data, and obtaining a first iterative fitting factor" as follows:

[0048] Obtain the coordinates of the highest point within the terrain edge data;

[0049] Place the first slope fitting line coinciding with the coordinates of the highest point, and calculate the average distance between all terrain edge coordinates within the terrain edge data and the first slope fitting line, using this as the first iterative fitting factor.

[0050] In this embodiment of the application, when performing slope fitting on terrain edge data, in order to ensure the correlation between the fitting line and the terrain features, it is necessary to first extract the coordinates of the point with the smallest Y value in the pixel coordinate system (such as (1520, 560) in the pixel coordinate system) from the terrain edge coordinate set.

[0051] The highest point is usually a characteristic point of the ridgeline in hilly terrain, which can be used as a reference point for slope fitting to improve the accuracy of the initial fitting.

[0052] Specifically, by checking the Y-value of the terrain edge coordinates, the coordinate point with the largest value is located and used as the reference point for the first slope fitting line.

[0053] Subsequently, a slope value is randomly selected (e.g., 45° within the range of 0–90°), and converted to a slope of 1 (tan(45°) = 1). Combined with the coordinates of the highest point within the terrain edge data (e.g., pixel coordinates (1520, 560)), and using the linear equation y = kx + b (where k is the slope and b is the intercept), substituting the coordinates yields 560 = 1 × 1520 + b. The intercept b = -960 is then calculated, thus determining the equation of the first slope fitting line as y = x - 960.

[0054] Furthermore, after aligning the fitted line with the coordinates of the highest point, for all coordinate points within the terrain edge data (such as 200 hill edge points), the vertical distance from each edge point to the fitted line is calculated using the point-to-line distance formula, and the arithmetic mean of all distances is calculated. This mean is used as the first iteration fitting factor.

[0055] For example, if the first slope fitting line is y = x - 960, and the coordinates of an edge point are (1256, 892), substituting these coordinates into the distance formula yields a vertical distance of approximately 398.8 pixels. When the average distance of all 200 points is 420 pixels, this value is used as the first iterative fitting factor.

[0056] In this process, the size of the fitting factor directly reflects the degree of closeness between the terrain edge and the fitted line. The closer the hill edge shape matches the selected 45° slope fitted line, the smaller the mean distance and the closer the fitting factor is to 0, indicating that the deviation between the current fitted line slope and the actual terrain slope is smaller. Conversely, if the mean distance is large, it indicates that the fitted line has a low degree of matching with the actual terrain, and a new slope needs to be selected for fitting.

[0057] Subsequently, different slope values ​​(such as 30°, 15°, etc.) are randomly selected from the slope candidate set, and the above fitting process is repeated until the preset number of iterations (such as 100 times) is reached. Finally, the fitting line with the smallest fitting factor is selected as the optimal solution, and its corresponding slope is the actual terrain slope, thereby achieving accurate fitting of the hilly terrain slope.

[0058] Furthermore, based on the obtained actual terrain slope, the first dynamic coefficient is obtained after processing.

[0059] The step of "processing to obtain the first dynamic coefficient based on the terrain slope" in the method provided in this application embodiment includes:

[0060] The terrain change classification table is invoked, which includes an index data table of sample terrain slope and sample dynamic coefficient. The terrain slope and dynamic coefficient are positively correlated, and the dynamic coefficient includes the average magnitude of vegetation and soil changes in the terrain per unit time under different terrain slopes.

[0061] Input the terrain slope into the terrain change classification table, and obtain the first dynamic coefficient by classification output.

[0062] In this embodiment of the application, when determining the first dynamic coefficient, a pre-constructed topographic change classification table is required to quantify the correlation between topographic slope and vegetation and soil changes.

[0063] This table is based on multiple sets of hilly sample data. By monitoring hilly areas with different slopes (such as 20°, 33°, and 46°) over a long period of time, it statistically analyzes the percentage of area affected by vegetation and soil erosion per unit time (such as one year). For example, 5% of the area with a 20° slope is eroded within one year, 9% in the 33° area, and 12% in the 46° area. This establishes a mapping relationship between slope and dynamic coefficient.

[0064] Specifically, the terrain change classification table uses structured indexed data storage, with each record corresponding to the sample terrain slope and its associated dynamic coefficient. For example, the table explicitly records a slope of 31° with a dynamic coefficient of 0.85, which represents the average magnitude of vegetation and soil change per unit time at this slope as 8.5%. Once the actual terrain slope (e.g., 31°) is determined through iterative fitting, this slope value is used as an index to call the classification table query interface for querying.

[0065] Furthermore, the sample dynamic coefficient corresponding to the actual terrain slope can be quickly located through the index. This coefficient is the first dynamic coefficient under the actual terrain slope.

[0066] Among them, the topographic slope is positively correlated with the first dynamic coefficient. That is, the greater the slope, the greater the degree of soil erosion, and the greater the first dynamic coefficient; conversely, the smaller the slope, the less the degree of soil erosion, and the smaller the first dynamic coefficient. This is used to quantify the impact of topographic change on carbon sequestration.

[0067] For example, if a hilly area is determined to have a slope of 31° by slope fitting, after calling the terrain change classification table, the dynamic coefficient 0.85 corresponding to the slope is quickly located by index and used as the first dynamic coefficient.

[0068] The first dynamic coefficient intuitively reflects the average magnitude of changes in topography, vegetation, and soil under the current slope, providing key parameter basis for subsequent dynamic assessment of carbon sequestration potential.

[0069] S200: Obtain the historical terrain slope of the main terrain within a historical period, process it to obtain the second dynamic coefficient, and combine it with the first dynamic coefficient to obtain the dynamic coefficient.

[0070] In this embodiment of the application, in order to fully reflect the dynamic fluctuation of carbon sequestration capacity caused by changes in vegetation and soil and water in the main terrain, it is necessary to comprehensively consider the current terrain slope characteristics and historical change trends, and obtain more accurate dynamic coefficients through comparative analysis, so as to provide more reliable parameter support for carbon sequestration capacity assessment.

[0071] Specifically, the first step is to retrieve the terrain slope data of the target hilly area from the historical database within a historical time period. This data can be obtained through multi-source information collection, such as historical drone images and terrain mapping reports.

[0072] Furthermore, the historical terrain slope is compared with the currently fitted terrain slope to calculate the magnitude of slope change between the two, thus obtaining a second dynamic coefficient. This coefficient characterizes the evolution trend of terrain slope over a historical time span.

[0073] Furthermore, the first dynamic coefficient (reflecting the magnitude of terrain change under the current slope) and the second dynamic coefficient (reflecting the historical trend of slope change) are summed and averaged to obtain a comprehensive dynamic coefficient.

[0074] This comprehensive dynamic coefficient integrates the static slope characteristics and dynamic change trends of the terrain, and more comprehensively reflects the degree of change in the main vegetation and soil of the terrain, providing core parameter basis for subsequent dynamic assessment and compensation of carbon sequestration capacity.

[0075] Step S200 in the method provided in this application embodiment includes:

[0076] Obtain the historical topographic slope of the main terrain within a historical time period;

[0077] Calculate the historical terrain slope and the slope change range to obtain the second dynamic coefficient;

[0078] The dynamic coefficients are calculated based on the first and second dynamic coefficients.

[0079] In this embodiment of the application, in order to fully reflect the impact of changes in topography, vegetation and soil and water on carbon sequestration capacity during the dynamic assessment of natural resource carbon sequestration potential, it is necessary to conduct a comprehensive analysis by combining the historical evolution trend and current characteristics of topographic slope.

[0080] Specifically, the slope data of the target terrain subject within a specified time period is first retrieved from the historical database. These data are derived from historical drone monitoring images or terrain mapping reports.

[0081] Among them, historical drone images recorded multi-angle images of the same hilly area taken in the past year and the past three years. By performing edge extraction and slope fitting processing on these historical images, terrain slope data at the corresponding time points can be obtained, such as a slope of 33° one year ago and a slope of 34° three years ago.

[0082] Furthermore, the historical terrain slope is compared and analyzed with the current terrain slope obtained through iterative fitting. The percentage calculation formula (slope change range = |(current terrain slope - historical terrain slope) / historical terrain slope| × 100%) is used to quantify the slope change range between the two, thereby obtaining a second dynamic coefficient, which directly reflects the evolution trend of terrain slope over historical time spans.

[0083] For example, if the historical terrain slope is 33° and the current terrain slope is 31°, then the slope change range = ((31°-33°) / 33°)×100%≈6.1%, and the corresponding second dynamic coefficient is 0.61.

[0084] Among them, the second dynamic coefficient directly reflects the intensity of the evolution of topographic slope over a historical time span. The larger the percentage change in slope, the larger the second dynamic coefficient, indicating that the interference of topographic erosion or deposition on the stability of vegetation and soil is more significant, and the greater the potential impact on carbon sequestration capacity.

[0085] Finally, the first dynamic coefficient (reflecting the range of terrain change under the current slope) and the second dynamic coefficient (reflecting the historical trend of slope change) are arithmetically averaged (i.e., dynamic coefficient = (first dynamic coefficient + second dynamic coefficient) / 2) to obtain the comprehensive dynamic coefficient.

[0086] For example, if the first dynamic coefficient is 0.85 and the second dynamic coefficient is 0.61, then the combined dynamic coefficient = (0.85 + 0.61) / 2 = 0.73.

[0087] This dynamic coefficient integrates the static slope characteristics and dynamic change trends of the terrain, and more comprehensively quantifies the degree of change in the main vegetation and soil of the terrain, providing core parameter support for subsequent carbon sequestration capacity assessment.

[0088] S300: Based on the monitoring data of the main terrain, a carbon sequestration capacity prediction model is used to predict carbon sequestration capacity and obtain carbon sequestration capacity parameters. Based on the fitting factor, confidence compensation is performed on the predicted carbon sequestration capacity parameters to obtain the first compensated carbon sequestration capacity parameters.

[0089] In this embodiment of the application, in order to accurately assess the dynamic characteristics of carbon sequestration capacity of the main terrain due to changes in vegetation and soil and water, it is necessary to construct a carbon sequestration capacity prediction model in combination with monitoring data, predict carbon sequestration capacity, and improve the reliability of the prediction results through the confidence compensation mechanism of fitting factors, so as to provide more scientific parameter support for carbon sequestration potential assessment.

[0090] Specifically, firstly, based on the monitoring data of the target terrain, the measured data of the carbon sequestration capacity of the terrain within the corresponding time period are obtained synchronously, providing basic samples for model training.

[0091] Furthermore, the monitoring data is input into a pre-built carbon sequestration capacity prediction model. This model is based on a machine learning algorithm, using the monitoring data as input, and learns the mapping relationship between the monitoring data and carbon sequestration capacity parameters through model training, outputting the predicted carbon sequestration capacity parameters.

[0092] Furthermore, confidence compensation is applied to the predicted carbon sequestration capacity parameters based on the fitting factors generated during the slope fitting process. A confidence compensation coefficient is generated by calculating the deviation between the fitting factors and the historical average fitting factors, and then the prediction results are extended across intervals to obtain the first compensated carbon sequestration capacity parameter.

[0093] The first compensation carbon sink capacity parameter integrates the prediction results of topographic monitoring data with the reliability assessment of the fitting process. It not only reflects the dynamic characteristics of the carbon sink capacity of the main topographic features, but also quantifies the uncertainty of the prediction results through a confidence compensation mechanism, providing a basis for subsequent carbon sink potential assessment and ecological compensation decision-making.

[0094] Step S300 in the method provided in this application embodiment includes:

[0095] Collect sample data on the carbon sequestration capacity of multiple sample terrain features at different time points to obtain multiple sample monitoring data sets and multiple sample carbon sequestration capacity parameter sets;

[0096] Multiple dynamic coefficients of the main terrain features of multiple samples are obtained, and the preset training data volume is allocated to obtain multiple data volumes.

[0097] Based on multiple data volumes, sample monitoring data and sample carbon sequestration capacity parameters are extracted from the multiple sample monitoring data sets and multiple sample carbon sequestration capacity parameter sets respectively to obtain carbon sequestration capacity prediction training data.

[0098] A carbon sequestration capacity prediction model is constructed based on machine learning. The input features of the carbon sequestration capacity prediction model are monitoring data, and the output features are carbon sequestration capacity parameters.

[0099] The carbon sequestration capacity prediction model is trained under supervision using the carbon sequestration capacity prediction training data until convergence.

[0100] The monitoring data is input into the carbon sequestration capacity prediction model, and the carbon sequestration capacity parameters are obtained from the prediction output.

[0101] Multiple sample terrain features are obtained for slope fitting, and the mean is calculated to obtain the average fitting factor.

[0102] The deviation magnitude between the fitting factor and the average fitting factor is calculated and used as the confidence compensation coefficient;

[0103] The confidence compensation coefficient is used to perform confidence compensation calculation on the predicted carbon sequestration capacity parameter to obtain a first compensated carbon sequestration capacity parameter range, which is used as the first compensated carbon sequestration capacity parameter.

[0104] In this embodiment of the application, in order to achieve accurate prediction of carbon sink capacity during the dynamic assessment of natural resource carbon sink potential, it is necessary to construct a carbon sink capacity prediction model based on monitoring data and carbon sink capacity parameters, and optimize the results by combining the fitting process.

[0105] First, by simultaneously conducting UAV image acquisition and carbon sequestration capacity measurement on multiple sample terrain subjects at different time points, multiple sample monitoring data sets and multiple sample carbon sequestration capacity parameter sets are constructed.

[0106] The sample carbon sequestration capacity parameter set was obtained by measuring the organic carbon content of each sample through soil stratification sampling and summarizing the data in chronological order.

[0107] For each sample terrain subject, the terrain slope is extracted from the monitoring data, and the first dynamic coefficient corresponding to the current slope is calculated by an iterative fitting algorithm; historical slope data is retrieved to calculate the slope change range and obtain the second dynamic coefficient; the arithmetic mean of the two is taken to generate a comprehensive dynamic coefficient.

[0108] Furthermore, multiple dynamic coefficients of multiple sample terrain subjects are obtained, and the preset training data volume is allocated to obtain multiple data volumes.

[0109] Specifically, terrain slope data is first extracted from each sample monitoring data set, and the first dynamic coefficient corresponding to the current terrain slope is calculated by an iterative fitting algorithm. At the same time, historical slope data of the same sample in the historical database is retrieved, and the slope change range is calculated according to the percentage formula to obtain the second dynamic coefficient. Finally, the arithmetic mean of the two is calculated to generate a comprehensive dynamic coefficient.

[0110] Furthermore, based on a preset model training data volume (e.g., 5000), the data volume is allocated by calculating the ratio of the reciprocal of each dynamic coefficient to the sum of the reciprocals of multiple dynamic coefficients and multiplying it by the total data volume of 5000.

[0111] For example, if the dynamic coefficients of samples A, B, and C are 0.8 (8 / 10), 0.6 (6 / 10), and 0.4 (4 / 10), respectively, and their reciprocals are 1.25 (10 / 8), 1.67 (10 / 6), and 2.5 (10 / 4), respectively, and the sum of the reciprocals is 5.42 (5.42 = 1.25 + 1.67 + 2.5), then the amount of data allocated to samples A, B, and C is approximately 1153 (1153 = 5000 × (1.25 / 5.42)), 1540 (1540 = 5000 × (1.67 / 5.42)), and 2307 (2307 = 5000 × (2.5 / 5.42)), respectively.

[0112] The allocation logic is based on the principle that "the larger the dynamic coefficient, the lower the data accuracy and the worse the quality, and the more sample data needs to be reduced" to ensure the overall reliability of the training data and avoid interference from low-quality data on model training.

[0113] Furthermore, according to the data allocation scheme, feature data such as terrain slope and fitting factor are extracted from the sample monitoring data set, and measured carbon sequestration data at corresponding time nodes are extracted from the sample carbon sequestration capacity parameter set. These data are then structured and spliced ​​together to form a carbon sequestration capacity prediction training dataset.

[0114] Furthermore, a carbon sequestration capacity prediction model is constructed based on a deep learning framework (such as support vector regression algorithm). The model is trained under supervision with monitoring data as input and carbon sequestration capacity parameters as output until it converges.

[0115] Specifically, the training dataset was split into a training set and a validation set in an 8:2 ratio. Batch gradient descent was used, selecting 32 data points at a time to train the model. The model parameters were adjusted by reducing the error between the prediction results and the carbon sequestration capacity parameters.

[0116] Furthermore, the model performance is evaluated using a validation set after every 10 training cycles. If five consecutive evaluations show that the model's error reduction on the validation set is insufficient to meet a preset threshold, a learning rate decay mechanism is triggered, which reduces the learning rate to finely adjust the model parameters.

[0117] Furthermore, to avoid the model overfitting to the training data, an early stopping mechanism is introduced. That is, if the validation set error does not improve within 15 consecutive training cycles, the training is immediately terminated and the current optimal model parameters are saved.

[0118] After approximately 200 training cycles of iterative optimization, the model's performance on the validation set tends to stabilize. The root mean square error between the predicted results and the actual carbon fixation amount is less than 0.05, indicating that the model has completed training and possesses high prediction accuracy and stability.

[0119] Furthermore, the target monitoring data is input into the trained model, and based on the mapping relationship between terrain features and carbon sequestration capacity, the predicted carbon sequestration capacity parameters are output.

[0120] The prediction results obtained through the above steps will serve as a quantitative basis for assessing the carbon sequestration capacity of the target area, providing data support for subsequent ecological environment analysis and carbon sequestration potential research.

[0121] Furthermore, terrain edge extraction, slope iterative fitting, and fitting factor calculation are performed uniformly on multiple sample monitoring data. After obtaining the fitting factors of multiple samples, the arithmetic mean is taken to obtain the average fitting factor.

[0122] Furthermore, the fit factor of each sample is compared with the average fit factor, and the deviation magnitude is calculated using the formula (sample fit factor - average fit factor) / average fit factor × 100%. This deviation magnitude is used as the confidence compensation coefficient.

[0123] Furthermore, the confidence compensation coefficient is substituted into the preset confidence compensation calculation formula to perform range expansion calculations on the predicted carbon sequestration capacity parameters.

[0124] Specifically, the lower and upper limits of the parameter range are determined by the formulas “lower limit = predicted carbon sink capacity parameter × (1 - |confidence compensation coefficient|)” and “upper limit = predicted carbon sink capacity parameter × (1 + |confidence compensation coefficient|)”, respectively. This range is used as the first compensation carbon sink capacity parameter to improve the reliability of carbon sink capacity assessment.

[0125] For example, assuming three hilly terrain samples A, B, and C are selected, the fitted factors for samples A, B, and C after processing are 0.8, 0.9, and 0.7, respectively, with an average fitted factor of (0.8 + 0.9 + 0.7) / 3 = 0.8. The confidence compensation coefficients for samples A, B, and C are (0.8 - 0.8) / 0.8 × 100% = 0%, (0.9 - 0.8) / 0.8 × 100% = 12.5%, and (0.7 - 0.8) / 0.8 × 100% = -12.5%, respectively.

[0126] If the predicted carbon sequestration capacity parameter for sample B is 50 tons, the lower limit of its first compensation carbon sequestration capacity parameter range is 50×(1-|0.125|)=43.75 tons, and the upper limit is 50x(1+0.125)=56.25 tons. Finally, (43.75 tons, 56.25 tons) is used as the first compensation carbon sequestration capacity parameter for sample B. Compared with a single predicted value, this range more comprehensively reflects the fluctuation range of the prediction results and enhances the credibility of the carbon sequestration capacity assessment.

[0127] S400: Based on the dynamic coefficient, the first compensation carbon sequestration capacity parameter is dynamically compensated to obtain the second compensation carbon sequestration capacity parameter, which serves as the dynamic evaluation result.

[0128] In this embodiment of the application, in order to fully reflect the dynamic fluctuations in carbon sequestration capacity caused by changes in vegetation and soil and water in the main terrain, it is necessary to further compensate the dynamic coefficients based on the confidence compensation of the fitting factor, so as to improve the adaptability of the carbon sequestration potential assessment results to the characteristics of terrain evolution.

[0129] Specifically, the obtained dynamic coefficient is first used as the dynamic compensation coefficient. This coefficient integrates the current terrain slope characteristics (first dynamic coefficient) and the historical slope change trend (second dynamic coefficient), intuitively representing the average amplitude of vegetation and soil changes per unit time. Its value is positively correlated with the dynamic fluctuation of carbon sequestration capacity.

[0130] Furthermore, the first compensation carbon sink capacity parameter is extended twice based on the dynamic compensation coefficient to obtain the second compensation carbon sink capacity range, which serves as the second compensation carbon sink capacity parameter.

[0131] The larger the dynamic compensation coefficient, the stronger the interference of topographic changes on carbon sequestration capacity, thus requiring a greater expansion of the prediction range; conversely, the expansion range needs to be reduced.

[0132] This second compensation carbon sequestration capacity parameter, as the final dynamic assessment result, deeply integrates the static characteristics (slope, fitting factor) and dynamic characteristics (historical slope change trend) of topographic monitoring data, providing a reliable quantitative basis for carbon sequestration capacity assessment.

[0133] Step S400 in the method provided in this application embodiment includes:

[0134] The dynamic coefficient is used as the dynamic compensation coefficient;

[0135] Using the dynamic compensation coefficient, the first compensation carbon sink capacity parameter is dynamically compensated to obtain the second compensation carbon sink capacity parameter range, which is used as the second compensation carbon sink capacity parameter to obtain the dynamic assessment result of carbon sink potential.

[0136] In this embodiment of the application, in the process of dynamic assessment of natural resource carbon sink potential, in order to quantify the real-time impact of topographic evolution on carbon sink capacity, it is necessary to further compensate the dynamic coefficients to realize the transformation from static valuation to dynamic range assessment.

[0137] Specifically, the dynamic coefficient is used as the dynamic compensation coefficient to perform range-extended calculations on the first compensation carbon sink capacity parameter.

[0138] Specifically, secondary compensation is achieved through the formulas “lower limit = lower limit of the first compensation carbon sink capacity parameter × (1 - dynamic compensation coefficient)” and “upper limit = upper limit of the first compensation carbon sink capacity parameter × (1 + dynamic compensation coefficient)”, resulting in the range of the second compensation carbon sink capacity parameter, which serves as the second compensation carbon sink capacity parameter.

[0139] For example, the first carbon sequestration capacity parameter range for a certain sample is (43.75 tons, 56.25 tons). After substituting the dynamic compensation coefficient of 0.73, the lower limit is calculated to be 43.75×(1-0.73)=11.81 tons, and the upper limit is 56.25×(1+0.73)=97.31 tons, thus forming the second carbon sequestration capacity parameter range (11.81 tons, 97.31 tons).

[0140] The dynamic compensation coefficient quantifies the intensity of topographic change, expanding carbon sequestration capacity prediction from static estimation to dynamic range assessment. When the dynamic compensation coefficient is large (e.g., steep terrain with dramatic historical changes), it indicates that carbon sequestration capacity is significantly affected by topographic evolution, requiring an expanded prediction range to cover potential fluctuations; conversely, when the dynamic compensation coefficient is small, the terrain is relatively stable, and the expansion of the prediction range is correspondingly reduced.

[0141] The final obtained second compensation carbon sink capacity parameter will serve as the dynamic assessment result of carbon sink potential. This result includes both the prediction uncertainty brought about by the fitting factor and the influence of dynamic topographic changes. Through the dual compensation mechanism, the static characteristics (slope, fitting factor) and dynamic characteristics (historical slope change trend) of topographic monitoring data are deeply integrated, providing data support for the calculation of carbon sequestration in carbon sink projects.

[0142] The embodiments of this application, through the specific implementation methods described above, achieve the following technical effects:

[0143] This application provides a method for dynamically assessing the carbon sequestration potential of natural resources. First, image data of the target terrain and measured carbon sequestration capacity are collected using drones to establish a mapping relationship between terrain slope and dynamic coefficients, providing a standardized data foundation for subsequent assessments. Second, a carbon sequestration capacity prediction model is constructed based on machine learning algorithms. Through iterative fitting and compensation mechanisms, carbon sequestration capacity parameters with confidence intervals are generated based on terrain characteristics and the quantification of the uncertainty of the prediction results. Finally, a secondary compensation system is established based on the dynamic coefficients to dynamically adjust the prediction parameters, achieving a high-precision dynamic assessment of the carbon sequestration potential of natural resources. This method effectively reduces the interference of data fluctuations on the assessment results by collecting multi-source data and combining a standardized process of allocating training data to dynamic coefficients. The analysis of terrain slope, dynamic coefficients, and other features using machine learning algorithms improves the accuracy of carbon sequestration capacity prediction. Through confidence compensation of fitting factors and secondary compensation of dynamic coefficients, static carbon sequestration estimates are transformed into dynamic interval assessments, making the assessment results more consistent with actual terrain changes.

[0144] The method provided in this application addresses the problems of large assessment bias and poor adaptability in traditional carbon sink assessments due to neglecting dynamic topographic changes and lack of reliability in prediction results. It effectively improves the efficiency and accuracy of carbon sink potential assessment, providing reliable data support for applications such as the calculation of carbon sequestration in carbon sink projects.

[0145] Example 2, as shown in the appendix Figure 2 As shown, based on the inventive concept of a dynamic assessment method for the carbon sequestration potential of natural resources provided in Embodiment 1, this application also provides a dynamic assessment system for the carbon sequestration potential of natural resources, specifically including:

[0146] The terrain data processing module 01 is used to collect monitoring data of the main terrain in the target area, perform slope fitting of the main terrain, obtain terrain slope and fitting factor, and process to obtain the first dynamic coefficient.

[0147] The dynamic coefficient calculation module 02 is used to obtain the historical terrain slope of the main terrain within a historical period, process it to obtain the second dynamic coefficient, and combine it with the first dynamic coefficient to obtain the dynamic coefficient.

[0148] The carbon sequestration capacity prediction module 03 is used to predict carbon sequestration capacity based on the monitoring data of the main terrain and the carbon sequestration capacity prediction model, obtain carbon sequestration capacity parameters, and perform confidence compensation on the predicted carbon sequestration capacity parameters according to the fitting factor to obtain the first compensated carbon sequestration capacity parameters.

[0149] The compensation assessment generation module 04 is used to dynamically compensate the first compensation carbon sequestration capacity parameter based on the dynamic coefficient to obtain the second compensation carbon sequestration capacity parameter as the dynamic assessment result.

[0150] In one embodiment, the terrain data processing module 01 is further configured to:

[0151] Collect monitoring data on the main terrain features within the target area, including UAV data, with the main terrain feature being hills;

[0152] The edges of the main terrain features within the monitoring data are separated and extracted to obtain terrain edge data, wherein the terrain edge data includes multiple terrain edge coordinates;

[0153] A first slope fitting line is randomly generated, and the terrain edge data is fitted to obtain a first iterative fitting factor, wherein the first slope fitting line includes a first slope.

[0154] Continue to randomly select slope fitting lines to iteratively fit the terrain edge data until the preset number of fittings is reached, and output the slope fitting line corresponding to the smallest iterative fitting factor to obtain the terrain slope and fitting factor.

[0155] The first dynamic coefficient is obtained by processing the terrain slope.

[0156] In one embodiment, the dynamic coefficient calculation module 02 is further configured to:

[0157] Obtain the historical topographic slope of the main terrain within a historical time period;

[0158] Calculate the historical terrain slope and the slope change range to obtain the second dynamic coefficient;

[0159] The dynamic coefficients are calculated based on the first and second dynamic coefficients.

[0160] In one embodiment, the carbon sink capacity prediction module 03 is also used for:

[0161] Collect sample data on the carbon sequestration capacity of multiple sample terrain features at different time points to obtain multiple sample monitoring data sets and multiple sample carbon sequestration capacity parameter sets;

[0162] Multiple dynamic coefficients of the main terrain features of multiple samples are obtained, and the preset training data volume is allocated to obtain multiple data volumes.

[0163] Based on multiple data volumes, sample monitoring data and sample carbon sequestration capacity parameters are extracted from the multiple sample monitoring data sets and multiple sample carbon sequestration capacity parameter sets respectively to obtain carbon sequestration capacity prediction training data.

[0164] A carbon sequestration capacity prediction model is constructed based on machine learning. The input features of the carbon sequestration capacity prediction model are monitoring data, and the output features are carbon sequestration capacity parameters.

[0165] The carbon sequestration capacity prediction model is trained under supervision using the carbon sequestration capacity prediction training data until convergence.

[0166] The monitoring data is input into the carbon sequestration capacity prediction model, and the carbon sequestration capacity parameters are obtained from the prediction output.

[0167] Multiple sample terrain features are obtained for slope fitting, and the mean is calculated to obtain the average fitting factor.

[0168] The deviation magnitude between the fitting factor and the average fitting factor is calculated and used as the confidence compensation coefficient;

[0169] The confidence compensation coefficient is used to perform confidence compensation calculation on the predicted carbon sequestration capacity parameter to obtain a first compensated carbon sequestration capacity parameter range, which is used as the first compensated carbon sequestration capacity parameter.

[0170] In one embodiment, the compensation evaluation generation module 04 is further configured to:

[0171] The dynamic coefficient is used as the dynamic compensation coefficient;

[0172] Using the dynamic compensation coefficient, the first compensation carbon sink capacity parameter is dynamically compensated to obtain the second compensation carbon sink capacity parameter range, which is used as the second compensation carbon sink capacity parameter to obtain the dynamic assessment result of carbon sink potential.

[0173] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are possible or may be advantageous.

[0174] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

[0175] This specification and accompanying drawings are merely illustrative examples of this application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application intends to include such modifications and variations.

Claims

1. A method for dynamic assessment of the carbon sequestration potential of natural resources, characterized in that, The method includes: Monitoring data of the main terrain features within the target area are collected, slope fitting is performed on the main terrain features to obtain the terrain slope and fitting factor, and the first dynamic coefficient is obtained through processing, including: Collect monitoring data on the main terrain features within the target area, including UAV data, with the main terrain feature being hills; The edges of the main terrain features within the monitoring data are separated and extracted to obtain terrain edge data, wherein the terrain edge data includes multiple terrain edge coordinates; A first slope fitting line is randomly generated, and the terrain edge data is fitted to obtain a first iterative fitting factor, including: Obtain the coordinates of the highest point within the terrain edge data; Place the first slope fitting line coinciding with the coordinates of the highest point, and calculate the average distance between all terrain edge coordinates within the terrain edge data and the first slope fitting line as the first iterative fitting factor, wherein the first slope fitting line includes the first slope. Continue to randomly select slope fitting lines to iteratively fit the terrain edge data until the preset number of fittings is reached, and output the slope fitting line corresponding to the smallest iterative fitting factor to obtain the terrain slope and fitting factor. Based on the terrain slope, a first dynamic coefficient is obtained through processing, including: The terrain change classification table is invoked, which includes an index data table of sample terrain slope and sample dynamic coefficient. The terrain slope and dynamic coefficient are positively correlated, and the dynamic coefficient includes the average magnitude of vegetation and soil changes in the terrain per unit time under different terrain slopes. Input the terrain slope into the terrain change classification table, and obtain the first dynamic coefficient by classification output; The historical terrain slope of the main terrain over a historical period is obtained, processed to obtain the second dynamic coefficient, and combined with the first dynamic coefficient to obtain the dynamic coefficient. Based on the monitoring data of the main terrain, a carbon sequestration capacity prediction model is used to predict carbon sequestration capacity and obtain carbon sequestration capacity parameters. Based on the fitting factor, confidence compensation is performed on the predicted carbon sequestration capacity parameters to obtain the first compensated carbon sequestration capacity parameters. Based on the dynamic coefficient, the first compensation carbon sink capacity parameter is dynamically compensated to obtain the second compensation carbon sink capacity parameter, which serves as the dynamic evaluation result.

2. The method for dynamic assessment of natural resource carbon sequestration potential according to claim 1, characterized in that, The historical topographic slope of the main terrain over a historical period is obtained, processed to obtain a second dynamic coefficient, and combined with the first dynamic coefficient to obtain a dynamic coefficient, including: Obtain the historical topographic slope of the main terrain within a historical time period; Calculate the historical terrain slope and the slope change range to obtain the second dynamic coefficient; The dynamic coefficients are calculated based on the first and second dynamic coefficients.

3. The method for dynamic assessment of natural resource carbon sequestration potential according to claim 1, characterized in that, Based on the monitoring data of the main terrain features, a carbon sequestration capacity prediction model is used to predict carbon sequestration capacity and obtain carbon sequestration capacity parameters, including: Collect sample data on the carbon sequestration capacity of multiple sample terrain features at different time points to obtain multiple sample monitoring data sets and multiple sample carbon sequestration capacity parameter sets; Multiple dynamic coefficients of the main terrain features of multiple samples are obtained, and the preset training data volume is allocated to obtain multiple data volumes. Based on multiple data volumes, sample monitoring data and sample carbon sequestration capacity parameters are extracted from the multiple sample monitoring data sets and multiple sample carbon sequestration capacity parameter sets respectively to obtain carbon sequestration capacity prediction training data. A carbon sequestration capacity prediction model is constructed based on machine learning. The input features of the carbon sequestration capacity prediction model are monitoring data, and the output features are carbon sequestration capacity parameters. The carbon sequestration capacity prediction model is trained under supervision using the carbon sequestration capacity prediction training data until convergence. The monitoring data is input into the carbon sequestration capacity prediction model, and the carbon sequestration capacity parameters are obtained from the prediction output.

4. The method for dynamic assessment of natural resource carbon sequestration potential according to claim 1, characterized in that, Based on the fitting factor, confidence compensation is applied to the predicted carbon sequestration capacity parameters to obtain the first compensated carbon sequestration capacity parameters, including: Multiple sample terrain features are obtained for slope fitting, and the mean is calculated to obtain the average fitting factor. The deviation magnitude between the fitting factor and the average fitting factor is calculated and used as the confidence compensation coefficient; The confidence compensation coefficient is used to perform confidence compensation calculation on the predicted carbon sequestration capacity parameter to obtain a first compensated carbon sequestration capacity parameter range, which is used as the first compensated carbon sequestration capacity parameter.

5. The method for dynamic assessment of natural resource carbon sequestration potential according to claim 1, characterized in that, Based on the dynamic coefficient, the first compensation carbon sequestration capacity parameter is dynamically compensated to obtain the second compensation carbon sequestration capacity parameter, which serves as the dynamic assessment result, including: The dynamic coefficient is used as the dynamic compensation coefficient; Using the dynamic compensation coefficient, the first compensation carbon sink capacity parameter is dynamically compensated to obtain the second compensation carbon sink capacity parameter range, which is used as the second compensation carbon sink capacity parameter to obtain the dynamic assessment result of carbon sink potential.

6. A dynamic assessment system for the carbon sequestration potential of natural resources, characterized in that, The system is used to execute the dynamic assessment method for carbon sink potential of natural resources as described in any one of claims 1-5, and the system comprises: The terrain data processing module is used to collect monitoring data of the main terrain in the target area, perform slope fitting of the main terrain, obtain terrain slope and fitting factor, and process to obtain the first dynamic coefficient. The dynamic coefficient calculation module is used to obtain the historical terrain slope of the main terrain over a historical period, process it to obtain the second dynamic coefficient, and combine it with the first dynamic coefficient to obtain the dynamic coefficient. The carbon sequestration capacity prediction module is used to predict carbon sequestration capacity based on the monitoring data of the main terrain and the carbon sequestration capacity prediction model, obtain carbon sequestration capacity parameters, and perform confidence compensation on the predicted carbon sequestration capacity parameters according to the fitting factor to obtain the first compensated carbon sequestration capacity parameters. The compensation assessment generation module is used to dynamically compensate the first compensation carbon sequestration capacity parameter based on the dynamic coefficient to obtain the second compensation carbon sequestration capacity parameter, which serves as the dynamic assessment result.

Images