LU600359B1 - Prediction Method and System of Carbon Sink Change and Spatial Distribution of Forest Vegetation - Google Patents

Prediction Method and System of Carbon Sink Change and Spatial Distribution of Forest Vegetation

Info

Publication number
LU600359B1
LU600359B1 LU600359A LU600359A LU600359B1 LU 600359 B1 LU600359 B1 LU 600359B1 LU 600359 A LU600359 A LU 600359A LU 600359 A LU600359 A LU 600359A LU 600359 B1 LU600359 B1 LU 600359B1
Authority
LU
Luxembourg
Prior art keywords
vegetation
soil
data
carbon
obtaining
Prior art date
Application number
LU600359A
Other languages
German (de)
Inventor
Hongwei Zhang
Liheng Xu
Xianglong Liu
Original Assignee
Gansu Province Ziwuling Forestry Man Bureau Huachi Branch Bureau Donghuachi Forest Farm
Qingyang Forestry Science Res Institute
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Gansu Province Ziwuling Forestry Man Bureau Huachi Branch Bureau Donghuachi Forest Farm, Qingyang Forestry Science Res Institute filed Critical Gansu Province Ziwuling Forestry Man Bureau Huachi Branch Bureau Donghuachi Forest Farm
Priority to LU600359A priority Critical patent/LU600359B1/en
Application granted granted Critical
Publication of LU600359B1 publication Critical patent/LU600359B1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/02—Agriculture; Fishing; Forestry; Mining
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • G01N33/0098—Plants or trees

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Physics & Mathematics (AREA)
  • Tourism & Hospitality (AREA)
  • Theoretical Computer Science (AREA)
  • Marketing (AREA)
  • General Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Quality & Reliability (AREA)
  • Animal Husbandry (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Agronomy & Crop Science (AREA)
  • Development Economics (AREA)
  • Marine Sciences & Fisheries (AREA)
  • Mining & Mineral Resources (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention belong to that technical field of forest carbon sink prediction in the forestry industry, discloses a predicting method and system of carbon sink for predicting the change and spatial distribution of forest vegetation, including: obtaining the distribution data of vegetation types in the target area, and combining the preset vegetation growth rate and biomass allocation parameters to generate the mapping relationship between vegetation types and growth characteristics; using the preset grid division algorithm, combining the data of vegetation type distribution and forest age structure, determining the grid scale and generating the initial model of grid vegetation carbon sink; obtaining climate condition data of the target area, and combining with soil physical and chemical properties parameters, generating an interaction matrix between climate conditions and soil properties; according to the interaction matrix between climate conditions and soil properties, extracting the dynamic change law of soil carbon storage.

Description

DESCRIPTION LUB00359
PREDICTION METHOD AND SYSTEM OF CARBON SINK CHANGE AND
SPATIAL DISTRIBUTION OF FOREST VEGETATION
TECHNICAL FIELD
The invention relates to the technical field of forest carbon sink prediction in forestry industry, in particular to a predicting method and system of carbon sink for predicting the change and spatial distribution of forest vegetation.
BACKGROUND
It is necessary to consider the growth characteristics of different vegetation types and the differences of forest age structure when establishing the functional relationship of grid vegetation carbon sink with time based on vegetation types and forest age.
Because the growth rate, biomass allocation and dynamic changes of carbon storage of different tree species are different, it is necessary to parameterize each main vegetation type when establishing the functional relationship. In addition, due to the heterogeneity of forest age structure, the change trend of vegetation carbon sink in different forest age segments is also different, which needs to be reflected in the model.
At the same time, how to reasonably determine the grid size is also a key issue in grid processing. Too large a grid will reduce the accuracy of the model, while too small a grid will increase the amount of calculation and the difficulty of data acquisition.
Therefore, it is necessary to find a balance between accuracy and efficiency and choose the optimal grid scale. When establishing the function relationship of soil carbon sink, because the dynamic change of soil carbon storage is influenced by many factors, such as vegetation type, climatic conditions, soil physical and chemical properties, it is a complex problem to accurately describe the interaction mechanism between these factors. In addition, the change rate of soil carbon sink is relatively slow, which requires long-term monitoring data to accurately evaluate, which puts forward higher requirements for data acquisition and model verification.
SUMMARY LU600359
In order to solve the above technical problems, the invention provides a predicting method and system of carbon sink for predicting the change and spatial distribution of forest vegetation, and by integrating multi-dimensional data such as vegetation growth characteristics, forest age structure, climate conditions and soil properties, the accurate assessment of regional carbon sink is realized, which provides a scientific basis for carbon neutral strategy formulation and ecological environment protection.
The invention provides a predicting method of carbon sink for predicting the change and spatial distribution of forest vegetation, characterized in that the method includes: obtaining the distribution data of vegetation types in the target area, and combining the preset vegetation growth rate and biomass allocation parameters to generate the mapping relationship between vegetation types and growth characteristics; according to the mapping relationship between vegetation types and growth characteristics, extracting the data of forest age structure for vegetation in different forest age segments, and establishing the functional relationship between forest age and carbon sink in combination with the dynamic change law of carbon storage; using the preset grid division algorithm, combining the data of vegetation type distribution and forest age structure, determining the grid scale and generating the initial model of grid vegetation carbon sink; obtaining climate condition data of the target area, and combining with soil physical and chemical properties parameters, generating an interaction matrix between climate conditions and soil properties; according to the interaction matrix between climate conditions and soil properties, extracting the dynamic change law of soil carbon storage, and establishing the functional relationship of soil carbon sink by combining the distribution data of vegetation types; and fusing initial model of gridded vegetation carbon sink with the functional relationship of soil carbon sink to generate a comprehensive carbon sink model, according to the comprehensive carbon sink model, the change and spatial distribution of forest vegetation carbon sink in the area to be tested are predicted.
Preferably, obtaining the distribution data of vegetation types in the target area, LU800359 and combining the preset vegetation growth rate and biomass allocation parameters to generate the mapping relationship between vegetation types and growth characteristics includes:
obtaining satellite remote sensing image data of a target area, extracting vegetation type distribution information through an image segmentation algorithm, and obtaining spatial distribution vector data of each vegetation type;
according to the preset growth rate parameters of each vegetation type, establishing the mapping model between vegetation type and growth rate by using support vector machine algorithm, and obtaining the growth rate values of each vegetation type;
according to the preset biomass allocation parameters of each vegetation type, establishing the mapping model between vegetation type and biomass allocation by decision tree algorithm, and obtaining the biomass allocation ratio of each vegetation type;
carrying out spatial superposition analysis on the vector data of vegetation type distribution, growth rate value and biomass distribution ratio, obtaining the growth characteristic distribution map of each vegetation type in the target area;
if there is an unknown vegetation type in the target area, according to its spectral characteristics, the known vegetation type is judged by the minimum distance method, and the corresponding growth characteristic parameters are given;
carrying out spatial interpolation on the distribution map of vegetation growth characteristics in the target area, obtaining continuous grid data of vegetation growth characteristics distribution; and storing the raster data of vegetation growth characteristics distribution in the geographic information database to form a mapping data set of vegetation types and growth characteristics.
Preferably, according to the mapping relationship between vegetation types and LU800359 growth characteristics, extracting the data of forest age structure for vegetation in different forest age segments, and establishing the functional relationship between forest age and carbon sink in combination with the dynamic change law of carbon storage includes:
according to the mapping relationship between vegetation types and growth characteristics, establishing the knowledge base of vegetation types and growth characteristics, and obtaining the growth characteristics parameters corresponding to different vegetation types by the knowledge base;
according to the vegetation in the study area, obtaining the spatial distribution information of vegetation types by remote sensing image interpretation, and obtaining the distribution map of vegetation types;
according to the distribution map of vegetation types and the established knowledge base of vegetation types and growth characteristics, judging the growth characteristic parameters of each vegetation type pixel to form a vegetation growth characteristic parameter layer;
by the method of obtaining the data of forest age structure, obtaining the sample data of forest age structure of different vegetation types and different forest age segments by using the methods of sample plot investigation and tree ring analysis;
according to the obtained sample data of forest age structure, using machine learning algorithms such as support vector machine and random forest etc, establishing a prediction model of forest age structure, and using the layer of vegetation growth characteristic parameters as the model input to predict the forest age structure of each pixel, and obtaining the distribution map of forest age structure in the study area; and according to different vegetation types and different forest ages, obtaining the dynamic change data of carbon storage through field investigation, and analyzing the law of carbon storage changing with forest age, establishing and the functional relationship model between forest age and carbon storage.
Preferably, using the preset grid division algorithm, combining the data of LU800359 vegetation type distribution and forest age structure, determining the grid scale and generating the initial model of grid vegetation carbon sink includes: obtaining vegetation type distribution data and forest age structure data of the target area, preprocessing the data, and unifying the data format and coordinate system; according to the distribution data of vegetation types, the vegetation types are classified by clustering algorithm, and obtaining the distribution areas of different vegetation types, and calculating the area proportion of each area; according to the data of forest age structure, analyzing the forest ages in different vegetation types, and obtaining the area proportion of each forest age segment, and calculating the average forest age of each vegetation type region by weighted average method. using the preset grid division algorithm, according to the distribution of vegetation types and the structural characteristics of forest age, determining adaptively the appropriate grid scale, and dividing the target area into several grid units; aiming each grid unit, according to the vegetation type and average forest age, obtaining the corresponding carbon sink parameters from the carbon sink estimation model, and calculating the initial carbon sink of the grid unit; and summarizing the initial carbon sink data of each grid unit to generate the initial model of grid vegetation carbon sink covering the whole target area.
Preferably, obtaining climate condition data of the target area, and combining with soil physical and chemical properties parameters, generating an interaction matrix between climate conditions and soil properties includes: according to the geographical location information of the target area, obtaining the historical climate condition data of the area; obtaining soil physical and chemical property parameters of the target area; preprocessing the obtained climatic condition data and soil physical and chemical property parameter data; carrying out feature engineering on the pretreated climate condition data and soil physical and chemical property parameter data, extracting key features, and carrying out feature selection and feature combination to form a climate-soil feature matrix; using correlation analysis method, calculating the correlation between climatic conditions and soil properties, and obtaining the correlation coefficient matrix; and according to the correlation coefficient matrix, judging the interaction between LU600359 climate conditions and soil properties, determining the strength and direction of interaction, and forming the climate-soil interaction matrix.
Preferably, according to the interaction matrix between climate conditions and soil properties, extracting the dynamic change law of soil carbon storage, and establishing the functional relationship of soil carbon sink by combining the distribution data of vegetation types includes: obtaining the data of climate conditions and soil properties, constructing an interaction matrix, and extracting the key influencing factors and laws of the dynamic change of soil carbon storage through the matrix analysis method; using machine learning algorithm, establishing the nonlinear relationship model between climate conditions, soil properties and soil carbon storage, and obtaining the prediction function of soil carbon storage; obtaining the distribution data of vegetation types in the study area, classifying and coding the vegetation types to form a vegetation type distribution matrix; analyzing the prediction function of soil carbon storage and the distribution matrix of vegetation types are analyzed by spatial superposition, and calculating the soil carbon storage under different vegetation types, and obtaining the spatial distribution map of soil carbon storage; according to the spatial distribution map of soil carbon storage, generating the continuous distribution surface of soil carbon storage by spatial statistics method, and determining the spatial distribution law of soil carbon sink; and by mathematical fitting of the spatial distribution law of soil carbon sequestration, establishing the functional relationship model between soil carbon sequestration and climate conditions, soil properties and vegetation types, and obtaining the prediction equation of soil carbon sequestration.
Preferably, fusing initial model of gridded vegetation carbon sink with the LU800359 functional relationship of soil carbon sink to generate a comprehensive carbon sink model, according to the comprehensive carbon sink model, the change and spatial distribution of forest vegetation carbon sink in the area to be tested are predicted includes: according to the preset grid size, the research area is gridded to obtain the initial value of vegetation carbon sink and soil carbon sink of each grid unit; aiming each grid unit, establishing a functional relationship model between vegetation carbon sink and soil carbon sink, and obtaining a gridded functional relationship model between vegetation and soil carbon sink; and fusing the gridded initial model of vegetation carbon sink with the gridded model of vegetation-soil carbon sink function, and generating the gridded comprehensive carbon sink model by using the weighted average method.
The invention also provides a predicting system of carbon sink for predicting the change and spatial distribution of forest vegetation, the system is used for realizing any one of the methods, the system includes: a mapping module, a first function relation module, an initial model generation module, a matrix generation module, a second function relation module and a comprehensive carbon sink model generation module; the mapping module is used to obtain the distribution data of vegetation types in the target area and generate a mapping relationship between vegetation types and growth characteristics by combining the preset vegetation growth rate and biomass allocation parameters; the first function relation module is used to extract forest age structure data according to the mapping relation between vegetation types and growth characteristics, aim at the vegetation of different forest age segments, and combine with the dynamic change law of carbon storage, establish a functional relation between forest age and carbon sink; the initial model generation module is used to determine the grid scale by adopting a preset grid division algorithm and combine the vegetation type distribution data and the forest age structure data to generate an initial model of the grid vegetation carbon sink;
the matrix generation module is used to obtain the climate condition data of the LU600359 target area and combine the soil physical and chemical property parameters to generate an interaction matrix between the climate condition and the soil property; the second function relation module is used to extract the dynamic change law of soil carbon storage according to the interaction matrix between climate conditions and soil properties, and establish the function relation of soil carbon sink in combination with vegetation type distribution data; the comprehensive carbon sink model generation module is used to fuse the initial model of gridded vegetation carbon sink with the functional relationship of soil carbon sink to generate a comprehensive carbon sink model, and according to the comprehensive carbon sink model, predict the change and spatial distribution of forest vegetation carbon sink in the area to be measured.
Compared with the prior art, the invention has the beneficial effects that:
The invention discloses a predicting method and system of carbon sink for predicting the change and spatial distribution of forest vegetation. Firstly, the mapping relationship between vegetation types and growth characteristics is established, and the age-carbon sink function is constructed according to the age structure and the change law of carbon storage. Then, the initial vegetation carbon sink model is generated by grid division algorithm. At the same time, by analyzing the interaction between climate conditions and soil properties, the functional relationship of soil carbon sink is established. Finally, the vegetation and soil carbon sink models are fused to form a comprehensive carbon sink model. By integrating multi-dimensional data such as vegetation growth characteristics, forest age structure, climate conditions, soil properties and the like, the invention realizes accurate assessment of regional carbon sink, and provides scientific basis for carbon neutral strategy formulation and ecological environment protection.
BRIEF DESCRIPTION OF THE FIGURES LUB00359
In order to explain the technical scheme of the present invention more clearly, the drawings needed in the embodiments are briefly introduced below, obviously, the drawings in the following description are only some embodiments of the present invention. For ordinary people in the field, other drawings may be obtained according to these drawings without paying creative labor.
Fig. 1 is a flowchart of a predicting method of carbon sink for predicting the change and spatial distribution of forest vegetation of an embodiment of the invention.
DESCRIPTION OF THE INVENTION
In the following, the technical scheme in the embodiment of the invention will be clearly and completely described with reference to the attached drawings. Obviously, the described embodiment is only a part of the embodiment of the invention, but not the whole embodiment. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in the field without creative labour belong to the scope of protection of the present invention.
It should be noted that, unless otherwise defined, the technical or scientific terms used in this disclosure embodiment shall have the usual meaning understood by persons of general skill in the field to which the disclosure belongs. The terms "first", "second", and similar expressions used in this disclosure do not imply any order, quantity, or importance, but are used only to distinguish between different components.
Words such as "including" or "containing" mean that the component or object present before the word covers the component or object listed after the word and its equivalent, and does not exclude other components or objects. The term "connection" or "link" is not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "up", "down", "left", "right", etc., are used only to indicate the relative position relationship. When the absolute position of the described object changes, the relative position relationship may also change accordingly.
In order to make the above objects, features and advantages of the present invention more obvious and easier to understand, the present invention will be further described in detail with the attached drawings and specific embodiments.
Embodiment 1 LUB00359
As shown in Fig. 1, the embodiment of the present invention provides a method for predicting the change and spatial distribution of forest vegetation carbon sink, which specifically includes:
Step S101, obtaining the distribution data of vegetation types in the target area, and combining the preset vegetation growth rate and biomass allocation parameters to generate the mapping relationship between vegetation types and growth characteristics: obtaining satellite remote sensing image data of a target area, extracting vegetation type distribution information through an image segmentation algorithm, and obtaining spatial distribution vector data of each vegetation type; according to the preset growth rate parameters of each vegetation type, establishing the mapping model between vegetation type and growth rate by using support vector machine algorithm, and obtaining the growth rate values of each vegetation type; according to the preset biomass allocation parameters of each vegetation type, establishing the mapping model between vegetation type and biomass allocation by decision tree algorithm, and obtaining the biomass allocation ratio of each vegetation type; carrying out spatial superposition analysis on the vector data of vegetation type distribution, growth rate value and biomass distribution ratio, obtaining the growth characteristic distribution map of each vegetation type in the target area; if there is an unknown vegetation type in the target area, according to its spectral characteristics, the known vegetation type is judged by the minimum distance method, and the corresponding growth characteristic parameters are given; carrying out spatial interpolation on the distribution map of vegetation growth characteristics in the target area, obtaining continuous grid data of vegetation growth characteristics distribution; storing the raster data of vegetation growth characteristics distribution in the geographic information database to form a mapping data set of vegetation types and growth characteristics, and forming for subsequent vegetation growth simulation and ecosystem evaluation.
Step S102, according to the mapping relationship between vegetation types and growth characteristics, extracting the data of forest age structure for vegetation in different forest age segments, and establishing the functional relationship between forest age and carbon sink in combination with the dynamic change law of carbon storage.
According to the mapping relationship between vegetation types and growth LU600359 characteristics, the knowledge base of vegetation types and growth characteristics is established, and the growth characteristics parameters corresponding to different vegetation types are obtained through the knowledge base. Aiming at the vegetation in the study area, the spatial distribution information of vegetation types is obtained by remote sensing image interpretation, and the distribution map of vegetation types is obtained. According to the distribution map of vegetation types, combined with the knowledge base of vegetation types and growth characteristics established in step 1, the growth characteristic parameters of each vegetation type pixel are judged to form a vegetation growth characteristic parameter layer. Through the method of obtaining forest age structure data, sample data of forest age structure with different vegetation types and different forest age segments were obtained by means of sample plot investigation and tree ring analysis. According to the sample data of forest age structure obtained in step 4, a prediction model of forest age structure is established by using machine learning algorithms such as support vector machine and random forest, and the layer of vegetation growth characteristic parameters is used as the model input to predict the forest age structure of each pixel, and the distribution map of forest age structure in the study area is obtained. According to different vegetation types and different forest ages, the dynamic change data of carbon storage were obtained through field investigation, and the law of carbon storage changing with forest age was analyzed, and the functional relationship model between forest age and carbon storage was established. Taking the distribution map of forest age structure obtained in step 5 as input, combined with the functional model of forest age-carbon storage established in step 6, the carbon sink of each forest age structure pixel is calculated to obtain the distribution map of carbon sink in the study area, and the total carbon sink is counted.
Step S103, using the preset grid division algorithm, combining the data of vegetation type distribution and forest age structure, determining the grid scale and generating the initial model of grid vegetation carbon sink.
Obtaining the vegetation type distribution data and forest age structure data of the target area, preprocess the data, unify the data format and coordinate system, and ensure the accuracy and availability of the data.
According to the distribution data of vegetation types, the vegetation types are LU600359 classified by clustering algorithm, and the distribution areas of different vegetation types are obtained, and the area proportion of each area is calculated. According to the data of forest age structure, the forest ages in different vegetation types were analyzed, and the area proportion of each forest age segment was obtained, and the average forest age of each vegetation type region was calculated by weighted average method. Using the preset grid division algorithm, according to the distribution of vegetation types and the structural characteristics of forest age, the appropriate grid scale is adaptively determined, and the target area is divided into several grid units.
For each grid unit, according to its vegetation type and average forest age, the corresponding carbon sink parameters are obtained from the carbon sink estimation model, and the initial carbon sink of the grid unit is calculated. The initial carbon sink data of each grid unit are summarized to generate the initial model data set of grid vegetation carbon sink covering the whole target area. The generated initial model of grid vegetation carbon sequestration is displayed visually, and the accuracy and reliability of the model are evaluated by cross-validation, and the final initial model of vegetation carbon sequestration is obtained by optimizing and improving the model according to the evaluation results.
Step S104, obtaining climate condition data of the target area, and combining with soil physical and chemical properties parameters, generating an interaction matrix between climate conditions and soil properties.
According to the geographical location information of the target area, the historical climate condition data of the area are obtained, including meteorological element data such as temperature, humidity, precipitation and sunshine hours. Obtain the physical and chemical parameters of soil in the target area, including soil texture, organic matter content, pH value, cation exchange capacity and other index data. Pre-process the obtained data of climatic conditions and soil physical and chemical properties, including data cleaning, missing value processing, abnormal value processing, etc., to ensure the accuracy and integrity of the data. The preprocessed climate condition data and soil physical and chemical property parameter data are subjected to feature engineering, key features are extracted, and feature selection and feature combination are carried out to form a climate-soil feature matrix.
The correlation analysis method, such as Pearson correlation coefficient or LU600359
Spearman rank correlation coefficient, is used to calculate the correlation between climate conditions and soil properties, and the correlation coefficient matrix is obtained.
According to the correlation coefficient matrix, the interaction between climate conditions and soil properties is judged, the strength and direction of interaction are determined, and the climate-soil interaction matrix is formed. Visualize the generated climate-soil interaction matrix, such as heat map, network diagram, etc., to visually present the interaction between climate conditions and soil properties, and provide data support for subsequent agricultural production decisions.
Step S105, according to the interaction matrix between climate conditions and soil properties, extracting the dynamic change law of soil carbon storage, and establishing the functional relationship of soil carbon sink by combining the distribution data of vegetation types.
The data of climatic conditions and soil properties are obtained, and the interaction matrix is constructed. Through the matrix analysis method, the key influencing factors and laws of the dynamic change of soil carbon storage are extracted. Using machine learning algorithm, such as support vector machine or random forest, the nonlinear relationship model between climate conditions, soil properties and soil carbon storage is established, and the prediction function of soil carbon storage is obtained. Obtain the distribution data of vegetation types in the study area, classify and code the vegetation types, and form a vegetation type distribution matrix. The prediction function of soil carbon storage and the distribution matrix of vegetation types are analyzed by spatial superposition, and the soil carbon storage under different vegetation types is calculated to obtain the spatial distribution map of soil carbon storage. According to the spatial distribution map of soil carbon storage, the continuous distribution surface of soil carbon storage is generated by spatial statistical methods, such as kriging interpolation or inverse distance weighted interpolation, and the spatial distribution law of soil carbon sink is determined. Through mathematical fitting of the spatial distribution law of soil carbon sequestration, the functional relationship model between soil carbon sequestration and climate conditions, soil properties and vegetation types are established, and the prediction equation of soil carbon sequestration is obtained.
The cross-validation method is used to evaluate and verify the accuracy of the LU600359 prediction equation of soil carbon sequestration, to determine the applicability and reliability of the model, and to provide scientific basis for the dynamic monitoring and prediction of soil carbon sequestration.
Step S106, fusing initial model of gridded vegetation carbon sink with the functional relationship of soil carbon sink to generate a comprehensive carbon sink model, according to the comprehensive carbon sink model, the change and spatial distribution of forest vegetation carbon sink in the area to be tested are predicted.
According to the preset grid size, the research area is gridded to obtain the initial value of vegetation carbon sink and soil carbon sink of each grid unit. For each grid unit, a functional relationship model between vegetation carbon sink and soil carbon sink is established, and a gridded functional relationship model between vegetation and soil carbon sink is obtained. The gridded initial model of vegetation carbon sink is fused with the gridded functional model of vegetation-soil carbon sink, and a gridded comprehensive carbon sink model is generated by using the weighted average method.
Obtaining measured carbon sink data in the research area, and gridding the measured data according to the grid size to obtain gridded measured carbon sink data.
Calculating the error between the simulated value of the gridded comprehensive carbon sink model and the gridded measured carbon sink data, and evaluate the accuracy of the gridded comprehensive carbon sink model by using the root mean square error and other indicators. Comparing the accuracy of the gridded comprehensive carbon sink model with a preset accuracy threshold, and if the accuracy meets the threshold requirement, determining that the current gridded comprehensive carbon sink model is available. Otherwise, return to step 2, adjust the vegetation-soil carbon sink function model, and regenerate the gridded comprehensive carbon sink model until the accuracy meets the requirements.
Embodiment 2 LUB00359
Based on the same inventive concept, corresponding to the method of any of the above embodiments, the invention also provides a predicting system of carbon sink for predicting the change and spatial distribution of forest vegetation, the system is used for realizing any one of the methods, the system includes: a mapping module, a first function relation module, an initial model generation module, a matrix generation module, a second function relation module and a comprehensive carbon sink model generation module; the mapping module is used to obtain the distribution data of vegetation types in the target area and generate a mapping relationship between vegetation types and growth characteristics by combining the preset vegetation growth rate and biomass allocation parameters; the first function relation module is used to extract forest age structure data according to the mapping relation between vegetation types and growth characteristics, aim at the vegetation of different forest age segments, and combine with the dynamic change law of carbon storage, establish a functional relation between forest age and carbon sink; the initial model generation module is used to determine the grid scale by adopting a preset grid division algorithm and combine the vegetation type distribution data and the forest age structure data to generate an initial model of the grid vegetation carbon sink; the matrix generation module is used to obtain the climate condition data of the target area and combine the soil physical and chemical property parameters to generate an interaction matrix between the climate condition and the soil property; the second function relation module is used to extract the dynamic change law of soil carbon storage according to the interaction matrix between climate conditions and soil properties, and establish the function relation of soil carbon sink in combination with vegetation type distribution data; the comprehensive carbon sink model generation module is used to fuse the initial model of gridded vegetation carbon sink with the functional relationship of soil carbon sink to generate a comprehensive carbon sink model, and according to the comprehensive carbon sink model, predict the change and spatial distribution of forest vegetation carbon sink in the area to be measured.
The embodiment of that present invention is intended to cover all such alternatives, LU600359 modifications and variations that fall within the broad scope of the append claims.
Therefore, any omission, modification, equivalent substitution, improvement, etc. within the spirit and principle of the embodiment of the present invention should be included in the protection scope of the invention.

Claims (8)

CLAIMS LU600359
1. A predicting method of carbon sink for predicting the change and spatial distribution of forest vegetation, characterized in that the method comprises: obtaining the distribution data of vegetation types in the target area, and combining the preset vegetation growth rate and biomass allocation parameters to generate the mapping relationship between vegetation types and growth characteristics; according to the mapping relationship between vegetation types and growth characteristics, extracting the data of forest age structure for vegetation in different forest age segments, and establishing the functional relationship between forest age and carbon sink in combination with the dynamic change law of carbon storage; using the preset grid division algorithm, combining the data of vegetation type distribution and forest age structure, determining the grid scale and generating the initial model of grid vegetation carbon sink; obtaining climate condition data of the target area, and combining with soil physical and chemical properties parameters, generating an interaction matrix between climate conditions and soil properties; according to the interaction matrix between climate conditions and soil properties, extracting the dynamic change law of soil carbon storage, and establishing the functional relationship of soil carbon sink by combining the distribution data of vegetation types; and fusing initial model of gridded vegetation carbon sink with the functional relationship of soil carbon sink to generate a comprehensive carbon sink model, according to the comprehensive carbon sink model, the change and spatial distribution of forest vegetation carbon sink in the area to be tested are predicted.
2. The method according to claim 1, characterized in that obtaining the distribution LU600359 data of vegetation types in the target area, and combining the preset vegetation growth rate and biomass allocation parameters to generate the mapping relationship between vegetation types and growth characteristics comprises:
obtaining satellite remote sensing image data of a target area, extracting vegetation type distribution information through an image segmentation algorithm, and obtaining spatial distribution vector data of each vegetation type;
according to the preset growth rate parameters of each vegetation type, establishing the mapping model between vegetation type and growth rate by using support vector machine algorithm, and obtaining the growth rate values of each vegetation type;
according to the preset biomass allocation parameters of each vegetation type, establishing the mapping model between vegetation type and biomass allocation by decision tree algorithm, and obtaining the biomass allocation ratio of each vegetation type;
carrying out spatial superposition analysis on the vector data of vegetation type distribution, growth rate value and biomass distribution ratio, obtaining the growth characteristic distribution map of each vegetation type in the target area;
if there is an unknown vegetation type in the target area, according to its spectral characteristics, the known vegetation type is judged by the minimum distance method, and the corresponding growth characteristic parameters are given;
carrying out spatial interpolation on the distribution map of vegetation growth characteristics in the target area, obtaining continuous grid data of vegetation growth characteristics distribution; and storing the raster data of vegetation growth characteristics distribution in the geographic information database to form a mapping data set of vegetation types and growth characteristics.
3. The method according to claim 1, characterized in that according to the mapping LU600359 relationship between vegetation types and growth characteristics, extracting the data of forest age structure for vegetation in different forest age segments, and establishing the functional relationship between forest age and carbon sink in combination with the dynamic change law of carbon storage comprises:
according to the mapping relationship between vegetation types and growth characteristics, establishing the knowledge base of vegetation types and growth characteristics, and obtaining the growth characteristics parameters corresponding to different vegetation types by the knowledge base;
according to the vegetation in the study area, obtaining the spatial distribution information of vegetation types by remote sensing image interpretation, and obtaining the distribution map of vegetation types;
according to the distribution map of vegetation types and the established knowledge base of vegetation types and growth characteristics, judging the growth characteristic parameters of each vegetation type pixel to form a vegetation growth characteristic parameter layer;
by the method of obtaining the data of forest age structure, obtaining the sample data of forest age structure of different vegetation types and different forest age segments by using the methods of sample plot investigation and tree ring analysis;
according to the obtained sample data of forest age structure, using machine learning algorithms such as support vector machine and random forest etc, establishing a prediction model of forest age structure, and using the layer of vegetation growth characteristic parameters as the model input to predict the forest age structure of each pixel, and obtaining the distribution map of forest age structure in the study area; and according to different vegetation types and different forest ages, obtaining the dynamic change data of carbon storage through field investigation, and analyzing the law of carbon storage changing with forest age, establishing and the functional relationship model between forest age and carbon storage.
4. The method according to claim 1, characterized in that using the preset grid LU600359 division algorithm, combining the data of vegetation type distribution and forest age structure, determining the grid scale and generating the initial model of grid vegetation carbon sink comprises: obtaining vegetation type distribution data and forest age structure data of the target area, preprocessing the data, and unifying the data format and coordinate system; according to the distribution data of vegetation types, the vegetation types are classified by clustering algorithm, and obtaining the distribution areas of different vegetation types, and calculating the area proportion of each area; according to the data of forest age structure, analyzing the forest ages in different vegetation types, and obtaining the area proportion of each forest age segment, and calculating the average forest age of each vegetation type region by weighted average method; using the preset grid division algorithm, according to the distribution of vegetation types and the structural characteristics of forest age, determining adaptively the appropriate grid scale, and dividing the target area into several grid units: aiming each grid unit, according to the vegetation type and average forest age, obtaining the corresponding carbon sink parameters from the carbon sink estimation model, and calculating the initial carbon sink of the grid unit; and summarizing the initial carbon sink data of each grid unit to generate the initial model of grid vegetation carbon sink covering the whole target area.
5. The method according to claim 1, characterized in that obtaining climate condition data of the target area, and combining with soil physical and chemical properties parameters, generating an interaction matrix between climate conditions and soil properties comprises: according to the geographical location information of the target area, obtaining the historical climate condition data of the area; obtaining soil physical and chemical property parameters of the target area; preprocessing the obtained climatic condition data and soil physical and chemical property parameter data;
carrying out feature engineering on the pretreated climate condition data and soil LU600359 physical and chemical property parameter data, extracting key features, and carrying out feature selection and feature combination to form a climate-soil feature matrix; using correlation analysis method, calculating the correlation between climatic conditions and soil properties, and obtaining the correlation coefficient matrix; and according to the correlation coefficient matrix, judging the interaction between climate conditions and soil properties, determining the strength and direction of interaction, and forming the climate-soil interaction matrix.
6. The method according to claim 1, characterized in that according to the interaction matrix between climate conditions and soil properties, extracting the dynamic change law of soil carbon storage, and establishing the functional relationship of soil carbon sink by combining the distribution data of vegetation types comprises: obtaining the data of climate conditions and soil properties, constructing an interaction matrix, and extracting the key influencing factors and laws of the dynamic change of soil carbon storage through the matrix analysis method; using machine learning algorithm, establishing the nonlinear relationship model between climate conditions, soil properties and soil carbon storage, and obtaining the prediction function of soil carbon storage; obtaining the distribution data of vegetation types in the study area, classifying and coding the vegetation types to form a vegetation type distribution matrix; analyzing the prediction function of soil carbon storage and the distribution matrix of vegetation types are analyzed by spatial superposition, and calculating the soil carbon storage under different vegetation types, and obtaining the spatial distribution map of soil carbon storage; according to the spatial distribution map of soil carbon storage, generating the continuous distribution surface of soil carbon storage by spatial statistics method, and determining the spatial distribution law of soil carbon sink; and by mathematical fitting of the spatial distribution law of soil carbon sequestration, establishing the functional relationship model between soil carbon sequestration and climate conditions, soil properties and vegetation types, and obtaining the prediction equation of soil carbon sequestration.
7. The method according to claim 1, characterized in that fusing initial model of LU600359 gridded vegetation carbon sink with the functional relationship of soil carbon sink to generate a comprehensive carbon sink model, according to the comprehensive carbon sink model, the change and spatial distribution of forest vegetation carbon sink in the area to be tested are predicted comprises: according to the preset grid size, the research area is gridded to obtain the initial value of vegetation carbon sink and soil carbon sink of each grid unit; aiming each grid unit, establishing a functional relationship model between vegetation carbon sink and soil carbon sink, and obtaining a gridded functional relationship model between vegetation and soil carbon sink; and fusing the gridded initial model of vegetation carbon sink with the gridded model of vegetation-soil carbon sink function, and generating the gridded comprehensive carbon sink model by using the weighted average method.
8. A predicting system of carbon sink for predicting the change and spatial distribution of forest vegetation, the system is used for realizing the method of any one of claims 1-7, characterized in that the system comprises: a mapping module, a first function relation module, an initial model generation module, a matrix generation module, a second function relation module and a comprehensive carbon sink model generation module; the mapping module is used to obtain the distribution data of vegetation types in the target area and generate a mapping relationship between vegetation types and growth characteristics by combining the preset vegetation growth rate and biomass allocation parameters; the first function relation module is used to extract forest age structure data according to the mapping relation between vegetation types and growth characteristics, aim at the vegetation of different forest age segments, and combine with the dynamic change law of carbon storage, establish a functional relation between forest age and carbon sink; the initial model generation module is used to determine the grid scale by adopting a preset grid division algorithm and combine the vegetation type distribution data and the forest age structure data to generate an initial model of the grid vegetation carbon sink;
the matrix generation module is used to obtain the climate condition data of the LU600359 target area and combine the soil physical and chemical property parameters to generate an interaction matrix between the climate condition and the soil property;
the second function relation module is used to extract the dynamic change law of soil carbon storage according to the interaction matrix between climate conditions and soil properties, and establish the function relation of soil carbon sink in combination with vegetation type distribution data; and the comprehensive carbon sink model generation module is used to fuse the initial model of gridded vegetation carbon sink with the functional relationship of soil carbon sink to generate a comprehensive carbon sink model, and according to the comprehensive carbon sink model, predict the change and spatial distribution of forest vegetation carbon sink in the area to be measured.
LU600359A 2025-02-25 2025-02-25 Prediction Method and System of Carbon Sink Change and Spatial Distribution of Forest Vegetation LU600359B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
LU600359A LU600359B1 (en) 2025-02-25 2025-02-25 Prediction Method and System of Carbon Sink Change and Spatial Distribution of Forest Vegetation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
LU600359A LU600359B1 (en) 2025-02-25 2025-02-25 Prediction Method and System of Carbon Sink Change and Spatial Distribution of Forest Vegetation

Publications (1)

Publication Number Publication Date
LU600359B1 true LU600359B1 (en) 2025-08-25

Family

ID=96850323

Family Applications (1)

Application Number Title Priority Date Filing Date
LU600359A LU600359B1 (en) 2025-02-25 2025-02-25 Prediction Method and System of Carbon Sink Change and Spatial Distribution of Forest Vegetation

Country Status (1)

Country Link
LU (1) LU600359B1 (en)

Similar Documents

Publication Publication Date Title
CN113901384B (en) Ground PM2.5 concentration modeling method considering global spatial autocorrelation and local heterogeneity
CN112308292A (en) Method for drawing fire risk grade distribution map
CN118821074B (en) Third pole region climate change monitoring big data method and application platform
CN114972984B (en) Snow spatiotemporal analysis and prediction method based on random forest
CN117708551A (en) Flood disaster impact assessment method and system based on double-precision GDP data distribution
CN118396482B (en) Climate change-oriented dynamic monitoring method for cultivated quality
CN120125067B (en) Ecological protection red line foundation investigation method based on homeland space planning
CN120673549B (en) Meteorological disaster dynamic monitoring method and system applied to real-time meteorological data
CN120105161B (en) Deep learning-based intelligent carbon emission source identification and classification method
CN120894702B (en) Land ecological condition monitoring system and method based on remote sensing data
CN119692758A (en) Risk level prediction method and device for distribution network, and electronic equipment
CN119831158A (en) Forestry mapping method based on remote sensing big data
CN117235540B (en) Sensor dynamic information linkage analysis method based on feature matching and fusion
CN118134050A (en) A method and device for predicting economic losses from urban flood disasters
CN120566429B (en) A method for predicting regional medium- and long-term new energy power
CN120337022B (en) River basin glacier material balance analysis method and system based on big data
LU600359B1 (en) Prediction Method and System of Carbon Sink Change and Spatial Distribution of Forest Vegetation
CN119579029B (en) Rural digital control method and system based on cloud platform sharing
CN120470289A (en) A method, system and storage medium for screening time-varying characteristics of urban rainstorm flood model parameters based on vegetation changes
CN119848410A (en) Visibility forecast mode evaluation method and system
CN119559753A (en) A method, device, equipment and medium for geological disaster prediction based on big data
Amindin et al. Leveraging GEE and machine learning algorithm in dynamic modeling of eco-environmental quality
CN120782129B (en) Ecological system service function assessment method based on multisource geographic space-time data
CN120931320A (en) Accurate checking method, system, equipment and medium for manufacturing cost range based on geographic region characteristics
CN121481459A (en) Typhoon risk assessment method, typhoon risk assessment device, typhoon risk assessment equipment and typhoon risk assessment storage medium

Legal Events

Date Code Title Description
FG Patent granted

Effective date: 20250825