Soil carbon emission intelligent identification method based on multi-source remote sensing image fusion
Through the fusion of multi-source remote sensing images and the CENTURY model combined with time series data processing and isotope element labeling, the problem of accurate simulation of soil carbon emissions was solved, and intelligent identification and precise analysis of soil carbon emissions were achieved.
Patent Information
- Application Number
- CN202510459987.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-14
- Publication Date
- 2025-09-12
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing technologies make it difficult to accurately simulate soil carbon emissions through multi-source remote sensing images, especially to conduct effective analysis by combining data from optical, radar, and infrared remote sensing images.
The multi-source remote sensing image fusion method is used to store the remote sensing image data of each source in the CENTURY model. The carbon emission data is identified through time series data processing and isotope element labeling, and analyzed and called using the CENTURY model.
It achieves accurate and intelligent identification of soil carbon emissions, and improves the analysis accuracy and efficiency of soil carbon emission data.
Smart Images
Figure CN120635519A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of electronic digital data processing, and in particular relates to a method for intelligently identifying soil carbon emissions by fusing multi-source remote sensing images. Background Art
[0002] Multi-source remote sensing imagery refers to remote sensing image data acquired through different methods, including optical sensors, radar sensors, and infrared sensors. Optical sensors acquire and generate remote sensing images by recording reflected light in the visible and near-infrared bands; radar sensors utilize electromagnetic waves in the microwave band to acquire and generate remote sensing images; and infrared sensors acquire and generate remote sensing images using infrared light within a wide range of wavelengths.
[0003] Based on the ecological processes of the soil carbon cycle, including soil organic matter decomposition, plant root respiration, and soil microbial activity, soil also emits carbon. However, accurately simulating soil carbon emissions using multi-source remote sensing imagery and general mathematical models is difficult because general mathematical models cannot combine multi-source remote sensing imagery to simulate soil carbon emissions. However, the CENTURY model and multi-source remote sensing imagery can accurately analyze the obtained carbon emissions because the core functions of the CENTURY model include simulating the decomposition process of soil organic matter, plant growth, dynamic changes in soil organic matter, nutrient cycling, and key processes of the carbon cycle. Summary of the Invention
[0004] The present invention provides a method for intelligently identifying soil carbon emissions by fusing multi-source remote sensing images, which is used to solve the technical problem of how to integrate and intelligently identify soil carbon emissions. The carbon emission data in the remote sensing images of each source are used to identify the carbon emission data by using the isotope element quantity labeling method. The carbon emission data is identified or called according to the isotope element quantity of the carbon emission data in the remote sensing images of each source.
[0005] In order to achieve the above object, the present invention is implemented by the following technical solutions:
[0006] The intelligent identification method of soil carbon emissions based on multi-source remote sensing image fusion includes the following steps:
[0007] Step 1: Use the time series data processing method to store the remote sensing image data of each source in the CENTURY model, and the remote sensing image data of each source are stored separately according to the time series;
[0008] Step 2: Calculate or analyze carbon emission data from remote sensing images of each source using the CENTURY model based on the random arrangement of time series;
[0009] Step 3: Extract carbon emission data from remote sensing images of each source as appropriate, and use isotope element labeling to identify carbon emission data from remote sensing images of each source;
[0010] Step 4: Based on the identification of carbon emission data, call the carbon emission data.
[0011] Optionally, in step 1, the time series data processing method is the following formula (1):
[0012] (1);
[0013] in, For the time, From the first moment to the time, For Choose any moment in
[0014] For At any moment selected in For Select any operation at any time. For A moment chosen in For the Time series data, For A moment selected in the above corresponds to a certain time series data;
[0015] For the general Each moment in the Each time series data;
[0016] For the first time series data to the Time series data, To arrange the time series data in time sequence, for According to the first moment to the Arranged in order of time.
[0017] Optionally, the remote sensing image data of each source can be stored separately according to the time sequence, using the following method:
[0018] The remote sensing image data of each source is stored separately in sequence according to the time sequence; wherein the remote sensing image data of each source is stored separately in sequence according to the time sequence;
[0019] The remote sensing image data of each source are randomly stored separately according to a time sequence; wherein the remote sensing image data of each source are stored separately according to a random distribution of the time sequence.
[0020] Optionally, in step 2, a temporal random arrangement method is used to detect whether the carbon emission data in the remote sensing images of each source are arranged in temporal order. The temporal random arrangement method is as follows:
[0021] (2);
[0022] in, is the time range, including , Time range The operations are arranged in order of moments in time, Time range The moments in the are arranged in order;
[0023] The time series data included include , Arrange the time series data in time sequence. Arrange the included time series data in time sequence;
[0024] or Each moment corresponds to its own time series data.
[0025] Optionally, the carbon emission data in the remote sensing images of each source are randomly arranged in time sequence and then stored separately in sequence according to time sequence.
[0026] Optionally, in step 3, the carbon emission data in the remote sensing images of each source is extracted by:
[0027] Randomly extract carbon emission data from remote sensing images of a certain source according to the time series order;
[0028] Based on the random sampling method, carbon emission data from the remote sensing image of a certain source is randomly extracted.
[0029] Optionally, the isotope element quantity notation method is as follows (3):
[0030] (3);
[0031] in, To calibrate the Timing, is the number of isotopes of an element, To calculate the number of isotopes of an element, To calculate the The number of isotopic elements in the time series data, For the calibration In terms of timing, calculate the The number of isotopic elements in the time series data;
[0032] To calculate the first time series to the The number of each isotope element in the time series data;
[0033] for Follow the sequence from 1st to 2nd Timing of timing, for Operations arranged in time sequence.
[0034] Optionally, in step 4, the carbon emission data is called according to the isotope element amount of the carbon emission data in the remote sensing image of each source.
[0035] Optionally, in the process of calling the carbon emission data, the carbon emission data is called according to the amount of isotope elements in the carbon emission data in the remote sensing image of each source.
[0036] Beneficial effects of the present invention:
[0037] The present invention uses the carbon emission data in the remote sensing images of each source to identify the carbon emission data by using the isotope element quantity labeling method, and identifies or calls the carbon emission data according to the isotope element quantity of the carbon emission data in the remote sensing images of each source. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0039] Figure 1 Schematic diagram of the system structure of the present invention;
[0040] Figure 2 It is a workflow diagram of the present invention;
[0041] Figure 3 This is a schematic diagram of the carbon emission data storage principle of the present invention. DETAILED DESCRIPTION
[0042] The embodiments of the present application are described in detail below with reference to the accompanying drawings.
[0043] Example 1
[0044] like Figure 1 As shown, this embodiment provides a soil carbon emission intelligent identification system based on multi-source remote sensing image fusion, including:
[0045] Multiple sensors, each sensor is used to detect soil carbon emissions in a time series;
[0046] The image data module is used to perform image recognition on the detection conditions of each sensor in turn, and analyze the isotope elements in each sensor in turn to determine the isotope elements in each sensor. This is performed according to the software program.
[0047] A model data module, wherein the model data module is equipped with a CENTURY model, and is used to store remote sensing image data of each source in the CENTURY model, and to calculate or analyze carbon emission data in the remote sensing image of each source using the CENTURY model;
[0048] The data identification module is used to identify the carbon emission data in the remote sensing images of each source; the data identification module can be connected to the execution unit (not shown) to call the carbon emission data.
[0049] like Figure 1 As shown, multiple sensors are connected to the image data module, the image data module is connected to the model data module, and the model data module is further connected to the data recognition module.
[0050] Example 2
[0051] like Figure 2 As shown, this embodiment provides a method for intelligently identifying soil carbon emissions by fusion of multi-source remote sensing images, including the following steps:
[0052] Step 1: Use the time series data processing method to store the remote sensing image data of each source in the CENTURY model, and the remote sensing image data of each source are stored separately according to the time series;
[0053] Step 2: Calculate or analyze carbon emission data from remote sensing images of each source using the CENTURY model based on the random arrangement of time series;
[0054] Step 3: Extract carbon emission data from remote sensing images of each source as appropriate, and use isotope element labeling to identify carbon emission data from remote sensing images of each source;
[0055] Step 4: Based on the identification of carbon emission data, call the carbon emission data.
[0056] Example 3
[0057] Based on Example 2, specifically, in step 1, the time series data processing method is the following formula (1):
[0058] (1);
[0059] in, is the first moment, For the time, For the time, From the first moment to the time, For Choose any moment in
[0060] For At any moment selected in For Select any operation at any time. For A moment chosen in For the Time series data, For The moment selected in the above corresponds to a certain time series data, that is, Time series data Corresponding to the previous time , The working method is that the first time series data Corresponding to the first moment , No. Time series data Corresponding to the previous time , No. Time series data Corresponding to the previous time ;
[0061] For the general Each moment in the Each time series data, that is, the first moment corresponds to First time series data , No. time Corresponding to the previous Time series data , No. time Corresponding to the previous Time series data .
[0062] For the first time series data to the Time series data, To arrange the time series data in time sequence, for According to the first moment to the Arranged in order of time.
[0063] Remote sensing image data from various sources are stored separately according to time series in the following manner:
[0064] The remote sensing image data of each source is stored separately according to the time sequence; wherein, the remote sensing image data of each source is stored separately according to the time sequence, which is generally adopted;
[0065] The remote sensing image data of each source are randomly stored separately according to a time sequence; wherein the remote sensing image data of each source are stored separately according to a random distribution of the time sequence.
[0066] In step 2, the temporal random arrangement method is used to detect whether the carbon emission data in the remote sensing images of each source are arranged in time sequence. The temporal random arrangement method is as follows:
[0067] (2);
[0068] in, is the time range, including , Time range The operations are arranged in order of moments in time, Time range The moments in are arranged in order, i.e., according to Arrange in order;
[0069] The time series data included include , Arrange the time series data in time sequence. Arrange the time series data in chronological order, that is, according to Arrange in order;
[0070] or Each moment corresponds to its own time series data, that is, the first moment corresponds to First time series data , No. time Corresponding to the previous Time series data , No. time Corresponding to the previous Time series data .
[0071] The carbon emission data in the remote sensing images of each source are randomly arranged in time sequence, and then the carbon emission data in the remote sensing images of each source are stored separately in sequence according to time sequence.
[0072] In step 3, the carbon emission data in the remote sensing images of each source is extracted in the following way:
[0073] According to the time sequence, the carbon emission data from the remote sensing image of a certain source is randomly extracted, that is, according to Arranged in sequence In the ,random extraction of carbon emission data from remote sensing images of a certain source;
[0074] According to the random sampling method, carbon emission data from remote sensing images of a certain source are randomly extracted without Arranged in sequence In the , carbon emission data of a certain source is randomly extracted from the remote sensing image.
[0075] Regarding the isotope element quantity notation method, it is the following formula (3):
[0076] (3);
[0077] in, To calibrate the first time sequence, that is, to determine the first moment , To calibrate the The timing is determined as time , To calibrate the The timing is determined as time , is the number of isotopes of an element, To calculate the number of isotopes of an element, To calculate the number of isotope elements in the first time series data, To calculate the The number of isotopic elements in the time series data, To calculate the The number of isotopic elements in the time series data, To calculate the number of isotope elements in the first time series data at the calibrated first time series, For the calibration In terms of timing, calculate the The number of isotopic elements in the time series data, For the calibration In terms of timing, calculate the The number of isotopic elements in the time series data;
[0078] It is a data connection operation to connect the number of isotope elements in each time series data;
[0079] To calculate the first time series to the The number of each isotope element in the time series data;
[0080] for Follow the sequence from 1st to 2nd Timing of timing, for Operations arranged in time sequence.
[0081] Combined with formula (3) in step 3, in step 4, carbon emission data is called according to the isotope element amount of carbon emission data in the remote sensing image of each source. In the process of calling carbon emission data, carbon emission data is called according to the size of the isotope element amount of carbon emission data in the remote sensing image of each source. For example, carbon emission data is called according to the number of isotope elements in the carbon emission data in the remote sensing image of each source. Specifically, if the number of isotope elements in the first time series data is 5, then the number of isotope elements in the first time series data is 5. The number of isotopic elements in the time series data is 9. The number of isotopic elements in the time series data is 12.
[0082] It could be that as the time series increases, carbon emissions increase, such as small carbon emissions in the morning, increased carbon emissions at noon, and the largest carbon emissions in the afternoon. Therefore, as the time series increases, the number of isotope elements increases.
[0083] Example 4
[0084] Based on all the above embodiments, the first sensor is the first moment The first time series data obtained by scanning , similarly, The sensor is the time The scanned Time series data , No. The sensor is the time The scanned Time series data , Figure 2 The image data module recognizes the detection conditions of each sensor in turn, and analyzes the isotope elements in each sensor in turn. It can be assumed that the isotope element is C 12 The image data module analyzes or determines that the isotope element in each sensor is C 12 , therefore, formula (3) in step 3 calculates the number of isotope elements in each time series data.
[0085] like Figure 3 As shown, each carbon emission data can be stored in each storage unit in sequence from left to right, or each carbon emission data can be stored randomly and individually in each storage unit. Can be stored in the first storage unit to the The storage unit can also be, Randomly stored in the 1st storage unit to the In the storage unit.
[0086] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope of the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.
Claims
1. An intelligent identification method for soil carbon emissions based on multi-source remote sensing image fusion, characterized by: The steps include: Step 1: Use the time series data processing method to store the remote sensing image data of each source in the CENTURY model, and the remote sensing image data of each source are stored separately according to the time series; Step 2: Calculate or analyze carbon emission data from remote sensing images of each source using the CENTURY model based on the random arrangement of time series; Step 3: Extract carbon emission data from remote sensing images of each source as appropriate, and use isotope element labeling to identify carbon emission data from remote sensing images of each source; Step 4: Based on the identification of carbon emission data, call the carbon emission data.
2. The method for intelligent identification of soil carbon emissions based on multi-source remote sensing image fusion according to claim 1 is characterized in that: In step 1, the time series data processing method is the following formula (1): (1)； in, For the time, From the first moment to the time, For Choose any moment in For At any moment selected in For Select any operation at any time. For A moment chosen in For the Time series data, For A moment selected in the above corresponds to a certain time series data; For the general Each moment in the Each time series data; For the first time series data to the Time series data, To arrange the time series data in time sequence, for According to the first moment to the Arranged in order of time.
3. The method for intelligent identification of soil carbon emissions based on multi-source remote sensing image fusion according to claim 2 is characterized in that: The remote sensing image data of each source are stored separately according to the time sequence in the following manner: The remote sensing image data of each source is stored separately in sequence according to the time sequence; wherein the remote sensing image data of each source is stored separately in sequence according to the time sequence; The remote sensing image data of each source are randomly stored separately according to a time sequence; wherein the remote sensing image data of each source are stored separately according to a random distribution of the time sequence.
4. The method for intelligent identification of soil carbon emissions based on multi-source remote sensing image fusion according to claim 1 is characterized in that: In step 2, the temporal random arrangement method is used to detect whether the carbon emission data in the remote sensing images of each source are arranged in temporal order. The temporal random arrangement method is the following formula (2): (2)； in, is the time range, including , Time range The operations are arranged in order of moments in time, Time range The moments in the are arranged in order; The time series data included include , Arrange the time series data in time sequence. Arrange the included time series data in time sequence; or Each moment corresponds to its own time series data.
5. The method for intelligent identification of soil carbon emissions based on multi-source remote sensing image fusion according to claim 4 is characterized in that: The carbon emission data in the remote sensing images of the various sources after random arrangement in the time sequence are then stored separately in sequence according to the time sequence.
6. The method for intelligent identification of soil carbon emissions based on multi-source remote sensing image fusion according to claim 1 is characterized in that: In step 3, the carbon emission data in the remote sensing images of the various sources are extracted from the carbon emission data in the remote sensing images, using the following method: Randomly extract carbon emission data from remote sensing images of a certain source according to the time series order; Based on the random sampling method, carbon emission data from the remote sensing image of a certain source is randomly extracted.
7. The method for intelligent identification of soil carbon emissions based on multi-source remote sensing image fusion according to claim 6 is characterized in that: The isotope element quantity notation method is as follows: (3)； in, To calibrate the Timing, is the number of isotopes of an element, To calculate the number of isotopes of an element, To calculate the The number of isotopic elements in the time series data, For the calibration In terms of timing, calculate the The number of isotopic elements in the time series data; To calculate the first time series to the The number of each isotope element in the time series data; for Follow the sequence from 1st to 2nd The timing of the timing, for Operations arranged in time sequence.
8. The method for intelligent identification of soil carbon emissions based on multi-source remote sensing image fusion according to claim 1 is characterized in that: In step 4, the carbon emission data is called according to the isotope element amount of the carbon emission data in the remote sensing image of each source.
9. The method for intelligent identification of soil carbon emissions based on multi-source remote sensing image fusion according to claim 8, characterized in that: In the process of calling the carbon emission data, the carbon emission data is called according to the amount of isotope elements in the carbon emission data in the remote sensing image of each source.