Soil moisture content determination method, device, equipment, medium and program product

Abstract

The invention discloses a soil moisture content determination method, device and equipment, a medium and a product. The method comprises the following steps: acquiring first soil moisture data and second soil moisture data of a target area at target time; determining a first soil moisture content prediction result according to the first soil moisture data and a first prediction model; determining a second soil moisture content prediction result according to the second soil moisture data and a second prediction model; and determining the soil moisture content of the target area at the target time according to the first soil moisture content prediction result and the second soil moisture content prediction result. According to the technical scheme, the problem that the soil moisture monitoring depth is insufficient is solved, multi-layer soil moisture content monitoring of the target area is achieved through the multi-source soil moisture content data, the reliability of soil moisture content monitoring is guaranteed, meanwhile, the spatial resolution of the soil moisture content data is improved, and a stable and reliable basis is provided for agricultural irrigation.

Description

Technical Field

[0001] The present invention relates to the field of geographic surveying and mapping technology, and in particular to a method, device, equipment, medium and product for determining soil moisture conditions. Background Art

[0002] Soil moisture refers to the amount of water in the crop plough layer soil, which has important reference value in agricultural irrigation. Satellite remote sensing is an advantageous means of soil moisture monitoring, mainly optical remote sensing and microwave remote sensing. Among them, optical remote sensing uses sensors to receive the emissivity information of ground objects to realize soil moisture monitoring. Microwave remote sensing is divided into active microwave remote sensing and passive microwave remote sensing. Active microwave remote sensing obtains the surface backscattering coefficient through radar and inverts soil moisture data. Passive microwave remote sensing estimates soil moisture data by measuring surface brightness temperature. Optical remote sensing data has high spatial resolution and rich spectral information, but poor penetration ability, easily affected by bad weather, and poor data continuity. Microwaves have better penetration, can still work normally in cloudy and rainy weather, and are not restricted by light conditions. They can realize all-weather monitoring, and have strong sensitivity to soil moisture identification. They can carry out large-scale real-time soil moisture monitoring, but microwave remote sensing data has low spatial resolution, often several kilometers or even tens of kilometers.

[0003] In view of the characteristics of optical remote sensing and microwave remote sensing, the existing technology mainly uses microwave remote sensing data and optical remote sensing data for collaborative inversion, and downscaling the microwave remote sensing data to obtain the soil moisture conditions of the region. However, the perception depth of optical remote sensing and microwave remote sensing is limited, and usually can only reflect the moisture content of the soil surface (1-2 cm below the ground). The planting depth of many crops far exceeds this perception depth. Therefore, the existing technology is insufficient for the depth monitoring of soil moisture, and a soil moisture determination method is needed to overcome the problem of insufficient soil moisture monitoring depth. Summary of the invention

[0004] The present invention provides a soil moisture determination method, device, equipment, medium and product to solve the problem of insufficient soil moisture monitoring depth. By utilizing multi-source soil moisture data, multi-level soil moisture monitoring in the target area is realized. While ensuring the reliability of soil moisture monitoring, the spatial resolution of soil moisture data is improved, providing a stable and reliable basis for agricultural irrigation.

[0005] According to one aspect of the present invention, a method for determining soil moisture conditions is provided, the method comprising:

[0006] Acquire first soil moisture data and second soil moisture data of a target area at a target time; wherein the first soil moisture data is surface soil moisture data determined based on optical remote sensing data; the second soil moisture data is surface soil moisture data determined based on microwave remote sensing data; and the spatial resolution of the first soil moisture data is higher than the spatial resolution of the second soil moisture data;

[0007] Determine a first soil moisture prediction result according to the first soil moisture data and a pre-trained first prediction model; wherein the first soil moisture prediction result includes multi-level soil moisture data;

[0008] Determine a second soil moisture prediction result according to the second soil moisture data and a pre-trained second prediction model; wherein the second soil moisture prediction result has the same spatial resolution as the first soil moisture prediction result;

[0009] The soil moisture conditions of the target area at the target time are determined according to the first soil moisture prediction result and the second soil moisture prediction result.

[0010] According to another aspect of the present invention, there is provided a soil moisture determination device, the device comprising:

[0011] A data acquisition module, used to acquire first soil moisture data and second soil moisture data of a target area at a target time; wherein the first soil moisture data is surface soil moisture data determined based on optical remote sensing data; the second soil moisture data is surface soil moisture data determined based on microwave remote sensing data; and the spatial resolution of the first soil moisture data is higher than the spatial resolution of the second soil moisture data;

[0012] A first prediction result determination module, used to determine a first soil moisture prediction result according to the first soil moisture data and a pre-trained first prediction model; wherein the first soil moisture prediction result includes multi-level soil moisture data;

[0013] A second prediction result determination module, used to determine a second soil moisture prediction result according to the second soil moisture data and a pre-trained second prediction model; wherein the second soil moisture prediction result has the same spatial resolution as the first soil moisture prediction result;

[0014] The soil moisture determination module is used to determine the soil moisture of the target area at the target time according to the first soil moisture prediction result and the second soil moisture prediction result.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the soil moisture determination method described in any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the soil moisture determination method described in any embodiment of the present invention when executed.

[0018] According to another aspect of the present invention, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the method for determining soil moisture conditions according to any embodiment of the present invention is implemented.

[0019] The technical solution of the embodiment of the present invention is to obtain the first soil moisture data and the second soil moisture data of the target area at the target time; wherein the first soil moisture data is the surface soil moisture data determined based on the optical remote sensing data; the second soil moisture data is the surface soil moisture data determined based on the microwave remote sensing data; the spatial resolution of the first soil moisture data is higher than the spatial resolution of the second soil moisture data; according to the first soil moisture data and the pre-trained first prediction model, determine the first soil moisture prediction result; wherein the first soil moisture prediction result includes multi-level soil moisture data; according to the second soil moisture data and the pre-trained second prediction model, determine the second soil moisture prediction result; wherein the second soil moisture prediction result has the same spatial resolution as the first soil moisture prediction result; according to the first soil moisture prediction result and the second soil moisture prediction result, determine the soil moisture of the target area at the target time. This technical solution solves the problem of insufficient soil moisture monitoring depth, realizes multi-level soil moisture monitoring of the target area by using multi-source soil moisture data, improves the spatial resolution of soil moisture data while ensuring the reliability of soil moisture monitoring, and provides a stable and reliable basis for agricultural irrigation.

[0020] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0022] Figure 1 is a flow chart of a method for determining soil moisture conditions provided according to Embodiment 1 of the present invention;

[0023] Figure 2 is a flow chart of a method for determining soil moisture conditions provided according to Embodiment 2 of the present invention;

[0024] Figure 3 is a schematic structural diagram of a soil moisture determination device provided according to Embodiment 3 of the present invention;

[0025] Figure 4 It is a structural schematic diagram of an electronic device for implementing the soil moisture determination method of an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The acquisition, storage, use, processing, etc. of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0028] Embodiment 1

[0029] Figure 1A flow chart of a soil moisture determination method is provided for the first embodiment of the present invention. This embodiment can be applied to agricultural irrigation guidance scenarios, especially monitoring soil moisture content. The method can be executed by a soil moisture determination device, which can be implemented in the form of hardware and / or software, and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0030] S110. Acquire first soil moisture data and second soil moisture data of a target area at a target time; wherein the first soil moisture data is surface soil moisture data determined based on optical remote sensing data; the second soil moisture data is surface soil moisture data determined based on microwave remote sensing data; and the spatial resolution of the first soil moisture data is higher than the spatial resolution of the second soil moisture data.

[0031] This solution can be executed by electronic devices such as computers and servers, and the electronic devices can obtain the first soil moisture data and the second soil moisture data of the target area collected by the meteorological satellite at the target time. The target location area can be an area where the soil moisture needs to be determined, and the target time can be the time when the meteorological satellite passes through the target area. The meteorological satellite can be equipped with microwave imagers, spectral imagers and other equipment to obtain multi-source remote sensing data of the target area. For example, through a microwave imager, the electronic device can obtain microwave remote sensing data of the target area, and through a spectral imager, the electronic device can obtain optical remote sensing data of the target area.

[0032] The electronic device can determine the first soil moisture data based on the optical remote sensing data, and determine the second soil moisture data based on the microwave remote sensing data. The first soil moisture data may include one or more of the land surface temperature (Land Surface Temperature, LST), the normalized vegetation index (Normalized Difference Vegetation Index, NDVI), the water deficit index (Soil water Deficit Index, WDI), the temperature-vegetation drought index (Temperature Vegetation Dryness Index, TVDI) and the vegetation conditional index (VCI). Specifically, based on the optical remote sensing data, the electronic device can calculate the land surface temperature, the normalized vegetation index, the water deficit index, the temperature-vegetation drought index and the vegetation conditional index in the first soil moisture data. Similarly, the electronic device can extract the brightness temperature data of a preset channel in the microwave remote sensing data as the second soil moisture data. The microwave remote sensing data can also be inverted to calculate data such as land surface temperature, normalized vegetation index, water deficit index, temperature-vegetation drought index and vegetation condition index, and one or more of the data such as land surface temperature, normalized vegetation index, water deficit index, temperature-vegetation drought index and vegetation condition index can be used as the second soil moisture data.

[0033] It can be understood that the resolution of optical remote sensing data is higher than that of microwave remote sensing data, usually several times or even dozens of times higher than that of microwave remote sensing data. Therefore, the resolution of the first soil moisture data is higher than that of the second soil moisture data. Microwave remote sensing data and optical remote sensing data are both images of the earth's surface and can only reflect ground information. Therefore, the first soil moisture data is the surface soil moisture data determined based on the optical remote sensing data, and the second soil moisture data is the surface soil moisture data determined based on the microwave remote sensing data.

[0034] S120. Determine a first soil moisture prediction result based on the first soil moisture data and a pre-trained first prediction model; wherein the first soil moisture prediction result includes multi-level soil moisture data.

[0035] The electronic device can input the first soil moisture data into the first prediction model to obtain the first soil moisture prediction result. The electronic device can also obtain information such as the soil type and land use type of the target area as auxiliary data of the first soil moisture data, and input them into the first prediction model together to obtain the first soil moisture prediction result. Among them, the first prediction model can be used to characterize the correlation between the first soil moisture data and the actual soil moisture. The first soil moisture data is the surface soil moisture data determined based on the optical remote sensing data, that is, the first soil moisture data characterizes the soil moisture situation at a single level. The first prediction model may include multiple first prediction sub-models, each prediction sub-model corresponds to a preset level, that is, a soil depth interval, and the intersection between each soil depth interval is empty. Each first prediction sub-model is used to characterize the correlation between the first soil moisture data and the soil moisture at a level. The first soil moisture data is input into each first prediction sub-model, and each first prediction sub-model can output the soil moisture data at each level to obtain the first soil moisture prediction result.

[0036] S130. Determine a second soil moisture prediction result based on the second soil moisture data and a pre-trained second prediction model; wherein the second soil moisture prediction result has the same spatial resolution as the first soil moisture prediction result.

[0037] The electronic device can input the second soil moisture data into the second prediction model to obtain a second soil moisture prediction result. The electronic device can also obtain information such as soil type and land use type of the target area as first auxiliary data of the second soil moisture data, obtain the first soil moisture data as second auxiliary data of the second soil moisture data, and combine the second soil moisture data, the first auxiliary data and the second auxiliary data as input data of the second prediction model to obtain a second soil moisture prediction result.

[0038] It can be understood that the first soil moisture condition is the soil moisture condition determined based on the first soil moisture data. The second soil moisture data is the surface soil moisture data determined based on the microwave remote sensing data, that is, the second soil moisture data represents the soil moisture condition at a single level. The second prediction model may include multiple second prediction sub-models, each prediction sub-model corresponds to a preset level, that is, a soil depth interval, and the intersection between each soil depth interval is empty. The electronic device can input the second soil moisture data into each second prediction model, and each second prediction sub-model can output the soil moisture data of each level to obtain the second soil moisture prediction result.

[0039] It should be noted that the resolution of the first soil moisture data is higher than that of the second soil moisture data, and the resolution of the soil moisture data at each level in the first soil moisture prediction result is the same as the spatial resolution of the first soil moisture data. Each second prediction sub-model can downscale the second soil moisture data to obtain a second soil moisture prediction result with the same spatial resolution as the first soil moisture prediction result. The resolution of the soil moisture data at each level in the first soil moisture prediction result is the same as the spatial resolution of the soil moisture data at each level in the second soil moisture prediction result.

[0040] S140: Determine the soil moisture condition of the target area at the target time according to the first soil moisture condition prediction result and the second soil moisture condition prediction result.

[0041] After obtaining the first soil moisture prediction result and the second soil moisture prediction result, the electronic device can fuse the first soil moisture prediction result and the second soil moisture prediction result to obtain the soil moisture of the target area at the target time. Specifically, the electronic device can directly calculate the average value of the first soil moisture prediction result and the second soil moisture prediction result, and use the average value of the two as the soil moisture of the target area at the target time.

[0042] In a preferred solution, the electronic device can pre-set weight coefficient groups that match different weather conditions, and each weight coefficient group can include a weight coefficient of the first soil moisture prediction result and a weight coefficient of the second soil moisture prediction result. According to the weather conditions at the target time, the electronic device can select a target weight coefficient group, and calculate the soil moisture of the target area at the target time according to the first soil moisture prediction result, the second soil moisture prediction result, the weight coefficient of the first soil moisture prediction result, and the weight coefficient of the second soil moisture prediction result. For example, in cloudy and rainy weather, the weight coefficient of the first soil moisture prediction result is 0, and the weight coefficient of the second soil moisture prediction result is 1.

[0043] The technical solution of the embodiment of the present invention is to obtain the first soil moisture data and the second soil moisture data of the target area at the target time; wherein the first soil moisture data is the surface soil moisture data determined based on the optical remote sensing data; the second soil moisture data is the surface soil moisture data determined based on the microwave remote sensing data; the spatial resolution of the first soil moisture data is higher than the spatial resolution of the second soil moisture data; according to the first soil moisture data and the pre-trained first prediction model, determine the first soil moisture prediction result; wherein the first soil moisture prediction result includes multi-level soil moisture data; according to the second soil moisture data and the pre-trained second prediction model, determine the second soil moisture prediction result; wherein the second soil moisture prediction result has the same spatial resolution as the first soil moisture prediction result; according to the first soil moisture prediction result and the second soil moisture prediction result, determine the soil moisture of the target area at the target time. This technical solution solves the problem of insufficient soil moisture monitoring depth, realizes multi-level soil moisture monitoring of the target area by using multi-source soil moisture data, improves the spatial resolution of soil moisture data while ensuring the reliability of soil moisture monitoring, and provides a stable and reliable basis for agricultural irrigation.

[0044] Embodiment 2

[0045] Figure 2 This is a flow chart of a method for determining soil moisture provided by Embodiment 2 of the present invention. This embodiment is based on the above embodiment and is refined. Figure 2 As shown, the method includes:

[0046] S210. Obtain a first soil moisture sample set, a second soil moisture sample set, and a third soil moisture sample set of the target area, wherein the first soil moisture sample set is a set of surface soil moisture samples determined based on optical remote sensing data; the second soil moisture sample set is a set of surface soil moisture samples determined based on microwave remote sensing data; the third soil moisture sample set is a set of multi-level soil moisture samples measured by observation equipment; the first soil moisture sample set, the second soil moisture sample set, and the third soil moisture sample set are time-matched; the spatial resolution of the first soil moisture sample is higher than the spatial resolution of the second soil moisture sample; the temporal resolution of the first soil moisture sample is lower than the temporal resolution of the second soil moisture sample.

[0047] The electronic device can pre-acquire optical remote sensing data of the target area, determine multiple surface soil moisture samples of the target area based on the optical remote sensing data, and form a first soil moisture sample set, acquire microwave remote sensing data of the target area, determine multiple surface soil moisture samples of the target area based on the microwave remote sensing data, and form a second soil moisture sample set, and acquire multi-level soil moisture samples measured by observation equipment in the target area to form a third soil moisture sample set. Among them, the third soil moisture sample set includes multiple third soil moisture sample subsets, each third soil moisture sample subset corresponds to a level, that is, a soil depth interval, and each third soil moisture sample subset includes multiple soil moisture samples. Each soil moisture sample may include data such as sampling time, soil volume moisture content, relative soil moisture content, soil weight water content, and soil effective water storage.

[0048] According to the sampling time of the soil moisture samples in the first soil moisture sample set, the second soil moisture sample set and the third soil moisture sample set, the electronic device can time match the first soil moisture sample set, the second soil moisture sample set and the third soil moisture sample set, and establish an association relationship between the soil moisture samples in the first soil moisture sample set, the second soil moisture sample set and the third soil moisture sample set with the same sampling time or with approximately the same sampling time.

[0049] It should be noted that compared with microwave remote sensing data, optical remote sensing data has a higher spatial resolution. Therefore, the spatial resolution of the first soil moisture sample is higher than that of the second soil moisture sample. Optical remote sensing data is easily affected by bad weather and has poor data continuity. Microwaves have better penetration and can still work normally in cloudy and rainy weather, and can achieve all-weather monitoring. Therefore, the temporal resolution of the first soil moisture sample is lower than that of the second soil moisture sample.

[0050] S220: Train a pre-built machine learning model according to the first soil moisture sample set and the third soil moisture sample set to determine a first prediction model.

[0051] The electronic device can pre-build a machine learning model, such as a K-nearest neighbor model, a random forest model, and a decision tree model. The electronic device can sequentially use each third soil moisture sample subset of the third soil moisture sample set as a target sample subset, the level corresponding to the target sample subset as the target level, each first soil moisture sample in the first soil moisture sample set as input data for the machine learning model, and the third soil moisture sample in the target sample subset that matches the time of each first soil moisture sample as a supervision label, and perform at least one iterative training on the machine learning model until the machine learning model meets the preset evaluation index. The evaluation index can be a prediction accuracy rate, a prediction error rate, etc.

[0052] It is understandable that the electronic device can input the first soil moisture sample into the machine learning model, and the machine learning model can output the soil moisture prediction result corresponding to the first soil moisture sample, compare the soil moisture prediction result with the supervision label corresponding to the first soil moisture sample, and determine whether the two are consistent, so as to statistically calculate the accuracy or error rate of the soil moisture at the target level predicted by the machine learning model based on the first soil moisture sample set, and then determine whether the machine learning model meets the preset evaluation indicators. If the machine learning model meets the preset evaluation indicators, the electronic device can use the machine learning model obtained in this iteration as the first prediction model.

[0053] In this solution, optionally, the first prediction model includes first prediction sub-models matched at each level; the number of pre-built machine learning models is multiple;

[0054] The step of training a pre-built machine learning model according to the first soil moisture sample set and the third soil moisture sample set to determine a first prediction model includes:

[0055] Using the first soil moisture sample in the first soil moisture sample set as input data of the machine learning model, using the soil moisture samples of the target layer in the third soil moisture sample set as supervision labels, performing at least one iterative training on each machine learning model, and determining the training results of each machine learning model;

[0056] According to the training results of each machine learning model, a target machine learning model is determined in each machine learning model as the first prediction sub-model for target hierarchical matching.

[0057] In a preferred solution, the electronic device can pre-build multiple machine learning models, each machine learning model is different. Each third soil moisture sample subset of the third soil moisture sample set is used as the target sample subset in turn, the level corresponding to the target sample subset is used as the target level, each first soil moisture sample in the first soil moisture sample set is used as the input data of each machine learning model, and the third soil moisture sample in the target sample subset that matches the time of each first soil moisture sample is used as the supervision label, and each machine learning model is iteratively trained at least once to obtain the training results of each machine learning model.

[0058] Among them, the training results may include the accuracy or error rate of the soil moisture conditions of the target layer predicted by the machine learning model based on the first soil moisture sample set, and may also include the running time of the machine learning model. The electronic device may sort the machine learning models according to the training results of each machine learning model, and select the target machine learning model from each machine learning model as the first prediction sub-model corresponding to the target layer. Specifically, the target machine learning model may be a machine learning model with the highest prediction accuracy and the lowest error rate, or a machine learning model with the shortest running time, or a machine learning model with the highest prediction accuracy, the lowest error rate and the shortest running time.

[0059] S230: Train a pre-built machine learning model based on the second soil moisture sample set and the third soil moisture sample set to determine a second prediction model.

[0060] The electronic device can pre-build a machine learning model, such as a K-nearest neighbor model, a random forest model, and a decision tree model. The electronic device can sequentially use each third soil moisture sample subset of the third soil moisture sample set as a target sample subset, the level corresponding to the target sample subset as the target level, each second soil moisture sample in the second soil moisture sample set as input data for the machine learning model, and the third soil moisture sample in the target sample subset that matches the time of each second soil moisture sample as a supervision label, and perform at least one iterative training on the machine learning model until the machine learning model meets the preset evaluation index. The evaluation index can be a prediction accuracy rate, a prediction error rate, etc.

[0061] It can be understood that the electronic device can input the second soil moisture sample into the machine learning model, and the machine learning model can output the soil moisture prediction result corresponding to the second soil moisture sample, compare the soil moisture prediction result with the supervision label corresponding to the second soil moisture sample, and determine whether the two are consistent, so as to statistically calculate the accuracy or error rate of the soil moisture at the target level predicted by the machine learning model based on the second soil moisture sample set, and then determine whether the machine learning model meets the preset evaluation indicators. If the machine learning model meets the preset evaluation indicators, the electronic device can use the machine learning model obtained in this iteration as the second prediction model.

[0062] In a feasible solution, the second prediction model includes second prediction sub-models matched at each level; the number of pre-built machine learning models is multiple;

[0063] The step of training a pre-built machine learning model according to the second soil moisture sample set and the third soil moisture sample set to determine a second prediction model includes:

[0064] Resampling each second soil moisture sample in the second soil moisture sample set according to the spatial resolution of the first soil moisture sample;

[0065] Using the resampled second soil moisture samples in the second soil moisture sample set as input data of the machine learning model in sequence, using the soil moisture samples of the target layer in the third soil moisture sample set as supervision labels, performing at least one iterative training on each machine learning model, and determining the training results of each machine learning model;

[0066] According to the training results of each machine learning model, a target machine learning model is determined in each machine learning model as the second prediction sub-model for target hierarchical matching.

[0067] In a preferred scheme, since the spatial resolution of the first soil moisture sample is different from that of the second soil moisture sample, the electronic device can resample each second soil moisture sample in the second soil moisture sample set according to the spatial resolution of the first soil moisture sample to obtain a second soil moisture sample with the same spatial resolution as the first soil moisture sample.

[0068] The electronic device can pre-build multiple machine learning models, each machine learning model is different. Each third soil moisture sample subset of the third soil moisture sample set is used as the target sample subset in turn, the level corresponding to the target sample subset is used as the target level, each second soil moisture sample in the second soil moisture sample set is used as input data of each machine learning model, and the third soil moisture sample in the target sample subset that matches each second soil moisture sample is used as a supervision label. Each machine learning model is iteratively trained at least once to obtain the training results of each machine learning model.

[0069] Among them, the training results may include the accuracy or error rate of the soil moisture conditions of the target layer predicted by the machine learning model based on the second soil moisture sample set, and may also include the running time of the machine learning model. The electronic device may sort the machine learning models according to the training results of each machine learning model, and select the target machine learning model from each machine learning model as the second prediction sub-model corresponding to the target layer. Specifically, the target machine learning model may be a machine learning model with the highest prediction accuracy and the lowest error rate, or a machine learning model with the shortest running time, or a machine learning model with the highest prediction accuracy, the lowest error rate and the shortest running time.

[0070] Using the first prediction model obtained in S220, the electronic device can obtain a first soil moisture prediction result based on the first soil moisture data of the target area at the target time. Using the second prediction model obtained in S230, the electronic device can obtain a second soil moisture prediction result based on the second soil moisture data of the target area at the target time. By fusing the soil moisture prediction results obtained based on different data sources, a more reliable soil moisture prediction result can be obtained, avoiding unstable factors such as data loss and susceptibility to environmental influences caused by a single data source.

[0071] S240. Acquire first soil moisture data and second soil moisture data of a target area at a target time; wherein the first soil moisture data is surface soil moisture data determined based on optical remote sensing data; the second soil moisture data is surface soil moisture data determined based on microwave remote sensing data; and the spatial resolution of the first soil moisture data is higher than the spatial resolution of the second soil moisture data.

[0072] S250. Determine a first soil moisture prediction result based on the first soil moisture data and a pre-trained first prediction model; wherein the first soil moisture prediction result includes multi-level soil moisture data.

[0073] S260. Determine a second soil moisture prediction result based on the second soil moisture data and a pre-trained second prediction model; wherein the second soil moisture prediction result has the same spatial resolution as the first soil moisture prediction result.

[0074] S270: Determine the soil moisture condition of the target area at the target time according to the first soil moisture condition prediction result and the second soil moisture condition prediction result.

[0075] The technical solution of the embodiment of the present invention is to obtain the first soil moisture data and the second soil moisture data of the target area at the target time; wherein the first soil moisture data is the surface soil moisture data determined based on the optical remote sensing data; the second soil moisture data is the surface soil moisture data determined based on the microwave remote sensing data; the spatial resolution of the first soil moisture data is higher than the spatial resolution of the second soil moisture data; according to the first soil moisture data and the pre-trained first prediction model, determine the first soil moisture prediction result; wherein the first soil moisture prediction result includes multi-level soil moisture data; according to the second soil moisture data and the pre-trained second prediction model, determine the second soil moisture prediction result; wherein the second soil moisture prediction result has the same spatial resolution as the first soil moisture prediction result; according to the first soil moisture prediction result and the second soil moisture prediction result, determine the soil moisture of the target area at the target time. This technical solution solves the problem of insufficient soil moisture monitoring depth, realizes multi-level soil moisture monitoring of the target area by using multi-source soil moisture data, improves the spatial resolution of soil moisture data while ensuring the reliability of soil moisture monitoring, and provides a stable and reliable basis for agricultural irrigation.

[0076] Embodiment 3

[0077] Figure 3 A schematic diagram of the structure of a soil moisture determination device provided in Embodiment 3 of the present invention.

[0078] like Figure 3 As shown, the device comprises:

[0079] The data acquisition module 310 is used to acquire first soil moisture data and second soil moisture data of a target area at a target time; wherein the first soil moisture data is surface soil moisture data determined based on optical remote sensing data; the second soil moisture data is surface soil moisture data determined based on microwave remote sensing data; and the spatial resolution of the first soil moisture data is higher than the spatial resolution of the second soil moisture data;

[0080] A first prediction result determination module 320 is used to determine a first soil moisture prediction result according to the first soil moisture data and a pre-trained first prediction model; wherein the first soil moisture prediction result includes multi-level soil moisture data;

[0081] A second prediction result determination module 330 is used to determine a second soil moisture prediction result according to the second soil moisture data and a pre-trained second prediction model; wherein the second soil moisture prediction result has the same spatial resolution as the first soil moisture prediction result;

[0082] The soil moisture determination module 340 is used to determine the soil moisture of the target area at the target time according to the first soil moisture prediction result and the second soil moisture prediction result.

[0083] In this solution, the device further includes a first prediction model training module, and the first prediction model training module is used to:

[0084] Acquire a first soil moisture sample set, a second soil moisture sample set, and a third soil moisture sample set in a target area;

[0085] Among them, the first soil moisture sample set is a set of surface soil moisture samples determined based on optical remote sensing data; the second soil moisture sample set is a set of surface soil moisture samples determined based on microwave remote sensing data; the third soil moisture sample set is a set of multi-level soil moisture samples measured by observation equipment; the first soil moisture sample set, the second soil moisture sample set and the third soil moisture sample set are time-matched; the spatial resolution of the first soil moisture sample is higher than the spatial resolution of the second soil moisture sample; the temporal resolution of the first soil moisture sample is lower than the temporal resolution of the second soil moisture sample;

[0086] A pre-constructed machine learning model is trained according to the first soil moisture sample set and the third soil moisture sample set to determine a first prediction model.

[0087] Based on the above solution, the device further includes a second prediction model training module, and the second prediction model training module is specifically used to:

[0088] The pre-constructed machine learning model is trained according to the second soil moisture sample set and the third soil moisture sample set to determine a second prediction model.

[0089] In a feasible solution, the first prediction model includes first prediction sub-models matched at each level; the number of pre-built machine learning models is multiple;

[0090] The first prediction model training module is specifically used for:

[0091] Using the first soil moisture sample in the first soil moisture sample set as input data of the machine learning model, using the soil moisture samples of the target layer in the third soil moisture sample set as supervision labels, performing at least one iterative training on each machine learning model, and determining the training results of each machine learning model;

[0092] According to the training results of each machine learning model, a target machine learning model is determined in each machine learning model as the first prediction sub-model for target hierarchical matching.

[0093] In this embodiment, the second prediction model includes second prediction sub-models matched at each level; the number of pre-constructed machine learning models is multiple;

[0094] The second prediction model training module is specifically used for:

[0095] Resampling each second soil moisture sample in the second soil moisture sample set according to the spatial resolution of the first soil moisture sample;

[0096] Using the resampled second soil moisture samples in the second soil moisture sample set as input data of the machine learning model in sequence, using the soil moisture samples of the target layer in the third soil moisture sample set as supervision labels, performing at least one iterative training on each machine learning model, and determining the training results of each machine learning model;

[0097] According to the training results of each machine learning model, a target machine learning model is determined in each machine learning model as the second prediction sub-model for target hierarchical matching.

[0098] In a preferred embodiment, the first soil moisture data includes at least one of land surface temperature, normalized difference vegetation index, water deficit index, temperature-vegetation drought index and vegetation condition index;

[0099] The second soil moisture data includes brightness temperature data of a preset number of channels.

[0100] The soil moisture determination device provided in the embodiment of the present invention can execute the soil moisture determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0101] Embodiment 4

[0102] Figure 4 A schematic diagram of an electronic device 410 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0103] like Figure 4As shown, the electronic device 410 includes at least one processor 411, and a memory connected to the at least one processor 411 in communication, such as a read-only memory (ROM) 412, a random access memory (RAM) 413, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 411 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 412 or the computer program loaded from the storage unit 418 to the random access memory (RAM) 413. In the RAM 413, various programs and data required for the operation of the electronic device 410 can also be stored. The processor 411, the ROM 412, and the RAM 413 are connected to each other via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0104] Multiple components in the electronic device 410 are connected to the I / O interface 415, including: an input unit 416, such as a keyboard, a mouse, etc.; an output unit 417, such as various types of displays, speakers, etc.; a storage unit 418, such as a disk, an optical disk, etc.; and a communication unit 419, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 419 allows the electronic device 410 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0105] The processor 411 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 411 executes the various methods and processes described above, such as a soil moisture determination method.

[0106] In some embodiments, the soil moisture determination method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 418. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 410 via the ROM 412 and / or the communication unit 419. When the computer program is loaded into the RAM 413 and executed by the processor 411, one or more steps of the soil moisture determination method described above may be performed. Alternatively, in other embodiments, the processor 411 may be configured to perform the soil moisture determination method in any other appropriate manner (e.g., by means of firmware).

[0107] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0108] The computer programs for implementing the method of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable soil moisture determination device so that the computer programs, when executed by the processor, implement the functions / operations specified in the flow chart and / or block diagram. The computer programs may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0109] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0110] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0111] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0112] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0113] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0114] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for determining soil moisture, characterized in that: The method comprises: Acquire first soil moisture data and second soil moisture data of a target area at a target time; wherein the first soil moisture data is surface soil moisture data determined based on optical remote sensing data; the second soil moisture data is surface soil moisture data determined based on microwave remote sensing data; and the spatial resolution of the first soil moisture data is higher than the spatial resolution of the second soil moisture data; Determine a first soil moisture prediction result according to the first soil moisture data and a pre-trained first prediction model; wherein the first soil moisture prediction result includes multi-level soil moisture data; Determine a second soil moisture prediction result according to the second soil moisture data and a pre-trained second prediction model; wherein the second soil moisture prediction result has the same spatial resolution as the first soil moisture prediction result; The soil moisture conditions of the target area at the target time are determined according to the first soil moisture condition prediction result and the second soil moisture condition prediction result.

2. The method according to claim 1, characterized in that The training process of the first prediction model includes: Acquire a first soil moisture sample set, a second soil moisture sample set, and a third soil moisture sample set in a target area; Among them, the first soil moisture sample set is a set of surface soil moisture samples determined based on optical remote sensing data; the second soil moisture sample set is a set of surface soil moisture samples determined based on microwave remote sensing data; the third soil moisture sample set is a set of multi-level soil moisture samples measured by observation equipment; the first soil moisture sample set, the second soil moisture sample set and the third soil moisture sample set are time-matched; the spatial resolution of the first soil moisture sample is higher than the spatial resolution of the second soil moisture sample; the temporal resolution of the first soil moisture sample is lower than the temporal resolution of the second soil moisture sample; A pre-constructed machine learning model is trained according to the first soil moisture sample set and the third soil moisture sample set to determine a first prediction model.

3. The method according to claim 2, characterized in that The training process of the second prediction model includes: The pre-constructed machine learning model is trained according to the second soil moisture sample set and the third soil moisture sample set to determine a second prediction model.

4. The method according to claim 2, characterized in that: The first prediction model includes first prediction sub-models matched at each level; the number of pre-built machine learning models is multiple; The step of training a pre-built machine learning model according to the first soil moisture sample set and the third soil moisture sample set to determine a first prediction model includes: Using the first soil moisture sample in the first soil moisture sample set as input data of the machine learning model, using the soil moisture samples of the target layer in the third soil moisture sample set as supervision labels, performing at least one iterative training on each machine learning model, and determining the training results of each machine learning model; According to the training results of each machine learning model, a target machine learning model is determined in each machine learning model as the first prediction sub-model for target hierarchical matching.

5. The method according to claim 3, characterized in that: The second prediction model includes second prediction sub-models matched at each level; the number of pre-built machine learning models is multiple; The step of training a pre-built machine learning model according to the second soil moisture sample set and the third soil moisture sample set to determine a second prediction model includes: resampling each second soil moisture sample in the second soil moisture sample set according to the spatial resolution of the first soil moisture sample; Using the resampled second soil moisture samples in the second soil moisture sample set as input data of the machine learning model in sequence, using the soil moisture samples of the target layer in the third soil moisture sample set as supervision labels, performing at least one iterative training on each machine learning model, and determining the training results of each machine learning model; According to the training results of each machine learning model, a target machine learning model is determined in each machine learning model as the second prediction sub-model for target hierarchical matching.

6. The method according to claim 1, characterized in that The first soil moisture data includes at least one of land surface temperature, normalized difference vegetation index, water deficit index, temperature-vegetation drought index and vegetation condition index; The second soil moisture data includes brightness temperature data of a preset number of channels.

7. A soil moisture determination device, characterized in that: The device comprises: A data acquisition module, used to acquire first soil moisture data and second soil moisture data of a target area at a target time; wherein the first soil moisture data is surface soil moisture data determined based on optical remote sensing data; the second soil moisture data is surface soil moisture data determined based on microwave remote sensing data; and the spatial resolution of the first soil moisture data is higher than the spatial resolution of the second soil moisture data; A first prediction result determination module, used to determine a first soil moisture prediction result according to the first soil moisture data and a pre-trained first prediction model; wherein the first soil moisture prediction result includes multi-level soil moisture data; A second prediction result determination module, used to determine a second soil moisture prediction result according to the second soil moisture data and a pre-trained second prediction model; wherein the second soil moisture prediction result has the same spatial resolution as the first soil moisture prediction result; The soil moisture determination module is used to determine the soil moisture of the target area at the target time according to the first soil moisture prediction result and the second soil moisture prediction result.

8. An electronic device, characterized in that: The electronic device comprises: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the soil moisture determination method described in any one of claims 1-6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the soil moisture determination method described in any one of claims 1-6 when executed.

10. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the soil moisture determination method according to any one of claims 1 to 6.

Images