CN115511224B - Intelligent monitoring method and device for growing vigor of crops integrated with heaven and earth and electronic equipment - Google Patents
Intelligent monitoring method and device for growing vigor of crops integrated with heaven and earth and electronic equipment Download PDFInfo
- Publication number
- CN115511224B CN115511224B CN202211414732.6A CN202211414732A CN115511224B CN 115511224 B CN115511224 B CN 115511224B CN 202211414732 A CN202211414732 A CN 202211414732A CN 115511224 B CN115511224 B CN 115511224B
- Authority
- CN
- China
- Prior art keywords
- data
- crop growth
- crop
- satellite
- growth
- 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
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000012544 monitoring process Methods 0.000 title claims abstract description 21
- 238000011156 evaluation Methods 0.000 claims abstract description 68
- 238000012549 training Methods 0.000 claims abstract description 32
- 238000013507 mapping Methods 0.000 claims abstract description 21
- 230000001502 supplementing effect Effects 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims description 16
- 238000013506 data mapping Methods 0.000 claims description 12
- 238000012887 quadratic function Methods 0.000 claims description 12
- 238000003062 neural network model Methods 0.000 claims description 11
- 239000002689 soil Substances 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 8
- 241000607479 Yersinia pestis Species 0.000 claims description 7
- 238000013179 statistical model Methods 0.000 claims description 7
- 238000009795 derivation Methods 0.000 claims description 6
- 230000005855 radiation Effects 0.000 claims description 6
- 238000012417 linear regression Methods 0.000 claims description 5
- 238000012952 Resampling Methods 0.000 claims description 3
- 239000013589 supplement Substances 0.000 claims description 2
- 238000011022 operating instruction Methods 0.000 claims 1
- 238000013528 artificial neural network Methods 0.000 abstract description 4
- 208000027066 STING-associated vasculopathy with onset in infancy Diseases 0.000 description 5
- 230000002354 daily effect Effects 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012806 monitoring device Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 239000000047 product Substances 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000012271 agricultural production Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000003973 irrigation Methods 0.000 description 1
- 230000002262 irrigation Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Educational Administration (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Primary Health Care (AREA)
- Mining & Mineral Resources (AREA)
- Marine Sciences & Fisheries (AREA)
- Animal Husbandry (AREA)
- Agronomy & Crop Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field of remote sensing, and relates to a method, a device and electronic equipment for intelligently monitoring the growth vigor of crops by integrating the heaven and the earth, wherein the method comprises the following steps: acquiring satellite time sequence remote sensing data and constructing a first crop growth evaluation index; acquiring continuous near-ground observation data and constructing a second crop growth evaluation index; supplementing the missing value of the first crop growth evaluation index based on the second crop growth evaluation index, and constructing a model label; continuously interpolating the first crop growth evaluation index to obtain reconstructed crop growth data; training a neural network by using a label to obtain an index mapping model; and correcting the reconstructed crop growth data to obtain target crop growth evaluation data. The invention realizes the purpose of comprehensively using the space remote sensing data and the near-ground data to monitor the growth vigor of crops, and solves the problems of insufficient precision and time density of the space remote sensing data and small data range, low precision and discontinuity of the near-ground observation data in the existing method.
Description
Technical Field
The invention belongs to the technical field of remote sensing, and particularly relates to a method and a device for intelligently monitoring the growth vigor of crops by integrating the heaven and the earth and electronic equipment.
Background
The agricultural ecosystem is a typical artificial ecosystem, and the active management activities of human beings play an important role in improving the quality of agricultural products, increasing the yield, reducing disaster loss and the like. Currently, problems such as population increase and ecological environment deterioration have made higher demands on the yield and safety of food. Accurate crop growth parameter information can reflect the resource utilization condition in the agricultural production process, and is an important data support for crop yield prediction and agricultural planting structure adjustment.
In the application of agricultural management, although the remote sensing technology is widely applied to crop type identification and soil moisture monitoring, the difficulty of contradiction between large scale, precision and real-time performance of a space remote sensing platform in crop growth observation is difficult to overcome because most researches and applications still adopt the space remote sensing platform. In addition, due to the influence of interference factors such as atmospheric absorption and radiation, crop parameters cannot be accurately acquired by satellite remote sensing inversion, and therefore, only the relative difference of growth states among different types of crops is represented; and the result precision of the near-ground agriculture monitoring mode represented by an unmanned aerial vehicle, an observation tower and the like is high, but the problem of small monitoring area is difficult to avoid.
Disclosure of Invention
Aiming at the current situations that an absolute value of crop growth parameters obtained by a space remote sensing platform is inaccurate, data are not obtained timely, and a near-ground data observation range is small, a crop growth parameter inversion method based on space-ground multi-platform cooperation is provided, namely, the crop growth parameters calculated by space remote sensing in a large range are converted to high-precision and high-continuity near-ground crop growth parameters through a synchronization relation among data, so that the large-range, high-precision and high-continuity crop growth monitoring is realized.
In a first aspect, the present disclosure provides a method for intelligently monitoring the growth of a crop integrated with the sky and the ground, comprising:
collecting remote sensing satellite data and acquiring satellite time sequence remote sensing data in a target area;
calculating a crop growth state parameter and a crop stressed state parameter according to the satellite time sequence remote sensing data;
constructing a first crop growth evaluation index based on satellite time sequence remote sensing data by using the crop growth state parameters and the crop stressed state parameters; the first crop growth evaluation index is used for representing the relation between the crop growth state and the crop growth background;
collecting growth data of a target crop, and acquiring near-ground observation data containing daily growth index data of the target crop;
constructing a second crop growth evaluation index based on the near-ground observation data based on a statistical model by utilizing the growth index data;
supplementing missing values of the first crop growth evaluation index at the same position and the same time in the remote sensing satellite data by taking the near-ground observation data as a reference to obtain a mapping model training label of the first crop growth evaluation index model and the second crop growth evaluation index;
carrying out continuous interpolation on the first crop growth evaluation index by adopting an average interpolation mode to obtain reconstructed continuous crop growth data;
constructing a neural network model, and training the neural network model by using the mapping model training label to obtain a crop growth data mapping model;
and correcting the reconstructed continuous crop growth data by using the crop growth data mapping model to obtain target crop growth evaluation data.
In a second aspect, the present disclosure provides a world-integrated intelligent monitoring device for crop growth, which includes a first obtaining unit, a first processing unit, a first constructing unit, a second obtaining unit, a second constructing unit, a second processing unit, a reconstructing unit, a network model unit and a correcting unit;
the first acquisition unit is used for collecting remote sensing satellite data and acquiring satellite time sequence remote sensing data in a target area;
the first processing unit is used for calculating a crop growth state parameter and a crop stressed state parameter according to the satellite time sequence remote sensing data;
the first construction unit is used for constructing a first crop growth evaluation index based on satellite time sequence remote sensing data by using the crop growth state parameters and the crop stressed state parameters; the first crop growth evaluation index is used for representing the relation between the crop growth state and the crop growth background;
the second acquisition unit is used for acquiring growth data of a target crop and acquiring near-ground observation data containing daily growth index data of the target crop;
the second construction unit is used for constructing a second crop growth evaluation index based on the near-ground observation data based on a statistical model by utilizing the growth index data;
the second processing unit is used for supplementing missing values of the first crop growth evaluation index at the same position and the same time in the remote sensing satellite data by taking the near-ground observation data as a reference to obtain a mapping model training label of the first crop growth evaluation index model and the second crop growth evaluation index;
the reconstruction unit is used for continuously interpolating the first crop growth evaluation index in an average interpolation mode to obtain reconstructed continuous crop growth data;
the network model unit is used for constructing a neural network model, and training the neural network model by using the mapping model training labels to obtain a crop growth data mapping model;
and the correction unit is used for correcting the reconstructed continuous crop growth data by using the crop growth data mapping model to obtain target crop growth evaluation data.
In a third aspect, the present disclosure provides an electronic device, comprising:
a processor and a memory;
the memory is used for storing computer operation instructions;
the processor is used for executing the intelligent monitoring method for the growing vigor of the crops integrated with the heaven and earth by calling the computer operation instruction.
The beneficial effects of the invention are: the invention realizes the purpose of monitoring the growth vigor of crops by comprehensively using the space remote sensing data and the near-ground observation data, and solves the problems of insufficient precision and time density of the space remote sensing data and small data range, low precision and discontinuity of the near-ground observation data in the existing method.
On the basis of the technical scheme, the invention can be further improved as follows.
Further, collecting remote sensing satellite data and obtaining satellite time sequence remote sensing data in a target area comprises the following steps: collecting remote sensing satellite data, performing radiation correction and geometric registration on the remote sensing satellite data, resampling all data to the same spatial resolution, and acquiring satellite time sequence remote sensing data in a target area.
Further, the crop growth state parameters and the crop stressed state parameters are utilized, and a linear regression mode is adopted to construct the first crop growth evaluation index based on satellite time sequence remote sensing data.
Further, the crop growth state parameters include a normalized vegetation index, an enhanced vegetation index, and a greenness index; the stressed state parameters of the crops comprise red edge indexes and soil vegetation indexes.
Further, collecting growth state parameters of the target crops, and acquiring near-ground observation data containing daily growth index data of the target crops, wherein the method comprises the following steps:
observing the growth state parameters of the target crops in real time by using a sensor erected in a farmland;
counting the observed growth state parameters to obtain the growth index data;
the growth state parameters comprise the plant height, stem thickness, leaf density and pest density of the crops; the growth index data comprises an average plant height index and an average leaf density index of the target crop per day.
Further, with the near-ground observation data as a reference, supplementing missing values of the first crop growth evaluation index at the same position and the same time in the remote sensing satellite data to obtain a mapping model training label of the first crop growth evaluation index model and the second crop growth evaluation index, including:
defining points in the remote sensing satellite data, which are consistent with ground observation geographic positions, as reference points, acquiring a plurality of satellite data sequence point location values before and after the reference points, and defining satellite data sequence point locations of the reference points and ground observation sequence values corresponding to the satellite data sequence point locations of the points before and after the reference points;
respectively obtaining derivatives for representing the changes of the satellite data sequence point location values adjacent to each other by using a derivation mode, determining the relationship between the satellite data sequence point location values of the reference point and the satellite data sequence point location values of the points before and after the reference point, and constructing a fitting equation:
if the signs of all the derivatives in the fitting equation are consistent, or the signs of the derivatives in the fitting equation are different and the positions of the differences in the signs of the derivatives are located at points except the reference point, directly fitting a quadratic function to the fitting equation;
if the position of the difference of the signs of the derivatives in the fitting equation is located at the reference point, calculating the satellite data values of the two groups of reference points by using two groups of data groups which are formed by the satellite data sequence point location values of points except the reference point and the ground observation values corresponding to the satellite data sequence point location values in a piecewise fitting quadratic function mode, respectively calculating the satellite data values of the two groups of reference points by using the two groups of data groups, obtaining the target satellite data sequence point location value of the reference point by taking the average value of the satellite data values of the two groups of reference points, and combining the target satellite data sequence point location value, the ground observation values corresponding to the target satellite data sequence point location value, the satellite data sequence point location value of the reference point and the ground observation values corresponding to the reference point to obtain the training label.
Drawings
FIG. 1 is a schematic diagram of a method for intelligently monitoring the growth of a plant integrated with the sky and the ground in embodiment 1 of the invention;
FIG. 2 is a schematic diagram of an intelligent monitoring device for the growth of crops integrated with the sky and the land in embodiment 2 of the invention;
fig. 3 is a schematic diagram of an electronic device provided in embodiment 3 of the present invention.
An icon: 30-an electronic device; 310-a processor; 320-a bus; 330-a memory; 340-transceiver.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Example 1
As an embodiment, as shown in fig. 1, to solve the above technical problem, the present embodiment provides a method for intelligently monitoring the growth of a crop with integration of both space and ground, which specifically includes the following steps:
collecting remote sensing satellite data and acquiring satellite time sequence remote sensing data in a target area; specifically, multi-source remote sensing satellite data is collected, because different remote sensing data have differences in radiation, geometry and the like, preferably, the radiation correction and geometric registration are carried out on the rest data by taking the data with the widest coverage and the most frequent in the acquired multi-source remote sensing satellite data set as a reference, all the data are resampled to the same spatial resolution, and then time sequence satellite remote sensing data in a target area are acquired; in the practical application process, firstly, a data source of a target area is obtained, crop time sequence characteristics are constructed, statistics is carried out on collected satellite remote sensing data, and the data source is selected as reference data; with this as a reference, other data are registered, and the embodiment collects data of the Sentinel 2 satellite, the Landsat8 satellite and the grand 1 satellite, wherein the data of the Sentinel 2 satellite ensures that coverage is performed at least once a month, and the data of the Landsat8 satellite and the grand 1 satellite are used as interpolation data to encrypt the data of the Sentinel-2 satellite.
Calculating a crop growth state parameter and a crop stressed state parameter according to satellite time sequence remote sensing data; specifically, the time sequence satellite remote sensing data is utilized to calculate vegetation indexes such as normalized vegetation index NDVI, enhanced vegetation index EVI and greenness index GNDVI related to the growth state of crops, and redside index REIP and soil vegetation index SAVI related to the growth environment of the crops, wherein the crop growth state parameters comprise the normalized vegetation index NDVI, the enhanced vegetation index EVI and the greenness index GNDVI and are used for representing the growth state of the crops, and the crop stress state parameters comprise the redside index REIP and the soil vegetation index SAVI and are used for representing the stress state of the crops.
Optionally, a first crop growth evaluation index based on satellite time sequence remote sensing data is constructed by using the crop growth state parameters and the crop stressed state parameters in a linear regression mode. A first Crop growth evaluation Index (CGI _ S) based on a Satellite platform is constructed in a linear regression mode, and the Index is generally constructed in a linear relation and used for describing a correlation relation between a Crop growth state and a Crop growth background; the crop growth background refers to the state of a farmland where crops grow, and comprises the soil texture of the farmland where the crops are located, the irrigation level of the crops and the sunshine level.
Optionally, the crop growth state parameters include a normalized vegetation index, an enhanced vegetation index, and a greenness index; the parameters of the stressed state of the crops comprise a red edge index and a soil vegetation index. Is provided withw 0 To normalize the weight of the vegetation index NDVI, w 1 to be a weight for the enhanced vegetation index EVI,w 2 is a weight of the greenness index GNDVI, w 3 is the weight of the red-edge index REIP,w 4 the first crop growth assessment index CGI _ S is a weight of the soil vegetation index SAVI:
CGI_S=(w 0 *NDVI+w 1 *EVI+w 2 *GNDVI)/w 3 *REIP+w 4 *SAVI+a 1 )。
wherein the weight isw 0 、w 1 、w 2 、w 3 、w 4 Can be dynamically adjusted according to the type of crop being monitored, a 1 Is an optional parameter for preventing the parameters REIP and SAVI from being 0, which would cause the equation to be invalidated.
Establishing a first crop growth evaluation index based on satellite time sequence remote sensing data by using the crop growth state parameters and the crop stressed state parameters; the first crop growth evaluation index is used for representing the relation between the crop growth state and the crop growth background;
collecting growth data of a target crop, and acquiring near-ground observation data containing daily growth index data of the target crop; specifically, a sensor erected in a farmland is used for observing the growth state of a target crop in real time, the observed parameters comprise plant height, stem thickness, leaf density, pest density and the like, and the data are counted to obtain indexes such as average plant height, average leaf density and the like of the target crop every day;
constructing a second crop growth evaluation index based on near-ground observation data by using the growth index data based on a statistical model; specifically, a near-Ground second Crop growth state evaluation Index (CGI _ G) is constructed on the basis of a statistical model by using indexes such as the average plant height and the average leaf density of the target Crop per day;
is provided withHThe plant height is the height of the plant,Dthe diameter of the stem is the diameter of the stem,LDas the density of the blades, the number of the blades,PDthe density of the diseases and the pests is determined,w 5 the weight of the plant height,w 6 The weight of the stem thickness,w 7 Is the weight of the blade density,w 8 For the weight of the pest density, the second crop growth state evaluation index CGI _ G represents the correlation between the crop growth condition (positive direction) and the disaster condition (negative direction) obtained by using the near-ground observation data, and then:
CGI_G=(w 5 *H+w 6 *D+w 7 *LD)/(w 8 *PD+a 2 )。
wherein the weight isw 5 、w 6 、w 7 、w 8 Can be dynamically adjusted according to the type of crop being monitored, a 2 Is an optional parameter for preventing parametersPDA value of 0 causes the equation to be invalidated.
The method comprises the following steps of supplementing missing values of first crop growth evaluation indexes at the same position and the same time in remote sensing satellite data by taking near-ground observation data as a reference to obtain a mapping model training label of a first crop growth evaluation index model and a second crop growth evaluation index, wherein the mapping model training label comprises the following steps:
defining points in the remote sensing satellite data, which are consistent with ground observation geographic positions, as reference points, acquiring satellite data sequence point location numerical values before and after a plurality of reference points, and defining satellite data sequence point locations of the reference points and ground observation sequence values corresponding to the satellite data sequence point locations of the points before and after the reference points;
respectively obtaining derivatives for representing the changes of the satellite data sequence point location values adjacent to each other by using a derivation mode, determining the relationship between the satellite data sequence point location values of the reference point and the satellite data sequence point location values of the points before and after the reference point, and constructing a fitting equation:
if the signs of all the derivatives in the fitting equation are consistent, or the signs of the derivatives in the fitting equation are different and the positions of the signs of the derivatives which are different are positioned at points except the reference point, directly fitting a quadratic function to the fitting equation;
if the position of the difference of the signs of the derivatives in the fitting equation is located at a reference point, utilizing two groups of data group piecewise fitting quadratic functions consisting of satellite data sequence point location numerical values of points except the reference point and ground observation numerical values corresponding to the satellite data sequence point location numerical values, respectively utilizing the two groups of data groups to calculate the satellite data numerical values of the two groups of reference points, taking the average value of the satellite data numerical values of the two groups of reference points to obtain a target satellite data sequence point location numerical value of the reference point, and combining the target satellite data sequence point location numerical value, the ground observation numerical value corresponding to the target satellite data sequence point location numerical value, the satellite data sequence point location numerical value of the reference point and the ground observation numerical value corresponding to the reference point to obtain the training label.
Specifically, the process of obtaining the mapping model training label specifically comprises the following steps: in obtaining ground observation data (position)pTime of dayt) On the basis of the data sequence of the satellite, defining the point position consistent with the ground observation geographic position asy 3 Then the value of the sequence point before the point is defined asy 1 And withy 2 The numerical value of the sequence point after the point is defined asy 4 Andy 5 the corresponding ground observation sequence values are sequentiallyx 1 、x 2 、x 3 、x 4 Andx 5 ；
judgment by means of derivationy 1 、y 2 、y 4 、y 5 Respectively, obtaining the relative relationship ofy 1 And withy 2 , y 2 Andy 4 andy 4 andy 5 three derivatives betweenk i So as to judge whether the 5 values are in an increasing/decreasing relation or whether an inflection point exists in a fitting curve of the 5 values, further determine the position and the shape of the inflection point, and construct a fitting equation:
y = a 0 +a 1 * (x i -x 3 )+a 2 * (x i -x 3 ) 2 ；
wherein,x i according to the needk i Values are selected if allk i If the signs are consistent, only ordinary quadratic function fitting is carried out; if it is notk i Is changed, the position of the slope sign change is further judged, wherein if the slope sign change existsk i The position of the change of sign isy 2 Ory 4 Then still only fitting with the ordinary quadratic function, if the change location is locatedy 3 Then it needs to use (x 1 ,y 1 )、(x 2 ,y 2 ) Fitting is performed, andx 4 ,y 4 ) 、(x 5 ,y 5 ) Fitting to obtain satellite data values of two reference pointsy 3 ’Then the satellite data values for two reference pointsy 3 ’Obtaining the point location value of the target satellite data sequence of the reference point by taking the mean valuepPoint values of target satellite data sequencepGround observation value corresponding to target satellite data sequence point numerical valuetSatellite data sequence point location numerical value of reference pointx 3 And the ground observation value corresponding to the reference pointy 3 Combining to obtain training labels, thereby constructing a set of training labels (p，t，x 3 ，y 3 ) And realizing the conversion of the second crop growth state evaluation index CGI _ G to the first crop growth evaluation index CGI _ S at the point.
Carrying out continuous interpolation on the first crop growth evaluation index by adopting an average interpolation mode to obtain reconstructed crop growth data;
constructing a neural network model, and training the neural network model by using a mapping model training label to obtain a crop growth data mapping model; specifically, the attention mechanism of the neural network mapping model can be expressed by the following formula:
E=(w*(s t-1 , h 1 ), …, w*(s t-1 , h t ))；
wherein,win order to be the weight coefficient,h 1 …h t it is represented by a hidden neuron or neurons,s t representing sequence values representing the length of the crop time sequence characteristic, and representing the sequence values by an encoder in a dot product formy 3 And matching degree with corresponding position values in the reconstructed crop growth data.
Optionally, the network used by the neural network mapping model is subordinate to RNNs but not limited to RNNs, the basic unit is not limited to attention unit (attention unit), the near-ground sequence length used covers the growth period of the crop (2 months to 11 months), and the training environment of the neural network mapping model is not limited to tensflow.
And correcting the reconstructed continuous crop growth data by using the crop growth data mapping model to obtain continuous day-by-day and full-coverage crop growth evaluation values so as to obtain target crop growth evaluation data.
The invention realizes the purpose of monitoring the growth vigor of crops by comprehensively using the space remote sensing data and the near-ground observation data, and solves the problems of insufficient precision and time density of the space remote sensing data and small data range of the near-ground observation data in the existing method.
Example 2
Based on the same principle as the method shown in embodiment 1 of the present invention, as shown in fig. 3, an embodiment of the present invention further provides a space-to-ground integrated crop growth intelligent monitoring system, which includes a first obtaining unit, a first processing unit, a first constructing unit, a second obtaining unit, a second constructing unit, a second processing unit, a reconstructing unit, a network model unit, and a correcting unit;
the system comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for collecting remote sensing satellite data and acquiring satellite time sequence remote sensing data in a target area;
the first processing unit is used for calculating the crop growth state parameters and the crop stressed state parameters according to the satellite time sequence remote sensing data;
the first construction unit is used for constructing a first crop growth evaluation index based on satellite time sequence remote sensing data by utilizing the crop growth state parameters and the crop stressed state parameters; the first crop growth evaluation index is used for representing the relation between the crop growth state and the crop growth background;
the second acquisition unit is used for acquiring growth data of the target crop and acquiring near-ground observation data containing daily growth index data of the target crop;
the second construction unit is used for constructing a second crop growth evaluation index based on the near-ground observation data based on the statistical model by using the growth index data;
the second processing unit is used for supplementing the missing value of the first crop growth evaluation index at the same position and the same time in the remote sensing satellite data by taking the near-ground observation data as a reference to obtain a mapping model training label of the first crop growth evaluation index model and the second crop growth evaluation index;
the reconstruction unit is used for continuously interpolating the first crop growth evaluation index in an average interpolation mode to obtain reconstructed continuous crop growth data;
the network model unit is used for training the neural network model by utilizing the mapping model training label to obtain a crop growth data mapping model;
and the correction unit is used for correcting the reconstructed continuous crop growth data by using the crop growth data mapping model to obtain target crop growth evaluation data.
Optionally, the first obtaining unit is configured to collect remote sensing satellite data and obtain satellite timing remote sensing data in the target area, and the obtaining unit includes: the method comprises the steps of collecting remote sensing satellite data, carrying out radiation correction and geometric registration on the remote sensing satellite data, resampling all the data to the same spatial resolution, and obtaining satellite time sequence remote sensing data in a target area.
Optionally, the first construction unit constructs a first crop growth evaluation index based on the satellite time sequence remote sensing data by using the crop growth state parameter and the crop stressed state parameter and adopting a linear regression mode.
Optionally, the crop growth state parameters include a normalized vegetation index, an enhanced vegetation index, and a greenness index; the parameters of the stressed state of the crops comprise a red edge index and a soil vegetation index.
Optionally, the second acquiring unit observes the growth state parameters of the target crops in real time by using a sensor erected in the farmland; counting the observed growth state parameters to obtain growth index data, wherein the growth index data comprises the following steps:
observing the growth data of the target crops in real time by using a sensor erected in a farmland;
counting the observed growth data to obtain growth index data;
the growth data comprises the plant height, stem thickness, leaf density and pest density of the crops; the growth index data includes an average plant height index and an average leaf density index for the target crop per day.
The growth state parameters comprise the plant height, stem thickness, leaf density and pest density of the crops; the growth index data includes an average plant height index and an average leaf density index for the target crop per day.
Optionally, the second processing unit supplements missing values of satellite time series remote sensing data at the same position and the same time in the remote sensing satellite data by taking the near-ground observation data as a reference to obtain a mapping model training label of the first crop growth evaluation index model and the second crop growth evaluation index, and includes a second processing subunit, a first determining unit and a second determining unit;
the second processing subunit is used for defining a point in the remote sensing satellite data, which is consistent with the ground observation geographic position, as a reference point, acquiring satellite data sequence point locations of points before and after the reference point, defining a ground observation sequence value corresponding to the satellite data sequence point location of the reference point and the satellite data sequence point locations of the points before and after the reference point, and acquiring the numerical value;
the first determining unit is used for defining points in the remote sensing satellite data, which are consistent with the ground observation geographic position, as reference points, acquiring satellite data sequence point location numerical values before and after a plurality of reference points, and defining the satellite data sequence point location of the reference points and the ground observation sequence values corresponding to the satellite data sequence point location of the points before and after the reference points;
respectively obtaining derivatives for representing the changes of the point location values of adjacent satellite data sequences by utilizing a derivation mode, determining the relationship between the point location values of the satellite data sequences of the reference points and the point location values of the satellite data sequences of points before and after the reference points, and constructing a fitting equation:
if the signs of all the derivatives in the fitting equation are consistent, or the signs of the derivatives in the fitting equation are different and the positions of the signs of the derivatives which are different are positioned at points except the reference point, directly fitting a quadratic function to the fitting equation;
if the position of the difference of the signs of the derivatives in the fitting equation is located at a reference point, utilizing two groups of data group piecewise fitting quadratic functions consisting of satellite data sequence point location numerical values of points except the reference point and ground observation numerical values corresponding to the satellite data sequence point location numerical values, respectively utilizing the two groups of data groups to calculate the satellite data numerical values of the two groups of reference points, taking the average value of the satellite data numerical values of the two groups of reference points to obtain a target satellite data sequence point location numerical value of the reference point, and combining the target satellite data sequence point location numerical value, the ground observation numerical value corresponding to the target satellite data sequence point location numerical value, the satellite data sequence point location numerical value of the reference point and the ground observation numerical value corresponding to the reference point to obtain the training label.
Example 3
Based on the same principle as the method shown in the embodiment of the present invention, an embodiment of the present invention further provides an electronic device, as shown in fig. 3, which may include but is not limited to: a processor and a memory; a memory for storing a computer program; and the processor is used for executing the intelligent monitoring method for the growth of the crop integrated with the heaven and the earth shown in any embodiment of the invention by calling a computer program.
In an alternative embodiment, an electronic device is provided, the electronic device 30 shown in fig. 3 comprising: a processor 310 and a memory 330. Wherein the processor 310 is coupled to the memory 330, such as via a bus 320.
Optionally, the electronic device 30 may further include a transceiver 340, and the transceiver 340 may be used for data interaction between the electronic device and other electronic devices, such as transmission of data and/or reception of data. It should be noted that the transceiver 340 is not limited to one in practical applications, and the structure of the electronic device 30 does not limit the embodiment of the present invention.
The processor 310 may be a CPU central processing unit, general processor, DSP data signal processor, ASIC application specific integrated circuit, FPGA field programmable gate array or other programmable logic device, hardware component, or any combination thereof. The processor 310 may also be a combination of computing functions, e.g., comprising one or more microprocessors, a combination of a DSP and a microprocessor, or the like.
The memory 330 is used for storing application program codes (computer programs) for performing aspects of the present invention and is controlled to be executed by the processor 310. The processor 310 is configured to execute application program code stored in the memory 330 to implement the aspects illustrated in the foregoing method embodiments.
The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes will occur to those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (6)
1. The intelligent monitoring method for the growing vigor of the crops integrated with the heaven and earth is characterized by comprising the following steps:
collecting remote sensing satellite data, and acquiring satellite time sequence remote sensing data in a target area;
calculating a crop growth state parameter and a crop stressed state parameter according to the satellite time sequence remote sensing data;
constructing a first crop growth evaluation index based on satellite time sequence remote sensing data by using the crop growth state parameters and the crop stressed state parameters; the crop growth state parameters comprise a normalized vegetation index, an enhanced vegetation index and a greenness index; the stressed state parameters of the crops comprise red edge indexes and soil vegetation indexes; the first crop growth evaluation index is used for representing the relation between the crop growth state and the crop growth background;
acquiring growth data of a target crop, and acquiring near-ground observation data containing daily growth index data of the target crop;
constructing a second crop growth evaluation index based on the near-ground observation data based on a statistical model by utilizing the growth index data;
supplementing the missing value of the first crop growth evaluation index at the same position and the same time in the remote sensing satellite data by taking the near-ground observation data as a reference to obtain a mapping model training label of the first crop growth evaluation index model and the second crop growth evaluation index, wherein the mapping model training label comprises: defining a point in the remote sensing satellite data, which is consistent with the ground observation geographic position, as a reference point, acquiring satellite data sequence point location numerical values before and after a plurality of reference points, and defining satellite data sequence point locations of the reference points and ground observation sequence values corresponding to the satellite data sequence point locations of the points before and after the reference points; respectively obtaining derivatives for representing the changes of the satellite data sequence point location values adjacent to each other by using a derivation mode, determining the relationship between the satellite data sequence point location values of the reference point and the satellite data sequence point location values of the points before and after the reference point, and constructing a fitting equation: if the signs of all the derivatives in the fitting equation are consistent, or the signs of the derivatives in the fitting equation are different and the positions of the differences in the signs of the derivatives are located at points except the reference point, directly fitting a quadratic function to the fitting equation; if the position of the difference of the signs of the derivatives in the fitting equation is located at the reference point, calculating satellite data values of two groups of reference points by using two groups of data groups which are formed by satellite data sequence point location values of points except the reference point and ground observation values corresponding to the satellite data sequence point location values in a piecewise fitting quadratic function mode, respectively calculating the satellite data values of the two groups of reference points by using the two groups of data groups, obtaining a target satellite data sequence point location value of the reference point by taking the average value of the satellite data values of the two groups of reference points, and combining the target satellite data sequence point location value, the ground observation values corresponding to the target satellite data sequence point location value, the satellite data sequence point location value of the reference point and the ground observation values corresponding to the reference point to obtain the training label;
carrying out continuous interpolation on the first crop growth evaluation index by adopting an average interpolation mode to obtain reconstructed continuous crop growth data;
constructing a neural network model, and training the neural network model by using the mapping model training label to obtain a crop growth data mapping model;
and correcting the reconstructed continuous crop growth data by using the crop growth data mapping model to obtain target crop growth evaluation data.
2. The intelligent heaven-earth integrated crop growth monitoring method according to claim 1, wherein the step of collecting remote sensing satellite data and obtaining satellite time sequence remote sensing data in a target area comprises the following steps: collecting remote sensing satellite data, performing radiation correction and geometric registration on the remote sensing satellite data, resampling all data to the same spatial resolution, and acquiring satellite time sequence remote sensing data in a target area.
3. The method for intelligently monitoring the growth vigor of the crops integrated with the heaven and earth according to claim 1, wherein the first crop growth vigor assessment index based on satellite time sequence remote sensing data is constructed by utilizing the crop growth state parameters and the crop stressed state parameters in a linear regression mode.
4. The method for intelligently monitoring the growth vigor of the heaven-earth integrated crop as claimed in claim 1, wherein the steps of collecting growth data of a target crop and acquiring near-ground observation data containing daily growth index data of the target crop comprise:
observing the growth data of the target crops in real time by using a sensor erected in a farmland;
counting the observed growth data to obtain the growth index data;
the growth data comprises plant height, stem thickness, leaf density and pest density of crops; the growth index data includes an average plant height index and an average leaf density index for the target crop per day.
5. The device is characterized by comprising a first acquisition unit, a first processing unit, a first construction unit, a second acquisition unit, a second construction unit, a second processing unit, a reconstruction unit, a network model unit and a correction unit;
the first acquisition unit is used for collecting remote sensing satellite data and acquiring satellite time sequence remote sensing data in a target area;
the first processing unit is used for calculating a crop growth state parameter and a crop stressed state parameter according to the satellite time sequence remote sensing data; the crop growth state parameters comprise a normalized vegetation index, an enhanced vegetation index and a greenness index; the stressed state parameters of the crops comprise red edge indexes and soil vegetation indexes;
the first construction unit is used for constructing a first crop growth evaluation index based on satellite time sequence remote sensing data by using the crop growth state parameters and the crop stressed state parameters; the first crop growth evaluation index is used for representing the relation between the crop growth state and the crop growth background;
the second acquisition unit is used for acquiring growth data of a target crop and acquiring near-ground observation data containing daily growth index data of the target crop;
the second construction unit is used for constructing a second crop growth evaluation index based on the near-ground observation data based on a statistical model by utilizing the growth index data;
the second processing unit is configured to supplement, with the near-ground observation data as a reference, a missing value of the first crop growth evaluation index at the same position and at the same time in the remote sensing satellite data to obtain a mapping model training label of the first crop growth evaluation index model and the second crop growth evaluation index, and includes: defining a point in the remote sensing satellite data, which is consistent with the ground observation geographic position, as a reference point, acquiring satellite data sequence point location numerical values before and after a plurality of reference points, and defining satellite data sequence point locations of the reference points and ground observation sequence values corresponding to the satellite data sequence point locations of the points before and after the reference points; respectively obtaining derivatives for representing the changes of the satellite data sequence point location numerical values adjacent to each other by using a derivation mode, determining the relationship between the satellite data sequence point location numerical values of the reference point and the satellite data sequence point location numerical values of the points before and after the reference point, and constructing a fitting equation: if the signs of all the derivatives in the fitting equation are consistent, or the signs of the derivatives in the fitting equation are different and the positions of the differences in the signs of the derivatives are located at points except the reference point, directly fitting a quadratic function to the fitting equation; if the position of the difference of the signs of the derivatives in the fitting equation is located at the reference point, calculating satellite data values of two groups of reference points by using two groups of data groups which are formed by satellite data sequence point location values of points except the reference point and ground observation values corresponding to the satellite data sequence point location values in a piecewise fitting quadratic function mode, respectively calculating the satellite data values of the two groups of reference points by using the two groups of data groups, obtaining a target satellite data sequence point location value of the reference point by taking the average value of the satellite data values of the two groups of reference points, and combining the target satellite data sequence point location value, the ground observation values corresponding to the target satellite data sequence point location value, the satellite data sequence point location value of the reference point and the ground observation values corresponding to the reference point to obtain the training label;
the reconstruction unit is used for continuously interpolating the first crop growth evaluation index in an average interpolation mode to obtain reconstructed continuous crop growth data;
the network model unit is used for constructing a neural network model, and training the neural network model by using the mapping model training label to obtain a crop growth data mapping model;
and the correction unit is used for correcting the reconstructed continuous crop growth data by using the crop growth data mapping model to obtain target crop growth evaluation data.
6. An electronic device, comprising:
a processor and a memory;
the memory is used for storing computer operation instructions;
the processor is used for executing the intelligent monitoring method for the growth vigor of the heaven and earth integrated crop according to any one of claims 1 to 4 by calling the computer operating instructions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211414732.6A CN115511224B (en) | 2022-11-11 | 2022-11-11 | Intelligent monitoring method and device for growing vigor of crops integrated with heaven and earth and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211414732.6A CN115511224B (en) | 2022-11-11 | 2022-11-11 | Intelligent monitoring method and device for growing vigor of crops integrated with heaven and earth and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115511224A CN115511224A (en) | 2022-12-23 |
| CN115511224B true CN115511224B (en) | 2023-04-07 |
Family
ID=84513655
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211414732.6A Active CN115511224B (en) | 2022-11-11 | 2022-11-11 | Intelligent monitoring method and device for growing vigor of crops integrated with heaven and earth and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115511224B (en) |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103971199B (en) * | 2014-04-08 | 2017-09-05 | 武汉禾讯农业信息科技有限公司 | A kind of remote sensing ranking method of a wide range of Grain Growth Situation |
| CN106600434B (en) * | 2016-10-18 | 2021-04-23 | 河南省农业科学院农业经济与信息研究所 | Crop growth remote sensing monitoring method based on crop model and assimilation technology |
| CN107014753B (en) * | 2017-03-06 | 2020-09-29 | 中国科学院遥感与数字地球研究所 | Crop growth monitoring method and system |
| CN109816267A (en) * | 2019-01-31 | 2019-05-28 | 中国农业科学院农业信息研究所 | A kind of intelligence Soybean production management method and system |
| CN114118679B (en) * | 2021-10-14 | 2022-09-16 | 农业农村部规划设计研究院 | Crop yield per unit and growth evaluation method based on time sequence remote sensing data |
-
2022
- 2022-11-11 CN CN202211414732.6A patent/CN115511224B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115511224A (en) | 2022-12-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP3895067B1 (en) | Mapping soil properties with satellite data using machine learning approaches | |
| US11122734B1 (en) | Estimating nitrogen content using hyperspectral and multispectral images | |
| US10859732B2 (en) | Long-range temperature forecasting | |
| CA3073348C (en) | Digital modeling and tracking of agricultural fields for implementing agricultural field trials | |
| US11317562B2 (en) | Generating a yield map for an agricultural field using classification and regression methods | |
| US10754063B2 (en) | Supervised neural network to predict unlabeled rain rates | |
| US10267951B2 (en) | Statistical blending of weather data sets | |
| US10331931B2 (en) | Modeling trends in crop yields | |
| EP3496524B1 (en) | Automatically detecting outlier values in harvested data | |
| Son et al. | A phenological object-based approach for rice crop classification using time-series Sentinel-1 Synthetic Aperture Radar (SAR) data in Taiwan | |
| Son et al. | Field-scale rice yield prediction from Sentinel-2 monthly image composites using machine learning algorithms | |
| Amankulova et al. | Time-series analysis of Sentinel-2 satellite images for sunflower yield estimation | |
| Amankulova et al. | Sunflower crop yield prediction by advanced statistical modeling using satellite-derived vegetation indices and crop phenology | |
| US20220132724A1 (en) | Advanced crop manager for crops stress mitigation | |
| CN114821360A (en) | Method and device for intelligently extracting crop leaf area index and electronic equipment | |
| CN117876870B (en) | Crop estimated yield method and system based on multi-source remote sensing data | |
| CN115511224B (en) | Intelligent monitoring method and device for growing vigor of crops integrated with heaven and earth and electronic equipment | |
| CN114359725B (en) | Crop growth condition remote sensing monitoring system and method based on crop model and assimilation technology | |
| CN115496999A (en) | Method and device for estimating field straw yield | |
| CN115830458B (en) | Method and device for determining farmland irrigation frequency based on sunlight-induced chlorophyll fluorescence | |
| Gunasekara et al. | Expert prediction system for spice plants grown in Sri Lanka: An incentive for planters | |
| Gumma | Crop yield assessment at Gram Panchayat level using technology Rabi–2022-23 | |
| Gumma | Pilot studies on GP level Crop yield estimation using Technology (Rabi 2020-21) using Sentinel 1&2 Satellite data for Rice and Wheat | |
| Gumma | Crop yield assessment at Gram Panchayat level using technology Kharif-2022 | |
| Boukhris et al. | Satellite Imagery, Big Data, Iot and Deep Learning Techniques for Wheat Yield Prediction in Morocco |
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 |