CN113297904B - Method and system for estimating alpine grassland biomass based on satellite driving model - Google Patents
Method and system for estimating alpine grassland biomass based on satellite driving model Download PDFInfo
- Publication number
- CN113297904B CN113297904B CN202110412645.6A CN202110412645A CN113297904B CN 113297904 B CN113297904 B CN 113297904B CN 202110412645 A CN202110412645 A CN 202110412645A CN 113297904 B CN113297904 B CN 113297904B
- Authority
- CN
- China
- Prior art keywords
- index
- model
- biomass
- data information
- alpine
- Prior art date
- Legal status (The legal status 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 status listed.)
- Active
Links
- 239000002028 Biomass Substances 0.000 title claims abstract description 104
- 238000000034 method Methods 0.000 title claims abstract description 93
- 238000005457 optimization Methods 0.000 claims abstract description 68
- 238000004458 analytical method Methods 0.000 claims abstract description 67
- 238000012545 processing Methods 0.000 claims abstract description 45
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 40
- 238000007781 pre-processing Methods 0.000 claims abstract description 38
- 238000010219 correlation analysis Methods 0.000 claims abstract description 24
- 238000000605 extraction Methods 0.000 claims abstract description 24
- 238000012544 monitoring process Methods 0.000 claims description 42
- 230000007613 environmental effect Effects 0.000 claims description 27
- 239000002689 soil Substances 0.000 claims description 24
- 230000008569 process Effects 0.000 claims description 20
- 238000012706 support-vector machine Methods 0.000 claims description 17
- 239000004927 clay Substances 0.000 claims description 16
- 239000004576 sand Substances 0.000 claims description 16
- 238000007637 random forest analysis Methods 0.000 claims description 13
- 238000006243 chemical reaction Methods 0.000 claims description 12
- 230000003595 spectral effect Effects 0.000 claims description 10
- 238000012417 linear regression Methods 0.000 claims description 9
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims description 8
- 230000004927 fusion Effects 0.000 claims description 8
- 238000003062 neural network model Methods 0.000 claims description 8
- 230000005855 radiation Effects 0.000 claims description 8
- 238000012952 Resampling Methods 0.000 claims description 6
- 238000001556 precipitation Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims description 4
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 claims description 4
- 229910052757 nitrogen Inorganic materials 0.000 claims description 4
- 239000005416 organic matter Substances 0.000 claims description 4
- 229910052698 phosphorus Inorganic materials 0.000 claims description 4
- 239000011574 phosphorus Substances 0.000 claims description 4
- 239000011591 potassium Substances 0.000 claims description 4
- 229910052700 potassium Inorganic materials 0.000 claims description 4
- 230000008859 change Effects 0.000 abstract description 14
- 238000010586 diagram Methods 0.000 abstract description 7
- 238000009826 distribution Methods 0.000 abstract description 6
- 230000006870 function Effects 0.000 description 23
- 238000011156 evaluation Methods 0.000 description 8
- 238000012549 training Methods 0.000 description 8
- 238000013528 artificial neural network Methods 0.000 description 5
- 238000001228 spectrum Methods 0.000 description 5
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 description 4
- 238000013145 classification model Methods 0.000 description 4
- 238000012937 correction Methods 0.000 description 4
- 238000003066 decision tree Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000013507 mapping Methods 0.000 description 3
- 238000012876 topography Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 241000497386 Silveira Species 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000002790 cross-validation Methods 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000009304 pastoral farming Methods 0.000 description 2
- 238000010845 search algorithm Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000002945 steepest descent method Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 241000283984 Rodentia Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 244000144980 herd Species 0.000 description 1
- 244000144972 livestock Species 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Chemical & Material Sciences (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Remote Sensing (AREA)
- Astronomy & Astrophysics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a method and a system for estimating the biomass of alpine grasslands based on a satellite driving model, wherein the method comprises the following steps: obtaining data information; preprocessing the data information to obtain a preprocessing result; performing index extraction processing based on the pretreatment result to obtain a remote sensing index and an environment index; constructing an index system by utilizing the remote sensing index, the environment index and the alpine grassland biomass based on an XGboost algorithm and correlation analysis; carrying out optimization selection processing on the satellite driving model based on the index system to obtain an optimization model with optimization selection; and carrying out space-time dynamic analysis processing on the alpine grassland biomass based on the optimization model of optimization selection to obtain an alpine grassland biomass analysis result. In the embodiment of the invention, the optimal satellite driving model can be determined through model precision comparison, the space-time distribution diagram of AG-AGB is drawn, and the space-time dynamic change of AG-AGB is analyzed.
Description
Technical Field
The invention relates to the technical field of environmental monitoring and evaluation, in particular to a method and a system for estimating the biomass of alpine grasslands based on a satellite driving model.
Background
The Qinghai plateau alpine grassland is an important livestock production base and ecological safety barrier in China, and is extremely sensitive to global climate change and human activity (Fayiah et al, 2019; liu et al, 2016; zhang et al, 2014). However, in recent decades, alpine grasslands have significantly degraded due to excessive grazing, rodent activity and climate change (Chen et al, 2014; liu et al, 2020; sun et al, 2019). The high-cold grassland above-ground biomass (AG-AGB) is an important index for monitoring grassland ecosystem, directly affects grazing and bearing capacity, and is closely related to animal husbandry development and herd income (Gao et al, 2019; kong et al, 2019; zeng et al, 2019). Thus, the accurate and timely estimation of AG-AGB may provide a scientific reference for grassland resource management and sustainable utilization (Gao et al 2020; liang et al 2016; zeng et al 2019).
Currently, two main methods are used for AG-AGB monitoring, namely conventional ground monitoring and satellite monitoring. Traditional ground-based methods estimate biomass by mowing in the field, drying, and weighing in the laboratory (Yang et al, 2018). This conventional approach can provide AG-AGB information with high accuracy for sample positioning. However, it is time consuming and expensive and omits the spatial distribution of AG-AGB (Li et al, 2016; liang et al, 2016; zeng et al, 2019).
Satellite driving methods mainly use a model of the relationship between spectra (such as vegetation index and spectral reflectance data) and environmental (geographic, topography, soil, weather, etc.) indicators and AG-AGB to estimate biomass (Liang et al 2016). At present, a great deal of research conducted by using the method is mainly focused on determining evaluation indexes and establishing a relational model. Many studies use a single vegetation index, such as normalized vegetation index (NDVI), enhanced Vegetation Index (EVI), soil-adjusted vegetation index (SAVI), to estimate AG-AGB. Although the method is simple to apply, the method lacks accurate estimation capability for AG-AGB due to the influence of geographical, topographic, soil, meteorological and other environmental factors. Thus, some scholars comprehensively consider various metrics including vegetation index and environmental metrics to estimate AG-AGB (Liang et al, 2016;Silveira et al, 2019). Since these sensitivity indexes vary with the change of the regional environment, there is no unified index to estimate AG-AGB. To improve the accuracy of estimation of grassland biomass in a particular area, determining a key estimation indicator from a large number of spectral and environmental indicators remains a challenge.
Existing AG-AGB estimation models can be divided into two categories: linear models and nonlinear models. The linear model establishes a linear mathematical relationship between the estimation index and the AG-AGB. For example, multiple Linear Regression (MLR) is commonly used to estimate AG-AGB (Liang et al, 2016;Silveira et al, 2019). However, these relationships tend to fail because they lack popularity. Thus, with the development of machine learning algorithms, many scholars (Gao et al 2020; yang et al 2018; zeng et al 2019) have applied Artificial Neural Networks (ANN), support Vector Machines (SVM) and Random Forest (RF) algorithms to build satellite driven models to estimate AG-AGB. Satellite driven models constructed using machine learning algorithms can learn highly complex nonlinear mappings and achieve higher estimation accuracy compared to linear models (Xu et al 2020; yang et al 2018; zeng et al 2019). However, these machine learning algorithms also have drawbacks. For example, the accuracy of the estimation of the Back Propagation Neural Network (BPNN) algorithm depends on the number and quality of samples, and the convergence process may be slow or experience local minimum problems (Yang et al, 2018). The support vector machine algorithm is mainly affected by the kernel function and penalty factor because its parameters use only the expert experience of the reference and are limited in terms of accuracy of the estimation results (Zhu et al 2020). The results of the RF algorithm have limited interpretability because the relationship between the predicted value and the response cannot be checked individually for each tree in the forest (Chagas et al 2016). Therefore, the establishment of accurate satellite-driven models using machine learning algorithms has become a research hotspot for high-accuracy AG-AGB estimation.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides a method and a system for estimating the biomass of alpine grassland based on a satellite driving model, wherein the optimal satellite driving model can be determined through model precision comparison, a space-time distribution diagram of AG-AGB is drawn, and the space-time dynamic change of AG-AGB is analyzed.
In order to solve the technical problems, an embodiment of the present invention provides a method for estimating alpine grassland biomass based on a satellite driving model, the method comprising:
obtaining data information, wherein the data information comprises remote sensing image information, alpine grassland monitoring data information and environment data information;
preprocessing the data information to obtain a preprocessing result;
performing index extraction processing based on the pretreatment result to obtain a remote sensing index and an environment index;
constructing an index system by utilizing the remote sensing index, the environment index and the alpine grassland biomass based on an XGboost algorithm and correlation analysis;
carrying out optimization selection processing on the satellite driving model based on the index system to obtain an optimization model with optimization selection;
and carrying out space-time dynamic analysis processing on the alpine grassland biomass based on the optimization model of optimization selection to obtain an alpine grassland biomass analysis result.
Optionally, the preprocessing the data information to obtain a preprocessing result includes:
initializing the remote sensing image information to obtain a remote sensing image information initialization result;
initializing the alpine grassland monitoring data information to obtain an alpine grassland monitoring data information initialization result;
and initializing the environment data information to obtain an environment data information initialization result.
Optionally, the initializing the remote sensing image information to obtain a remote sensing image information initializing result includes:
converting MOD09A1 and MCD12Q1 data in the remote sensing image information from sinusoidal projection to Albers projection by using an MODIS reprojection tool, converting an HDF format into a Geo-Tiff format, and then carrying out image fusion and MCD12Q1 data reclassification to obtain a remote sensing image information initialization result;
initializing the alpine grassland monitoring data information to obtain an alpine grassland monitoring data information initializing result, comprising the following steps:
sequentially carrying out vectorization, projection conversion and outlier rejection processing on the alpine grassland monitoring data information to obtain an alpine grassland monitoring data information initialization result;
And initializing the environment data information to obtain an environment data information initialization result. Comprising the following steps:
and sequentially performing spatial interpolation, projection conversion and grid resampling on the environmental data information to obtain an environmental data information initialization result.
Optionally, the performing the index extraction process based on the preprocessing result to obtain a remote sensing index and an environmental index includes:
sequentially extracting remote sensing indexes and environment indexes based on the pretreatment result to obtain the remote sensing indexes and the environment indexes;
the environmental data information includes ground data, soil data, and meteorological data.
Optionally, the remote sensing index extraction processing includes obtaining 7 VIs and 5 spectral indexes from MOD09A1 data in the preprocessing result based on ENVI software, and extracting a maximum value of each of the visible light and the spectral indexes;
the environmental index extraction processing comprises acquiring longitude, latitude, altitude, gradient and slope landform indexes from space plane radar landform task digital elevation model products in the preprocessing result based on ArcGIS software; acquiring soil indexes of 0-30cm sand content, 0-30cm clay content, 30-60cm sand content, 30-60cm clay content, 0-30cm sand clay ratio, 30-60cm sand clay ratio, organic matter content, total nitrogen content, total phosphorus content, total potassium content and pH from soil data; meteorological indexes of annual average temperature, annual total precipitation, annual total solar radiation, annual accumulated temperature of >0 years and wettability are obtained from the meteorological data.
Optionally, the constructing an index system based on the XGboost algorithm and the correlation analysis by using the remote sensing index, the environmental index and the alpine grassland biomass comprises:
performing index analysis processing of the remote sensing index and the environment index for estimating the alpine grassland biomass based on the correlation analysis to obtain an initial estimation index of the alpine grassland biomass estimation;
performing redundancy removal on the initial estimation index of the alpine grassland biomass estimation based on an XGboost algorithm to obtain an estimation index of the alpine grassland biomass estimation;
and constructing an index system based on the estimation index, the environment index and the alpine grassland biomass.
Optionally, the satellite driving model comprises a multiple linear regression model, a BP neural network model, a support vector machine model and a random forest model.
Optionally, the optimizing selection processing is performed on the satellite driving model based on the index system to obtain an optimizing model with optimizing selection, which includes:
determining precision parameters, wherein the precision parameters comprise a decision coefficient, a relative root mean square error and a residual error prediction deviation;
and referring to the residual prediction bias of each model in the satellite driving model, comparing the determined coefficient sizes of each model when the residual prediction bias of each model is in the same interval, and then referring to the relative root mean square error sizes to obtain an optimized model for optimization selection.
Optionally, the optimizing model based on optimizing selection performs space-time dynamic analysis processing on the alpine grassland biomass to obtain an analysis result of the alpine grassland biomass, which comprises the following steps:
performing Sen and Mann-Kendall trend analysis on the alpine grassland biomass based on the optimization model selected by optimization to obtain a first analysis result;
R/S analysis is carried out on the alpine grassland biomass based on the optimization model selected by optimization, and a second analysis result is obtained;
and performing superposition judgment based on the first analysis result and the second analysis result to obtain the alpine grassland biomass analysis result.
In addition, the embodiment of the invention also provides a alpine grassland biomass estimation system based on a satellite driving model, which comprises the following steps:
the obtaining module is as follows: the method comprises the steps of obtaining data information, wherein the data information comprises remote sensing image information, alpine grassland monitoring data information and environment data information;
and a pretreatment module: the data information preprocessing method comprises the steps of preprocessing the data information to obtain a preprocessing result;
the index extraction module is used for: the method is used for carrying out index extraction processing based on the pretreatment result to obtain a remote sensing index and an environment index;
the index system construction module: the method is used for constructing an index system by utilizing the remote sensing index, the environment index and the alpine grassland biomass based on the XGboost algorithm and the correlation analysis;
And an optimization selection module: the method comprises the steps of carrying out optimization selection processing on a satellite driving model based on an index system to obtain an optimization model with optimization selection;
and a space-time dynamic analysis module: the method is used for carrying out space-time dynamic analysis processing on the alpine grassland biomass based on the optimization model of optimization selection to obtain the analysis result of the alpine grassland biomass.
In the embodiment of the invention, a set of grassland biomass monitoring index system is constructed by mainly using an XGBoost algorithm and a correlation analysis method through exploring the relation between indexes and biomass, then a plurality of linear/nonlinear inversion models are constructed according to the constructed index system, an optimal satellite driving model can be determined through model precision comparison, a space-time distribution diagram of AG-AGB is drawn, and the space-time dynamic change of AG-AGB is analyzed.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings which are required in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for estimating the biomass of alpine grasslands based on a satellite driving model in an embodiment of the invention;
fig. 2 is a schematic structural diagram of a alpine grassland biomass estimation system based on a satellite driving model in an embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
Referring to fig. 1, fig. 1 is a flow chart of a method for estimating the biomass of alpine grasslands based on a satellite driving model according to an embodiment of the invention
As shown in fig. 1, a method for estimating the biomass of alpine grasslands based on a satellite driving model, the method comprises:
s11: obtaining data information, wherein the data information comprises remote sensing image information, alpine grassland monitoring data information and environment data information;
in the implementation process of the invention, the region needing to be subjected to the evaluation of the biomass of the alpine grasslands is firstly determined, and then the data information of the region is obtained, wherein the data information comprises remote sensing image information, alpine grasslands monitoring data information and environment data information.
Specifically, in the present application, it was determined that the region where the evaluation of the biomass of the alpine grassland is required is located in Qinghai province in the northwest of China (31 ° 36'-39 ° 19' in north latitude, 89 ° 35'-103 ° 04' in east longitude), and the total area is about 69.67 ×104km2. The average elevation of the research area is more than 3000 m, and belongs to the continental plateau climate. The annual average air temperature is-5.7 ℃ to 8.5 ℃, the annual total precipitation is 50mm to 450mm, and the annual total solar radiation is 690.8kJ to 753.6kJ (Deng et al, 2017). The area of the alpine grassland is about 41.19 multiplied by 104km2, which accounts for 59.13 percent of the total area of Qinghai province. Major grassland types include alpine meadow, alpine grassland and temperate grassland (Qinghai et al 2012). The grassland growing season begins at the beginning of 5 months and ends in the next 9 months (Qinghai et al 2012).
S12: preprocessing the data information to obtain a preprocessing result;
in the implementation process of the application, the preprocessing the data information to obtain a preprocessing result comprises the following steps: initializing the remote sensing image information to obtain a remote sensing image information initialization result; initializing the alpine grassland monitoring data information to obtain an alpine grassland monitoring data information initialization result; and initializing the environment data information to obtain an environment data information initialization result.
Further, the initializing the remote sensing image information to obtain a remote sensing image information initializing result includes: converting MOD09A1 and MCD12Q1 data in the remote sensing image information from sinusoidal projection to Albers projection by using an MODIS reprojection tool, converting an HDF format into a Geo-Tiff format, and then carrying out image fusion and MCD12Q1 data reclassification to obtain a remote sensing image information initialization result; initializing the alpine grassland monitoring data information to obtain an alpine grassland monitoring data information initializing result, comprising the following steps: sequentially carrying out vectorization, projection conversion and outlier rejection processing on the alpine grassland monitoring data information to obtain an alpine grassland monitoring data information initialization result; and initializing the environment data information to obtain an environment data information initialization result. Comprising the following steps: and sequentially performing spatial interpolation, projection conversion and grid resampling on the environmental data information to obtain an environmental data information initialization result.
Specifically, the preprocessing of the remote sensing image data mainly comprises radiation correction, atmosphere correction and image fusion. MOD09A1 and MCD12Q1 data are converted from sinusoidal projection to Albers projection by using an MODIS Reprojection Tool (MRT), and HDF format is converted into Geo-Tiff format, and image fusion and MCD12Q1 data reclassification are performed. The pretreatment of the alpine grassland monitoring data mainly comprises vectorization, projection conversion and outlier rejection. Outlier rejection is mainly carried out by adopting a mean value +/-2X standard deviation method. The preprocessing of the environmental data such as geography, soil, weather and the like mainly comprises spatial interpolation, projection conversion and grid resampling. Where the meteorological data is interpolated primarily using Anuspli software (written by Hutchinson professor of the national university of Australia). In addition, in order to conveniently calculate the AG-AGB, the projection of all the data is converted into Albers projection, the format of the projection is adjusted to Geo Tiff, and environmental data with different spatial resolutions are resampled by adopting a Nearest Neighbor Method (NNM) to generate raster data with the spatial resolution of 500m multiplied by 500 m.
S13: performing index extraction processing based on the pretreatment result to obtain a remote sensing index and an environment index;
in the specific implementation process of the invention, the index extraction processing based on the pretreatment result to obtain a remote sensing index and an environment index comprises the following steps: and sequentially extracting the remote sensing index and the environment index based on the pretreatment result to obtain the remote sensing index and the environment index.
Further, the remote sensing index extraction processing comprises obtaining 7 VIS and 5 spectrum indexes from MOD09A1 data in the pretreatment result based on ENVI software, and extracting the maximum value of each visible light and spectrum index; the environment index extraction processing comprises acquiring the topographic indexes of longitude, latitude, altitude, gradient and slope direction from a space plane radar topographic task digital elevation model product in the preprocessing result based on ArcGIS software.
Specifically, the remote sensing index extraction is mainly to use ENVI software for obtaining 7 VIS (NDVI, EVI, SAVI, MSAVI, OSAVI, SATVI and RVI) and 5 spectral indexes (B7/B2, B2-B7, B7/B5, B5/B7 and (B5-B7)/(b5+b7)) from MOD09A1 data, and extract the maximum value of each of the visible light and spectral indexes (only 7 months and 8 months) of the investigation region.
The environmental index mainly comprises data such as topography, soil, weather and the like. And acquiring terrain indexes such as longitude, latitude, altitude, gradient, slope direction and the like from a space shuttle radar terrain task (SRTM) Digital Elevation Model (DEM) product by using ArcGIS software. Soil indexes such as 0-30cm sand soil content, 0-30cm clay content, 30-60cm sand soil content, 30-60cm clay content, 0-30cm sand soil clay ratio, 30-60cm sand soil clay ratio, organic matter content, total nitrogen content, total phosphorus content, total potassium content, pH and the like are obtained from soil data with spatial resolution of 1 km. Meteorological indexes such as annual average temperature, annual total precipitation, annual total solar radiation, annual accumulated temperature of >0 years, wettability and the like are obtained from the meteorological data.
S14: constructing an index system by utilizing the remote sensing index, the environment index and the alpine grassland biomass based on an XGboost algorithm and correlation analysis;
in the implementation process of the invention, the construction of an index system based on the XGboost algorithm and the correlation analysis by using the remote sensing index, the environment index and the alpine grassland biomass comprises the following steps: performing index analysis processing of the remote sensing index and the environment index for estimating the alpine grassland biomass based on the correlation analysis to obtain an initial estimation index of the alpine grassland biomass estimation; performing redundancy removal on the initial estimation index of the alpine grassland biomass estimation based on an XGboost algorithm to obtain an estimation index of the alpine grassland biomass estimation; and constructing an index system based on the estimation index, the environment index and the alpine grassland biomass.
Specifically, firstly, selecting AG-AGB estimation indexes by adopting a correlation analysis method; then, based on the correlation analysis result, an extreme gradient lifting (XGBoost) algorithm is introduced to determine an AG-AGB estimation index. The XGBoost algorithm provides an inherent measure of Feature Importance (FI) as a method of determining all relevant features or indicators. The XGBoost algorithm may rank the entire FI by averaging the FI in each tree, which is calculated based on the amount of information obtained after the tree is segmented using features. In order to accurately acquire key indexes and reduce data redundancy among indexes, the study adopts a XGBoost algorithm and a correlation analysis method, and remarkably important and irrelevant indexes are selected to estimate AG-AGB. The XGBoost algorithm is briefly described as follows:
a classification model based on an AGB estimation index system is established. The performance of the indicators in the classification model is checked to obtain FIs and ranked in descending order. The formula of FI is:
where H (T) and H (T|F) are entropy of parent and child nodes of the F-feature based segmentation, p i Is the fraction of each marked sample on a node. And selecting a plurality of indexes with higher FI values to generate an index subset, and classifying again. This process is repeated until all the indices are selected, the classification of all the subsets is checked, and the best index subset (i.e., the subset with relatively higher area and fewer indices under the curve value) is selected. And finally, constructing an index system according to the estimation index, the environment index and the alpine grassland biomass.
S15: carrying out optimization selection processing on the satellite driving model based on the index system to obtain an optimization model with optimization selection;
in the implementation process of the invention, the satellite driving model comprises a multiple linear regression model, a BP neural network model, a support vector machine model and a random forest model.
Further, the optimizing selection processing is performed on the satellite driving model based on the index system to obtain an optimizing model for optimizing selection, which comprises the following steps: determining precision parameters, wherein the precision parameters comprise a decision coefficient, a relative root mean square error and a residual error prediction deviation; and referring to the residual prediction bias of each model in the satellite driving model, comparing the determined coefficient sizes of each model when the residual prediction bias of each model is in the same interval, and then referring to the relative root mean square error sizes to obtain an optimized model for optimization selection.
Specifically, the satellite driving model comprises a multiple linear regression model, a BP neural network model, a support vector machine model and a random forest model.
The multiple linear regression model takes AG-AGB as a dependent variable (Y), and the corresponding AG-AGB estimation index as an independent variable (X);
wherein beta is i Is the i-th weight coefficient determined according to expert experience.
The BP neural network model is a multi-layer forward neural network based on an error back propagation algorithm, typically consisting of an input layer, an output layer, and one or more hidden layers. It can learn and train using guided learning methods and can simulate the relationship between any nonlinear input variable and output variable. The learning process mainly includes forward propagation of the input signal and backward propagation of the error. The training process includes continuously adjusting the connection weights using a steepest descent method and a back-propagation algorithm until the output mean square error meets the required criteria. The formulas for signal propagation and Mean Square Error (MSE) are expressed as follows:
o j ＝f i (∑w ji o i +θ j )；
o k ＝f j (∑w kj o j +θ k )；
in θ j Is hidden layer information; o (o) i Is input layer information (AG-AGB estimation index); w (w) ji Is the weight of the input layer to the hidden layer; θ j Is a threshold for the hidden layer; f (f) i Is a tranlm function of the input layer to the hidden layer; o (o) k Is output layer information (AG-AGB estimate); w (w) ki Is the weight of the hidden layer to the output layer; θ k Is the threshold of the output layer; f (f) j Is a purelin function of the hidden layer to the output layer; o is AG-AGB field measurement data; n is the number of samples.
The support vector machine model was proposed by cores and Vapnik (1995) which non-linearly transformed the training dataset by defining a kernel function and mapping it to a high-dimensional feature space, solving the practical problem (small sample, non-linearity, high and local minima). The expression of the SVM model is as follows:
Wherein f (x) is an AG-AGB estimate; w (w) i Is a weight vector; b is the deviation.Representing a nonlinear transfer function. Cortes and Vapnik (1995) introduced the following convex optimization problem with e-insensitive loss function to obtain a solution to the following equation:
in the formula, w is 2 Represents flatness of the m-dimensional space; epsilon is a parameter representing the maximum allowable error between the observed value and the model prediction; zeta type toy i Andis a relaxation variable, penalizing training errors using a loss function over the error margin ζ; c is a positive compromise parameter that determines the magnitude of the empirical error in the optimization problem. The above equation is typically solved in a dual form with the lagrangian multiplier and the applied optimality condition.
Wherein the method comprises the steps ofIs a transformation of w. The SVM function is expressed as:
wherein the method comprises the steps ofIs a kernel function. A Radial Basis Function (RBF) is chosen as the kernel function. And determining a penalty parameter C and a kernel function parameter gamma of the support vector machine by adopting a cross-validation grid search algorithm.
The random forest model is an integrated learning method proposed by Breiman and Adele (2001), and has strong adaptability to a data set. It can handle high-dimensional features and does not easily produce overfitting. In addition, the model training speed is relatively fast. The expression of the RF model and its error are as follows:
F in K Is a predictive value for each decision tree; k is the number of decision trees;is the AG-AGB estimate of the out-of-bag data (OOB) that consists of the unextracted samples in the original samples. y is i Is in combination with->Corresponding AG-AGB actual measurement values; n is the OOB sample number.
In this study, three precision parameters were chosen to verify the effect of the model: coefficients (R2), relative Root Mean Square Error (RRMSE) and residual prediction bias (PRD) are determined. Wherein R is 2 Is used to measure the stability of the model. R is R 2 The larger the model, the more stable the model. RRMSE reflects the accuracy of the model. The smaller the RRMSE, the better the predictive power. The performance of the model was evaluated using RPD. When RPD is less than 1.4, the model is not good; when RPD is more than or equal to 1.4 and less than or equal to 2, the model has certain prediction capability; when RPD > 2, the model has a strong predictive power. Model accuracy judgment criteria: referring to the RPD value first, if the RPD is in the same interval, the model R is preferentially compared 2 The size, then the RRMSE size is considered, and the optimal model judgment principle is R 2 Relatively large, RRMSE relatively small.
The precision evaluation index expression is as follows:
wherein y is i Is the measured value of the i-th sample;is the predicted value of the i-th sample; />Is the measured average of the samples; n is the number of samples.
S16: and carrying out space-time dynamic analysis processing on the alpine grassland biomass based on the optimization model of optimization selection to obtain an alpine grassland biomass analysis result.
In the specific implementation process of the invention, the optimization model based on optimization selection performs space-time dynamic analysis processing on the alpine grassland biomass to obtain the analysis result of the alpine grassland biomass, and the method comprises the following steps: performing Sen and Mann-Kendall trend analysis on the alpine grassland biomass based on the optimization model selected by optimization to obtain a first analysis result; R/S analysis is carried out on the alpine grassland biomass based on the optimization model selected by optimization, and a second analysis result is obtained; and performing superposition judgment based on the first analysis result and the second analysis result to obtain the alpine grassland biomass analysis result.
Specifically, the Sen and Mann-Kendall trend analysis method is adopted, and is based on two key parameters (slope beta and statistic |Z s I) analyzed the dynamic trend of AG-AGB in 2005-2018. Beta is obtained by Sen trend analysis and is expressed as:
in AGB i And AGB j AGB values for the i and j th years, respectively. Beta is the slope; beta > 0 indicates that AGB increased from 2005 to 2018And vice versa. Calculating parameter Z using Mann-Kendall test equation s |；
Where n is the time series length (n=14), i is 2005, 2006, …,2018, when |z given the significance level α s |＞u 1-α/2 At this time, representing significant changes in the time series data studied at the α level, generally α=0.05, when |z s When the I is more than 1 and 96, the confidence level alpha of the time sequence is less than 0.05, and Z is shown s The level of 1.96 is more than 0.05.
The Hurst index is a useful statistical method for estimating the autocorrelation characteristics of a time series, and predicting the sustainability of future vegetation trends through R/S analysis calculations. The expression of the Hurst index is:
R u ＝max 1≤t≤u X(t，u)-min 1≤t≤u X(t，u)，u＝1，2，…，n；
wherein R is u Is a range sequence; s is S u Is a standard deviation sequence. When R/S is ≡u H When AGB time series appear in Hurst phenomenon, hurst index is expressed by H value. The H value may be obtained using a least squares method based on an equation:
where H is the slope of the line; a is the intercept of a straight line. When H > 0.5, the change in AGB is sustainable; when H.ltoreq.0.5, the change in AGB is not sustainable.
To clearly determine whether the AG-AGB trend was good or bad, sen and Mann-Kendall trend analysis (beta and Z were used s ) And R/S analysis (H) for superposition judgment. The criteria are shown in the following table.
AG-AGB dynamic change trend judgment standard table
In the embodiment of the invention, a set of grassland biomass monitoring index system is constructed by mainly using an XGBoost algorithm and a correlation analysis method through exploring the relation between indexes and biomass, then a plurality of linear/nonlinear inversion models are constructed according to the constructed index system, an optimal satellite driving model can be determined through model precision comparison, a space-time distribution diagram of AG-AGB is drawn, and the space-time dynamic change of AG-AGB is analyzed.
Example two
Referring to fig. 2, fig. 2 is a schematic structural diagram of a alpine grassland biomass estimation system based on a satellite driving model according to an embodiment of the invention.
As shown in fig. 2, a system for estimating the biomass of alpine grasslands based on a satellite driving model, the system comprising:
obtaining module 21: the method comprises the steps of obtaining data information, wherein the data information comprises remote sensing image information, alpine grassland monitoring data information and environment data information;
in the implementation process of the invention, the region needing to be subjected to the evaluation of the biomass of the alpine grasslands is firstly determined, and then the data information of the region is obtained, wherein the data information comprises remote sensing image information, alpine grasslands monitoring data information and environment data information.
Specifically, in the present application, it was determined that the region where the evaluation of the biomass of the alpine grassland is required is located in Qinghai province in the northwest of China (31 ° 36'-39 ° 19' in north latitude, 89 ° 35'-103 ° 04' in east longitude), and the total area is about 69.67 ×104km2. The average elevation of the research area is more than 3000 m, and belongs to the continental plateau climate. The annual average air temperature is-5.7 ℃ to 8.5 ℃, the annual total precipitation is 50mm to 450mm, and the annual total solar radiation is 690.8kJ to 753.6kJ (Deng et al, 2017). The area of the alpine grassland is about 41.19 multiplied by 104km2, which accounts for 59.13 percent of the total area of Qinghai province. Major grassland types include alpine meadow, alpine grassland and temperate grassland (Qinghai et al 2012). The grassland growing season begins at the beginning of 5 months and ends in the next 9 months (Qinghai et al 2012).
The preprocessing module 22: the data information preprocessing method comprises the steps of preprocessing the data information to obtain a preprocessing result;
in the implementation process of the application, the preprocessing the data information to obtain a preprocessing result comprises the following steps: initializing the remote sensing image information to obtain a remote sensing image information initialization result; initializing the alpine grassland monitoring data information to obtain an alpine grassland monitoring data information initialization result; and initializing the environment data information to obtain an environment data information initialization result.
Further, the initializing the remote sensing image information to obtain a remote sensing image information initializing result includes: converting MOD09A1 and MCD12Q1 data in the remote sensing image information from sinusoidal projection to Albers projection by using an MODIS reprojection tool, converting an HDF format into a Geo-Tiff format, and then carrying out image fusion and MCD12Q1 data reclassification to obtain a remote sensing image information initialization result; initializing the alpine grassland monitoring data information to obtain an alpine grassland monitoring data information initializing result, comprising the following steps: sequentially carrying out vectorization, projection conversion and outlier rejection processing on the alpine grassland monitoring data information to obtain an alpine grassland monitoring data information initialization result; and initializing the environment data information to obtain an environment data information initialization result. Comprising the following steps: and sequentially performing spatial interpolation, projection conversion and grid resampling on the environmental data information to obtain an environmental data information initialization result.
Specifically, the preprocessing of the remote sensing image data mainly comprises radiation correction, atmosphere correction and image fusion. MOD09A1 and MCD12Q1 data are converted from sinusoidal projection to Albers projection by using an MODIS Reprojection Tool (MRT), and HDF format is converted into Geo-Tiff format, and image fusion and MCD12Q1 data reclassification are performed. The pretreatment of the alpine grassland monitoring data mainly comprises vectorization, projection conversion and outlier rejection. Outlier rejection is mainly carried out by adopting a mean value +/-2X standard deviation method. The preprocessing of the environmental data such as geography, soil, weather and the like mainly comprises spatial interpolation, projection conversion and grid resampling. Where the meteorological data is interpolated primarily using Anuspli software (written by Hutchinson professor of the national university of Australia). In addition, in order to conveniently calculate the AG-AGB, the projection of all the data is converted into Albers projection, the format of the projection is adjusted to Geo Tiff, and environmental data with different spatial resolutions are resampled by adopting a Nearest Neighbor Method (NNM) to generate raster data with the spatial resolution of 500m multiplied by 500 m.
The index extraction module 23: the method is used for carrying out index extraction processing based on the pretreatment result to obtain a remote sensing index and an environment index;
in the specific implementation process of the invention, the index extraction processing based on the pretreatment result to obtain a remote sensing index and an environment index comprises the following steps: and sequentially extracting the remote sensing index and the environment index based on the pretreatment result to obtain the remote sensing index and the environment index.
Further, the remote sensing index extraction processing comprises obtaining 7 VIS and 5 spectrum indexes from MOD09A1 data in the pretreatment result based on ENVI software, and extracting the maximum value of each visible light and spectrum index; the environment index extraction processing comprises acquiring the topographic indexes of longitude, latitude, altitude, gradient and slope direction from a space plane radar topographic task digital elevation model product in the preprocessing result based on ArcGIS software.
Specifically, the remote sensing index extraction is mainly to use ENVI software for obtaining 7 VIS (NDVI, EVI, SAVI, MSAVI, OSAVI, SATVI and RVI) and 5 spectral indexes (B7/B2, B2-B7, B7/B5, B5/B7 and (B5-B7)/(b5+b7)) from MOD09A1 data, and extract the maximum value of each of the visible light and spectral indexes (only 7 months and 8 months) of the investigation region.
The environmental index mainly comprises data such as topography, soil, weather and the like. And acquiring terrain indexes such as longitude, latitude, altitude, gradient, slope direction and the like from a space shuttle radar terrain task (SRTM) Digital Elevation Model (DEM) product by using ArcGIS software. Soil indexes such as 0-30cm sand soil content, 0-30cm clay content, 30-60cm sand soil content, 30-60cm clay content, 0-30cm sand soil clay ratio, 30-60cm sand soil clay ratio, organic matter content, total nitrogen content, total phosphorus content, total potassium content, pH and the like are obtained from soil data with spatial resolution of 1 km. Meteorological indexes such as annual average temperature, annual total precipitation, annual total solar radiation, annual accumulated temperature of >0 years, wettability and the like are obtained from the meteorological data.
Index system construction module 24: the method is used for constructing an index system by utilizing the remote sensing index, the environment index and the alpine grassland biomass based on the XGboost algorithm and the correlation analysis;
in the implementation process of the invention, the construction of an index system based on the XGboost algorithm and the correlation analysis by using the remote sensing index, the environment index and the alpine grassland biomass comprises the following steps: performing index analysis processing of the remote sensing index and the environment index for estimating the alpine grassland biomass based on the correlation analysis to obtain an initial estimation index of the alpine grassland biomass estimation; performing redundancy removal on the initial estimation index of the alpine grassland biomass estimation based on an XGboost algorithm to obtain an estimation index of the alpine grassland biomass estimation; and constructing an index system based on the estimation index, the environment index and the alpine grassland biomass.
Specifically, firstly, selecting AG-AGB estimation indexes by adopting a correlation analysis method; then, based on the correlation analysis result, an extreme gradient lifting (XGBoost) algorithm is introduced to determine an AG-AGB estimation index. The XGBoost algorithm provides an inherent measure of Feature Importance (FI) as a method of determining all relevant features or indicators. The XGBoost algorithm may rank the entire FI by averaging the FI in each tree, which is calculated based on the amount of information obtained after the tree is segmented using features. In order to accurately acquire key indexes and reduce data redundancy among indexes, the study adopts a XGBoost algorithm and a correlation analysis method, and remarkably important and irrelevant indexes are selected to estimate AG-AGB. The XGBoost algorithm is briefly described as follows:
a classification model based on an AGB estimation index system is established. The performance of the indicators in the classification model is checked to obtain FIs and ranked in descending order. The formula of FI is:
where H (T) and H (T|F) are entropy of parent and child nodes of the F-feature based segmentation, p i Is the fraction of each marked sample on a node. And selecting a plurality of indexes with higher FI values to generate an index subset, and classifying again. This process is repeated until all the indices are selected, the classification of all the subsets is checked, and the best index subset (i.e., the subset with relatively higher area and fewer indices under the curve value) is selected. And finally, constructing an index system according to the estimation index, the environment index and the alpine grassland biomass.
The optimization selection module 25: the method comprises the steps of carrying out optimization selection processing on a satellite driving model based on an index system to obtain an optimization model with optimization selection;
in the implementation process of the invention, the satellite driving model comprises a multiple linear regression model, a BP neural network model, a support vector machine model and a random forest model.
Further, the optimizing selection processing is performed on the satellite driving model based on the index system to obtain an optimizing model for optimizing selection, which comprises the following steps: determining precision parameters, wherein the precision parameters comprise a decision coefficient, a relative root mean square error and a residual error prediction deviation; and referring to the residual prediction bias of each model in the satellite driving model, comparing the determined coefficient sizes of each model when the residual prediction bias of each model is in the same interval, and then referring to the relative root mean square error sizes to obtain an optimized model for optimization selection.
Specifically, the satellite driving model comprises a multiple linear regression model, a BP neural network model, a support vector machine model and a random forest model.
The multiple linear regression model takes AG-AGB as a dependent variable (Y), and the corresponding AG-AGB estimation index as an independent variable (X);
wherein beta is i Is the i-th weight coefficient determined according to expert experience.
The BP neural network model is a multi-layer forward neural network based on an error back propagation algorithm, typically consisting of an input layer, an output layer, and one or more hidden layers. It can learn and train using guided learning methods and can simulate the relationship between any nonlinear input variable and output variable. The learning process mainly includes forward propagation of the input signal and backward propagation of the error. The training process includes continuously adjusting the connection weights using a steepest descent method and a back-propagation algorithm until the output mean square error meets the required criteria. The formulas for signal propagation and Mean Square Error (MSE) are expressed as follows:
o j ＝f i (∑w ji o i +θ j )；
o k ＝f j (∑w kj o j +θ k )；
in θ j Is hidden layer information; o (o) i Is input layer information (AG-AGB estimation index); w (w) ji Is the weight of the input layer to the hidden layer; θ j Is a threshold for the hidden layer; f (f) i Is a tranlm function of the input layer to the hidden layer; o (o) k Is output layer information (AG-AGB estimate); w (w) kj Is the weight of the hidden layer to the output layer; θ k Is the threshold of the output layer; f (f) j Is a purelin function of the hidden layer to the output layer; o is AG-AGB field measurement data; n is the number of samples.
The support vector machine model was proposed by cores and Vapnik (1995) which non-linearly transformed the training dataset by defining a kernel function and mapping it to a high-dimensional feature space, solving the practical problem (small sample, non-linearity, high and local minima). The expression of the SVM model is as follows:
Wherein f (x) is an AG-AGB estimate; w (w) i Is a weight vector; b is the deviation.Representing a nonlinear transfer function. Cortes and Vapnik (1995) introduced the following convex optimization problem with e-insensitive loss function to obtain a solution to the following equation:
in the formula, w is 2 Represents flatness of the m-dimensional space; epsilon is a parameter representing the maximum allowable error between the observed value and the model prediction;ξ i andis a relaxation variable, penalizing training errors using a loss function over the error margin ζ; c is a positive compromise parameter that determines the magnitude of the empirical error in the optimization problem. The above equation is typically solved in a dual form with the lagrangian multiplier and the applied optimality condition.
Wherein the method comprises the steps ofIs a transformation of w. The SVM function is expressed as:
wherein the method comprises the steps ofIs a kernel function. A Radial Basis Function (RBF) is chosen as the kernel function. And determining a penalty parameter C and a kernel function parameter gamma of the support vector machine by adopting a cross-validation grid search algorithm.
The random forest model is an integrated learning method proposed by Breiman and Adele (2001), and has strong adaptability to a data set. It can handle high-dimensional features and does not easily produce overfitting. In addition, the model training speed is relatively fast. The expression of the RF model and its error are as follows:
F in K Is a predictive value for each decision tree; k is the number of decision trees;is the AG-AGB estimate of the out-of-bag data (OOB) that consists of the unextracted samples in the original samples. y is i Is in combination with->Corresponding AG-AGB actual measurement values; n is the OOB sample number.
In this study, three precision parameters were chosen to verify the effect of the model: determining coefficient (R) 2 ) Relative Root Mean Square Error (RRMSE) and residual prediction bias (PRD). Wherein R is 2 Is used to measure the stability of the model. R is R 2 The larger the model, the more stable the model. RRMSE reflects the accuracy of the model. The smaller the RRMSE, the better the predictive power. The performance of the model was evaluated using RPD. When RPD is less than 1.4, the model is not good; when RPD is more than or equal to 1.4 and less than or equal to 2, the model has certain prediction capability; when RPD > 2, the model has a strong predictive power. Model accuracy judgment criteria: referring to the RPD value first, if the RPD is in the same interval, the model R is preferentially compared 2 The size, then the RRMSE size is considered, and the optimal model judgment principle is R 2 Relatively large, RRMSE relatively small.
The precision evaluation index expression is as follows:
wherein y is i Is the measured value of the i-th sample;is the predicted value of the i-th sample; />Is the measured average of the samples; n is the number of samples.
Spatiotemporal dynamic analysis module 26: the method is used for carrying out space-time dynamic analysis processing on the alpine grassland biomass based on the optimization model of optimization selection to obtain the analysis result of the alpine grassland biomass.
In the specific implementation process of the invention, the optimization model based on optimization selection performs space-time dynamic analysis processing on the alpine grassland biomass to obtain the analysis result of the alpine grassland biomass, and the method comprises the following steps: performing Sen and Mann-Kendall trend analysis on the alpine grassland biomass based on the optimization model selected by optimization to obtain a first analysis result; R/S analysis is carried out on the alpine grassland biomass based on the optimization model selected by optimization, and a second analysis result is obtained; and performing superposition judgment based on the first analysis result and the second analysis result to obtain the alpine grassland biomass analysis result.
Specifically, the Sen and Mann-Kendall trend analysis method is adopted, and is based on two key parameters (slope beta and statistic |Z s I) analyzed the dynamic trend of AG-AGB in 2005-2018. Beta is obtained by Sen trend analysis and is expressed as:
in AGB i And AGB j AGB values for the i and j th years, respectively. Beta is the slope; beta > 0 indicates that AGB increases from 2005 to 2018 and vice versa. Calculating parameter Z using Mann-Kendall test equation s |；
Where n is the time series length (n=14), i is 2005, 2006, …,2018, when |z given the significance level α s |＞u 1-α/2 At this time, representing significant changes in the time series data studied at the α level, generally α=0.05, when |z s When the I is more than 1 and 96, the confidence level alpha of the time sequence is less than 0.05, and Z is shown s The level of 1.96 is more than 0.05.
The Hurst index is a useful statistical method for estimating the autocorrelation characteristics of a time series, and predicting the sustainability of future vegetation trends through R/S analysis calculations. The expression of the Hurst index is:
R u ＝max 1≤t≤u X(t，u)-min 1≤t≤u X(t，u)，u＝1，2，…，n；
wherein R is u Is the rangeA sequence; s is S u Is a standard deviation sequence. When R/S is ≡u H When AGB time series appear in Hurst phenomenon, hurst index is expressed by H value. The H value may be obtained using a least squares method based on an equation:
where H is the slope of the line; a is the intercept of a straight line. When H > 0.5, the change in AGB is sustainable; when H.ltoreq.0.5, the change in AGB is not sustainable.
To clearly determine whether the AG-AGB trend was good or bad, sen and Mann-Kendall trend analysis (beta and Z were used s ) And R/S analysis (H) for superposition judgment. The criteria are shown in the following table.
AG-AGB dynamic change trend judgment standard table
In the embodiment of the invention, a set of grassland biomass monitoring index system is constructed by mainly using an XGBoost algorithm and a correlation analysis method through exploring the relation between indexes and biomass, then a plurality of linear/nonlinear inversion models are constructed according to the constructed index system, an optimal satellite driving model can be determined through model precision comparison, a space-time distribution diagram of AG-AGB is drawn, and the space-time dynamic change of AG-AGB is analyzed.
Those of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be implemented by a program to instruct related hardware, the program may be stored in a computer readable storage medium, and the storage medium may include: read Only Memory (ROM), random access Memory (RAM, random Access Memory), magnetic or optical disk, and the like.
In addition, the method and the system for estimating the biomass of the alpine grassland based on the satellite driving model provided by the embodiment of the invention are described in detail, and specific examples are adopted to illustrate the principle and the implementation mode of the invention, and the description of the above examples is only used for helping to understand the method and the core idea of the invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (10)
1. A method for estimating the biomass of alpine grasslands based on a satellite driving model, which is characterized by comprising the following steps:
obtaining data information, wherein the data information comprises remote sensing image information, alpine grassland monitoring data information and environment data information;
preprocessing the data information to obtain a preprocessing result;
performing index extraction processing based on the pretreatment result to obtain a remote sensing index and an environment index;
constructing an index system by utilizing the remote sensing index, the environment index and the alpine grassland biomass based on an XGboost algorithm and correlation analysis;
carrying out optimization selection processing on the satellite driving model based on the index system to obtain an optimization model with optimization selection;
and carrying out space-time dynamic analysis processing on the alpine grassland biomass based on the optimization model of optimization selection to obtain an alpine grassland biomass analysis result.
2. The method for estimating the biomass of alpine grassland according to claim 1, wherein the preprocessing the data information to obtain the preprocessing result comprises:
initializing the remote sensing image information to obtain a remote sensing image information initialization result;
initializing the alpine grassland monitoring data information to obtain an alpine grassland monitoring data information initialization result;
And initializing the environment data information to obtain an environment data information initialization result.
3. The method for estimating the biomass of alpine grassland according to claim 2, wherein the initializing the remote sensing image information to obtain the remote sensing image information initializing result comprises:
converting MOD09A1 and MCD12Q1 data in the remote sensing image information from sinusoidal projection to Albers projection by using an MODIS reprojection tool, converting an HDF format into a Geo-Tiff format, and then carrying out image fusion and MCD12Q1 data reclassification to obtain a remote sensing image information initialization result;
initializing the alpine grassland monitoring data information to obtain an alpine grassland monitoring data information initializing result, comprising the following steps:
sequentially carrying out vectorization, projection conversion and outlier rejection processing on the alpine grassland monitoring data information to obtain an alpine grassland monitoring data information initialization result;
initializing the environment data information to obtain an environment data information initialization result; comprising the following steps:
and sequentially performing spatial interpolation, projection conversion and grid resampling on the environmental data information to obtain an environmental data information initialization result.
4. The method for estimating the biomass of alpine grassland according to claim 1, wherein the performing the index extraction process based on the preprocessing result to obtain the remote sensing index and the environmental index comprises:
sequentially extracting remote sensing indexes and environment indexes based on the pretreatment result to obtain the remote sensing indexes and the environment indexes;
the environmental data information includes ground data, soil data, and meteorological data.
5. The alpine grassland biomass estimation method of claim 4, wherein the remote sensing index extraction process comprises obtaining 7 VIs and 5 spectral indexes from MOD09A1 data in the preprocessing result based on ENVI software, and extracting a maximum value of each of the visible light and the spectral indexes;
the environmental index extraction processing comprises acquiring longitude, latitude, altitude, gradient and slope landform indexes from space plane radar landform task digital elevation model products in the preprocessing result based on ArcGIS software; acquiring soil indexes of 0-30cm sand content, 0-30cm clay content, 30-60cm sand content, 30-60cm clay content, 0-30cm sand clay ratio, 30-60cm sand clay ratio, organic matter content, total nitrogen content, total phosphorus content, total potassium content and pH from soil data; meteorological indexes of annual average temperature, annual total precipitation, annual total solar radiation, annual accumulated temperature of >0 years and wettability are obtained from the meteorological data.
6. The method for estimating the biomass of the alpine grasslands according to claim 1, wherein the constructing an index system based on the XGboost algorithm and the correlation analysis using the remote sensing index, the environmental index and the biomass of the alpine grasslands comprises:
performing index analysis processing of the remote sensing index and the environment index for estimating the alpine grassland biomass based on the correlation analysis to obtain an initial estimation index of the alpine grassland biomass estimation;
performing redundancy removal on the initial estimation index of the alpine grassland biomass estimation based on an XGboost algorithm to obtain an estimation index of the alpine grassland biomass estimation;
and constructing an index system based on the estimation index, the environment index and the alpine grassland biomass.
7. The method of claim 1, wherein the satellite driving model comprises a multiple linear regression model, a BP neural network model, a support vector machine model, and a random forest model.
8. The method for estimating the biomass of alpine grassland according to claim 7, wherein the optimizing selection process is performed on the satellite driving model based on the index system to obtain an optimizing model for optimizing selection, comprising:
Determining precision parameters, wherein the precision parameters comprise a decision coefficient, a relative root mean square error and a residual error prediction deviation;
and referring to the residual prediction bias of each model in the satellite driving model, comparing the determined coefficient sizes of each model when the residual prediction bias of each model is in the same interval, and then referring to the relative root mean square error sizes to obtain an optimized model for optimization selection.
9. The method for estimating the biomass of the alpine grassland according to claim 1, wherein the performing the spatiotemporal dynamic analysis processing on the biomass of the alpine grassland based on the optimization model of the optimization selection to obtain the analysis result of the biomass of the alpine grassland comprises:
performing Sen and Mann-Kendall trend analysis on the alpine grassland biomass based on the optimization model selected by optimization to obtain a first analysis result;
R/S analysis is carried out on the alpine grassland biomass based on the optimization model selected by optimization, and a second analysis result is obtained;
and performing superposition judgment based on the first analysis result and the second analysis result to obtain the alpine grassland biomass analysis result.
10. A alpine grassland biomass estimation system based on a satellite-driven model, the system comprising:
The obtaining module is as follows: the method comprises the steps of obtaining data information, wherein the data information comprises remote sensing image information, alpine grassland monitoring data information and environment data information;
and a pretreatment module: the data information preprocessing method comprises the steps of preprocessing the data information to obtain a preprocessing result;
the index extraction module is used for: the method is used for carrying out index extraction processing based on the pretreatment result to obtain a remote sensing index and an environment index;
the index system construction module: the method is used for constructing an index system by utilizing the remote sensing index, the environment index and the alpine grassland biomass based on the XGboost algorithm and the correlation analysis;
and an optimization selection module: the method comprises the steps of carrying out optimization selection processing on a satellite driving model based on an index system to obtain an optimization model with optimization selection;
and a space-time dynamic analysis module: the method is used for carrying out space-time dynamic analysis processing on the alpine grassland biomass based on the optimization model of optimization selection to obtain the analysis result of the alpine grassland biomass.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110412645.6A CN113297904B (en) | 2021-04-16 | 2021-04-16 | Method and system for estimating alpine grassland biomass based on satellite driving model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110412645.6A CN113297904B (en) | 2021-04-16 | 2021-04-16 | Method and system for estimating alpine grassland biomass based on satellite driving model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113297904A CN113297904A (en) | 2021-08-24 |
| CN113297904B true CN113297904B (en) | 2023-11-21 |
Family
ID=77318822
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110412645.6A Active CN113297904B (en) | 2021-04-16 | 2021-04-16 | Method and system for estimating alpine grassland biomass based on satellite driving model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113297904B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115598164B (en) * | 2022-12-14 | 2023-04-07 | 南京师范大学 | Machine learning integrated soil heavy metal concentration detection method and system |
| CN117387581B (en) * | 2023-12-12 | 2024-02-13 | 北京麦麦趣耕科技有限公司 | Cinnamomum camphora biomass estimation method, apparatus and storage medium |
| CN118152985B (en) * | 2024-05-09 | 2024-08-02 | 山东农业大学 | Method for estimating grassland biomass based on HASM |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103678914A (en) * | 2013-12-16 | 2014-03-26 | 中国科学院遥感与数字地球研究所 | Alpine grassland soil respiration estimation method based on satellite remote sensing data |
| CN104778451A (en) * | 2015-03-31 | 2015-07-15 | 中国科学院上海技术物理研究所 | Grassland biomass remote sensing inversion method considering grassland height factor |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109459392B (en) * | 2018-11-06 | 2019-06-14 | 南京农业大学 | A kind of rice the upperground part biomass estimating and measuring method based on unmanned plane multispectral image |
| CN109884664B (en) * | 2019-01-14 | 2022-12-02 | 武汉大学 | Optical microwave collaborative inversion method and system for urban overground biomass |
-
2021
- 2021-04-16 CN CN202110412645.6A patent/CN113297904B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103678914A (en) * | 2013-12-16 | 2014-03-26 | 中国科学院遥感与数字地球研究所 | Alpine grassland soil respiration estimation method based on satellite remote sensing data |
| CN104778451A (en) * | 2015-03-31 | 2015-07-15 | 中国科学院上海技术物理研究所 | Grassland biomass remote sensing inversion method considering grassland height factor |
Non-Patent Citations (2)
| Title |
|---|
| 基于ADC和MODIS遥感数据的高寒草地地上生物量监测研究――以黄河源区为例;葛静;孟宝平;杨淑霞;高金龙;殷建鹏;张仁平;冯琦胜;梁天刚;;草业学报(07);全文 * |
| 基于多源遥感数据的高寒草地生物量反演模型精度――以夏河县桑科草原试验区为例;孟宝平;陈思宇;崔霞;冯琦胜;梁天刚;;草业科学(11);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113297904A (en) | 2021-08-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113297904B (en) | Method and system for estimating alpine grassland biomass based on satellite driving model | |
| Zheng et al. | Improved estimation of rice aboveground biomass combining textural and spectral analysis of UAV imagery | |
| CN115356249B (en) | Satellite polarization PM2.5 estimation method and system based on machine learning fusion model | |
| Gos et al. | Combined TBATS and SVM model of minimum and maximum air temperatures applied to wheat yield prediction at different locations in Europe | |
| Li et al. | Actual evapotranspiration estimation over the Tuojiang River Basin based on a hybrid CNN-RF model | |
| CN114463616B (en) | Multi-source satellite precipitation fusion method based on Stacking and EMOS-CSG | |
| CN117114147A (en) | Method and device for estimating forest vegetation carbon reserves based on radar and satellite remote sensing | |
| CN117648863B (en) | Regional water supply capacity acquisition method under special drought conditions based on water system communication | |
| Hu et al. | Forecasting of solar radiation in photovoltaic power station based on ground‐based cloud images and BP neural network | |
| CN114880933A (en) | Atmospheric temperature and humidity profile inversion method and system for non-exploration-site foundation microwave radiometer based on reanalysis data | |
| CN117036928A (en) | Urban forest carbon sink measuring and calculating method and system based on remote sensing images and machine learning | |
| Shi et al. | High spatial-temporal resolution estimation of ground-based global navigation satellite system interferometric reflectometry (GNSS-IR) soil moisture using the genetic algorithm back propagation (GA-BP) neural network | |
| CN117437538A (en) | Tropical rainforest ecosystem space-time pattern feature extraction and prediction method | |
| CN117493476A (en) | Runoff backtracking simulation method and system integrating physical mechanism and artificial intelligence | |
| CN111597692B (en) | Method, system, electronic equipment and storage medium for estimating surface net radiation | |
| Sun et al. | Construction of a spatially gridded heat flux map based on airborne flux Measurements using remote sensing and machine learning methods | |
| Yahi et al. | Exploratory study for estimating atmospheric low level particle pollution based on vertical integrated optical measurements | |
| CN114357885B (en) | Photosynthetic effective radiation scattering proportion prediction method fusing multisource data | |
| CN115937714A (en) | Net Primary Productivity Estimation Method Based on Neural Network and CASA Model | |
| CN116229288A (en) | Urban river TSM concentration inversion method based on unmanned aerial vehicle multispectral image | |
| Yang et al. | Optimization of Hourly PM 2.5 Inversion Model Integrating Upper-Air Meteorological Elements | |
| You et al. | Crop Mapping of Complex Agricultural Landscapes Based on Discriminant Space | |
| CN114047563A (en) | All-weather assimilation method of infrared hyperspectrum | |
| Wu et al. | Estimating Forest Aboveground Biomass Using a Combination of Geographical Random Forest and Empirical Bayesian Kriging Models | |
| Jiang et al. | Surface global and diffuse solar radiation over China acquired from geostationary Multi-functional Transport Satellite data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |