CN110826173B - Soil moisture data acquisition method and system, storage medium and equipment - Google Patents
Soil moisture data acquisition method and system, storage medium and equipment Download PDFInfo
- Publication number
- CN110826173B CN110826173B CN201910905363.2A CN201910905363A CN110826173B CN 110826173 B CN110826173 B CN 110826173B CN 201910905363 A CN201910905363 A CN 201910905363A CN 110826173 B CN110826173 B CN 110826173B
- Authority
- CN
- China
- Prior art keywords
- soil moisture
- data
- inversion model
- decision tree
- albedo
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Abstract
The invention relates to a method, a system, a storage medium and equipment for acquiring soil moisture data. Compared with the prior art, the method can realize the acquisition of the medium and high resolution satellite remote sensing soil moisture data and improve the resolution of the soil moisture data.
Description
Technical Field
The invention relates to the technical field of geographic information, in particular to a method, a system, a storage medium and equipment for acquiring soil moisture data.
Background
The soil moisture reflects the agricultural drought degree, and the soil moisture is used as an index to guide agricultural irrigation. The water content of soil is commonly called soil moisture content, and also includes the states of soil property, depth and the like, which are related to the high-quality growth of crops. The absorption rate of crops to nutrients is directly influenced by the level of soil moisture, the decomposition and mineralization of organic nutrients in soil cannot separate moisture, chemical fertilizers applied to the soil can be dissolved only in water, the migration of nutrient ions to the surface of root systems and the absorption of the crop root systems to the nutrients are realized by moisture media, and if the roots of crops cannot timely and sufficiently irrigate or excessively irrigate, roots of the crops cannot timely absorb the moisture from the soil, so that the normal growth of the crops is influenced.
The soil moisture data has great significance for development and planning of agriculture, however, the existing soil moisture data has the problems of low spatial resolution and insufficient precision, specific positions of soil moisture nodes are difficult to specifically position, and production and application are not facilitated.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide a high-precision soil moisture data acquisition method, a high-precision soil moisture data acquisition system, a high-precision soil moisture data storage medium and high-precision soil moisture data acquisition equipment.
A soil moisture data acquisition method comprises the following steps:
acquiring satellite soil moisture data, albedo, evapotranspiration, surface temperature, vegetation index, longitude and latitude position and elevation data as a training data set, taking the albedo, evapotranspiration, surface temperature, vegetation index, longitude and latitude position and elevation data as explanatory variables, taking the soil moisture data as dependent variables, and establishing a soil moisture inversion model based on an extreme gradient lifting algorithm;
the soil moisture inversion model takes a plurality of decision trees as learning units, fits the next decision tree according to the residual error between the output result of the previous decision tree and the actual value, and obtains a soil moisture prediction value by summing the output results of the decision trees;
and acquiring an explanatory variable with a target resolution as an explanatory variable data set, inputting the explanatory variable data set into the soil moisture inversion model for downscaling inversion, and acquiring the soil moisture data with the target resolution.
Compared with the prior art, the method has the advantages that the albedo, the evapotranspiration, the earth surface temperature, the vegetation index, the longitude and latitude position and the elevation data are used as explanatory variables, the soil moisture data are used as dependent variables, a soil moisture inversion model is established based on an extreme gradient lifting algorithm, and the inversion relation of the soil moisture and the earth surface parameters is simulated. And then obtaining an explanatory variable with a target resolution as an explanatory variable data set, inputting the explanatory variable data set into the soil moisture inversion model for downscaling inversion to obtain soil moisture data of the target resolution, wherein a user can utilize the method for obtaining the medium and high resolution satellite remote sensing soil moisture data to improve the resolution of the soil moisture data.
In an embodiment of the present invention, the step of establishing a soil moisture inversion model based on an extreme gradient lifting algorithm by using the albedo, evapotranspiration, surface temperature, vegetation index, longitude and latitude position and elevation data as explanatory variables and soil moisture data as dependent variables comprises:
given data set
Setting a loss function of the learning unit to
The number of iterations t and the number of decision trees k, where xiFor the explanatory variables of the model, yiIn order to actually output the result of the output,
outputting a result for the soil moisture inversion model;
obtaining the simulation predicted value of the soil moisture inversion model at the t time according to the following mode
Wherein the content of the first and second substances,
is the output result of the soil moisture inversion model for t-1 times, ft(xi) Predicting the result for the t-th iteration of the decision tree;
randomly putting back and extracting subset K in training data set, training each decision tree to obtain residual error
And minimizing a training loss function according to the following mode to obtain the minimum residual error of the soil moisture inversion model:
wherein gamma is a regular term coefficient;
summing the prediction results of all the single decision trees to obtain a soil moisture prediction value:
wherein f iskIs the prediction result of a single decision tree, and K is the number of the decision trees;
and traversing the iteration times t and the number k of the decision tree in the training data set, calculating the precision of each t and k combined output result, and selecting the iteration times with the highest precision of the output result and the number of the decision tree as parameters of the soil moisture inversion model. The soil moisture inversion model simulates the inversion relation of the soil moisture and the earth surface parameters based on the close correlation relation of the soil moisture and the earth surface parameters.
In an embodiment of the present invention, before the step of establishing a soil moisture inversion model based on an extreme gradient lifting algorithm by using the albedo, evapotranspiration, surface temperature, vegetation index, longitude and latitude position and elevation data as explanatory variables and soil moisture data as dependent variables, the method further includes: preprocessing the data of the training data set, which specifically comprises the following steps:
carrying out space-time sequence reconstruction based on low-pass filtering processing on the albedo, evapotranspiration, surface temperature and vegetation index, and smoothing out abnormal values;
unifying the spatial projection, the geographic coordinates, the spatial resolution and the temporal resolution of the soil moisture data, the albedo, the evapotranspiration, the earth surface temperature, the vegetation index, the longitude and latitude position and the elevation data;
and filtering the water body area in the soil moisture, the albedo, the evapotranspiration, the surface temperature, the vegetation index, the longitude and latitude position and the elevation data by using the water body mask data. By preprocessing the data of the training data set, the predicted value of the vegetation data is more accurate and comprehensive.
The invention also provides a soil moisture data acquisition system, comprising:
the soil moisture inversion model building module is used for acquiring satellite soil moisture data, albedo, evapotranspiration, surface temperature, vegetation index, longitude and latitude positions and elevation data as a training data set, taking the albedo, the evapotranspiration, the surface temperature, the vegetation index, the longitude and latitude positions and the elevation data as explanatory variables, taking the soil moisture data as dependent variables and building a soil moisture inversion model based on an extreme gradient lifting algorithm;
the soil moisture inversion model takes a plurality of decision trees as learning units, fits the next decision tree according to the residual error between the output result of the previous decision tree and the actual value, and obtains a soil moisture prediction value by summing the output results of the decision trees;
and the soil moisture inversion model inversion module is used for acquiring an explanatory variable with a target resolution as an explanatory variable data set, inputting the explanatory variable data set into the soil moisture inversion model for scale reduction inversion, and acquiring soil moisture data with the target resolution.
In one embodiment of the present invention, the soil moisture inversion model building module includes:
parameter acquisition unit for a given data set
The extreme gradient lifting algorithm takes a decision tree as a learning unit, and the loss function of the learning unit is
The number of iterations t and the number of decision trees k, where xiFor the explanatory variables of the model, yiIn order to actually output the result of the output,
outputting a result for the soil moisture inversion model;
a predicted value obtaining unit for obtaining the predicted value of the t-th time of the soil moisture inversion model according to the following mode
Wherein the content of the first and second substances,
is the output result of the soil moisture inversion model for t-1 times, ft(xi) Predicting the result for the t-th iteration of the decision tree;
a residual error obtaining unit for randomly putting back the extraction subset K in the training data set, training each decision tree and obtaining the residual error
A loss function training unit for minimizing a training loss function in the following manner:
wherein gamma is a regular term coefficient;
the predicted value obtaining unit is used for summing the predicted results of all the single decision trees to obtain the predicted value of the soil moisture:
wherein f iskIs the prediction result of a single decision tree, and K is the number of the decision trees;
and the parameter selection unit is used for traversing the iteration times t and the number k of the decision tree in the training data set, calculating the precision of the combined output result of each iteration time t and the number k of the decision tree, and selecting the iteration times with the highest precision of the output result and the number of the decision tree as the parameters of the soil moisture inversion model.
In an embodiment of the present invention, the soil moisture data acquisition system further includes a data preprocessing module, and the data preprocessing unit is configured to preprocess the training data set data; the preprocessing module comprises:
the filtering unit is used for carrying out space-time sequence reconstruction based on low-pass filtering processing on the albedo, evapotranspiration, surface temperature and vegetation index to smooth out abnormal values;
the unifying unit is used for unifying the spatial projection, the geographic coordinate, the spatial resolution and the time resolution of the soil moisture data, the albedo, the evapotranspiration, the surface temperature, the vegetation index, the longitude and latitude position and the elevation data;
and the water body filtering unit is used for filtering the water body area in the soil moisture, the albedo, the evapotranspiration, the surface temperature, the vegetation index, the longitude and latitude position and the elevation data by using the water body mask data.
The present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the soil moisture data acquisition method as set forth in any one of the above.
The invention also provides computer equipment comprising a memory, a processor and a computer program stored in the memory and executable by the processor, wherein the processor executes the computer program to realize the steps of the soil moisture data acquisition method.
For a better understanding and practice, the invention is described in detail below with reference to the accompanying drawings.
Drawings
FIG. 1 is a flow chart of a method of soil moisture data acquisition in an embodiment of the invention;
FIG. 2 is a flowchart of step S10 of the soil water data acquisition method according to the embodiment of the present invention;
FIG. 3 is a flowchart of step S11 of the soil water data acquisition method according to the embodiment of the present invention;
FIG. 4 is a schematic diagram of a soil moisture data acquisition system according to an embodiment of the present invention;
FIG. 5 is a schematic structural diagram of the data preprocessing module 10 according to the embodiment of the present invention
Fig. 6 is a schematic structural diagram of the soil moisture inversion model building module 11 in the embodiment of the present invention.
Detailed Description
Examples
Referring to fig. 1, the present invention provides a method for acquiring soil moisture data, including the following steps:
step S1: acquiring satellite soil moisture data, albedo, evapotranspiration, surface temperature, vegetation index, longitude and latitude position and elevation data as a training data set, taking the albedo, evapotranspiration, surface temperature, vegetation index, longitude and latitude position and elevation data as explanatory variables, taking the soil moisture data as dependent variables, and establishing a soil moisture inversion model based on an extreme gradient lifting algorithm;
in this embodiment, the medium-high resolution satellite remote sensing Soil Moisture data is based on the close correlation between Soil water (SM) and dynamic and steady state variables, a nonlinear regression mapping model is established on the scale of 0.25 ° (about 25km) of the original spatial resolution of the Soil Moisture of the satellite, and the inverse relationship between the Soil Moisture and the surface parameters is simulated. In other embodiments, the spatial resolution may also be set according to the user requirement. Wherein the dynamic variables include: albedo (Albedo), Evapotranspiration (ET), Land Surface Temperature (LST), Vegetation Index (Normalized Difference Vegetation Index, NDVI), and steady state variables including: longitude and Latitude position (LL) and Elevation Data (DEM).
In a preferred embodiment, before the step of establishing the soil moisture inversion model based on the extreme gradient lifting algorithm by using the albedo, the evapotranspiration, the surface temperature, the vegetation index, the longitude and latitude position and the elevation data as explanatory variables and using the soil moisture data as dependent variables, the method further includes: preprocessing the training data set data, as shown in fig. 2, specifically including:
step S101: carrying out space-time sequence reconstruction based on low-pass filtering processing on the albedo, evapotranspiration, surface temperature and vegetation index, and smoothing out abnormal values;
step S102: unifying the spatial projection, the geographic coordinates, the spatial resolution and the temporal resolution of the soil moisture data, the albedo, the evapotranspiration, the earth surface temperature, the vegetation index, the longitude and latitude position and the elevation data; in this embodiment, the spatial resolution is 0.25 ° pel resolution.
Step S103: and filtering the water body area in the soil moisture, the albedo, the evapotranspiration, the surface temperature, the vegetation index, the longitude and latitude position and the elevation data by using the water body mask data.
The soil moisture inversion model takes a plurality of decision trees as learning units, fits the next decision tree according to the residual error between the output result of the previous decision tree and the actual value, and obtains a soil moisture predicted value by summing the output results of the decision trees; the soil moisture inversion model is derived from a gradient enhancement idea and is an optimization algorithm based on a proper cost function. According to the method, the extreme gradient lifting algorithm is applied to a multisource satellite remote sensing data scene with a spatial position attribute, so that high-resolution reconstruction of a soil moisture space-time sequence dataset is realized.
The step of establishing a soil moisture inversion model by taking the albedo, evapotranspiration, surface temperature, vegetation index, longitude and latitude positions and elevation data as explanatory variables and soil moisture data as dependent variables and based on an extreme gradient lifting algorithm comprises the following steps of:
step S111: given data set
The extreme gradient lifting algorithm takes a decision tree as a learning unit, and the loss function of the learning unit is
The number of iterations t and the number of decision trees k, where xiFor the explanatory variables of the model, yiIn order to actually output the result of the output,
outputting a result for the soil moisture inversion model;
step S112: obtaining the simulation predicted value of the soil moisture inversion model at the t time according to the following mode
Wherein the content of the first and second substances,
is the output result of the soil moisture inversion model for t-1 times, ft(xi) Predicting the result for the t-th iteration of the decision tree;
step S113: randomly putting back and extracting subset K in training data set, training each decision tree to obtain residual error
Step S114: and minimizing a training loss function according to the following mode to obtain the minimum residual error of the soil moisture inversion model:
wherein gamma is a regular term coefficient;
step S115: summing the prediction results of all the single decision trees to obtain a soil moisture prediction value:
wherein f iskIs a singleThe result of the prediction of the decision tree,
is the set of all decision trees, and K is the number of the decision trees;
step S116: and traversing the iteration times t and the number k of the decision trees in the training data set, calculating the precision of each t and k combined output result, and selecting the iteration times with the highest precision of the output results and the number of the decision trees as parameters of the soil moisture inversion model.
Step S2: and acquiring an explanatory variable with a target resolution as an explanatory variable data set, inputting the explanatory variable data set into the soil moisture inversion model for downscaling inversion, and acquiring the soil moisture data with the target resolution. And applying the inversion relation between the soil moisture and the surface parameters in the soil moisture inversion model to a multisource surface parameter data set with the resolution of 1km/500m to invert and develop a satellite remote sensing soil moisture data set with the medium and high resolution of 1km/500 m.
The invention also provides a soil moisture data acquisition system, comprising:
the soil moisture inversion model building module 11 is used for acquiring satellite soil moisture data, albedo, evapotranspiration, surface temperature, vegetation index, longitude and latitude positions and elevation data as a training data set, taking the albedo, the evapotranspiration, the surface temperature, the vegetation index, the longitude and latitude positions and the elevation data as explanatory variables, taking the soil moisture data as dependent variables, and building a soil moisture inversion model based on an extreme gradient lifting algorithm;
the soil moisture inversion model takes a plurality of decision trees as learning units, fits the next decision tree according to the residual error between the output result of the previous decision tree and the actual value, and obtains a soil moisture prediction value by summing the output results of the decision trees;
in one embodiment, as shown in fig. 5, the soil water data acquisition system further comprises a data preprocessing module 10, wherein the data preprocessing module 10 is used for preprocessing the training data set data; the pre-processing module 10 comprises:
the filtering unit 101 is used for performing space-time sequence reconstruction based on low-pass filtering processing on albedo, evapotranspiration, surface temperature and vegetation indexes to smooth out abnormal values;
the unifying unit 102 is configured to unify spatial projection, geographic coordinates, spatial resolution, and temporal resolution of the soil moisture data, albedo, evapotranspiration, surface temperature, vegetation index, longitude and latitude position, and elevation data;
and the water body filtering unit 103 is used for filtering the water body area in the soil moisture, the albedo, the evapotranspiration, the surface temperature, the vegetation index, the longitude and latitude position and the elevation data by using the water body mask data.
As shown in fig. 6, the soil moisture inversion model building module 11 includes:
a parameter acquisition unit 111 for giving a data set
The extreme gradient lifting algorithm takes a decision tree as a learning unit, and the loss function of the learning unit is
The number of iterations t and the number of decision trees k, where xiFor the explanatory variables of the model, yiIn order to actually output the result of the output,
outputting a result for the soil moisture inversion model;
a predicted value obtaining unit 112, configured to obtain the predicted value of the soil moisture inversion model at the t-th time in the following manner
Wherein the content of the first and second substances,
is the output result of the soil moisture inversion model for t-1 times, ft(xi) Predicting the result for the t-th iteration of the decision tree;
a residual obtaining unit 113, configured to randomly have a put-back extraction subset K in the training data set, train each decision tree, and obtain a residual
A loss function training unit 114 for minimizing a training loss function in the following manner:
wherein gamma is a regular term coefficient;
the predicted value obtaining unit 115 is configured to sum the prediction results of all the single decision trees to obtain a predicted value of soil moisture:
wherein f iskIs the prediction result of a single decision tree, and K is the number of the decision trees;
and the parameter selecting unit 116 is configured to traverse the iteration times t and the number k of the decision tree in the training data set, calculate the precision of each t and k combined output result, and select the iteration times with the highest precision of the output result and the number of the decision tree as parameters of the soil moisture inversion model.
The soil moisture inversion model inversion module 2 is used for acquiring an explanatory variable with a target resolution as an explanatory variable data set, inputting the explanatory variable data set into the soil moisture inversion model for scale reduction inversion, and acquiring soil moisture data with the target resolution;
the present invention also provides a computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the soil moisture data acquisition method according to any one of the above.
The present invention may take the form of a computer program product embodied on one or more storage media including, but not limited to, disk storage, CD-ROM, optical storage, and the like, having program code embodied therein. Computer readable storage media, which include both non-transitory and non-transitory, removable and non-removable media, may implement any method or technology for storage of information. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of the storage medium of the computer include, but are not limited to: phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technologies, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic tape storage or other magnetic storage devices, or any other non-transmission medium, may be used to store information that may be accessed by a computing device.
The invention also provides computer equipment comprising a memory, a processor and a computer program stored in the memory and executable by the processor, wherein the processor executes the computer program to realize the steps of the soil moisture data acquisition method.
Compared with the prior art, the method has the advantages that the albedo, the evapotranspiration, the earth surface temperature, the vegetation index, the longitude and latitude position and the elevation data are used as explanatory variables, the soil moisture data are used as dependent variables, a soil moisture inversion model is established based on an extreme gradient lifting algorithm, and the inversion relation of the soil moisture and the earth surface parameters is simulated. And then obtaining an explanatory variable with a target resolution as an explanatory variable data set, inputting the explanatory variable data set into the soil moisture inversion model for downscaling inversion to obtain soil moisture data of the target resolution, wherein a user can utilize the method for obtaining the medium and high resolution satellite remote sensing soil moisture data to improve the resolution of the soil moisture data.
The present invention is not limited to the above-described embodiments, and various modifications and variations of the present invention are intended to be included within the scope of the claims and the equivalent technology of the present invention if they do not depart from the spirit and scope of the present invention.
Claims (8)
1. A method for acquiring soil moisture data is characterized by comprising the following steps:
acquiring satellite soil moisture data, albedo, evapotranspiration, surface temperature, vegetation index, longitude and latitude position and elevation data as a training data set, taking the albedo, evapotranspiration, surface temperature, vegetation index, longitude and latitude position and elevation data as explanatory variables, taking the soil moisture data as dependent variables, and establishing a soil moisture inversion model based on an extreme gradient lifting algorithm;
the soil moisture inversion model takes a plurality of decision trees as learning units, fits the next decision tree according to the residual error between the output result of the previous decision tree and the actual value, and obtains a soil moisture prediction value by summing the output results of the decision trees;
and acquiring an explanatory variable with a target resolution as an explanatory variable data set, inputting the explanatory variable data set into the soil moisture inversion model for downscaling inversion, and acquiring the soil moisture data with the target resolution.
2. The soil moisture data acquisition method according to claim 1, characterized in that: the step of establishing a soil moisture inversion model by taking the albedo, evapotranspiration, surface temperature, vegetation index, longitude and latitude positions and elevation data as explanatory variables and soil moisture data as dependent variables and based on an extreme gradient lifting algorithm comprises the following steps of:
given data set
Setting a loss function of the learning unit to
The number of iterations t and the number of decision trees k, where xiFor the explanatory variables of the model, yiIn order to actually output the result of the output,
outputting a result for the soil moisture inversion model;
obtaining the simulation predicted value of the soil moisture inversion model at the t time according to the following mode
Wherein the content of the first and second substances,
is the output result of the soil moisture inversion model for t-1 times, ft(xi) Predicting the result for the t-th iteration of the decision tree;
randomly putting back and extracting subset K in training data set, training each decision tree to obtain residual error
And minimizing a training loss function according to the following mode to obtain the minimum residual error of the soil moisture inversion model:
wherein gamma is a regular term coefficient;
summing the prediction results of all the single decision trees to obtain a soil moisture prediction value:
wherein f iskIs the prediction result of a single decision tree, and K is the number of the decision trees;
and traversing the iteration times t and the number k of the decision tree in the training data set, calculating the precision of each t and k combined output result, and selecting the iteration times with the highest precision of the output result and the number of the decision tree as parameters of the soil moisture inversion model.
3. The soil moisture data acquisition method according to claim 1, characterized in that: the method comprises the following steps of establishing a soil moisture inversion model by taking the albedo, evapotranspiration, surface temperature, vegetation index, longitude and latitude positions and elevation data as explanatory variables and soil moisture data as dependent variables based on an extreme gradient lifting algorithm, and further comprising the following steps of: preprocessing the data of the training data set, which specifically comprises the following steps:
carrying out space-time sequence reconstruction based on low-pass filtering processing on the albedo, evapotranspiration, surface temperature and vegetation index, and smoothing out abnormal values;
unifying the spatial projection, the geographic coordinates, the spatial resolution and the temporal resolution of the soil moisture data, the albedo, the evapotranspiration, the earth surface temperature, the vegetation index, the longitude and latitude position and the elevation data;
and filtering the water body area in the soil moisture, the albedo, the evapotranspiration, the surface temperature, the vegetation index, the longitude and latitude position and the elevation data by using the water body mask data.
4. A soil moisture data acquisition system characterized by: the method comprises the following steps:
the soil moisture inversion model building module is used for acquiring satellite soil moisture data, albedo, evapotranspiration, surface temperature, vegetation index, longitude and latitude positions and elevation data as a training data set, taking the albedo, the evapotranspiration, the surface temperature, the vegetation index, the longitude and latitude positions and the elevation data as explanatory variables, taking the soil moisture data as dependent variables and building a soil moisture inversion model based on an extreme gradient lifting algorithm;
the soil moisture inversion model takes a plurality of decision trees as learning units, fits the next decision tree according to the residual error between the output result of the previous decision tree and the actual value, and obtains a soil moisture prediction value by summing the output results of the decision trees;
and the soil moisture inversion model inversion module is used for acquiring an explanatory variable with a target resolution as an explanatory variable data set, inputting the explanatory variable data set into the soil moisture inversion model for scale reduction inversion, and acquiring soil moisture data with the target resolution.
5. The soil water data acquisition system according to claim 4, wherein: the soil moisture inversion model building module comprises:
parameter acquisition unit for a given data set
The extreme gradient lifting algorithm takes a decision tree as a learning unit, and the loss function of the learning unit is
The number of iterations t and the number of decision trees k, where xiFor the explanatory variables of the model, yiIn order to actually output the result of the output,
outputting a result for the soil moisture inversion model;
a predicted value obtaining unit for obtaining the predicted value of the t-th time of the soil moisture inversion model according to the following mode
Wherein the content of the first and second substances,
is the output result of the soil moisture inversion model for t-1 times, ft(xi) Predicting the result for the t-th iteration of the decision tree;
a residual error obtaining unit for randomly putting back the extraction subset K in the training data set, training each decision tree and obtaining the residual error
A loss function training unit for minimizing a training loss function in the following manner:
wherein gamma is a regular term coefficient;
the predicted value obtaining unit is used for summing the predicted results of all the single decision trees to obtain the predicted value of the soil moisture:
wherein f iskIs the prediction result of a single decision tree, and K is the number of the decision trees;
and the parameter selection unit is used for traversing the iteration times t and the number k of the decision tree in the training data set, calculating the precision of the combined output result of each iteration time t and the number k of the decision tree, and selecting the iteration times with the highest precision of the output result and the number of the decision tree as the parameters of the soil moisture inversion model.
6. The soil water data acquisition system according to claim 4, wherein: the soil water data acquisition system further comprises a data preprocessing module, and the data preprocessing module is used for preprocessing the training data set data; the preprocessing module comprises:
the filtering unit is used for carrying out space-time sequence reconstruction based on low-pass filtering processing on the albedo, evapotranspiration, surface temperature and vegetation index to smooth out abnormal values;
the unifying unit is used for unifying the spatial projection, the geographic coordinate, the spatial resolution and the time resolution of the soil moisture data, the albedo, the evapotranspiration, the surface temperature, the vegetation index, the longitude and latitude position and the elevation data;
and the water body filtering unit is used for filtering the water body area in the soil moisture, the albedo, the evapotranspiration, the surface temperature, the vegetation index, the longitude and latitude position and the elevation data by using the water body mask data.
7. A computer-readable storage medium having stored thereon a computer program, characterized in that: the computer program, when being executed by a processor, carries out the steps of the soil moisture data acquisition method according to any one of claims 1 to 3.
8. A computer device, characterized by: comprising a memory, a processor and a computer program stored in said memory and executable by said processor, said processor when executing said computer program implementing the steps of the soil moisture data acquisition method according to any of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910905363.2A CN110826173B (en) | 2019-09-24 | 2019-09-24 | Soil moisture data acquisition method and system, storage medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910905363.2A CN110826173B (en) | 2019-09-24 | 2019-09-24 | Soil moisture data acquisition method and system, storage medium and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110826173A CN110826173A (en) | 2020-02-21 |
| CN110826173B true CN110826173B (en) | 2020-10-23 |
Family
ID=69548250
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910905363.2A Active CN110826173B (en) | 2019-09-24 | 2019-09-24 | Soil moisture data acquisition method and system, storage medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110826173B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112162014A (en) * | 2020-09-02 | 2021-01-01 | 塔里木大学 | Cotton field soil profile water data processing method based on electromagnetic induction data |
| CN112214923A (en) * | 2020-09-09 | 2021-01-12 | 广州地理研究所 | Satellite soil moisture reconstruction method, device and equipment |
| CN113111567A (en) * | 2021-02-26 | 2021-07-13 | 中国科学院空天信息创新研究院 | Evapotranspiration component separation method, component separation device, apparatus, and medium |
| CN112989286B (en) * | 2021-03-22 | 2021-09-07 | 自然资源部国土卫星遥感应用中心 | Space-time information fused microwave remote sensing soil moisture product downscaling method |
| CN115308386B (en) * | 2022-07-18 | 2023-04-07 | 中国科学院地理科学与资源研究所 | Soil salinity inversion method and system based on CYGNSS satellite data |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109115995A (en) * | 2018-08-30 | 2019-01-01 | 清华大学 | Soil moisture information acquisition methods, device, computer equipment and storage medium |
| CN109307752A (en) * | 2017-07-28 | 2019-02-05 | 中国农业大学 | It is a kind of for obtaining the sensor and method of the more depth moisture contents of soil |
| CN109425636A (en) * | 2017-08-28 | 2019-03-05 | 上海花小二科技有限公司 | Four sections of soil moisture detection sensors based on TDR mode |
| CN109613216A (en) * | 2019-02-25 | 2019-04-12 | 赵云红 | A kind of moisture in soil continuity detection system and its detection method |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105160192B (en) * | 2015-09-17 | 2017-12-26 | 浙江大学 | TRMM satellite rainfall data NO emissions reduction methods based on M5 LocalR |
| CN105760814B (en) * | 2016-01-25 | 2019-07-02 | 中国水利水电科学研究院 | A kind of drought monitoring method based on data mining |
| CN106991412B (en) * | 2017-04-19 | 2020-03-20 | 中国农业科学院农业资源与农业区划研究所 | Method for obtaining all-weather effective soil moisture |
| CN108764688B (en) * | 2018-05-21 | 2021-11-23 | 浙江大学 | Winter wheat wet waterlogging remote sensing monitoring method based on satellite-ground multi-source rainfall data fusion |
| CN109115807A (en) * | 2018-10-26 | 2019-01-01 | 中国气象局气象探测中心 | A kind of soil moisture automatic Observation data exception value detection method and system |
-
2019
- 2019-09-24 CN CN201910905363.2A patent/CN110826173B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109307752A (en) * | 2017-07-28 | 2019-02-05 | 中国农业大学 | It is a kind of for obtaining the sensor and method of the more depth moisture contents of soil |
| CN109425636A (en) * | 2017-08-28 | 2019-03-05 | 上海花小二科技有限公司 | Four sections of soil moisture detection sensors based on TDR mode |
| CN109115995A (en) * | 2018-08-30 | 2019-01-01 | 清华大学 | Soil moisture information acquisition methods, device, computer equipment and storage medium |
| CN109613216A (en) * | 2019-02-25 | 2019-04-12 | 赵云红 | A kind of moisture in soil continuity detection system and its detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110826173A (en) | 2020-02-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110826173B (en) | Soil moisture data acquisition method and system, storage medium and equipment | |
| Pecchi et al. | Species distribution modelling to support forest management. A literature review | |
| US10824861B2 (en) | System and method using image based machine learning process for earth observation and analysis | |
| AU2016294138B2 (en) | Generating digital models of nutrients available to a crop over the course of the crop's development based on weather and soil data | |
| Weiskittel et al. | Forest growth and yield modeling | |
| Bryan | Physical environmental modeling, visualization and query for supporting landscape planning decisions | |
| Hill et al. | The use of CO 2 flux time series for parameter and carbon stock estimation in carbon cycle research | |
| CN108733952B (en) | Three-dimensional characterization method for spatial variability of soil water content based on sequential simulation | |
| CN110852149B (en) | Vegetation index prediction method, system and equipment based on classification and regression tree algorithm | |
| CN105893590A (en) | Automatic processing method for real-situation cases of DTA (Digital Terrain Analysis) modelling knowledge | |
| CN110826764A (en) | Random forest algorithm-based vegetation index prediction method, system and equipment | |
| CN110852475A (en) | Extreme gradient lifting algorithm-based vegetation index prediction method, system and equipment | |
| Sverdrup et al. | Developing an approach for Sweden, Switzerland, United States and France for setting critical loads based on biodiversity including management, pollution and climate change | |
| Zalipynis | Bitfun: fast answers to queries with tunable functions in geospatial array dbms | |
| Milliken et al. | Designing experiments to evaluate the effectiveness of precision agricultural practices on research fields: part 1 concepts for their formulation | |
| Portier et al. | Plot size matters: Toward comparable species richness estimates across plot‐based inventories | |
| CN109636018A (en) | Calculate the method and device of temperature and the distant correlativity of climatic factor | |
| Alvarez et al. | Climate defined but not soil-restricted: the distribution of a Neotropical tree through space and time | |
| Thakur et al. | Water–energy, climate, and habitat heterogeneity mutually drives spatial pattern of tree species richness in the Indian Western Himalaya | |
| Guo et al. | High-resolution satellite images reveal the prevalent positive indirect impact of urbanization on urban tree canopy coverage in South America | |
| US20230281924A1 (en) | Operational efficiencies in iot agricultural ecosystems | |
| CN116127273B (en) | Snow index acquisition method, device, storage medium and equipment | |
| CN110837913B (en) | Method and equipment for predicting land water reserves based on extreme gradient algorithm | |
| US20230056985A1 (en) | Microbial efficiency-matrix stabilization (mems) ecosystem model and methods | |
| Estacio | Simulating the future of the Ifugao rice terraces through observations of the past |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 510075 one of the compound No. 100, Xianlie Middle Road, Yuexiu District, Guangzhou City, Guangdong Province Patentee after: Guangzhou Institute of geography, Guangdong Academy of Sciences Address before: 510075 one of the compound No. 100, Xianlie Middle Road, Yuexiu District, Guangzhou City, Guangdong Province Patentee before: GUANGZHOU INSTITUTE OF GEOGRAPHY |