CN117746001B - High-precision estimation method for organic carbon in soil in karst trough region - Google Patents
High-precision estimation method for organic carbon in soil in karst trough region Download PDFInfo
- Publication number
- CN117746001B CN117746001B CN202311828013.3A CN202311828013A CN117746001B CN 117746001 B CN117746001 B CN 117746001B CN 202311828013 A CN202311828013 A CN 202311828013A CN 117746001 B CN117746001 B CN 117746001B
- Authority
- CN
- China
- Prior art keywords
- soil
- karst
- index
- organic carbon
- region
- 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
- 239000002689 soil Substances 0.000 title claims abstract description 41
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 title claims abstract description 32
- 229910052799 carbon Inorganic materials 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 17
- 238000011160 research Methods 0.000 claims abstract description 11
- 230000003595 spectral effect Effects 0.000 claims abstract description 8
- 230000002068 genetic effect Effects 0.000 claims abstract description 7
- 238000010801 machine learning Methods 0.000 claims abstract description 6
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 238000010586 diagram Methods 0.000 claims abstract description 5
- 238000005192 partition Methods 0.000 claims abstract description 4
- 238000012876 topography Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 5
- 238000007621 cluster analysis Methods 0.000 claims description 4
- 208000005156 Dehydration Diseases 0.000 claims description 3
- 208000027066 STING-associated vasculopathy with onset in infancy Diseases 0.000 claims description 3
- 239000004927 clay Substances 0.000 claims description 3
- 238000003066 decision tree Methods 0.000 claims description 3
- 230000010287 polarization Effects 0.000 claims description 3
- 238000001556 precipitation Methods 0.000 claims description 3
- 230000005855 radiation Effects 0.000 claims description 3
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000000638 solvent extraction Methods 0.000 claims description 3
- 239000002352 surface water Substances 0.000 claims description 3
- 238000004088 simulation Methods 0.000 abstract description 4
- 238000011835 investigation Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Landscapes
- Image Processing (AREA)
Abstract
The invention provides a high-precision estimation method of organic carbon in soil in a karst trough region, which comprises the steps of firstly collecting Sentinel-2 image data in the karst region, and preprocessing the image data; respectively calculating spectral indexes of the research karst drainage basin; dividing a research area into different areas by adopting a clustering algorithm surrounding a central partition PAM; optimizing the combination and selection of auxiliary variables for each region using a genetic algorithm GA; two machine learning algorithms are adopted to respectively establish soil organic carbon content prediction models in different subareas and the whole area; and generating a spatial distribution diagram of the organic carbon content of the soil in the karst trough region. According to the method, the remote sensing fine estimation of the organic carbon content of the soil in the karst trough region is realized, and the problem that the simulation accuracy is low due to the fact that a single model is used for simulating the SOC in the existing karst region is solved.
Description
Technical Field
The invention belongs to the technical field of ecological environment evaluation, and particularly relates to a high-precision estimation method for organic carbon in soil in a karst trough region.
Background
The rapid, accurate and large-scale acquisition of soil organic carbon space-time information is important for water and soil conservation, land carbon sink accounting and regional sustainable development. The karst region has special geology, and how to accurately monitor the organic carbon in the soil of the karst region faces a great challenge. The main method for the organic carbon in the soil in the karst region comprises the following steps: manual field investigation, ground instrument observation, ecological process model simulation and remote sensing monitoring. Although the traditional manual field investigation method has high accuracy, the field information acquisition is time-consuming and labor-consuming, and needs to face the environment conditions of complex terrains, bad climates and the like, so that the real-time monitoring of a large area cannot be realized. In addition, in fragile ecosystems, human interference can also cause damage to the land. The process model is difficult to realize and has high uncertainty in simulation of the organic carbon in the soil with large area due to the need of inputting a large amount of management measure data. However, satellite remote sensing is an important means for estimating the organic carbon of the current soil by virtue of the advantages of large scale, rapidness, high space-time resolution, low cost, strong operability and the like.
At present, most methods are used for modeling and estimating soil organic carbon based on the whole research area, and the remote sensing estimation of the soil organic carbon content in the karst area still has some defects, and the remote sensing fine estimation method of the soil organic carbon specially aiming at the karst landform area is lacking.
Disclosure of Invention
In order to solve the problems, the invention provides a high-precision estimation method for soil organic carbon in a karst trough region, which comprises the following specific technical scheme:
A high-precision estimation method for organic carbon in soil in a karst trough region comprises the following steps:
Step S1, firstly, acquiring Sentinel-2 image data of a karst region, and preprocessing the image data; collecting VV and VH polarization data of Sentinel-1, surface temperature LST data and annual average air temperature and precipitation data; extracting a topography index from a digital elevation model DEM of 12.5 m;
S2, respectively calculating the spectral indexes of the karst drainage basin in the research area according to the preprocessed Sentinel-2 data;
S3, dividing a research area into different areas by adopting a clustering algorithm surrounding a central partition PAM; after this partitioning, the combination and selection of auxiliary variables for each region is optimized using the genetic algorithm GA;
Step S4, based on the regional division result after cluster analysis and the factor screening result of the genetic algorithm, establishing a soil organic carbon content prediction model in different subregions and the whole region by adopting two machine learning algorithms; and generating a spatial distribution diagram of the organic carbon content of the soil in the karst trough region according to the prediction accuracy comparison of different models.
Further, in step S1, the preprocessing includes the radiation calibration, the atmosphere correction, the image stitching and the cutting processing of the Sentinel-2 image data;
Terrain indexes including elevation, terrain relief, gradient, slope direction and terrain humidity index TWI are extracted from the digital elevation model DEM of 12.5 m.
The spectral indexes of karst region in step S2 include a luminance index BI, a second luminance index BI2, a color index CI, a clay index CI1, a green-red vegetation index GRVI, a green normalized difference vegetation index GNDVI, a surface water index LSWI, a secondary corrected soil corrected vegetation index MSAVI2, a water stress index MSI, a redness index RI, a soil adjusted total vegetation index SATVI, a soil corrected vegetation index SAVI, a converted vegetation index TVI and a vegetation index V, and a total of 15 indexes.
In step S4, the two machine learning algorithms are respectively a random forest and a limit gradient lifting decision tree.
The beneficial effects of the invention are as follows: according to the invention, on the basis of fully considering environmental variables, remote sensing vegetation indexes and microwave remote sensing data, a cluster analysis method is introduced aiming at the characteristics of the topography of the karst region, a research region is reasonably divided, a soil organic carbon remote sensing estimation model suitable for the karst trough region is constructed, remote sensing fine estimation of the soil organic carbon content of the karst trough region is realized, and the problem that the simulation accuracy is lower due to the fact that a single model is used for simulating the SOC in the existing karst region is solved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. Like elements or portions are generally identified by like reference numerals throughout the several figures. In the drawings, the various elements are not necessarily drawn to scale.
FIG. 1 is a schematic diagram of a technical process of the present invention;
FIG. 2 is a schematic view of a region of a research karst region selected in an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. 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.
It should be understood that the terms "comprises" and "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It is also to be understood that the terminology used in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be further understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
As shown in FIG. 1, the embodiment of the invention provides a high-precision estimation method for soil organic carbon in karst regions, which comprises the following steps:
Step S1, selecting a southwest karst trough area as shown in FIG. 2 as a research karst area, firstly acquiring Sentinel-2 image data of the karst area, and preprocessing the image data; the pretreatment comprises the steps of radiation calibration, atmosphere correction, image stitching and cutting treatment on the Sentinel-2 image data. VV and VH polarization data of Sentinel-1, surface temperature (LST) data, annual average gas temperature and precipitation data were collected. 5 terrain indexes including elevation, terrain relief, slope direction and terrain humidity index (TWI) are extracted from a Digital Elevation Model (DEM) of 12.5 m.
Step S2, calculating and researching spectral indexes of the karst river basin according to the preprocessed Sentinel-2 data, wherein the spectral indexes comprise a Brightness Index (BI), a second brightness index (BI 2), a Color Index (CI), a clay index (CI 1), a green-red vegetation index (GRVI), a Green Normalized Difference Vegetation Index (GNDVI), a surface water index (LSWI), a secondary corrected soil corrected vegetation index (MSAVI 2), a water stress index (MSI), a Redness Index (RI), a total vegetation index after Soil Adjustment (SATVI), a vegetation index after soil correction (SAVI), a converted vegetation index (TVI) and a vegetation index (V), and the total is 15 indexes as shown in a table 1.
TABLE 1 index definition of spectral index
Here, ρgreen, ρred, ρnir, ρswir1, ρswir2 represent the reflectivities of the Green band (band 3), the Red band (band 4), the near infrared band (band 8), the far infrared band 1 (band 11), and the far infrared band 2 (band 12) of the Sentinel-2 image, respectively.
And S3, dividing the research area into three different areas by adopting a clustering algorithm surrounding a central Partition (PAM). After this partitioning, the combination and selection of auxiliary variables for each region is optimized using a Genetic Algorithm (GA).
And S4, based on the regional division result after cluster analysis and the factor screening result of the genetic algorithm, respectively establishing a soil organic carbon content prediction model in different subregions and the whole region by adopting two machine learning algorithms (random forest and extreme gradient lifting decision tree). And generating a spatial distribution diagram of the organic carbon content of the soil in the karst trough region according to the prediction accuracy comparison of different models.
Those of ordinary skill in the art will appreciate that the elements of the examples described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the elements of the examples have been described generally in terms of functionality in the foregoing description to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present application, it should be understood that the division of the units is merely a logic function division, and there may be other division manners in actual implementation, for example, multiple units may be combined into one unit, one unit may be split into multiple units, different unit combinations or some features may be omitted, etc.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention, and are intended to be included within the scope of the appended claims and description.
Claims (5)
1. The high-precision estimation method for the organic carbon in the soil in the karst trough area is characterized by comprising the following steps of:
Step S1, firstly, acquiring Sentinel-2 image data of a karst region, and preprocessing the image data; collecting VV and VH polarization data of Sentinel-1, surface temperature LST data and annual average air temperature and precipitation data; extracting a topography index from a digital elevation model DEM of 12.5 m;
s2, respectively calculating spectral indexes of the research karst basin according to the preprocessed Sentinel-2 data;
step S3, dividing a research area into three different areas by adopting a clustering algorithm surrounding a central partition PAM; after this partitioning, the combination and selection of auxiliary variables for each region is optimized using the genetic algorithm GA;
Step S4, based on the regional division result after cluster analysis and the factor screening result of the genetic algorithm, establishing a soil organic carbon content prediction model in different subregions and the whole region by adopting two machine learning algorithms; and generating a spatial distribution diagram of the organic carbon content of the soil in the karst trough region according to the prediction accuracy comparison of different models.
2. The method for estimating organic carbon in soil in a karst trough region with high accuracy according to claim 1, wherein in step S1, the preprocessing includes performing radiation calibration, atmospheric correction, image stitching and cropping on Sentinel-2 image data.
3. The method for estimating the organic carbon content of the soil in the karst trough region with high accuracy according to claim 1, wherein in the step S1, the topography index is extracted from a digital elevation model DEM of 12.5m, including elevation, topography relief, gradient, slope direction and topography humidity index TWI.
4. The method for estimating the organic carbon content of the soil in the karst trough region with high accuracy according to claim 1, wherein the spectral indexes of the karst basin in the step S2 include a luminance index BI, a second luminance index BI2, a color index CI, a clay index CI1, a green-red vegetation index GRVI, a green normalized difference vegetation index GNDVI, a surface water index LSWI, a secondary corrected soil corrected vegetation index MSAVI, a water stress index MSI, a redness index RI, a total vegetation index SATVI after soil adjustment, a vegetation index SAVI after soil correction, a converted vegetation index TVI, and a vegetation index V, and a total of 15 indexes.
5. The method for estimating the organic carbon in the soil of the karst trough region with high precision according to claim 1, wherein in the step S4, two machine learning algorithms are respectively a random forest and an extreme gradient lifting decision tree.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311828013.3A CN117746001B (en) | 2023-12-28 | 2023-12-28 | High-precision estimation method for organic carbon in soil in karst trough region |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311828013.3A CN117746001B (en) | 2023-12-28 | 2023-12-28 | High-precision estimation method for organic carbon in soil in karst trough region |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117746001A CN117746001A (en) | 2024-03-22 |
| CN117746001B true CN117746001B (en) | 2024-06-04 |
Family
ID=90259186
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311828013.3A Active CN117746001B (en) | 2023-12-28 | 2023-12-28 | High-precision estimation method for organic carbon in soil in karst trough region |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117746001B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110174506A (en) * | 2019-06-28 | 2019-08-27 | 中国科学院地球化学研究所 | A kind of Karst region soil organic matter evaluation method |
| CN114462579A (en) * | 2022-02-10 | 2022-05-10 | 中南大学 | Soil organic carbon content estimation method based on terrain and remote sensing data |
| CN114740180A (en) * | 2022-04-07 | 2022-07-12 | 中山大学 | Soil organic carbon estimation method and device based on multi-source remote sensing data |
| WO2022223681A1 (en) * | 2021-04-22 | 2022-10-27 | Smartcloudfarming Gmbh | System and method for estimating dynamic soil parameters based on multispectral or hyperspectral images |
| CN116183868A (en) * | 2023-02-03 | 2023-05-30 | 贵州大学 | Remote sensing estimation method and system for organic carbon in soil of complex ecological system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11606896B2 (en) * | 2021-01-12 | 2023-03-21 | Mineral Earth Sciences Llc | Predicting soil organic carbon content |
-
2023
- 2023-12-28 CN CN202311828013.3A patent/CN117746001B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110174506A (en) * | 2019-06-28 | 2019-08-27 | 中国科学院地球化学研究所 | A kind of Karst region soil organic matter evaluation method |
| WO2022223681A1 (en) * | 2021-04-22 | 2022-10-27 | Smartcloudfarming Gmbh | System and method for estimating dynamic soil parameters based on multispectral or hyperspectral images |
| CN114462579A (en) * | 2022-02-10 | 2022-05-10 | 中南大学 | Soil organic carbon content estimation method based on terrain and remote sensing data |
| CN114740180A (en) * | 2022-04-07 | 2022-07-12 | 中山大学 | Soil organic carbon estimation method and device based on multi-source remote sensing data |
| CN116183868A (en) * | 2023-02-03 | 2023-05-30 | 贵州大学 | Remote sensing estimation method and system for organic carbon in soil of complex ecological system |
Non-Patent Citations (3)
| Title |
|---|
| Ting Wang,Wei Zhou,Jieyun Xiao,Haoran Li,Li Yao,Lijuan Xie and Keming Wang.Soil Organic Carbon Prediction Using Sentinel-2 Data and Environmental Variables in a Karst Trough Valley Area of Southwest China.Remote Sensing.2023,全文. * |
| Wenping Yu ,Wei Zhou ,Ting Wang ,Jieyun Xiao ,Yao Peng ,Haoran Li and Yuechen Li.Significant Improvement in Soil Organic Carbon Estimation Using Data-Driven Machine Learning Based on Habitat Patches.Remote Sensing.2024,全文. * |
| 土壤有机碳含量高光谱建模研究 ——以青藏高原三江源区为例;周伟， 曹鑫， 王科明， 肖洁芸， 王婷， 李浩然， 姬翠翠;冰川冻土;20230430;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117746001A (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110751094B (en) | Crop yield estimation method based on GEE comprehensive remote sensing image and deep learning method | |
| CN108921885B (en) | Method for jointly inverting forest aboveground biomass by integrating three types of data sources | |
| CN111368736B (en) | Rice refined estimation method based on SAR and optical remote sensing data | |
| CN111242224B (en) | Multi-source remote sensing data classification method based on unmanned aerial vehicle extraction classification sample points | |
| CN103914678B (en) | Abandoned land remote sensing recognition method based on texture and vegetation indexes | |
| CN104462809A (en) | Grassland productivity estimation method based on remote sensing and GIS (geographic information system) | |
| Liu et al. | Estimating potato above-ground biomass by using integrated unmanned aerial system-based optical, structural, and textural canopy measurements | |
| CN104899448B (en) | A kind of self-adapting compensation method of the static localization scheme of Ensemble Kalman Filter | |
| CN103529189A (en) | Soil organic matter space distribution predication method based on qualitative and quantitative auxiliary variables | |
| CN109934109B (en) | Remote sensing-based method for extracting forest and grass vegetation information in loess plateau water and soil loss area | |
| CN109063553A (en) | Field-crop growth defect area's remote sensing fast diagnosis method after a kind of land control | |
| CN113205014B (en) | Time sequence data farmland extraction method based on image sharpening | |
| CN1996044B (en) | Canopy spatial statistics quantitative estimation method based on remote sensing image with fine spatial resolution | |
| CN113436153A (en) | Method for predicting carbon components of undisturbed soil profile based on hyperspectral imaging and support vector machine technology | |
| GB2620469A (en) | Spatial prediction and evaluation method of soil organic matter content based on partition algorithm | |
| CN115468917A (en) | Method and system for extracting crop information of farmland plot based on high-resolution remote sensing | |
| CN116881812A (en) | Method for estimating forest carbon reserves based on multisource remote sensing data and random forest method | |
| CN115496146A (en) | Urban ecological restoration priority identification method and device and electronic equipment | |
| CN114462579A (en) | Soil organic carbon content estimation method based on terrain and remote sensing data | |
| CN117746001B (en) | High-precision estimation method for organic carbon in soil in karst trough region | |
| CN109344769A (en) | A kind of photovoltaic plant detection method and system based on remote sensing image | |
| CN117152110A (en) | Rice AGB monitoring method based on image texture features | |
| CN111814666A (en) | Single tree parameter extraction method, system, medium and equipment under complex forest stand | |
| CN107063210A (en) | The mapping method of project is renovated in a kind of reallocation of land | |
| CN115841615A (en) | Tobacco yield prediction method and device based on multispectral data of unmanned aerial vehicle |
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 |