CN117496351A - Farmland irrigation frequency determining method and device based on microwave remote sensing and computing equipment - Google Patents
Farmland irrigation frequency determining method and device based on microwave remote sensing and computing equipment Download PDFInfo
- Publication number
- CN117496351A CN117496351A CN202311487512.0A CN202311487512A CN117496351A CN 117496351 A CN117496351 A CN 117496351A CN 202311487512 A CN202311487512 A CN 202311487512A CN 117496351 A CN117496351 A CN 117496351A
- Authority
- CN
- China
- Prior art keywords
- data
- irrigation
- decision tree
- remote sensing
- microwave remote
- 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.)
- Pending
Links
- 238000003973 irrigation Methods 0.000 title claims abstract description 92
- 230000002262 irrigation Effects 0.000 title claims abstract description 92
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000003066 decision tree Methods 0.000 claims abstract description 77
- 239000002689 soil Substances 0.000 claims abstract description 59
- 238000004088 simulation Methods 0.000 claims abstract description 18
- 238000012549 training Methods 0.000 claims abstract description 17
- 238000013138 pruning Methods 0.000 claims abstract description 13
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 39
- 238000001556 precipitation Methods 0.000 claims description 19
- 238000012544 monitoring process Methods 0.000 claims description 18
- 238000004891 communication Methods 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 13
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 3
- 239000003621 irrigation water Substances 0.000 description 7
- 230000008901 benefit Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000001704 evaporation Methods 0.000 description 5
- 230000008020 evaporation Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 238000012937 correction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000005855 radiation Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 206010012601 diabetes mellitus Diseases 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000003746 surface roughness Effects 0.000 description 2
- 241000238631 Hexapoda Species 0.000 description 1
- 241000607479 Yersinia pestis Species 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000011022 operating instruction Methods 0.000 description 1
- 230000010287 polarization Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000000528 statistical test Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/188—Vegetation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention discloses a farmland irrigation frequency determining method and device based on microwave remote sensing and computing equipment, wherein the method comprises the following steps: acquiring microwave remote sensing data and observation statistical data of an irrigation farmland area to be detected; inverting according to the microwave remote sensing data to obtain soil moisture data, and obtaining evapotranspiration data according to the mode simulation system; constructing a decision tree support model according to the soil moisture data, the evapotranspiration data and the first partial data of the observation statistical data, and taking the information gain of the first partial data as a branch value of the decision tree support model; and extracting the remaining second partial data, pruning the decision tree of the decision tree support model, and obtaining the irrigation frequency of the irrigation area to be detected. According to the invention, the characteristic attribute in the training sample is extracted through the integrated decision tree model, so that the farmland irrigation frequency is predicted more comprehensively and accurately.
Description
Technical Field
The invention relates to the technical field of farmland irrigation frequency determination based on microwave remote sensing of an unmanned aerial vehicle-mounted L-band passive microwave radiometer, in particular to a farmland irrigation frequency determination method and device based on microwave remote sensing and computing equipment.
Background
With economic development and population growth, the problem of water resource shortage is increasingly serious. The agricultural water accounts for more than 60% of the total water in China, and the irrigation water accounts for more than 90% of the agricultural water. The accurate estimation of irrigation water has important influence on the accuracy of total water consumption statistics and has important significance for the fine management of supporting water resources. However, the agricultural water is widely distributed and dispersed, the metering difficulty is relatively high compared with industrial and domestic water, the total agricultural water amount estimation in the area is limited by data conditions, the manual experience is greatly relied on, and great uncertainty exists.
The conventional monitoring method mainly comprises a conventional ground monitoring method and a satellite remote sensing monitoring method, wherein the conventional ground monitoring method comprises the following steps: neutron measurement, TDR (time domain reflectometer) measurement, hygrometry, weighing and drying methods, and the like. The biggest problem of the method is that the soil moisture content between farmlands is not synchronous, because the soil moisture content in the same field is different even with the conditions of crop planting, irrigation and environmental influence, and the method of single-point measurement causes extremely high cost and poor representativeness. The satellite remote sensing monitoring method also has a plurality of problems, such as: the downloaded remote sensing data are often secondary data (system geometric correction products), so that a plurality of pre-processing works such as radiation calibration, geometric fine correction, atmospheric correction, cutting, cloud mask and the like are required to be carried out; because the soil properties of the soil subsurface in different areas are different, the selected model method can seriously influence the accuracy and the reliability of the final inversion drought.
The current irrigation water estimation methods are generally divided into two types, namely a quota deduction method and a water balance deduction method. The former is mainly estimated according to irrigation quota and real irrigation area data, typical investigation is firstly carried out and then quota deduction is carried out on the determination of the irrigation quota, the problems that agricultural water metering facilities are imperfect, the statistics difficulty of complex irrigation areas is large and the like are generally existed on the determination of the irrigation quota, and in the actual work of agricultural irrigation water deduction, dynamic adjustment is difficult to carry out according to hydrological changes, field water conditions, crop growth conditions and the like, so that the method cannot accurately calculate the agricultural irrigation water consumption.
Disclosure of Invention
In view of the above problems, the invention provides a farmland irrigation frequency determining method, a device and a computing device for overcoming the problem of lower accuracy of farmland irrigation frequency calculation by using a farmland scale soil humidity observation method with high space-time resolution based on an unmanned aerial vehicle-mounted L-band passive microwave radiometer.
According to one aspect of the invention, there is provided a method for determining the frequency of farm irrigation based on a micro-unmanned on-board L-band passive microwave radiometer, comprising:
acquiring microwave remote sensing data and observation statistical data of an irrigation farmland area to be detected, wherein the observation statistical data comprise historical precipitation, cross-river basin precipitation, non-agricultural water consumption, soil moisture data inverted by an unmanned aerial vehicle-mounted L-band passive microwave radiometer, evapotranspiration data obtained after the observation brightness temperature of the unmanned aerial vehicle-mounted L-band passive microwave radiometer is brought into a land mode through data assimilation, historical moisture data and water output and input of a administrative area of a hydrological monitoring station;
inverting according to the unmanned aerial vehicle-mounted L-band passive microwave radiation remote sensing data to obtain soil moisture data, and simulating and assimilating according to the numerical mode to obtain evapotranspiration data;
constructing a decision tree support model according to the soil moisture data, the evapotranspiration data and the first partial data of the observation statistical data, and taking the information gain of the first partial data as a branch value of the decision tree support model;
and extracting the remaining second partial data, pruning the decision tree of the decision tree support model, and obtaining the irrigation frequency of the irrigation area to be detected.
In an alternative manner, the constructing a decision tree support model from the first portion of data further includes:
extracting a first part of data with a first preset proportion as a training sample set of the decision tree support model;
and acquiring sample characteristics according to the training sample set as input variables of the decision tree support model.
In an optional manner, the extracting the remaining second part of data to prune the decision tree of the decision tree support model, and obtaining the irrigation frequency of the irrigation area to be detected further includes:
and extracting the second partial data of a second preset proportion, pruning the second partial data from bottom to top, and obtaining the irrigation frequency of the irrigation area to be detected of the second partial data.
In an alternative manner, the specific formula of the information gain of the first portion of data is:
wherein i=1, 2, …, n, I(s) is information entropy, I (x) i ) Is the characteristic x i Conditional entropy of I (x) ij ) Is the characteristic x ij Is a conditional entropy of (a).
In an alternative manner, the specific formula of the information entropy I(s) is:
wherein f (C) k S) is C in sample S k The number of classes, |S|, is the number of samples S;
the conditional entropy I (x i ) The specific formula of (2) is:
wherein, |x i I is x in the sample i Number of (x) ij I is x in the sample ij Is a number of (3).
In an alternative, the conditional entropyI(x ij ) The specific formula of (2) is:
wherein f (C) k ,x ij ) For a classification value x ij Belonging to C k Number of classes.
In an alternative manner, the specific formula for obtaining the irrigation frequency of the irrigation area to be detected is:
wherein P (C) k )＝f(C k ,S)/|S|，P(C k ) The analysis result in the sample is C k K=1, 2,3, σ, σ is the second preset number, |s| is the number of samples, P (y) m |C k ) The analysis result in the sample is C k And comprises a characteristic y m Is a probability of (2).
In an alternative way, the decision tree support model integrates ID3, C4.5, CART classifiers, and learns a plurality of the classifiers by using boosting algorithm, wherein the i-th classifier learns samples that are not correctly classified by the i-1 th classifier, and the plurality of classifiers are linearly combined to jointly classify the samples.
According to another aspect of the present invention, there is provided a device for determining a frequency of farm irrigation based on microwave remote sensing, comprising:
the system comprises an acquisition module, a detection module and a control module, wherein the acquisition module is used for acquiring remote sensing data and observation statistical data of an unmanned aerial vehicle-mounted L-band passive microwave radiometer of an irrigation farmland area to be detected, wherein the observation statistical data comprise historical precipitation, cross-river basin precipitation, non-agricultural water consumption, soil moisture data inverted by the unmanned aerial vehicle-mounted L-band passive microwave radiometer, numerical mode simulation and data assimilation evaporation data, historical moisture data and water output and input quantity of a administrative area of a hydrological monitoring station;
the inversion and numerical simulation module is used for inverting according to the microwave remote sensing data to obtain soil moisture data, and simulating according to the numerical mode and assimilating the data to obtain evapotranspiration data;
the model construction module is used for constructing a decision tree support model according to the soil moisture data, the evapotranspiration data and the first partial data of the observation statistical data, and taking the information gain of the first partial data as a branch value of the decision tree support model;
and the optimization module is used for extracting the remaining second partial data and pruning the decision tree of the decision tree support model to obtain the irrigation frequency of the irrigation area to be detected.
According to yet another aspect of the present invention, there is provided a computing device comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute operations corresponding to the farmland irrigation frequency determination method based on unmanned aerial vehicle-mounted L-band passive microwave radiometer remote sensing, numerical mode simulation and data assimilation simulation.
According to the scheme provided by the invention, microwave remote sensing data and observation statistical data of an irrigation farmland area to be detected are obtained, wherein the observation statistical data comprise historical precipitation, cross-river basin precipitation, non-agricultural water consumption, soil moisture data inverted by an unmanned airborne L-band passive microwave radiometer, numerical mode simulation and data assimilation simulation evaporation data, historical moisture data and water output and input quantity of a administrative area of a hydrological monitoring station; inversion is carried out according to the microwave remote sensing data to obtain soil moisture data, and evapotranspiration data is obtained according to the numerical mode simulation and the data assimilation simulation; constructing a decision tree support model according to the soil moisture data, the evapotranspiration data and the first partial data of the observation statistical data, and taking the information gain of the first partial data as a branch value of the decision tree support model; and extracting the remaining second partial data, pruning the decision tree of the decision tree support model, and obtaining the irrigation frequency of the irrigation area to be detected. According to the invention, the characteristic attribute in the training sample is extracted through the integrated decision tree model, so that the farmland irrigation frequency is predicted more comprehensively and accurately.
The foregoing description is only an overview of the present invention, and is intended to be implemented in accordance with the teachings of the present invention in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present invention more readily apparent.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
FIG. 1 shows a flow diagram of a method for determining a frequency of farm irrigation based on microwave remote sensing according to an embodiment of the present invention;
FIG. 2 shows a schematic structural diagram of a device for determining a frequency of farmland irrigation based on microwave remote sensing according to an embodiment of the present invention;
FIG. 3 illustrates a schematic diagram of a computing device in accordance with an embodiment of the invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Fig. 1 shows a flow chart of a method for determining a farmland irrigation frequency based on microwave remote sensing according to an embodiment of the present invention. The method extracts the characteristic attribute in the training sample through the integrated decision tree model so as to more comprehensively and accurately predict the farmland irrigation frequency. Specifically, as shown in fig. 1, the method comprises the following steps:
step S101, acquiring microwave remote sensing data and observation statistical data of an irrigation farmland area to be detected, wherein the observation statistical data comprise historical precipitation, cross-river basin precipitation, non-agricultural water consumption, soil moisture data inverted by an unmanned airborne L-band passive microwave radiometer, numerical mode simulation and data assimilation simulation evaporation data, historical moisture data and water yield entering and exiting from administrative areas of hydrologic monitoring sites.
Compared with the scheme of detecting irrigation information by optical remote sensing data, the microwave has obvious sensing capability on water components, so that remote sensing monitoring becomes a more reasonable mode (including an active mode and a passive mode) for measuring the water content of soil. The soil moisture content can be well inverted because the soil backscattering parameter is mainly measured in an active mode, the soil roughness and the dielectric constant can determine the soil backscattering parameter, and the soil humidity determines the dielectric constant; the passive mode is that the sensor receives microwaves radiated by the ground object, and the soil humidity can be obtained by inversion of the calculated soil brightness temperature.
The L-band passive microwave radiometer has the advantages of all-weather, high resolution, strong penetrability and sensitivity to soil moisture change, can capture moisture information more accurately than optical remote sensing data, and is beneficial to improving accuracy of determining farmland irrigation frequency. The remote sensing technology can solve the estimation problems of regional water storage variable and evaporation in the water balance equation, can improve the feasibility of the water balance method in calculating irrigation water, but most remote sensing products have the problems of regional applicability and precision, and need to combine the observation statistical data of a plurality of data sources, wherein the observation statistical data comprise historical precipitation, cross-river basin precipitation, non-agricultural water consumption, soil moisture data inverted by an unmanned airborne L-band passive microwave radiometer, numerical mode simulation and data assimilation simulation evaporation data, historical moisture data and water output and input of a administrative area of a hydrological monitoring station, and provide more data support for the rationality of the irrigation water statistical data in a farmland area.
In this embodiment, the applicant obtains the microwave remote sensing data and the observation statistical data of the irrigation farmland area to be detected by using a self-developed first-generation Liu Haidi frequency microwave integrated monitoring system (such as a multi-rotor unmanned aerial vehicle, a small-sized L-band micro remote sensing radiometer and the like), and a "farmland sentinel" strategy software system (the system combines with the latest microwave radiation transmission model of the complex denier university and adopts the "numerical fit and assimilation technology and the like"). Compared with the traditional meteorological station soil humidity monitoring and the inversion route based on the remote sensing technology, the method has the characteristics of quick response, accurate measurement, wide coverage, high space-time precision, soil humidity inversion and the like, and has the advantages of being not influenced by weather conditions, enabling the depth of penetrable vegetation observation soil to be matched with the occurrence depth of root systems and plant diseases and insect pests in the middle.
And step S102, inverting according to the microwave remote sensing data to obtain soil moisture data, and simulating according to a numerical mode and data assimilation to simulate evapotranspiration data.
For example, the soil dielectric constant is determined according to the soil surface emissivity, the incident angle and the polarization mode of the microwave remote sensing data, and the soil dielectric constant is converted into the soil volume water content by adopting a dielectric mixed model. In practice, the soil surface emissivity is mainly affected by factors such as the dielectric constant of the soil (mainly depending on the soil moisture), the surface roughness and the vegetation coverage. Assuming that the surface roughness and vegetation condition are unchanged in a certain time, the change of the soil surface emissivity can be attributed to the change of the soil dielectric constant (soil moisture), and the extraction of the soil moisture and the change information thereof can adopt a multi-time repeated observation method. Therefore, soil moisture data can be obtained according to inversion of the microwave remote sensing data, and evapotranspiration data can be obtained according to numerical simulation and data assimilation of brightness temperature of the unmanned aerial vehicle-mounted L-band passive microwave radiometer.
Step S103, constructing a decision tree supporting model according to the soil moisture data, the evapotranspiration data and the first part data of the observation statistical data, and taking the information gain of the first part data as the branch value of the decision tree supporting model.
A decision tree is a tree structure (e.g., binary or non-binary) in which each internal node represents a decision on an attribute, each branch represents the output of a decision result, and each leaf node represents a classification result. In this embodiment, a decision tree supporting model is constructed according to the first part of data of the sample, the information gain according to the first part of data is used as the branch value of the decision tree supporting model, the information entropy is an index for measuring the purity of the sample, and the greater the information entropy is, the lower the purity of the sample is according to the knowledge of the information theory, that is, the information gain reflects the reduction of the uncertainty of the information given a new condition. And extracting second part data of the sample, pruning a decision tree of the decision tree support model, and obtaining an analysis result of the sample. The advantages of the decision tree model are almost no data cleaning, while other models such as neural network models usually need to be normalized before training, otherwise poor effects or gradient explosion/disappearance can occur. The decision tree model has high operation speed, the cost of training the decision tree and the number of data points are logarithmic, continuous variables and discrete variables can be processed simultaneously, and phenomena observed in the model can be explained by logic analysis. However, for results of models such as neural networks, which are difficult to interpret, decision tree models can use statistical tests to verify the reliability of the model results.
In an alternative manner, the constructing a decision tree support model from the first portion of data further includes:
extracting a first part of data with a first preset proportion as a training sample set of the decision tree support model;
and acquiring sample characteristics according to the training sample set as input variables of the decision tree support model.
For example, 60% of samples are extracted as a training sample set of the decision tree support model, and diabetes characteristics are obtained as input variables of the decision tree support model according to the training sample set, wherein each input variable has a corresponding category.
In an alternative manner, the specific formula of the information gain of the first portion of data is:
wherein i=1, 2, …, n, I(s) is information entropy, I (x) i ) Is the characteristic x i Conditional entropy of I (x) ij ) Is the characteristic x ij Is a conditional entropy of (a).
To solve the problem of large entropy of sample information, in this embodiment, according to the information gain G (x i ) As a characteristic variable of the first portion of data.
In an alternative manner, the specific formula of the information entropy I(s) is:
wherein f (C) k S) is C in sample S k The number of classes, |S|, is the number of samples S;
the conditional entropy I (x i ) The specific formula of (2) is:
wherein, |x i I is x in the sample i Number of (x) ij I is x in the sample ij Is a number of (3).
In an alternative, the conditional entropy I (x ij ) The specific formula of (2) is:
wherein f (C) k ,x ij ) For a classification value x ij Belonging to C k Number of classes.
And step S104, extracting the rest second partial data to prune the decision tree of the decision tree support model to obtain the irrigation frequency of the irrigation area to be detected.
In an optional manner, the extracting the remaining second part of data to prune the decision tree of the decision tree support model, and obtaining the irrigation frequency of the irrigation area to be detected further includes:
and extracting the second partial data of a second preset proportion, pruning the second partial data from bottom to top, and obtaining the irrigation frequency of the irrigation area to be detected of the second partial data.
For example, the remaining 40% of the samples are extracted, and the samples are pruned from bottom to top to obtain analysis results of the samples, wherein the analysis results include yes, no and possibly diabetes analysis results.
In an alternative manner, the specific formula for obtaining the irrigation frequency of the irrigation area to be detected is:
wherein P (C) k )＝f(C k ,S)/|S|，P(C k ) The analysis result in the sample is C k K=1, 2,3, σ, σ is the second preset number, |s| is the number of samples, P (y) m |C k ) The analysis result in the sample is C k And comprises a characteristic y m Is a probability of (2).
In an alternative way, the decision tree support model integrates ID3, C4.5, CART classifiers, and learns a plurality of the classifiers by using boosting algorithm, wherein the i-th classifier learns samples that are not correctly classified by the i-1 th classifier, and the plurality of classifiers are linearly combined to jointly classify the samples.
According to the scheme provided by the invention, microwave remote sensing data and observation statistical data of an irrigation farmland area to be detected are obtained, wherein the observation statistical data comprise historical precipitation, cross-river basin water regulation, non-agricultural water consumption, soil moisture data inverted by an unmanned airborne L-band passive microwave radiometer, evapotranspiration data obtained by numerical simulation and data assimilation calculation, historical moisture data and water output and input of a administrative area of a hydrological monitoring station; inverting according to the microwave remote sensing data to obtain soil moisture data, and inverting according to the observation statistical data to obtain evapotranspiration data; constructing a decision tree support model according to the soil moisture data, the evapotranspiration data and the first partial data of the observation statistical data, and taking the information gain of the first partial data as a branch value of the decision tree support model; and extracting the remaining second partial data, pruning the decision tree of the decision tree support model, and obtaining the irrigation frequency of the irrigation area to be detected. According to the invention, the characteristic attribute in the training sample is extracted through the integrated decision tree model, so that the farmland irrigation frequency is predicted more comprehensively and accurately.
Fig. 2 shows a schematic structural diagram of a device for determining a frequency of farmland irrigation based on microwave remote sensing according to an embodiment of the present invention. The farmland irrigation frequency determining device based on microwave remote sensing comprises: the system comprises an acquisition module 210, an inversion module 220, a model construction module 230 and an optimization module 240.
The obtaining module 210 is configured to obtain microwave remote sensing data and observation statistics data of an irrigation farmland area to be detected, where the observation statistics data includes historical precipitation, cross-river basin precipitation, non-agricultural water consumption, soil moisture data inverted by an unmanned airborne L-band passive microwave radiometer, evapotranspiration data calculated by numerical simulation and data assimilation, historical moisture data, and water output and input of a administrative area of a hydrological monitoring site;
the inversion module 220 is configured to invert the microwave remote sensing data to obtain soil moisture data, and invert the microwave remote sensing data to obtain evapotranspiration data;
the model construction module 230 is configured to construct a decision tree support model according to the soil moisture data, the evapotranspiration data, and the first partial data of the observation statistics data, and take the information gain of the first partial data as a branch value of the decision tree support model;
the optimizing module 240 is configured to extract the remaining second portion of data, prune the decision tree of the decision tree support model, and obtain the irrigation frequency of the irrigation area to be detected.
In an alternative manner, the model building module 230 is further configured to:
extracting a first part of data with a first preset proportion as a training sample set of the decision tree support model;
and acquiring sample characteristics according to the training sample set as input variables of the decision tree support model.
In an alternative manner, the model building module 230 is further configured to:
and extracting the second partial data of a second preset proportion, pruning the second partial data from bottom to top, and obtaining the irrigation frequency of the irrigation area to be detected of the second partial data.
In an alternative manner, the specific formula of the information gain of the first portion of data is:
wherein i=1, 2, …, n, I(s) is information entropy, I (x) i ) Is the characteristic x i Conditional entropy of I (x) ij ) Is the characteristic x ij Is a conditional entropy of (a).
In an alternative manner, the specific formula of the information entropy I(s) is:
wherein f (C) k S) is C in sample S k The number of classes, |S|, is the number of samples S;
the conditional entropy I (x i ) The specific formula of (2) is:
wherein, |x i I is x in the sample i Number of (x) ij I is x in the sample ij Is a number of (3).
In an alternative, the conditional entropy I (x ij ) The specific formula of (2) is:
wherein f (C) k ,x ij ) For a classification value x ij Belonging to C k Number of classes.
In an alternative manner, the specific formula for obtaining the irrigation frequency of the irrigation area to be detected is:
wherein P (C) k )＝f(C k ,S)/|S|，P(C k ) The analysis result in the sample is C k K=1, 2,3, σ, σ is the second preset number, |s| is the number of samples, P (y) m |C k ) The analysis result in the sample is C k And comprises a characteristic y m Is a probability of (2).
In an alternative way, the decision tree support model integrates ID3, C4.5, CART classifiers, and learns a plurality of the classifiers by using boosting algorithm, wherein the i-th classifier learns samples that are not correctly classified by the i-1 th classifier, and the plurality of classifiers are linearly combined to jointly classify the samples.
FIG. 3 illustrates a schematic diagram of an embodiment of a computing device of the present invention, and the embodiments of the present invention are not limited to a particular implementation of the computing device.
As shown in fig. 3, the computing device may include: a processor (processor) 302, a communication interface (Communications Interface) 304, a memory (memory) 306, and a communication bus 308.
Wherein: processor 302, communication interface 304, and memory 306 perform communication with each other via communication bus 308. A communication interface 304 for communicating with network elements of other devices, such as clients or other servers. The processor 302 is configured to execute the program 310, and may specifically perform the relevant steps in the above-described embodiment of the method for determining a frequency of farmland irrigation based on microwave remote sensing.
In particular, program 310 may include program code including computer-operating instructions.
The processor 302 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included by the computing device may be the same type of processor, such as one or more CPUs; but may also be different types of processors such as one or more CPUs and one or more ASICs.
Memory 306 for storing programs 310. Memory 306 may comprise high-speed RAM memory or may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
According to the scheme provided by the invention, microwave remote sensing data and observation statistical data of an irrigation farmland area to be detected are obtained, wherein the observation statistical data comprise historical precipitation, cross-river basin precipitation, non-agricultural water consumption, soil moisture data inverted by an unmanned airborne L-band passive microwave radiometer, evapotranspiration data calculated by numerical simulation and data assimilation, historical moisture data and water output and input quantity of a administrative area of a hydrological monitoring station; inverting according to the microwave remote sensing data to obtain soil moisture data, and inverting according to the observation statistical data to obtain evapotranspiration data; constructing a decision tree support model according to the soil moisture data, the evapotranspiration data and the first partial data of the observation statistical data, and taking the information gain of the first partial data as a branch value of the decision tree support model; and extracting the remaining second partial data, pruning the decision tree of the decision tree support model, and obtaining the irrigation frequency of the irrigation area to be detected. According to the invention, the characteristic attribute in the training sample is extracted through the integrated decision tree model, so that the farmland irrigation frequency is predicted more comprehensively and accurately.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with the teachings herein. The required structure for a construction of such a system is apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It will be appreciated that the teachings of the present invention described herein may be implemented in a variety of programming languages, and the above description of specific languages is provided for disclosure of enablement and best mode of the present invention.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the above description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.
Various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functionality of some or all of the components according to embodiments of the present invention may be implemented in practice using a microprocessor or Digital Signal Processor (DSP). The present invention can also be implemented as an apparatus or device program (e.g., a computer program and a computer program product) for performing a portion or all of the methods described herein. Such a program embodying the present invention may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specifically stated.
Claims (10)
1. A farmland irrigation frequency determining method based on microwave remote sensing is characterized by comprising the following steps:
acquiring microwave remote sensing data and observation statistical data of an irrigation farmland area to be detected, wherein the observation statistical data comprise historical precipitation, cross-river basin precipitation, non-agricultural water consumption, soil moisture data inverted by an unmanned airborne L-band passive microwave radiometer, evapotranspiration data calculated by numerical simulation and data assimilation, historical moisture data and water yield of a administrative area of a hydrological monitoring station;
inverting according to the microwave remote sensing data to obtain soil moisture data, and inverting according to the observation statistical data to obtain evapotranspiration data;
constructing a decision tree support model according to the soil moisture data, the evapotranspiration data and the first partial data of the observation statistical data, and taking the information gain of the first partial data as a branch value of the decision tree support model;
and extracting the remaining second partial data, pruning the decision tree of the decision tree support model, and obtaining the irrigation frequency of the irrigation area to be detected.
2. The method of determining a frequency of farmland irrigation based on microwave remote sensing according to claim 1, wherein said constructing a decision tree support model from said first portion of data further comprises:
extracting a first part of data with a first preset proportion as a training sample set of the decision tree support model;
and acquiring sample characteristics according to the training sample set as input variables of the decision tree support model.
3. The method for determining a frequency of farmland irrigation based on microwave remote sensing according to claim 1 or 2, wherein the extracting the remaining second portion of data to prune the decision tree of the decision tree support model to obtain the irrigation frequency of the irrigation area to be detected further comprises:
and extracting the second partial data of a second preset proportion, pruning the second partial data from bottom to top, and obtaining the irrigation frequency of the irrigation area to be detected of the second partial data.
4. The method for determining a frequency of farmland irrigation based on microwave remote sensing according to claim 1, wherein the specific formula of the information gain of the first portion of data is:
wherein i=1, 2, …, n, I(s) is information entropy, I (x) i ) Is the characteristic x i Conditional entropy of I (x) ij ) Is the characteristic x ij Is a conditional entropy of (a).
5. The method for determining the frequency of farmland irrigation based on microwave remote sensing according to claim 4, wherein the specific formula of the information entropy I(s) is:
wherein f (C) k S) is C in sample S k The number of classes, |S|, is the number of samples S;
the conditional entropy I (x i ) The specific formula of (2) is:
wherein, |x i I is x in the sample i Number of (x) ij I is x in the sample ij Is a number of (3).
6. The method for determining a frequency of farmland irrigation based on microwave remote sensing according to claim 1, wherein the conditional entropy I (x ij ) The specific formula of (2) is:
wherein f (C) k ,x ij ) For a classification value x ij Belonging to C k Number of classes.
7. The method for determining the irrigation frequency of a farmland based on microwave remote sensing according to claim 1, wherein the specific formula for obtaining the irrigation frequency of the irrigation area to be detected is:
wherein P (C) k )＝f(C k ,S)/|S|，P(C k ) The analysis result in the sample is C k K=1, 2,3, σ, σ is the second preset number, |s| is the number of samples, P (y) m |C k ) The analysis result in the sample is C k And comprises a characteristic y m Is a probability of (2).
8. The method for determining the frequency of farmland irrigation based on microwave remote sensing according to claim 1, wherein the decision tree support model integrates ID3, C4.5, CART classifiers, and learns a plurality of the classifiers by using boosting algorithm, wherein the i-th classifier learns samples that the i-1 th classifier does not classify correctly, and the plurality of classifiers are combined linearly to classify the samples together.
9. A device for determining a frequency of farmland irrigation based on microwave remote sensing, comprising:
the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring microwave remote sensing data and observation statistical data of an irrigation farmland area to be detected, wherein the observation statistical data comprise historical precipitation, cross-river basin precipitation, non-agricultural water consumption, historical soil moisture data, historical evapotranspiration data, historical moisture data and water output and input of a administrative area of a hydrological monitoring station;
the inversion module is used for inverting the microwave remote sensing data to obtain soil moisture data and inverting the microwave remote sensing data to obtain evapotranspiration data according to the observation statistical data;
the model construction module is used for constructing a decision tree support model according to the soil moisture data, the evapotranspiration data and the first partial data of the observation statistical data, and taking the information gain of the first partial data as a branch value of the decision tree support model;
and the optimization module is used for extracting the remaining second partial data and pruning the decision tree of the decision tree support model to obtain the irrigation frequency of the irrigation area to be detected.
10. A computing device, comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;
the memory is configured to store at least one executable instruction, where the executable instruction causes the processor to perform operations corresponding to the method for determining a frequency of farmland irrigation based on microwave remote sensing according to any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311487512.0A CN117496351A (en) | 2023-11-09 | 2023-11-09 | Farmland irrigation frequency determining method and device based on microwave remote sensing and computing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311487512.0A CN117496351A (en) | 2023-11-09 | 2023-11-09 | Farmland irrigation frequency determining method and device based on microwave remote sensing and computing equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117496351A true CN117496351A (en) | 2024-02-02 |
Family
ID=89675999
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311487512.0A Pending CN117496351A (en) | 2023-11-09 | 2023-11-09 | Farmland irrigation frequency determining method and device based on microwave remote sensing and computing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117496351A (en) |
-
2023
- 2023-11-09 CN CN202311487512.0A patent/CN117496351A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Park et al. | Drought monitoring using high resolution soil moisture through multi-sensor satellite data fusion over the Korean peninsula | |
| Bitew et al. | Evaluation of high-resolution satellite rainfall products through streamflow simulation in a hydrological modeling of a small mountainous watershed in Ethiopia | |
| Betbeder et al. | Assimilation of LAI and dry biomass data from optical and SAR images into an agro-meteorological model to estimate soybean yield | |
| Cui et al. | Estimation of actual evapotranspiration and its components in an irrigated area by integrating the Shuttleworth-Wallace and surface temperature-vegetation index schemes using the particle swarm optimization algorithm | |
| Kundu et al. | The value of remotely sensed surface soil moisture for model calibration using SWAT | |
| Tian et al. | Estimating zero-plane displacement height and aerodynamic roughness length using synthesis of LiDAR and SPOT-5 data | |
| Wang et al. | An auto-calibration tool for the Agricultural Policy Environmental eXtender (APEX) model | |
| Lien et al. | Statistical properties of global precipitation in the NCEP GFS model and TMPA observations for data assimilation | |
| CN110427995A (en) | A kind of Bayes's soil moisture evaluation method based on multi- source Remote Sensing Data data | |
| Pierdicca et al. | Monitoring soil moisture in an agricultural test site using SAR data: design and test of a pre-operational procedure | |
| CN112232554A (en) | Construction method of local short-term rainfall forecast model based on BP neural network | |
| Dehkordi et al. | Yield gap analysis using remote sensing and modelling approaches: Wheat in the northwest of Iran | |
| Blankenship et al. | Assimilation of SMOS retrievals in the Land Information System | |
| CN112585505A (en) | Determining location-specific weather information for agronomic decision support | |
| CN104732045A (en) | Crop growth model based method of determining drought natural vulnerability curve of crop | |
| Cunha et al. | Influence of the estimated global solar radiation on the reference evapotranspiration obtained through the Penman-Monteith FAO 56 method | |
| Zhang et al. | Estimation of rice yield from a C-band radar remote sensing image by integrating a physical scattering model and an optimization algorithm | |
| CN116485174B (en) | Method and device for evaluating risk of ozone pollution on crop yield reduction | |
| Benedetti et al. | Assimilation of MODIS cloud optical depths in the ECMWF model | |
| Shin et al. | High-resolution wind speed forecast system coupling numerical weather prediction and machine learning for agricultural studies—a case study from South Korea | |
| CN117496351A (en) | Farmland irrigation frequency determining method and device based on microwave remote sensing and computing equipment | |
| CN115688955A (en) | Vegetation growth prediction method, vegetation growth prediction device and storage medium | |
| Moreto et al. | Sugarcane decision-making support using Eta Model precipitation forecasts | |
| Tsheko et al. | Sorghum yield and associated satellite-derived meteorological parameters in semi-arid Botswana | |
| Semire et al. | Evaluation of satellite retrieval algorithm to ground rainfall estimates over Malaysia |
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 |