Crop drought monitoring method, device and equipment based on three-dimensional feature space, medium and product

Abstract

The invention discloses a crop drought monitoring method and device based on a three-dimensional feature space, equipment, a medium and a product, and relates to the technical field of agricultural remote sensing, and the method comprises the steps: obtaining a remote sensing image with a red band, a near-infrared band and a thermal infrared band of a to-be-monitored region; constructing a three-dimensional characteristic space of a crop canopy leaf area index value, a surface temperature value and a surface water index value, and calculating an Euclidean distance crop health index from the to-be-monitored point to the most drought point; calculating a vertical moisture stress index and a differential crop health index of each to-be-monitored point based on the two-dimensional feature space; and representing the drought condition of the to-be-monitored area based on the Euclidean distance crop health index, the vertical moisture stress index and the differential crop health index of each to-be-monitored point. The precision of crop drought monitoring is improved.

Description

Technical Field

[0001] This application relates to the field of agricultural remote sensing technology, and in particular to a method, device, equipment, medium and product for monitoring crop drought based on three-dimensional feature space. Background Technology

[0002] Drought is a natural phenomenon caused by an imbalance between surface water and precipitation, resulting in insufficient supply and demand. It is generally classified into meteorological drought, agricultural drought, hydrological drought, and socioeconomic drought. Agricultural drought refers to the phenomenon during the crop growing season where insufficient water supply leads to an imbalance between water supply and demand in farmland, hindering normal crop growth and development. Timely and accurate monitoring of crop drought stress over large areas can provide scientific support for the rational formulation of irrigation strategies and the optimization of water resource utilization and allocation. It can also serve agricultural disaster prevention and mitigation, minimizing the impact of drought on the socio-economic sphere and ultimately ensuring sustainable agricultural development.

[0003] Drought monitoring methods can be divided into two categories: station-based observation and remote sensing-based monitoring. Station-based observation methods offer high accuracy near meteorological stations, but are costly and lack stations in remote areas, significantly limiting the coverage and accuracy of drought monitoring. Remote sensing is an effective technology for rapidly acquiring surface information over large areas, making it possible to conduct dynamic monitoring of crop drought over large regions. Currently, commonly used remote sensing methods for crop drought monitoring include single spectral indices and composite spectral indices. However, current composite spectral indices rarely consider vegetation canopy water content. Furthermore, existing monitoring indices generally use the NDVI (Normalized Difference Vegetation Index) to characterize crop growth, which can become saturated after the canopy closes in the later stages of crop growth, affecting the accuracy of crop drought monitoring. Summary of the Invention

[0004] The purpose of this application is to provide a method, device, equipment, medium and product for monitoring crop drought based on three-dimensional feature space, which is applicable to the detection of crop drought degree over a large area and can improve the monitoring accuracy of crop drought degree.

[0005] To achieve the above objectives, this application provides the following solution:

[0006] Firstly, this application provides a crop drought monitoring method based on a three-dimensional feature space, including:

[0007] Acquire remote sensing images of the area to be monitored, including red band, near-infrared band, and thermal infrared band;

[0008] Based on the remote sensing image, the crop canopy leaf area index, surface temperature, and surface moisture index of each pixel point are calculated for the monitoring point.

[0009] A three-dimensional feature space and a two-dimensional feature space are constructed based on the crop canopy leaf area index, surface temperature, and surface moisture index values ​​of each monitoring point. In the three-dimensional feature space, the x-axis represents the crop canopy leaf area index, the y-axis represents the surface moisture index, and the z-axis represents the surface temperature. In the two-dimensional feature space, the x-axis represents the comprehensive index value, and the y-axis represents the surface temperature value.

[0010] The Euclidean distance to the crop health index of each monitoring point is calculated based on the three-dimensional feature space.

[0011] The vertical water stress index and differential crop health index of each monitoring point are calculated based on the two-dimensional feature space.

[0012] The drought situation in the monitored area is characterized by the Euclidean distance crop health index, vertical water stress index, and differential crop health index of each monitoring point.

[0013] Secondly, this application provides a crop drought monitoring device based on a three-dimensional feature space, comprising:

[0014] The data acquisition module is used to acquire remote sensing images of the area to be monitored, including red band, near-infrared band, and thermal infrared band.

[0015] The multi-index calculation module is used to obtain the crop canopy leaf area index, surface temperature and surface moisture index of each monitoring point based on the remote sensing image.

[0016] The feature space construction module is used to construct a three-dimensional feature space and a two-dimensional feature space based on the crop canopy leaf area index, surface temperature, and surface moisture index values ​​of each monitoring point. In the three-dimensional feature space, the x-axis represents the crop canopy leaf area index, the y-axis represents the surface moisture index, and the z-axis represents the surface temperature. In the two-dimensional feature space, the x-axis represents the comprehensive index value, and the y-axis represents the surface temperature value.

[0017] The first index calculation module is used to calculate the Euclidean distance crop health index of each monitoring point based on the three-dimensional feature space.

[0018] The second index calculation module is used to calculate the vertical water stress index and differential crop health index of each monitoring point based on the two-dimensional feature space.

[0019] The drought condition characterization module is used to characterize the drought condition of the monitored area based on the Euclidean distance crop health index, vertical water stress index, and differential crop health index of each monitored point.

[0020] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the crop drought monitoring method for crop canopy parameters as described above.

[0021] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the crop drought monitoring method for crop canopy parameters as described above.

[0022] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the crop drought monitoring method for crop canopy parameters as described above.

[0023] According to the specific embodiments provided in this application, the following technical effects are disclosed:

[0024] This application provides a method, device, equipment, medium, and product for crop drought monitoring based on a three-dimensional feature space. It obtains the crop canopy leaf area index, surface temperature, and surface moisture index of the monitored points using remote sensing images with red, near-infrared, and thermal infrared bands. By comprehensively considering multiple indices of the crop canopy during drought events, it provides a more accurate data foundation for subsequent construction of three-dimensional and two-dimensional feature spaces. Based on this, it calculates the Euclidean distance crop health index, vertical water stress index, and differential crop health index for each monitored point, improving the accuracy of each index. Subsequently, the drought situation in the monitored area is characterized through multi-dimensional indices, thus improving the accuracy and reliability of crop drought monitoring. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is an application environment diagram of a crop drought monitoring method based on three-dimensional feature space in one embodiment of this application;

[0027] Figure 2 A flowchart illustrating a crop drought monitoring method based on three-dimensional feature space, provided as an embodiment of this application;

[0028] Figure 3 A schematic diagram of the constructed three-dimensional feature space provided in an embodiment of this application;

[0029] Figure 4 This is a schematic diagram illustrating the calculation process of a differential crop health index according to an embodiment of this application;

[0030] Figure 5 A schematic diagram of the calculation process of the vertical water stress index is provided in an embodiment of this application; wherein (a) is a schematic diagram of the calculation process of the vertical water stress index when the surface temperature value of the monitoring point is greater than b2, and (b) is a schematic diagram of the calculation process of the vertical water stress index when the surface temperature value of the monitoring point is less than b2.

[0031] Figure 6 A schematic diagram of the functional modules of a crop drought monitoring device based on crop canopy parameters, provided for another embodiment of this application;

[0032] Figure 7 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0033] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0034] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0035] The crop drought monitoring method based on three-dimensional feature space provided in this application can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be set up independently, integrated into server 104, or placed in the cloud or on another server. Terminal 102 can send remote sensing images of the area to be monitored, containing red, near-infrared, and thermal infrared bands, to server 104. Server 104 receives the remote sensing images of the area to be monitored, and calculates the crop canopy leaf area index, land surface temperature, and land surface moisture index for each monitoring point based on the remote sensing images. It then constructs a three-dimensional feature space and a two-dimensional feature space based on these values. Based on the three-dimensional feature space, it calculates the Euclidean distance crop health index for each monitoring point. Based on the two-dimensional feature space, it calculates the vertical water stress index and differential crop health index for each monitoring point. The Euclidean distance crop health index, vertical water stress index, and differential crop health index for each monitoring point characterize the drought situation in the monitored area. Server 104 can then feed back the obtained drought situation of the monitored area to terminal 102. Furthermore, in some embodiments, the crop drought monitoring method based on three-dimensional feature space can also be implemented by the server 104 or the terminal 102 alone. For example, the terminal 102 can directly process remote sensing images of the area to be monitored that have red band, near-infrared band and thermal infrared band. Alternatively, the server 104 can retrieve remote sensing images of the area to be monitored that have red band, near-infrared band and thermal infrared band from the data storage system and calculate the Euclidean distance crop health index, vertical water stress index and differential crop health index of each monitoring point, thereby obtaining the drought situation of the area to be monitored.

[0036] The terminal 102 can be, but is not limited to, various desktop computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. The server 104 can be implemented using a standalone server or a server cluster composed of multiple servers, or it can be a cloud server.

[0037] In one exemplary embodiment, such as Figure 2 As shown, a crop drought monitoring method based on three-dimensional feature space is provided. This method is executed by computer equipment, specifically by a terminal or server alone, or by both a terminal and a server. In this embodiment, the method is applied to... Figure 1 Taking server 104 as an example, the explanation includes the following steps 201 to 206.

[0038] in:

[0039] Step 201: Acquire remote sensing images of the area to be monitored, including red band, near-infrared band, and thermal infrared band.

[0040] Step 202: Calculate the crop canopy leaf area index, surface temperature, and surface moisture index for each monitoring point based on the remote sensing image.

[0041] The leaf area index (LAI) of crop canopy was calculated using multispectral remote sensing imagery as the data source and obtained through inversion using the PROSAIL crop canopy radiative transfer model. The PROSAIL model is a coupling of the Leaf Optical Properties (PROSPCT) model and the Scattering by Arbitrarily Inclined Leaves (SAIL) model. The PROSPCT model can simulate the directional-hemispherical reflectance and transmittance of leaves in the 400–2500 nm solar spectral range at the leaf scale. The SAIL model is a bidirectional reflectance model at the canopy scale. Based on the assumption that the vegetation canopy is a horizontally homogeneous turbid medium, it uses radiative transfer theory to solve for the scattering and absorption of four upward / downward radiative fluxes, thereby simulating the bidirectional reflectance factor of the vegetation canopy.

[0042]

[0043]

[0044] Where x is the depth of the crop canopy, E s E0 and E0 represent the direct solar radiation from top to bottom and the radiative flux density along the observation direction, respectively. + E - denoted as the upward and downward diffuse radiance of the hemispherical light, respectively; k and K are the extinction coefficients of direct solar radiation and direct radiation in the observation direction, respectively; ∈ and σ are the extinction coefficient and backscattering coefficient, respectively; s and s ' Let μ, υ, and v be the direct radiation scattering coefficients in the same and backward directions, respectively. E respectively + E - E s The conversion coefficient in the direction of observation, It can be viewed as the antiderivative in the radiative transfer equation.

[0045] The surface temperature value during the drought process is retrieved using the split-window algorithm. Step 201 obtains remote sensing images that also include shortwave infrared bands. Based on the reflectance of the near-infrared and shortwave infrared bands of the remote sensing images during the drought process, the surface moisture index value is calculated using the following formula.

[0046]

[0047] Where, ρ NIR ρ is the reflectance in the near-infrared band. SWIR This refers to the reflectivity in the shortwave infrared band.

[0048] Step 203: Construct a three-dimensional feature space and a two-dimensional feature space based on the crop canopy leaf area index, surface temperature, and surface moisture index values ​​of each monitoring point; wherein, in the three-dimensional feature space, the x-axis represents the crop canopy leaf area index, the y-axis represents the surface moisture index, and the z-axis represents the surface temperature; in the two-dimensional feature space, the x-axis represents the comprehensive index value, and the y-axis represents the surface temperature value.

[0049] The constructed three-dimensional feature space, such as Figure 3 As shown, the larger the LST value, the smaller the LAI value, and the smaller the LSWI value at the location of the monitoring point, the more severe the drought condition; conversely, the more humid the area. Therefore, Figure 2 Point M represents the driest bare soil, and point N represents the full vegetation cover state under saturated water content. The smaller the distance from any monitoring point to M(0,0,1), the more severe the drought of the crop; conversely, the greater the distance, the less severe the drought or the absence of drought.

[0050] Step 204: Calculate the Euclidean distance crop health index for each monitoring point based on the three-dimensional feature space.

[0051] The Euclidean distance crop health index essentially calculates the Euclidean distance from any monitored point to point M in a three-dimensional feature space, used to characterize crop drought conditions. The formula for calculating the Euclidean distance crop health index is:

[0052]

[0053] Among them, ECHI is the Euclidean distance crop health index, LAI is the crop canopy leaf area index of the monitoring point, LST is the land surface temperature of the monitoring point, and LSWI is the land surface moisture index of the monitoring point.

[0054] The value range of ECHI is within Between. The extreme drought value (ECHI value of 0) is located at point M, which has the highest LST value, lowest LAI value, and lowest LSWI value; the extreme wet value (ECHI value of...) is... The point is located at point N, which has the lowest LST value, the highest LAI value, and the highest LSWI value.

[0055] The comprehensive index value Q is calculated based on the LAI and LSWI values ​​of each monitoring point in the three-dimensional feature space. The calculation formula is as follows: Furthermore, a two-dimensional feature space is constructed based on the comprehensive index value and the LST value.

[0056] Step 205: Calculate the vertical water stress index and differential crop health index for each monitoring point based on the two-dimensional feature space. Specifically, this includes steps 301-303:

[0057] Step 301: Determine the dry edge and wet edge based on the dry bare soil points, different vegetation cover states under different moisture contents, and the clustering distribution of each monitoring point in the two-dimensional feature space.

[0058] LAI and LSWI are positively correlated, while both are negatively correlated with LST. The plane containing the diagonal MN of the points M (dry bare soil point) and N (full vegetation cover state under saturated water content) is extracted. The projection of each monitoring point in three-dimensional space onto this plane is abstracted as a trapezoid. The different positions of the monitoring points in the two-dimensional feature space reflect changes in drought conditions. For example... Figure 4 As shown, Figure 4 Point A represents dry bare soil, point B represents bare soil with saturated moisture content, point C represents the state of water stress under full vegetation cover (vegetation wilting point), and point D represents the state of full vegetation cover with saturated moisture content. Line segment AC represents dry edge, and line segment BD represents wet edge.

[0059] Step 302: Based on the surface temperature value and comprehensive index value of each monitoring point, the expression of the straight line in the two-dimensional feature space of the dry edge and the wet edge is obtained by fitting the linear regression method.

[0060] All monitoring points are clustered in a trapezoidal pattern in the two-dimensional feature space, with the two hypotenuses representing the dry and wet edges, respectively, and the two parallel sides representing the y-axis distances from the dry and wet edges. Based on the distribution characteristics of the monitoring points in the two-dimensional feature space, the dry and wet edges are obtained using linear regression. The expressions for the lines containing the dry and wet edges are as follows:

[0061]

[0062] Among them, LST dry LST represents the surface temperature value at the monitoring point on the dry side. wet denoted as , where is the surface temperature value at the monitoring point on the wet edge, a1 and b1 are the fitting coefficients for the extreme dry edge, a2 and b2 are the fitting coefficients for the extreme wet edge, LAI is the crop canopy leaf area index, and LSWI is the surface moisture index.

[0063] Step 303: Calculate the vertical water stress index and differential crop health index for each monitoring point using the straight lines containing the dry and wet sides.

[0064] The differential crop health index is calculated based on the distances of the monitored points to the dry and wet edges in a two-dimensional feature space. Specifically, for example... Figure 4 As shown, the differential crop health index is calculated based on the distance from any monitoring point q to the dry edge LST, under the same Q value. dry The difference m between the monitoring point and the LST on the dry edge dry and wet edge LST wet The ratio between the differences n is the proportion of m to n.

[0065]

[0066] The smaller the proportion of m to n, the closer the crop is to the dry side, indicating more severe drought stress; the larger the proportion, the closer the crop is to the wet side, indicating less severe or no drought stress. Therefore, the differential crop health index (DCHI) has a value of 0 on the dry side and a value of 1 on the wet side, with a smaller DCHI value indicating a higher degree of drought.

[0067] The formula for calculating the differential crop health index is:

[0068]

[0069] Among them, DCHI is the Differential Crop Health Index, and LST is the surface temperature value of the monitoring point.

[0070] The degree of drought stress on crops is quantified by calculating the shortest distance (i.e., vertical distance) from the monitoring point to the wet edge. For example... Figure 5 As shown, based on the relationship between the vertical distance from the monitoring point to the wet edge and the intercept b2 of the wet edge fitting equation, the vertical moisture stress index is calculated in two cases.

[0071] like Figure 5 As shown in (a), when the surface temperature value at the monitoring point is greater than b2,

[0072] θ = arctan(|a²|));

[0073] PWSI = AB + CP;

[0074] Therefore, when the surface temperature at the monitoring point is greater than b2, the formula for calculating the vertical moisture stress index is:

[0075]

[0076] like Figure 5As shown in (b), when the surface temperature value of the monitoring point is less than b2, PWSI = EF - EG;

[0077] Therefore, when the surface temperature at the monitoring point is less than b2, the formula for calculating the vertical moisture stress index is:

[0078]

[0079] Wherein, PWSI is the vertical water stress index, b2 is the fitting parameter of the extreme wet edge, LST is the surface temperature value of the monitoring point, θ is the angle between the wet edge and the x-axis in the two-dimensional feature space, LAI is the crop canopy leaf area index value of the monitoring point, and LSWI is the surface water index value of the monitoring point.

[0080] from Figure 5 As can be seen, the value of the vertical water stress index depends on the value of the line segment OP, reflecting the difference between the crop state and the wet state represented by the monitoring point. The larger the value of OP, the higher the value of the vertical water stress index, the farther the monitoring point is from the wet edge, and the more severe the drought stress of the crop it represents. The smaller the value of OP, the lower the value of the vertical water stress index, the closer the monitoring point is to the wet edge, and the lower the degree of drought stress of the crop it represents.

[0081] Step 206: Characterize the drought situation in the monitored area based on the Euclidean distance crop health index, vertical water stress index, and differential crop health index of each monitoring point.

[0082] The crop drought monitoring method based on three-dimensional feature space provided in this application creates an efficient and robust crop drought monitoring method by comprehensively considering crop growth, canopy water content and canopy temperature at the time of drought event. This improves the accuracy and reliability of crop drought monitoring and solves the problem of accuracy monitoring of drought in the later stage of crop growth.

[0083] Based on the same inventive concept, this application also provides an apparatus for implementing the above-mentioned crop drought monitoring method based on three-dimensional feature space. The solution provided by this apparatus is similar to the implementation scheme described in the above method. Therefore, the specific limitations of one or more embodiments of the crop drought monitoring apparatus based on crop canopy parameters provided below can be found in the limitations of the crop drought monitoring method based on three-dimensional feature space described above, and will not be repeated here.

[0084] In one exemplary embodiment, such as Figure 6 As shown, a crop drought monitoring device based on a three-dimensional feature space is provided, comprising:

[0085] The data acquisition module 61 is used to acquire remote sensing images of the area to be monitored, which include red band, near-infrared band and thermal infrared band.

[0086] The multi-index calculation module 62 is used to obtain the crop canopy leaf area index, surface temperature value and surface moisture index value of each monitoring point based on the remote sensing image.

[0087] The feature space construction module 63 is used to construct a three-dimensional feature space and a two-dimensional feature space based on the crop canopy leaf area index, surface temperature, and surface moisture index values ​​of each monitoring point. In the three-dimensional feature space, the x-axis represents the crop canopy leaf area index, the y-axis represents the surface moisture index, and the z-axis represents the surface temperature. In the two-dimensional feature space, the x-axis represents the comprehensive index value, and the y-axis represents the surface temperature value.

[0088] The first index calculation module 64 is used to calculate the Euclidean distance crop health index of each monitoring point based on the three-dimensional feature space.

[0089] The second index calculation module 65 is used to calculate the vertical water stress index and differential crop health index of each monitoring point based on the two-dimensional feature space.

[0090] The drought condition characterization module 66 is used to characterize the drought condition of the monitored area based on the Euclidean distance crop health index, vertical water stress index and differential crop health index of each monitoring point.

[0091] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 7 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs in the non-volatile storage media to run. The database contains remote sensing images of the monitored area in the red, near-infrared, and thermal infrared bands. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a crop drought monitoring method based on three-dimensional feature space.

[0092] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0093] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0094] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0095] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0096] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0097] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0098] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0099] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0100] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A crop drought monitoring method based on three-dimensional feature space, characterized in that, include: Acquire remote sensing images of the area to be monitored, including red band, near-infrared band, and thermal infrared band; The crop canopy leaf area index, surface temperature, and surface moisture index of each monitoring point were calculated based on the remote sensing images. A three-dimensional feature space and a two-dimensional feature space are constructed based on the crop canopy leaf area index, surface temperature, and surface moisture index values ​​of each monitoring point. In the three-dimensional feature space, the x-axis represents the crop canopy leaf area index, the y-axis represents the surface moisture index, and the z-axis represents the surface temperature. In the two-dimensional feature space, the x-axis represents the comprehensive index value, and the y-axis represents the surface temperature value. The Euclidean distance to the crop health index of each monitoring point is calculated based on the three-dimensional feature space. The vertical water stress index and differential crop health index of each monitoring point are calculated based on the two-dimensional feature space. The drought situation in the monitored area is characterized by the Euclidean distance crop health index, vertical water stress index, and differential crop health index of each monitoring point.

2. The crop drought monitoring method based on three-dimensional feature space according to claim 1, characterized in that, The vertical water stress index and differential crop health index for each monitoring point are calculated based on the two-dimensional feature space, specifically including: Based on the dry bare soil points, points with different vegetation cover states under different moisture contents, and the clustering distribution of each monitoring point in the two-dimensional feature space, dry edges and wet edges are determined. Based on the surface temperature and comprehensive index values ​​of each monitoring point, the expressions of the straight lines containing the dry and wet edges in the two-dimensional feature space are obtained by fitting the linear regression method. The vertical water stress index and differential crop health index of each monitoring point are calculated using the straight lines containing the dry and wet sides, respectively.

3. The crop drought monitoring method based on three-dimensional feature space according to claim 2, characterized in that, The expressions for the lines containing the dry and wet edges are as follows: Among them, LST dry LST represents the surface temperature value at the monitoring point on the dry side. wet denoted as , where is the surface temperature value at the monitoring point on the wet edge, a1 and b1 are the fitting coefficients for the extreme dry edge, a2 and b2 are the fitting coefficients for the extreme wet edge, LAI is the crop canopy leaf area index, and LSWI is the surface moisture index.

4. The crop drought monitoring method based on three-dimensional feature space according to claim 1, characterized in that, The Euclidean distance crop health index is calculated using the following formula: Among them, ECHI is the Euclidean distance crop health index, LAI is the crop canopy leaf area index of the monitoring point, LST is the land surface temperature of the monitoring point, and LSWI is the land surface moisture index of the monitoring point.

5. The crop drought monitoring method based on three-dimensional feature space according to claim 2, characterized in that, The formula for calculating the differential crop health index is as follows: Where DCHI is the Differential Crop Health Index, and LST is the LST index. dry LST represents the surface temperature value at the monitoring point on the dry side. wet LST represents the surface temperature value of the monitoring point on the wet edge.

6. The crop drought monitoring method based on three-dimensional feature space according to claim 2, characterized in that, The formula for calculating the vertical moisture stress index is as follows: When the surface temperature value at the monitoring point is greater than b2 When the surface temperature value at the monitoring point is less than b2 Wherein, PWSI is the vertical water stress index, b2 is the fitting parameter of the extreme wet edge, LST is the surface temperature value of the monitoring point, θ is the angle between the wet edge and the x-axis in the two-dimensional feature space, LAI is the crop canopy leaf area index value of the monitoring point, and LSWI is the surface water index value of the monitoring point.

7. A crop drought monitoring device based on crop canopy parameters, characterized in that, include: The data acquisition module is used to acquire remote sensing images of the area to be monitored, including red band, near-infrared band, and thermal infrared band. The multi-index calculation module is used to obtain the crop canopy leaf area index, surface temperature and surface moisture index of each monitoring point based on the remote sensing image. The feature space construction module is used to construct a three-dimensional feature space and a two-dimensional feature space based on the crop canopy leaf area index, surface temperature, and surface moisture index values ​​of each monitoring point. In the three-dimensional feature space, the x-axis represents the crop canopy leaf area index, the y-axis represents the surface moisture index, and the z-axis represents the surface temperature. In the two-dimensional feature space, the x-axis represents the comprehensive index value, and the y-axis represents the surface temperature value. The first index calculation module is used to calculate the Euclidean distance crop health index of each monitoring point based on the three-dimensional feature space. The second index calculation module is used to calculate the vertical water stress index and differential crop health index of each monitoring point based on the two-dimensional feature space. The drought condition characterization module is used to characterize the drought condition of the monitored area based on the Euclidean distance crop health index, vertical water stress index, and differential crop health index of each monitored point.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the crop drought monitoring method based on three-dimensional feature space as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the crop drought monitoring method based on three-dimensional feature space as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the crop drought monitoring method based on three-dimensional feature space as described in any one of claims 1-6.

Images