CN116773516A - Soil carbon content analysis system based on remote sensing data - Google Patents
Soil carbon content analysis system based on remote sensing data Download PDFInfo
- Publication number
- CN116773516A CN116773516A CN202310463695.6A CN202310463695A CN116773516A CN 116773516 A CN116773516 A CN 116773516A CN 202310463695 A CN202310463695 A CN 202310463695A CN 116773516 A CN116773516 A CN 116773516A
- Authority
- CN
- China
- Prior art keywords
- soil
- remote sensing
- module
- carbon content
- sample
- 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.)
- Pending
Links
- 239000002689 soil Substances 0.000 title claims abstract description 139
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 67
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 67
- 238000004458 analytical method Methods 0.000 title claims abstract description 24
- 238000000034 method Methods 0.000 claims abstract description 35
- 238000007781 pre-processing Methods 0.000 claims abstract description 30
- 238000010276 construction Methods 0.000 claims abstract description 18
- 238000012417 linear regression Methods 0.000 claims abstract description 5
- 230000009466 transformation Effects 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 12
- 238000002310 reflectometry Methods 0.000 claims description 11
- 238000012360 testing method Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 7
- 238000005070 sampling Methods 0.000 claims description 7
- KMUONIBRACKNSN-UHFFFAOYSA-N potassium dichromate Chemical compound [K+].[K+].[O-][Cr](=O)(=O)O[Cr]([O-])(=O)=O KMUONIBRACKNSN-UHFFFAOYSA-N 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000010438 heat treatment Methods 0.000 claims description 2
- 238000001514 detection method Methods 0.000 description 3
- 230000005855 radiation Effects 0.000 description 3
- 230000003595 spectral effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 239000005416 organic matter Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 239000002253 acid Substances 0.000 description 1
- 239000003905 agrochemical Substances 0.000 description 1
- 239000011449 brick Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 125000002496 methyl group Chemical group [H]C([H])([H])* 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 230000003647 oxidation Effects 0.000 description 1
- 238000007254 oxidation reaction Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
- 239000002344 surface layer Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/58—Extraction of image or video features relating to hyperspectral data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
- G06V10/765—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects using rules for classification or partitioning the feature space
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/194—Terrestrial scenes using hyperspectral data, i.e. more or other wavelengths than RGB
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N2021/1793—Remote sensing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Immunology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Artificial Intelligence (AREA)
- Pathology (AREA)
- Chemical & Material Sciences (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Computing Systems (AREA)
- Remote Sensing (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Astronomy & Astrophysics (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a soil carbon content analysis system based on remote sensing data, which comprises: the system comprises a visible light image module, a soil sample acquisition module, a remote sensing image preprocessing module, a model construction module and a prediction module; the visible light image module is used for identifying the bare soil area; the soil sample acquisition module is used for acquiring soil information in the region to be detected; the remote sensing image acquisition module is used for acquiring an original remote sensing image of the region to be detected; the remote sensing image preprocessing module is used for preprocessing an original remote sensing image; the model construction module is used for constructing a soil carbon content prediction model; the prediction model is used for predicting the carbon content in the soil, and the method provides support for estimating the carbon content in the carbon library in the area by constructing a multiple linear regression equation.
Description
Technical Field
The invention relates to the technical field of soil carbon content estimation, in particular to a soil carbon content analysis system based on remote sensing data.
Background
The soil carbon pool is the main body of the carbon pool of the land ecological system and plays an important role in global carbon balance. Small changes in the soil organic carbon reservoir may lead to an ever-increasing atmospheric CO2 isothermal chamber gas by releasing carbon to the atmosphere, thereby accelerating the global air temperature rise rate. Soil is continuously distributed on the whole surface layer of land, and the time-space variability is continuous, so that the soil is difficult to monitor by means of general investigation and sample plot actual measurement.
The traditional soil nutrient monitoring method has the advantages that after the field fixed-point sampling, the samples are brought to a laboratory for agrochemical analysis, so that the time and the labor are consumed, the cost is high, the instantaneity is poor, the measuring points are few, and the representativeness is poor. Since the 70 s of the 20 th century, many students began to invert the spatial pattern of the organic matter content of the soil by using the Remote Sensing (RS) technology with large information quantity, short period and high efficiency and find that the organic matter of the soil has obvious spectral characteristics in the visible light-short wave infrared band range. In recent years, remote sensing methods are becoming more common in the research of soil organic carbon.
Therefore, how to accurately estimate the change of the carbon in the soil by using remote sensing data and technology, and analyze the spatial pattern of the carbon reserves in the land soil and the variability thereof, thereby providing theoretical basis for predicting the carbon fixing capacity of the future land ecological system, and having important theoretical significance and practical application significance.
Disclosure of Invention
In order to solve the problems in the prior art, the invention provides a soil carbon content analysis system based on remote sensing data.
In order to achieve the technical purpose, the invention provides the following technical scheme: a soil carbon content analysis system based on remote sensing data, comprising: the system comprises a visible light image module, a soil sample acquisition module, a remote sensing image preprocessing module, a model construction module and a prediction module;
the system comprises a visible light image module, a soil sample acquisition module, a remote sensing image preprocessing module, a model construction module and a prediction module, wherein the visible light image module is connected with the soil sample acquisition module, the remote sensing image acquisition module is connected with the remote sensing image preprocessing module, the soil sample acquisition module and the remote sensing image preprocessing module are both connected with the model construction module, and the model construction module is connected with the prediction module;
the visible light image module is used for identifying the bare soil area;
the soil sample acquisition module is used for acquiring soil information in a region to be detected;
the remote sensing image acquisition module is used for acquiring an original remote sensing image of the region to be detected;
the remote sensing image preprocessing module is used for preprocessing an original remote sensing image;
the model construction module is used for constructing a soil carbon content prediction model;
the prediction model is used for predicting the carbon content in the soil.
Optionally, the visible light image module includes an image acquisition unit and an image processing unit;
the image acquisition unit acquires a visible light image in a region to be detected based on a visible light camera;
the image processing unit is connected with the image acquisition unit and is used for receiving the visible light image in the to-be-detected area and extracting the bare soil area from the visible light image in the to-be-detected area.
Optionally, in the process that the image processing unit extracts the bare soil region from the image acquisition unit, the bare soil region and the non-bare soil region of the visible light image in the region to be detected are divided based on SU-Net deep learning algorithm, so as to obtain the bare soil region to be detected.
Optionally, the soil sample collection module comprises a sample acquisition unit and a sample processing unit;
the sample acquisition unit acquires a soil sample based on the bare soil area to be detected;
the sample processing unit is connected with the sample acquisition unit and is used for receiving the soil sample and measuring the carbon content of the soil sample.
Optionally, in the process of collecting the soil sample by the sample obtaining unit, sampling the soil in the to-be-detected area based on the checkerboard method to obtain the soil sample.
Optionally, in the process of preprocessing the soil sample by the sample processing unit, processing the soil sample based on a potassium dichromate oxidation-external heating method to obtain a plurality of carbon contents of the soil sample, and removing sample singular points based on the carbon contents of the soil sample to obtain a sample point set;
wherein the sample point set comprises a training set test set;
the training set and the test set each include a plurality of pre-treated soil samples and a plurality of pre-treated soil sample carbon contents.
Optionally, the method for eliminating the singular points of the samples comprises the following steps: mahalanobis distance method and prediction residual analysis method.
Optionally, the preprocessing of the original remote sensing image in the remote sensing image preprocessing module includes:
acquiring corresponding coordinates of a plurality of the pretreated soil samples based on the plurality of the pretreated soil samples;
mapping a plurality of coordinates to the original remote sensing image based on ArcGIS to obtain a fused remote sensing image;
preprocessing the fused remote sensing image based on a radiometric calibration and atmospheric correction method to obtain a plurality of band reflectivity values corresponding to a plurality of coordinates.
Optionally, in the process of constructing the soil carbon content prediction model by the model construction module, a multiple linear regression equation is established based on the carbon content of the plurality of preprocessed soil samples in the training set and the reflectivity value of the plurality of wave bands, so as to obtain the soil carbon content prediction model.
Optionally, the obtaining the reflectance values of the plurality of bands includes: reciprocal transformation, logarithmic transformation, reciprocal transformation, and first order differential transformation.
The invention has the following technical effects:
according to the invention, by constructing a multiple linear regression equation, the correlation relationship between the carbon content of soil and the reflectivity of different wave bands in the remote sensing hyperspectral image is established on the basis of the criteria of higher correlation coefficient, smaller standard deviation and higher significance. According to the multiple regression model, the prediction of the carbon content of the soil sample to be detected can be realized under the condition that laboratory detection is not allowed, and the detection cost is reduced. The method is suitable for predicting the carbon content of the soil in a large-area, and provides support for estimating the carbon content in the carbon library in the area.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present 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 system flow diagram 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
As shown in fig. 1, this embodiment discloses a soil carbon content analysis system based on remote sensing data, including: the system comprises a visible light image module, a soil sample acquisition module, a remote sensing image preprocessing module, a model construction module and a prediction module;
the system comprises a visible light image module, a soil sample acquisition module, a remote sensing image preprocessing module, a model construction module, a prediction module and a remote sensing image preprocessing module, wherein the visible light image module is connected with the soil sample acquisition module;
the visible light image module is used for identifying the bare soil area;
the soil sample acquisition module is used for acquiring soil information in the region to be detected;
the remote sensing image acquisition module is used for acquiring an original remote sensing image of the region to be detected;
the remote sensing image preprocessing module is used for preprocessing an original remote sensing image;
the model construction module is used for constructing a soil carbon content prediction model;
the prediction model is used for predicting the carbon content in the soil.
In the embodiment, the agricultural land in the North China plain area is taken as an object, and the method is suitable for carrying out remote sensing inversion research on the carbon content in large-area soil due to factors such as cultivation mode, climate and the like. By utilizing the characteristics of convenience in acquisition, wide spectrum range, wide coverage area and the like of the high-resolution first satellite and combining the soil geochemistry sampling analysis result of the region, a multi-band spectral reflectivity and a multi-element stepwise regression prediction model between the constructed spectral index and soil organic carbon are established, a rapid and efficient inversion method of soil carbon content remote sensing in the North China plain region is discussed, and support is provided for estimating the organic carbon library in the North China plain region.
1. Visible light image acquisition and preprocessing
And a fixed wing unmanned aerial vehicle is adopted to carry a visible light camera, and a visible light image in a region to be detected is collected.
The method comprises the steps of collecting weather conditions and terrain information in advance, collecting data in time under severe weather conditions, avoiding potential dangerous objects which can cause flight safety to an unmanned aerial vehicle, designing proper voyage to ensure that the resolution of images to the ground can reach decimeter level (which is superior to 30 cm), determining route planning information, and providing necessary preparation information for unmanned aerial vehicle flight outside industry data collection.
And (3) starting field collection, carrying out flight by using unmanned aerial vehicle carrying equipment according to a route planned route, obtaining a visible light image of an observation area, and storing the visible light image in an airborne memory card.
Dividing a bare soil region and a non-bare soil region of the visible light image in the region to be detected based on an SU-Net deep learning algorithm to obtain the bare soil region to be detected; the visible light image in the region to be detected is input for feature extraction, and the output classification mark is 0 (non-bare soil area) or 1 (bare soil area).
2. Sampling point distribution
Based on the geochemical sampling analysis result of the region in 2016, sampling soil in the region to be detected by adopting a checkerboard method in the obtained bare soil region in the region to be detected to obtain 186 soil samples and coordinate information of Jilin soil samples.
3. Soil sample pretreatment
After the soil sample is brought back to a laboratory, the invaded matters such as plant root systems, stone bricks, small animals and the like are selected, and after the invaded matters are air-dried, knocked and ground, the invaded matters are screened by a 100-mesh sieve, and then the soil organic carbon content is measured by adopting a heavy-complex acid methyl oxidation method.
The collection of the samples has certain randomness, meanwhile, because the measurement of the samples is influenced by various factors, errors and even errors exist, and in the actual detection, the detected sample data always show data deviating from the overall data or not conforming to the normal rule, which is called singular point. In the modeling process, even if few singular points are mixed, serious interference can be generated on model prediction and analysis, so that samples need to be screened before the model is built, and the singular points are removed, so that the built model can obtain higher precision.
In this embodiment, a mahalanobis distance method or a prediction residual error analysis method is adopted to perform sample singular point rejection, so as to obtain a sample point set, where the sample point set includes 173 sample points, such as descriptive statistics after soil sample division in table 1.
TABLE 1
The sample point set comprises a training set test set, wherein a training set sample comprises 138 sample points, and the test set comprises 35 sample points;
both the training set and the test set include a plurality of pre-treated soil samples and a plurality of pre-treated soil sample carbon contents.
4. Remote sensing image acquisition and preprocessing
The embodiment adopts a high-resolution one-size WFV1 data image, wherein the high-resolution one-size WFV1 data image is acquired from China resource satellite application center, is acquired in the 9 th month 15 th year 2016 (consistent with the acquisition time of soil samples), has the spatial resolution of 16m and comprises 4 wave bands of blue (450-520 nm), green (520-590 nm), red (630-690 nm) and near red (770-890 nm).
The multispectral image is used as an inversion base map of the organic carbon content of the soil, and needs to contain as much soil information as possible. Therefore, in addition to the pretreatment such as common radiation correction and geometric correction, the present study also performed removal of the water area and vegetation information on the image.
Based on the condition that the soil sample is processed by intervention, corresponding coordinates of a plurality of preprocessed soil samples are obtained; mapping a plurality of coordinates to an original remote sensing image based on ArcGIS to obtain a fused remote sensing image;
and preprocessing the fused remote sensing image based on a radiometric calibration and atmospheric correction method by adopting EVNI software to obtain a plurality of band reflectivity values corresponding to a plurality of coordinates.
Radiometric calibration is a process of converting a voltage or digital quantification recorded by a sensor into an absolute radiance value (radiance), or into a relative value related to physical quantities such as surface (apparent) reflectivity, surface (apparent) temperature, etc.
Atmospheric correction means that the total radiance of the ground target as ultimately measured by the sensor is not a reflection of the true reflectivity of the ground, including errors in the amount of radiation due to atmospheric absorption, especially scattering. The atmospheric correction is the process of eliminating radiation errors caused by atmospheric influences and inverting the actual surface reflectivity of the ground object.
5. Constructing a soil carbon content prediction model
And respectively performing reciprocal transformation, logarithmic transformation, reciprocal transformation and first-order differential transformation on the reflectivity values of the wave bands.
And respectively constructing multiple linear regression equations based on the reflectance value transformation form.
The soil carbon content prediction model is constructed by a multiple linear stepwise regression analysis method, 3 groups of parameters with correlation larger than 0.40,0.45,0.50 are selected to participate in the model construction respectively, and an inversion model is determined by a model determination coefficient R2 and a root mean square error RMSE.
6. Prediction of soil carbon content
According to the embodiment, the test set is input into the prediction model, the accuracy of the test model is shown, and the result shows that the multiple regression model in the embodiment is high in accuracy and suitable for predicting the carbon content of soil in an area.
The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (10)
1. A soil carbon content analysis system based on remote sensing data, comprising: the system comprises a visible light image module, a soil sample acquisition module, a remote sensing image preprocessing module, a model construction module and a prediction module;
the system comprises a visible light image module, a soil sample acquisition module, a remote sensing image preprocessing module, a model construction module and a prediction module, wherein the visible light image module is connected with the soil sample acquisition module, the remote sensing image acquisition module is connected with the remote sensing image preprocessing module, the soil sample acquisition module and the remote sensing image preprocessing module are both connected with the model construction module, and the model construction module is connected with the prediction module;
the visible light image module is used for identifying the bare soil area;
the soil sample acquisition module is used for acquiring soil information in a region to be detected;
the remote sensing image acquisition module is used for acquiring an original remote sensing image of the region to be detected;
the remote sensing image preprocessing module is used for preprocessing an original remote sensing image;
the model construction module is used for constructing a soil carbon content prediction model;
the prediction model is used for predicting the carbon content in the soil.
2. The remote sensing data based soil carbon content analysis system of claim 1, wherein: the visible light image module comprises an image acquisition unit and an image processing unit;
the image acquisition unit acquires a visible light image in a region to be detected based on a visible light camera;
the image processing unit is connected with the image acquisition unit and is used for receiving the visible light image in the to-be-detected area and extracting the bare soil area from the visible light image in the to-be-detected area.
3. The remote sensing data based soil carbon content analysis system of claim 2, wherein: and in the process of extracting the bare soil region from the image acquisition unit by the image processing unit, dividing the bare soil region and the non-bare soil region of the visible light image in the region to be detected based on an SU-Net deep learning algorithm to obtain the bare soil region to be detected.
4. The remote sensing data based soil carbon content analysis system of claim 3, wherein: the soil sample acquisition module comprises a sample acquisition unit and a sample processing unit;
the sample acquisition unit acquires a soil sample based on the bare soil area to be detected;
the sample processing unit is connected with the sample acquisition unit and is used for receiving the soil sample and measuring the carbon content of the soil sample.
5. The remote sensing data based soil carbon content analysis system of claim 4, wherein: in the process of collecting a soil sample by the sample acquisition unit, sampling soil in a to-be-detected area based on a checkerboard method to obtain the soil sample.
6. The remote sensing data based soil carbon content analysis system of claim 4, wherein: in the pretreatment process of the soil sample by a sample treatment unit, treating the soil sample based on a potassium dichromate oxidation-external heating method to obtain a plurality of carbon contents of the soil sample, and removing sample singular points based on the carbon contents of the soil sample to obtain a sample point set;
wherein the sample point set comprises a training set test set;
the training set and the test set each include a plurality of pre-treated soil samples and a plurality of pre-treated soil sample carbon contents.
7. The remote sensing data based soil carbon content analysis system of claim 6, wherein: the method for eliminating the singular points of the samples comprises the following steps: mahalanobis distance method and prediction residual analysis method.
8. The remote sensing data based soil carbon content analysis system of claim 6, wherein: the process for preprocessing the original remote sensing image in the remote sensing image preprocessing module comprises the following steps:
acquiring corresponding coordinates of a plurality of the pretreated soil samples based on the plurality of the pretreated soil samples;
mapping a plurality of coordinates to the original remote sensing image based on ArcGIS to obtain a fused remote sensing image;
preprocessing the fused remote sensing image based on a radiometric calibration and atmospheric correction method to obtain a plurality of band reflectivity values corresponding to a plurality of coordinates.
9. The remote sensing data based soil carbon content analysis system of claim 8, wherein: in the process of constructing a soil carbon content prediction model by the model construction module, a multiple linear regression equation is established based on the carbon content of the plurality of preprocessed soil samples in the training set and the reflectance values of the plurality of wave bands, so as to obtain the soil carbon content prediction model.
10. The remote sensing data based soil carbon content analysis system of claim 9, wherein: the method for obtaining the reflectivity values of the wave bands comprises the following steps: reciprocal transformation, logarithmic transformation, reciprocal transformation, and first order differential transformation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310463695.6A CN116773516A (en) | 2023-04-26 | 2023-04-26 | Soil carbon content analysis system based on remote sensing data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310463695.6A CN116773516A (en) | 2023-04-26 | 2023-04-26 | Soil carbon content analysis system based on remote sensing data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116773516A true CN116773516A (en) | 2023-09-19 |
Family
ID=88012305
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310463695.6A Pending CN116773516A (en) | 2023-04-26 | 2023-04-26 | Soil carbon content analysis system based on remote sensing data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116773516A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117114453A (en) * | 2023-10-24 | 2023-11-24 | 生态环境部华南环境科学研究所(生态环境部生态环境应急研究所) | Marine carbon sink state evaluation system based on aquatic organism observation |
-
2023
- 2023-04-26 CN CN202310463695.6A patent/CN116773516A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117114453A (en) * | 2023-10-24 | 2023-11-24 | 生态环境部华南环境科学研究所(生态环境部生态环境应急研究所) | Marine carbon sink state evaluation system based on aquatic organism observation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zheng et al. | Improved estimation of rice aboveground biomass combining textural and spectral analysis of UAV imagery | |
| Li et al. | Remote estimation of canopy height and aboveground biomass of maize using high-resolution stereo images from a low-cost unmanned aerial vehicle system | |
| CN108732129B (en) | System and method for representing farmland soil components by images | |
| CN109212505B (en) | A kind of forest stand characteristics inversion method based on the multispectral high degree of overlapping image of unmanned plane | |
| CN110174359B (en) | Aviation hyperspectral image soil heavy metal concentration assessment method based on Gaussian process regression | |
| CN114091613B (en) | Forest biomass estimation method based on high-score joint networking data | |
| CN111597756A (en) | Water quality parameter inversion method based on multispectral data of unmanned aerial vehicle | |
| Wan et al. | A model for phenotyping crop fractional vegetation cover using imagery from unmanned aerial vehicles | |
| CN114740180A (en) | Soil organic carbon estimation method and device based on multi-source remote sensing data | |
| CN115561181B (en) | Water quality inversion method based on unmanned aerial vehicle multispectral data | |
| CN114460013B (en) | Coastal wetland vegetation overground biomass GAN model self-learning remote sensing inversion method | |
| Cho et al. | Mapping beech (Fagus sylvatica L.) forest structure with airborne hyperspectral imagery | |
| CN114202675A (en) | Crop growth parameter determination method and system based on multispectral remote sensing image of unmanned aerial vehicle | |
| CN114241331B (en) | Remote sensing modeling method for ground biomass of reed in wetland by taking UAV as ground and Septinel-2 medium | |
| CN108898070A (en) | A kind of high-spectrum remote-sensing extraction Mikania micrantha device and method based on unmanned aerial vehicle platform | |
| CN113436153A (en) | Method for predicting carbon components of undisturbed soil profile based on hyperspectral imaging and support vector machine technology | |
| CN116773516A (en) | Soil carbon content analysis system based on remote sensing data | |
| Zhang et al. | An evaluation model for aboveground biomass based on hyperspectral data from field and TM8 in Khorchin grassland, China | |
| CN115494007A (en) | Random forest based high-precision rapid detection method and device for soil organic matters | |
| Yang et al. | Forest canopy height mapping over China using GLAS and MODIS data | |
| CN116148188A (en) | Air-space-ground integrated lake water quality tracing method, system, equipment and storage medium | |
| Lou et al. | An effective method for canopy chlorophyll content estimation of marsh vegetation based on multiscale remote sensing data | |
| Calou et al. | Estimation of maize biomass using unmanned aerial vehicles | |
| Berger et al. | The DAISEX campaigns in support of a future land-surface-processes mission | |
| Shanmugapriya et al. | Cotton yield prediction using drone derived LAI and chlorophyll content |
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 |