A soil moisture inversion method and device based on remote sensing data

Abstract

The invention discloses a soil moisture inversion method and device based on remote sensing data, the method comprising: first obtaining microwave remote sensing soil moisture products, optical remote sensing data and elevation data of the target area; then determining the modified vegetation drought index, soil evapotranspiration efficiency, temperature-vegetation-shortwave infrared reflection drought index of the target area; performing pixel matching on the above data and the soil moisture product to obtain various surface parameters with the same spatial resolution as the soil moisture product, and using them as the first training data of the independent variable, the soil moisture product is input as the dependent variable to train the random forest model to obtain the soil moisture inversion model; finally, the surface parameters with high spatial resolution of the target area are input into the soil moisture inversion model to obtain soil moisture. The soil moisture inversion can be performed accurately to obtain accurate soil moisture data.

Description

Technical Field

[0001] The invention belongs to the technical field of soil moisture inversion, and in particular relates to a soil moisture inversion method and device based on remote sensing data. Background Art

[0002] Soil moisture usually refers to the amount of water contained in unsaturated soil. It is the main water resource for vegetation growth and one of the main factors affecting the cycle of terrestrial surface water and energy. Currently, soil moisture data has been widely used in many fields such as drought detection, weather forecasting, water resources management, and crop yield estimation.

[0003] The existing methods for soil moisture inversion are usually based on microwave remote sensing. Microwave remote sensing can penetrate clouds and the surface, is not restricted by sunlight and weather conditions, and is all-weather. However, the soil moisture obtained by microwave remote sensing usually has a coarse spatial resolution of about tens of kilometers. Sole reliance on microwave remote sensing data can easily lead to large errors in the results of soil moisture inversion.

[0004] Therefore, how to accurately perform soil moisture inversion is a technical problem to be solved by those skilled in the art. Summary of the invention

[0005] The purpose of the present invention is to solve the technical problem in the prior art that the soil moisture inversion result has low accuracy due to the coarse spatial resolution of microwave remote sensing.

[0006] To achieve the above technical objectives, on the one hand, the present invention provides a soil moisture inversion method based on remote sensing data, the method comprising:

[0007] Obtain microwave remote sensing soil moisture products, optical remote sensing data and elevation data of the target area;

[0008] Based on the trapezoidal feature space of surface temperature-vegetation coverage, the modified vegetation drought index and soil evapotranspiration efficiency of the target area are determined, and based on the three-dimensional feature space of surface temperature-enhanced vegetation index-shortwave infrared reflectivity, the temperature-vegetation-shortwave infrared reflectivity drought index of the target area is determined;

[0009] The modified vegetation drought index, soil evapotranspiration efficiency, temperature-vegetation-shortwave infrared reflectance drought index, surface temperature in optical remote sensing data, normalized difference vegetation index, surface albedo, elevation and surface parameters in elevation data are matched with soil moisture products to obtain surface parameters with the same spatial resolution as soil moisture products, and these are used as the first training data;

[0010] The soil moisture inversion model is obtained by training the random forest model using the first training data as an independent variable and the soil moisture product as a dependent variable;

[0011] The high spatial resolution surface parameters of the target area are input into a soil moisture inversion model to obtain soil moisture.

[0012] Furthermore, the determining of the modified temperature vegetation drought index of the target area specifically includes:

[0013] Based on the surface temperature-vegetation coverage trapezoidal feature space, the surface temperature of bare soil under extreme drought and sufficient water supply conditions and the temperature of bare soil within the soil moisture contour were determined;

[0014] The modified vegetation drought index is determined based on the surface temperature of bare soil under extreme drought and sufficient water supply conditions and the temperature of bare soil within the soil moisture contour.

[0015] Furthermore, the modified vegetation drought index is determined by the following formula:

[0016]

[0017] Where MTVDI is the modified vegetation drought index, T smax,i is the temperature of bare soil within the soil moisture contour, T max is the surface temperature under extreme drought conditions, T w The surface temperature under the condition of sufficient water supply.

[0018] Furthermore, the soil evapotranspiration efficiency is determined by the following formula:

[0019]

[0020] Where SEE is soil evapotranspiration efficiency, T smax is the first temperature end member in the feature space, T smax,i is the temperature of bare soil within the soil moisture contour, T smin is the second temperature end member in the feature space, LST M is the surface temperature corresponding to the wet edge, LST is the surface temperature, LST N is the surface temperature corresponding to the dry side, f c is the vegetation coverage, T cmax is the third temperature end member in the characteristic space, T cmin is the fourth temperature end member in the feature space.

[0021] Furthermore, the temperature-vegetation-shortwave infrared reflectance drought index TVSDI is determined by the following formula:

[0022]

[0023] Where LST is the land surface temperature, SWIR is the shortwave infrared reflectivity, and EVI is the enhanced vegetation index.

[0024] Furthermore, the soil moisture inversion model is as follows:

[0025] SM=RF(MTVDI,SEE,TVSDI,LST,NDVI,TB H ,TB V ,ALB,H)

[0026] In the formula, SM is soil moisture, RF is the random forest model, MTVDI is the vegetation drought index, SEE is the soil evapotranspiration efficiency, TVSDI is the temperature-vegetation-shortwave infrared reflectance drought index, LST is the land surface temperature, NDVI is the normalized difference vegetation index, TB is H is the horizontal polarization brightness temperature, TB V is the vertically polarized brightness temperature, ALB is the surface albedo, and H is the elevation.

[0027] On the other hand, the present invention also provides a soil moisture inversion device based on remote sensing data, the device comprising:

[0028] An acquisition module is used to obtain microwave remote sensing soil moisture products, optical remote sensing data and elevation data of the target area;

[0029] A determination module is used to determine the modified vegetation drought index and soil evapotranspiration efficiency of the target area based on the trapezoidal feature space of surface temperature-vegetation coverage, and to determine the temperature-vegetation-shortwave infrared reflectivity drought index of the target area based on the three-dimensional feature space of surface temperature-enhanced vegetation index-shortwave infrared reflectivity;

[0030] A matching module is used to match the modified vegetation drought index, soil evapotranspiration efficiency, temperature-vegetation-shortwave infrared reflectance drought index, surface temperature in optical remote sensing data, normalized vegetation index, surface albedo, elevation and surface parameters in elevation data with soil moisture products to obtain surface parameters with the same spatial resolution as the soil moisture products, and use them as the first training data;

[0031] A training module, used for training a random forest model using the first training data as an independent variable and a soil moisture product as a dependent variable to obtain a soil moisture inversion model;

[0032] The inversion module is used to input the high spatial resolution surface parameters of the target area into the soil moisture inversion model to obtain soil moisture.

[0033] The invention provides a soil moisture inversion method and device based on remote sensing data. Compared with the prior art, the method first obtains microwave remote sensing soil moisture products, optical remote sensing data and elevation data of the target area; then determines the modified vegetation drought index and soil evapotranspiration efficiency of the target area based on the trapezoidal feature space of surface temperature-vegetation coverage, and determines the temperature-vegetation-shortwave infrared reflectivity drought index of the target area based on the three-dimensional feature space of surface temperature-enhanced vegetation index-shortwave infrared reflectivity; then the modified vegetation drought index, soil evapotranspiration efficiency, temperature and soil evapotranspiration efficiency are calculated. - Vegetation-Shortwave infrared reflectance drought index, surface temperature in optical remote sensing data, normalized vegetation index, surface albedo, elevation and surface parameters in elevation data are matched with soil moisture products to obtain surface parameters with the same spatial resolution as soil moisture products, and used as the first training data; then the first training data is used as the independent variable and the soil moisture product is used as the dependent variable to train the random forest model to obtain the soil moisture inversion model; finally, the high spatial resolution surface parameters of the target area are input into the soil moisture inversion model to obtain soil moisture. It is possible to accurately invert soil moisture and obtain accurate soil moisture data. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 The figure is a schematic diagram of the flow of a soil moisture inversion method based on remote sensing data provided in an embodiment of this specification;

[0036] Figure 2 The figure shows a schematic diagram of the structure of a soil moisture inversion device based on remote sensing data provided in an embodiment of this specification;

[0037] Figure 3 Shown is a schematic diagram of the surface temperature-vegetation coverage trapezoidal feature space;

[0038] Figure 4 Shown is a schematic diagram of the two-step trapezoidal feature space of surface temperature and vegetation coverage;

[0039] Figure 5 Shown is a schematic diagram of the three-dimensional feature space of land surface temperature-enhanced vegetation index-shortwave infrared reflectivity;

[0040] Figure 6 Shown are the soil moisture inversion results of the traditional method;

[0041] Figure 7 The soil moisture inversion result of the embodiment of this specification is shown;

[0042] Figure 8 The figure shows the soil moisture prediction accuracy diagram of this scheme in the embodiment of this specification. DETAILED DESCRIPTION

[0043] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0044] like Figure 1 The flowchart of the soil moisture inversion method based on remote sensing data provided by the embodiment of this specification is shown. Although this specification provides the method operation steps or device structures shown in the following embodiments or drawings, the method or device may include more or fewer operation steps or module units after partial merger based on routine or no creative labor. In the steps or structures where there is no necessary causal relationship logically, the execution order of these steps or the module structure of the device is not limited to the execution order or module structure shown in the embodiments of this specification or drawings. When the method or module structure is applied in an actual device, server or terminal product, it can be executed sequentially or in parallel according to the method or module structure shown in the embodiment or drawings.

[0045] The soil moisture inversion method based on remote sensing data provided in the present embodiment can be applied to various terminal devices, such as Figure 1 As shown, the method specifically comprises the following steps:

[0046] Step S101: Acquire microwave remote sensing soil moisture products, optical remote sensing data and elevation data of a target area.

[0047] Specifically, the soil moisture product of microwave remote sensing is obtained, and the spatial resolution of the soil moisture product is 36km, the spatial resolution of the optical remote sensing data is 500m, 1km and 5km, and the spatial resolution of the elevation data is 90m. The soil moisture product, optical remote sensing data and elevation data are integrated to invert high-precision soil moisture data with a spatial resolution of 1km.

[0048] After obtaining the above data, the microwave remote sensing soil moisture product is reprojected, cropped and the soil moisture and brightness temperature (TB H and TBV ) information. The optical remote sensing data include MCD43A3 and MCD43A4 daily albedo products with a spatial resolution of 500m, and MCD12Q1 annual land use products; MOD03 daily solar zenith angle products, MOD11A1 daily surface temperature products, and MOD13A2 16-day NDVI (Normalized Difference Vegetation Index) products with a spatial resolution of 1km; MOD06_L2 daily cloud products and MOD07_L2 daily atmospheric profile products with a spatial resolution of 5km. The main steps of optical remote sensing data preprocessing include: according to the MRT and HEG tools provided by the MODIS (Moderate-resolution Imaging Spectroradiometer) official website, all data products are converted to the WGS-1984 coordinate system, and then spliced, resampled to 1km, and cropped. The 16-day NDVI product was smoothed using the cubic spline capping algorithm and linearly interpolated to daily values ​​to ensure the temporal and spatial consistency of the optical remote sensing data product. The elevation data was projected, resampled to 1 km, and clipped.

[0049] Step S102: determining the modified vegetation drought index and soil evapotranspiration efficiency of the target area based on the surface temperature-vegetation coverage trapezoidal feature space, and determining the temperature-vegetation-shortwave infrared reflectivity drought index of the target area based on the surface temperature-enhanced vegetation index-shortwave infrared reflectivity three-dimensional feature space.

[0050] In the embodiment of the present application, the surface temperature that can be achieved by pure bare soil under extreme drought and sufficient water supply conditions and the temperature of bare soil within the soil moisture contour are calculated based on the surface temperature-vegetation coverage trapezoidal feature space, and then the dry-wet boundary is used to construct a modified vegetation drought index, such as Figure 3 The figure shows a schematic diagram of the surface temperature-vegetation coverage trapezoidal feature space. Specifically, the modified vegetation drought index is determined by the following formula:

[0051]

[0052] Where MTVDI is the modified vegetation drought index, T smax,i is the temperature of bare soil within the soil moisture contour, T max is the surface temperature under extreme drought conditions, T w The surface temperature under the condition of sufficient water supply.

[0053] Specifically, the MTVDI construction scheme believes that the thermal conductivity of soil and vegetation is different. cAs the temperature of the ground increases, the LST, i.e. the surface temperature, gradually approaches the air temperature T a When the vegetation coverage is full, the surface radiation temperature is T a Based on this, T smax,i It can be expressed as:

[0054] T smax,i =(LST i -f c,i T a,i ) / (1-f c,i )

[0055] Where, LST i is the surface temperature of the ith pixel, f c,i is the vegetation coverage of the ith pixel, T a,i is the air temperature of the ith pixel.

[0056] According to the definition of MTVDI, the most important task is to determine the dry side temperature and the wet side temperature.

[0057] Dry side temperature solution: Dry side temperature T smax The seasonal variation of is affected by solar radiation and can be expressed as a cosine function of the solar zenith angle. smax The seasonal variation of can be expressed as:

[0058] T smax,k,j =A k cos(a k θ k,j +b k )

[0059] Where, T smax,k,j is the dry edge temperature of the kth pixel in the soil moisture product observed on the jth day, A k is the amplitude, θ k,j is the solar zenith angle, b k and a k is the phase parameter.

[0060] Among them, the optimal amplitude A in the dry edge is calculated k The optimal A when the correlation between 36kmMTVDI and microwave soil moisture products is the strongest is obtained by data-driven method. k , A k The change step size is set to 1K, and the optimal A k Obtain the dry edge temperature T within each SMAP pixel size smax For each SMAP pixel, the objective function is:

[0061]

[0062] Where Abs is the absolute value, Cor is the correlation coefficient, N is the number of clear sky days in the selected year, SM k,j is the soil moisture of the k-th pixel on the j-th day obtained from the SMAP product, MTVDI k,j is the average value of all MTVDI in the selected SMAP pixel.

[0063] Wet edge temperature T w The calculation formula is as follows:

[0064] T w =min(T smin,k,j ,T min,k,j )

[0065] Where, T min,k,j T represents the minimum surface temperature observed by remote sensing within the kth 36km pixel on the jth day, smin,k,j is T obtained by the cosine function w The prediction function, T smin,k,j According to T min,k,j and the solar zenith angle, obtained by fitting the cosine function.

[0066] The soil evapotranspiration efficiency is determined by the following formula:

[0067]

[0068] Where SEE is soil evapotranspiration efficiency, T smax is the first temperature end member in the feature space, T smax,i is the temperature of bare soil within the soil moisture contour, T smin is the second temperature end member in the feature space, LST M is the surface temperature corresponding to the wet edge, LST is the surface temperature, LST N is the surface temperature corresponding to the dry side, f c is the vegetation coverage, T cmax is the third temperature end member in the characteristic space, T cmin is the fourth temperature end member in the feature space.

[0069] Specifically, based on the two-step trapezoidal feature space of surface temperature and vegetation coverage, the temperature end-members involved in the dry-wet boundary are calculated, such as Figure 4 The figure shows a schematic diagram of the two-step characteristic space of surface temperature and vegetation coverage. The soil evapotranspiration efficiency can be defined as:

[0070]

[0071] Assume that point P is located at coordinates (LST,f c), M and N are respectively the pixels in the lower triangle space of the two trapezoids of point P f c For the same intermediate dry edge and wet edge pixels, the SEE of point P can be determined by the above formula.

[0072] The four temperature end members are solved as follows:

[0073]

[0074] In the formula, S d is the downlink shortwave radiation obtained from MODIS data (W / m2); α s and α v Represent soil albedo and vegetation albedo respectively; ε v , ε s and ε a represents the emissivity of vegetation, soil and air respectively; σ represents the Stefan-Boltzmann constant, which is equal to 5.76×10-8W / (m2·K4); c p is the specific heat capacity of air, equal to 1006 J / (kg·K); T a represents the air temperature obtained from MODIS data; ρ represents the air density, which is approximately equal to 1.225 kg / m3; and Represents the aerodynamic resistance of the soil and vegetation surface, in s / m; n s and n v It represents the fractional coefficient between soil heat flux and net radiation flux of soil and vegetation, and the default values ​​are 0.35 and 0 respectively. Δ represents the slope of saturated vapor pressure-temperature relationship; γ represents the psychrometric constant, which is 0.658 hPa / ℃.

[0075] In the embodiment of the present application, based on the three-dimensional feature space of land surface temperature-enhanced vegetation index-shortwave infrared reflectivity (LST-EVI-SWIR), a temperature-vegetation-shortwave infrared reflectivity drought index (TVSDI) is constructed. In order to construct the three-dimensional TVSDI, the SWIR reflectivity axis is perpendicular to the two-dimensional (land surface temperature-vegetation index) plane, such as Figure 5 The widely used EVI is selected as the enhanced vegetation index. EVI is easy to calculate and can reduce the noise of clouds and aerosols and the saturation effect of dense vegetation areas. The formula is as follows:

[0076]

[0077] Where G (set to 2.5) is the gain factor; R BLUE , R NIR and R RED are the reflectances of blue light, near infrared light and red light, respectively; L is the canopy adjustment coefficient, which is 1; C 1 and C2 are the aerosol resistance correction factors, and their values ​​are 6 and 7.5 respectively.

[0078] In this three-dimensional space, each axis represents one of the three indicators (EVI, LST, and SWIR reflectivity), and changes in any of the three indicators will lead to changes in the other two indicators. In order to ensure that the values ​​of the three coordinate axes are comparable to each other, each axis is set between 0 and Normalize between.

[0079]

[0080] In the formula, Z represents a variable, Z i is Z=(Z 1 ,Z 2 , …, Z n ). In order to reduce the error, the Z values ​​at 5% and 95% of the histogram cumulative frequency are set as min(Z) and max(Z), respectively.

[0081] After normalization of each axis, according to the Euclidean distance theory, the temperature-vegetation-shortwave infrared reflectance drought index TVSDI at a certain point D1 in space is calculated as follows:

[0082]

[0083] Where LST is the land surface temperature, SWIR is the shortwave infrared reflectivity, and EVI is the enhanced vegetation index.

[0084] Step S103, pixel matching is performed on the modified vegetation drought index, soil evapotranspiration efficiency, temperature-vegetation-shortwave infrared reflectance drought index, surface temperature in optical remote sensing data, normalized vegetation index, surface albedo, elevation and surface parameters in elevation data with the soil moisture product to obtain various surface parameters with the same spatial resolution as the soil moisture product, and use them as the first training data.

[0085] Specifically, the surface parameters such as MTVDI, SEE, TVSDI, LST, NDVI, ALB and H with a spatial resolution of 1 km are matched with the SMAP product pixels. Taking the SMAP data as the benchmark, the average value is taken within the SMAP pixel to obtain the surface parameters with the same spatial resolution as the SMAP product. ALB is calculated by averaging the short-wave black sky and white sky albedo parameters extracted from the MCD43A3 data. TB H and TB V Extracted from SMAP data.

[0086] Step S104: training the random forest model using the first training data as an independent variable and the soil moisture product as a dependent variable to obtain a soil moisture inversion model.

[0087] In the embodiment of the present application, the soil moisture inversion model is as follows:

[0088] SM=RF(MTVDI,SEE,TVSDI,LST,NDVI,TB H ,TB V ,ALB,H)

[0089] In the formula, SM is soil moisture, RF is the random forest model, MTVDI is the modified vegetation drought index, SEE is the soil evapotranspiration efficiency, TVSDI is the temperature-vegetation-shortwave infrared reflectance drought index, LST is the land surface temperature, NDVI is the normalized difference vegetation index, TB is H is the horizontal polarization brightness temperature, TB V is the vertically polarized brightness temperature, ALB is the surface albedo, and H is the elevation.

[0090] Specifically, during training, 70% of the data can be randomly selected and brought into the model for training to reduce the risk of overfitting, and the remaining 30% of the data is used as validation data for cross-validation.

[0091] Step S105: inputting the high spatial resolution surface parameters of the target area into a soil moisture inversion model to obtain soil moisture.

[0092] Specifically, TB extracted from SMAP data H and TB V Resample to 1 km to ensure the same spatial resolution as the optical remote sensing data and elevation data. All surface parameters with a high spatial resolution of 1 km are input as prediction variables into the soil moisture inversion model trained by S6 to obtain soil moisture data with a spatial resolution of 1 km in the target area. Figure 6 The soil moisture inversion results of the traditional method are shown. Figure 7 The inversion results of soil moisture inversion in the embodiment of this specification are shown in Figure 2. By comparison, it can be seen that the inverted soil moisture data improves the spatial resolution of the original SMAP soil moisture data, can well track the dynamics of in-situ observations, can clearly capture the spatial heterogeneity of soil parameters, and has the same spatial correspondence with the original SMAP soil moisture data. The accuracy verification results based on the actual measured values ​​of the site are shown in Figure 2. Figure 8 , Figure 8 The figure shows the soil moisture prediction accuracy diagram of this scheme. The accuracy verification indicators used here are correlation coefficient (r), mean absolute error (MAE), root mean square error (RMSE) and bias (B).

[0093] Based on the above-mentioned soil moisture inversion method based on remote sensing data, one or more embodiments of this specification also provide a platform and terminal for soil moisture inversion based on remote sensing data. The platform or terminal may include a device, software, module, plug-in, server, client, etc. using the method described in the embodiments of this specification and a device combined with necessary implementation hardware. Based on the same innovative concept, the system in one or more embodiments provided in the embodiments of this specification is as described in the following embodiments. Since the implementation scheme and method for solving the problem of the system are similar, the implementation of the specific system in the embodiments of this specification can refer to the implementation of the aforementioned method, and the repetitions will not be repeated. The terms "unit" or "module" used below can be a combination of software and / or hardware that implements predetermined functions. Although the system described in the following embodiments is preferably implemented in software, hardware, and the combination of software and hardware are also possible and conceived.

[0094] Specifically, Figure 2 is a schematic diagram of the module structure of an embodiment of a soil moisture inversion device based on remote sensing data provided in this specification, such as Figure 2 As shown, the soil moisture inversion device based on remote sensing data provided in this specification includes:

[0095] An acquisition module 201 is used to acquire microwave remote sensing soil moisture products, optical remote sensing data and elevation data of a target area;

[0096] The determination module 202 is used to determine the modified vegetation drought index and soil evapotranspiration efficiency of the target area based on the trapezoidal feature space of surface temperature-vegetation coverage, and to determine the temperature-vegetation-shortwave infrared reflectivity drought index of the target area based on the three-dimensional feature space of surface temperature-enhanced vegetation index-shortwave infrared reflectivity;

[0097] The matching module 203 is used to match the modified vegetation drought index, soil evapotranspiration efficiency, temperature-vegetation-shortwave infrared reflectance drought index, surface temperature in optical remote sensing data, normalized vegetation index, surface albedo, elevation and surface parameters in elevation data with the soil moisture product to obtain various surface parameters with the same spatial resolution as the soil moisture product, and use them as the first training data;

[0098] A training module 204 is used to train a random forest model using the first training data as an independent variable and the soil moisture product as a dependent variable to obtain a soil moisture inversion model;

[0099] The inversion module 205 is used to input the high spatial resolution surface parameters of the target area into the soil moisture inversion model to obtain soil moisture.

[0100] It should be noted that the above-mentioned system may also include other implementation modes according to the description of the corresponding method embodiment. The specific implementation modes may refer to the description of the above-mentioned corresponding method embodiment, which will not be described one by one here.

[0101] The present application also provides an electronic device, including:

[0102] processor;

[0103] a memory for storing instructions executable by the processor;

[0104] The processor is configured to execute the method provided in the above embodiment.

[0105] The electronic device provided in the embodiment of the present application stores executable instructions of the processor in the memory. When the processor executes the executable instructions, it can first obtain the microwave remote sensing soil moisture product, optical remote sensing data and elevation data of the target area; then determine the modified vegetation drought index and soil evapotranspiration efficiency of the target area based on the trapezoidal feature space of surface temperature-vegetation coverage, and determine the temperature-vegetation-shortwave infrared reflectivity drought index of the target area based on the three-dimensional feature space of surface temperature-enhanced vegetation index-shortwave infrared reflectivity; then determine the modified vegetation drought index and soil evapotranspiration efficiency of the target area based on the three-dimensional feature space of surface temperature-enhanced vegetation index-shortwave infrared reflectivity; The rate, temperature-vegetation-shortwave infrared reflectance drought index, surface temperature in optical remote sensing data, normalized vegetation index, surface albedo, elevation and surface parameters in elevation data are matched with soil moisture products to obtain surface parameters with the same spatial resolution as soil moisture products, and used as the first training data; then the first training data is used as the independent variable and the soil moisture product is used as the dependent variable to train the random forest model to obtain the soil moisture inversion model; finally, the high spatial resolution surface parameters of the target area are input into the soil moisture inversion model to obtain soil moisture. It can accurately invert soil moisture and obtain accurate soil moisture data.

[0106] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0107] The methods or devices described in the above embodiments provided in this specification can implement business logic through computer programs and record them on storage media, and the storage media can be read and executed by computers to achieve the effects of the solutions described in the embodiments of this specification, such as:

[0108] Obtain microwave remote sensing soil moisture products, optical remote sensing data and elevation data of the target area;

[0109] Based on the trapezoidal feature space of surface temperature-vegetation coverage, the modified vegetation drought index and soil evapotranspiration efficiency of the target area are determined, and based on the three-dimensional feature space of surface temperature-enhanced vegetation index-shortwave infrared reflectivity, the temperature-vegetation-shortwave infrared reflectivity drought index of the target area is determined;

[0110] The modified vegetation drought index, soil evapotranspiration efficiency, temperature-vegetation-shortwave infrared reflectance drought index, surface temperature in optical remote sensing data, normalized difference vegetation index, surface albedo, elevation and surface parameters in elevation data are matched with soil moisture products to obtain surface parameters with the same spatial resolution as soil moisture products, and these are used as the first training data;

[0111] The soil moisture inversion model is obtained by training the random forest model using the first training data as an independent variable and the soil moisture product as a dependent variable;

[0112] The high spatial resolution surface parameters of the target area are input into a soil moisture inversion model to obtain soil moisture.

[0113] The storage medium may include a physical device for storing information, which is usually a medium that digitizes information and then stores it in an electrical, magnetic or optical manner. The storage medium may include: a device that stores information in an electrical energy manner, such as various memories, such as RAM, ROM, etc.; a device that stores information in a magnetic energy manner, such as a hard disk, a floppy disk, a magnetic tape, a magnetic core memory, a magnetic bubble memory, a USB flash drive; a device that stores information in an optical manner, such as a CD or a DVD. Of course, there are other readable storage media, such as quantum memory, graphene memory, etc.

[0114] The embodiments of this specification are not limited to complying with industry communication standards, standard computer resource data update and data storage rules, or the situations described in one or more embodiments of this specification. Certain industry standards or slightly modified implementation plans based on the implementation described in the custom method or embodiment can also achieve the same, equivalent or similar, or predictable implementation effects after deformation of the above-mentioned embodiments. The embodiments obtained by using these modified or deformed data acquisition, storage, judgment, processing methods, etc. can still fall within the scope of the optional implementation plans of the embodiments of this specification.

[0115] The controller can be implemented in any appropriate manner, for example, the controller can take the form of a computer-readable medium such as a microprocessor or processor and a computer-readable program code (such as software or firmware) that can be executed by the (micro)processor, a logic gate, a switch, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, ATMEL AT91SAM, MICROCHIP PIC18F26K20, and SILICONE LABS C8051F320. The memory controller can also be implemented as part of the control logic of the memory. It is also known to those skilled in the art that in addition to implementing the controller in a purely computer-readable program code manner, the controller can be implemented in the form of a logic gate, a switch, an application specific integrated circuit, a programmable logic controller, and an embedded microcontroller by logically programming the method steps. Therefore, such a controller can be considered as a hardware component, and the devices included therein for implementing various functions can also be considered as structures within the hardware component. Or even, the devices for implementing various functions can be considered as both software modules for implementing the method and structures within the hardware component.

[0116] The device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. There may be other divisions in actual implementation, such as multiple units or plug-ins may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed may be through some interface, indirect coupling or communication connection of the device or unit, which may be electrical, mechanical or other forms.

[0117] These computer program instructions may also be loaded onto a computer or other programmable resource data updating device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions executed on the computer or other programmable device for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0118] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can refer to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of this specification. In addition, unless there is a contradiction, a person skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0119] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the principles of the present invention, and should be understood that the protection scope of the present invention is not limited to such specific statements and embodiments. Those skilled in the art can make various other specific variations and combinations that do not deviate from the essence of the present invention based on the technical revelations disclosed by the present invention, and these variations and combinations are still within the protection scope of the present invention.

Claims

1. A soil moisture inversion method based on remote sensing data, characterized in that: The method comprises: Obtain microwave remote sensing soil moisture products, optical remote sensing data and elevation data of the target area; Based on the trapezoidal feature space of surface temperature-vegetation coverage, the modified vegetation drought index and soil evapotranspiration efficiency of the target area are determined, and based on the three-dimensional feature space of surface temperature-enhanced vegetation index-shortwave infrared reflectivity, the temperature-vegetation-shortwave infrared reflectivity drought index of the target area is determined; The modified vegetation drought index, soil evapotranspiration efficiency, temperature-vegetation-shortwave infrared reflectance drought index, surface temperature in optical remote sensing data, normalized difference vegetation index, surface albedo, elevation and surface parameters in elevation data are matched with soil moisture products to obtain surface parameters with the same spatial resolution as soil moisture products, and these are used as the first training data; The soil moisture inversion model is obtained by training the random forest model using the first training data as an independent variable and the soil moisture product as a dependent variable; Inputting the high spatial resolution surface parameters of the target area into a soil moisture inversion model to obtain soil moisture; The soil evapotranspiration efficiency is determined by the following formula: ， Where SEE is soil evapotranspiration efficiency, is the first temperature end member in the feature space, is the temperature of bare soil within the soil moisture contour, is the second temperature end member in the characteristic space, is the surface temperature corresponding to the wet edge, LST is the surface temperature, is the surface temperature corresponding to the dry side, is the vegetation coverage, is the third temperature end member in the characteristic space, is the fourth temperature end member in the characteristic space; Among them, the temperature-vegetation-shortwave infrared reflectance drought index is determined by the following formula: : ， Where LST is the land surface temperature, SWIR is the shortwave infrared reflectivity, and EVI is the enhanced vegetation index.

2. The soil moisture inversion method based on remote sensing data according to claim 1, characterized in that: The determination of the modified vegetation drought index of the target area specifically includes: Based on the surface temperature-vegetation coverage trapezoidal feature space, the surface temperature of bare soil under extreme drought and sufficient water supply conditions and the temperature of bare soil within the soil moisture contour were determined; The modified vegetation drought index is determined based on the surface temperature of bare soil under extreme drought and sufficient water supply conditions and the temperature of bare soil within the soil moisture contour.

3. The soil moisture inversion method based on remote sensing data according to claim 2, characterized in that: The modified vegetation drought index is determined by the following formula: ， In the formula, is the modified vegetation drought index, is the temperature of bare soil within the soil moisture contour, is the surface temperature under extreme drought conditions, The surface temperature under the condition of sufficient water supply.

4. The soil moisture inversion method based on remote sensing data according to claim 3, characterized in that: The soil moisture inversion model is as follows: ， In the formula, SM is soil moisture, RF is random forest model, is the modified vegetation drought index, SEE is the soil evapotranspiration efficiency, is the temperature-vegetation-shortwave infrared reflectance drought index, LST is the land surface temperature, is the normalized difference vegetation index, is the horizontal polarization brightness temperature, is the vertically polarized brightness temperature, ALB is the surface albedo, and H is the elevation.

5. A soil moisture inversion device based on remote sensing data, characterized in that: The device comprises: An acquisition module is used to obtain microwave remote sensing soil moisture products, optical remote sensing data and elevation data of the target area; A determination module is used to determine the modified vegetation drought index and soil evapotranspiration efficiency of the target area based on the trapezoidal feature space of surface temperature-vegetation coverage, and to determine the temperature-vegetation-shortwave infrared reflectivity drought index of the target area based on the three-dimensional feature space of surface temperature-enhanced vegetation index-shortwave infrared reflectivity; A matching module is used to match the modified vegetation drought index, soil evapotranspiration efficiency, temperature-vegetation-shortwave infrared reflectance drought index, surface temperature in optical remote sensing data, normalized vegetation index, surface albedo, elevation and surface parameters in elevation data with soil moisture products to obtain surface parameters with the same spatial resolution as the soil moisture products, and use them as the first training data; A training module, used for training a random forest model using the first training data as an independent variable and a soil moisture product as a dependent variable to obtain a soil moisture inversion model; An inversion module, used for inputting the high spatial resolution surface parameters of the target area into a soil moisture inversion model to obtain soil moisture; The soil evapotranspiration efficiency is determined by the following formula: ， Where SEE is soil evapotranspiration efficiency, is the first temperature end member in the feature space, is the temperature of bare soil within the soil moisture contour, is the second temperature end member in the characteristic space, is the surface temperature corresponding to the wet edge, LST is the surface temperature, is the surface temperature corresponding to the dry side, is the vegetation coverage, is the third temperature end member in the characteristic space, is the fourth temperature end member in the characteristic space; Among them, the temperature-vegetation-shortwave infrared reflectance drought index is determined by the following formula: : ， Where LST is the land surface temperature, SWIR is the shortwave infrared reflectivity, and EVI is the enhanced vegetation index.

Images