CN111582554B - Crop growth prediction method and system - Google Patents
Crop growth prediction method and system Download PDFInfo
- Publication number
- CN111582554B CN111582554B CN202010307610.1A CN202010307610A CN111582554B CN 111582554 B CN111582554 B CN 111582554B CN 202010307610 A CN202010307610 A CN 202010307610A CN 111582554 B CN111582554 B CN 111582554B
- Authority
- CN
- China
- Prior art keywords
- growth
- current
- historical
- year
- ndvi
- 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 55
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 25
- 238000010606 normalization Methods 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 15
- 238000002310 reflectometry Methods 0.000 claims description 11
- 230000007774 longterm Effects 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 7
- 238000012544 monitoring process Methods 0.000 description 28
- 241000209140 Triticum Species 0.000 description 18
- 235000021307 Triticum Nutrition 0.000 description 18
- 238000009331 sowing Methods 0.000 description 12
- 238000010586 diagram Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 244000025254 Cannabis sativa Species 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 230000004720 fertilization Effects 0.000 description 2
- 244000037666 field crops Species 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000001556 precipitation Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 238000009333 weeding Methods 0.000 description 2
- 238000012098 association analyses Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
- G06F18/21355—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis nonlinear criteria, e.g. embedding a manifold in a Euclidean space
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Operations Research (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a crop growth condition prediction method and a crop growth condition prediction system, wherein the crop growth condition prediction method comprises the following steps: acquiring a normalized vegetation index corresponding to the current year and a normalized vegetation index corresponding to each historical year; fitting and reconstructing normalized vegetation indexes corresponding to the current year and each historical year to obtain a current NDVI fitting curve and each historical NDVI fitting curve; performing normalization processing on the current NDVI fitting curve and each historical NDVI fitting curve by using a DTW algorithm to obtain a current NDVI growth curve and each historical NDVI growth curve; calculating the shortest distance between the current NDVI growth curve and each historical NDVI growth curve, taking the year corresponding to the historical NDVI growth curve with the smallest distance as the optimal NDVI growth matching year, and predicting the growth of the target crop in the current year. And predicting the growth vigor of the target crops in the later period according to the obtained optimal matching year, so as to guide the crop management.
Description
Technical Field
The invention relates to the technical field of agriculture, in particular to a crop growth prediction method and a crop growth prediction system.
Background
The dynamic change of the growth vigor in the production process of field crops has close association relation with the final yield and quality, so the dynamic monitoring of the growth vigor of the crops has important value and significance. The remote sensing observation has the advantages of wide coverage area, high efficiency and the like, and solves the problems of time consumption, high cost, destructiveness and the like caused by ground sampling observation. However, at present, the crop growth condition is monitored by remote sensing mainly by discrete periodic observation, for example, remote sensing vegetation indexes (such as NDVI, EVI and the like) are estimated by selecting nodes in the jointing period, the grouting period and the like of winter wheat, and the quality degree of the growth condition is determined by comparing the remote sensing vegetation indexes with the remote sensing vegetation indexes in the same period in history. The method has the advantages of little data and calculation amount, and three aspects are the greatest deficiency:
(1) Only limited growth period is adopted for comparison analysis, but differences of weather and climate between different years are ignored. When the air temperature, the rainfall and the like between years are obviously changed, the sowing period and the subsequent climates are obviously influenced, so that larger errors are generated when the history contemporaneous comparison is carried out, and the overestimation or underestimation of the growth vigor when the reference history year climates deviate can occur because the climates are not completely regular.
(2) The remote sensing monitoring has large-area instantaneous coverage monitoring capability, for example, the MODIS data width can reach 1000 km, and the high-resolution data GF-1 width of China can reach 800 km. When the growth condition of remote sensing crops in provincial areas or nationwide scales is monitored, the differences of latitudes and physical conditions exist in different areas, the differences of early and late sowing periods exist in the same areas, and the areas with low latitudes are early in sowing period and the areas with high latitudes are late in sowing period, so that the relationship with accumulated temperature is close. The difference of the growth conditions caused by the sowing period can also generate larger error for the remote sensing monitoring evaluation in the later period.
(3) The remote sensing is instantaneous observation, only represents the growth state of crops at the satellite transit time, and can monitor a plurality of growth periods, but because the remote sensing is independent comparison analysis of a plurality of growth periods, and the remote sensing lacks the association analysis of different growth periods, the judgment of the growth conditions of different growth periods is often contradicted, and the dynamic trend of the growth conditions of crops is difficult to comprehensively evaluate.
Disclosure of Invention
In order to solve the problems, the embodiment of the invention provides a crop growth prediction method and a crop growth prediction system.
In a first aspect, an embodiment of the present invention provides a method for predicting crop growth, the method including:
acquiring normalized vegetation indexes corresponding to each current growth condition remote sensing data of a target crop in current years according to each current growth condition remote sensing data of the target crop in current years, and acquiring normalized vegetation indexes corresponding to each historical growth condition remote sensing data of each historical year according to each historical growth condition remote sensing data of the target crop in a plurality of historical years;
fitting and reconstructing the normalized vegetation indexes corresponding to each current growth condition remote sensing data in the current year to obtain a current NDVI fitting curve, and fitting and reconstructing the normalized vegetation indexes corresponding to each historical growth condition remote sensing data in each historical year to obtain each historical NDVI fitting curve;
performing normalization processing on the current NDVI fitting curve and each historical NDVI fitting curve by using a DTW algorithm to obtain a current NDVI long-term curve and each historical NDVI long-term curve;
calculating the shortest distance between the current NDVI growth curve and each historical NDVI growth curve, and taking the year corresponding to the historical NDVI growth curve with the smallest distance as the optimal NDVI growth matching year;
And predicting the growth condition of the target crop in the current year according to the growth condition of the target crop in the optimal NDVI growth condition matching year.
Preferably, the calculating the shortest distance between the current NDVI growth curve and each historical NDVI growth curve specifically includes:
step one: the sequence distance matrix D is calculated using the following formula M * N ；
D(i,j)＝|R i -T j |，i＝1,2,…,M,j＝1,2,…,N，
Wherein D (i, j) represents Euclidean distance, R represents the current NDVI growth curve, and T represents any historical NDVI growth curve;
step two: calculated according to the following formula:
where g (i, j) represents the distance between the i component in R and the j component in T, and D (i, j) represents the value of the j-th element of the i-th row in matrix D.
Preferably, the obtaining, according to each current growth condition remote sensing data of the target crop in the current year, a normalized vegetation index corresponding to each current growth condition remote sensing data in the current year further includes:
and periodically acquiring current growth condition remote sensing data of the target crops in the preset time period of the current year.
Preferably, the normalized vegetation index corresponding to each current growth condition remote sensing data of the target crop in the current year is obtained according to each current growth condition remote sensing data of the target crop in the current year, and a specific calculation formula is as follows:
Wherein NDVI represents the normalized vegetation index, ρ NIR Representing the reflectivity in the near infrared band ρ RED Representing the reflectivity of the red band.
Preferably, the fitting reconstruction is performed on the normalized vegetation index corresponding to each current growth condition remote sensing data in the current year to obtain a current NDVI fitting curve, which specifically includes:
and adopting an SG filtering algorithm to fit and reconstruct the normalized vegetation index corresponding to each current growth remote sensing data in the current year, and obtaining a current NDVI fitting curve.
In a second aspect, an embodiment of the present invention provides a method for predicting crop growth, the method including:
acquiring an enhanced vegetation index corresponding to each current growth condition remote sensing data of a target crop in a current year according to each current growth condition remote sensing data of the target crop in the current year, and acquiring an enhanced vegetation index corresponding to each historical growth condition remote sensing data of each historical year according to each historical growth condition remote sensing data of the target crop in a plurality of historical years;
fitting and reconstructing the enhanced vegetation indexes corresponding to each current growth condition remote sensing data in the current year to obtain a current EVI fitting curve, and fitting and reconstructing the enhanced vegetation indexes corresponding to each historical growth condition remote sensing data in each historical year to obtain each historical EVI fitting curve;
Performing normalization processing on the current EVI fitting curve and each historical EVI fitting curve by using a DTW algorithm to obtain a current EVI growth curve and each historical EVI growth curve;
calculating the shortest distance between the current EVI growth curve and each historical EVI growth curve, and taking the year corresponding to the historical EVI growth curve with the smallest distance as the optimal EVI growth matching year;
and predicting the growth condition of the target crop in the current year according to the growth condition of the target crop in the optimal EVI growth condition matching year.
Preferably, the obtaining, according to each current growth condition remote sensing data of the target crop in the current year, an enhanced vegetation index corresponding to each current growth condition remote sensing data in the current year specifically includes:
wherein EVI represents the enhanced vegetation index, ρ NIR Representing the reflectivity in the near infrared band ρ RED Representing the reflectance of the red band ρ BLUE Indicating the reflectivity in the blue band.
In a second aspect, an embodiment of the present invention provides a system for predicting crop growth, the system comprising:
the remote sensing module is used for acquiring normalized vegetation indexes corresponding to each current growth condition remote sensing data of the target crops in the current year according to each current growth condition remote sensing data of the target crops in the current year, and acquiring normalized vegetation indexes corresponding to each historical growth condition remote sensing data of each historical year according to each historical growth condition remote sensing data of the target crops in a plurality of historical years;
The fitting module is used for carrying out fitting reconstruction on the normalized vegetation indexes corresponding to each current growth condition remote sensing data in the current year to obtain a current NDVI fitting curve, and carrying out fitting reconstruction on the normalized vegetation indexes corresponding to each historical growth condition remote sensing data in each historical year to obtain each historical NDVI fitting curve;
the normalization module is used for performing normalization processing on the current NDVI fitting curve and each historical NDVI fitting curve by using a DTW algorithm to obtain a current NDVI growth curve and each historical NDVI growth curve;
the shortest distance module is used for calculating the shortest distance between the current NDVI growth curve and each historical NDVI growth curve, and taking the year corresponding to the historical NDVI growth curve with the smallest distance as the optimal NDVI growth matching year;
and the prediction module is used for predicting the growth condition of the target crop in the current year according to the growth condition of the target crop in the optimal NDVI growth condition matching year.
In a fourth aspect, an embodiment of the present invention provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor invoking program instructions capable of performing the crop growth prediction method provided by any of the various possible implementations of the first aspect.
In a fifth aspect, embodiments of the present invention provide a non-transitory computer-readable storage medium having stored thereon a computer program that causes a computer to perform the crop growth prediction method provided by any one of the various possible implementations of the first aspect.
The embodiment of the invention provides a crop growth situation prediction method and a crop growth situation prediction system, which utilize continuous monitoring information of crop growth situations obtained by time sequence remote sensing data, fully consider the physical difference existing in the distribution of crop areas, establish a unified growth situation dynamic curve regulation method, enable remote sensing growth situation curves of all complete years to optimally correspond according to physical response through a DTW dynamic time regulation algorithm, and sequentially judge that the difference between the growth situation curve of a current year target crop and the growth situation curve of a historical year target crop in each growth period is minimum by adopting a Euclidean distance method, wherein the minimum difference year is the best matching year. The user can predict the growth vigor of the target crops in the later period according to the obtained best matching year, so as to guide the crop management.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a crop growth prediction method according to an embodiment of the present invention;
FIG. 2 is a flowchart of a method for predicting crop growth according to still another embodiment of the present invention;
FIG. 3 is a schematic diagram of a current NDVI fitted curve and a current EVI fitted curve in an embodiment of the invention;
FIG. 4 is a schematic diagram of a historical NDVI growth curve and a historical EVI growth curve in an embodiment of the invention;
FIG. 5 is a schematic diagram of shortest path calculation in an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a crop growth prediction system according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The crop growth remote sensing annual type can be defined as: the remote sensing monitoring of the crop growth vigor in the whole monitoring year or in the key stage is matched with the remote sensing monitoring result of the corresponding monitoring year in the history, so that the optimal matching history year is obtained, and the year is the optimal growth vigor remote sensing year type of the crop in the current monitoring year.
The growth vigor of field crops is influenced by factors such as weather, soil and artificial management besides the factors of the types and varieties of the crops, is a comprehensive action representation of the physiological ecology and the growth environment of the crops, and the growth vigor year type obtained by remote sensing exactly corresponds to the representation, so that the method not only comprises the growth characteristics of the crops, but also covers the actions such as weather and environment.
Therefore, the analysis is carried out according to the growth condition remote sensing dynamics of the whole growth period of the crops, the influence of different regional sowing periods and different annual climates on the growth condition of the crops is considered to be eliminated, the comparison and the matching are carried out with the growth condition dynamics of the historical years, the optimal matching year is determined, the annual quantitative analysis and evaluation of the growth condition of the crops under the unified time-space scale are realized, and scientific decision information is provided for guiding the cultivation and harvest arrangement of the crops and the like.
Fig. 1 is a flowchart of a method for predicting crop growth status, which includes:
S1, acquiring a normalized vegetation index corresponding to each current growth condition remote sensing data of a target crop in a current year according to each current growth condition remote sensing data of the target crop in the current year, and acquiring a normalized vegetation index corresponding to each historical growth condition remote sensing data of each historical year according to each historical growth condition remote sensing data of the target crop in a plurality of historical years;
s2, fitting reconstruction is carried out on the normalized vegetation indexes corresponding to each current growth condition remote sensing data in the current year, a current NDVI fitting curve is obtained, fitting reconstruction is carried out on the normalized vegetation indexes corresponding to each historical growth condition remote sensing data in each historical year, and each historical NDVI fitting curve is obtained;
s3, performing normalization processing on the current NDVI fitting curve and each historical NDVI fitting curve by using a DTW algorithm to obtain a current NDVI growth curve and each historical NDVI growth curve;
s4, calculating the shortest distance between the current NDVI growth curve and each historical NDVI growth curve, and taking the year corresponding to the historical NDVI growth curve with the smallest distance as the optimal NDVI growth matching year;
s5, predicting the growth condition of the target crop in the current year according to the growth condition of the target crop in the optimal NDVI growth condition matching year.
In order to predict growth vigor of a target crop in a current year, the current year refers to a year in which growth monitoring is required, remote sensing data from a sensor is first acquired, in the embodiment of the invention, the remote sensing data obtained by shooting at a plurality of different time points is acquired and is used as a plurality of current growth vigor remote sensing data of the target crop in the current year, and a normalized vegetation index corresponding to each current growth vigor remote sensing data is acquired according to each current growth vigor remote sensing data.
In the prior art, the growth vigor of the target crops is usually predicted only according to one remote sensing data, when the limited growth period is compared and analyzed, the difference of weather and physical conditions among different years is ignored, and when the conditions such as air temperature, precipitation and the like are obviously different, the sowing period and the growth condition of the crops are obviously influenced. Therefore, when the growth of the target crop is predicted based on only one remote sensing data, the influence of the weather and the weather on the growth of the target crop cannot be avoided, thereby causing errors in prediction.
Therefore, in the embodiment of the invention, a plurality of current growth condition remote sensing data are adopted, the growth condition of the target crops is predicted based on the data, and the prediction error caused by a single growth period is overcome.
In addition, it is also necessary to acquire remote sensing data of a target crop in a plurality of historical years before the current year, generally, if the current year is 2020, the target crop is wheat, in order to predict the growth vigor of the wheat in 2020, it is necessary to acquire historical growth remote sensing data of different time points in the whole growth period of the wheat in 2009 by taking 2009 as an example according to the remote sensing data of the wheat in 10 years from 2009 to 2019, and the historical growth remote sensing data of different time points is each historical growth remote sensing data of the target crop, and the corresponding normalized vegetation index is calculated for each historical growth remote sensing data.
And then fitting and reconstructing each normalized vegetation index according to the normalized vegetation index corresponding to each current growth remote sensing data, wherein a curve obtained by fitting and reconstructing is called a current NDVI fitting curve.
Fitting and reconstructing the normalized vegetation indexes according to the normalized vegetation indexes corresponding to each historical growth condition remote sensing data of one historical year to obtain a historical NDVI fitting curve corresponding to the historical year, and obtaining the historical NDVI fitting curve corresponding to each historical year according to the method.
As the remote sensing monitoring has large-area instantaneous coverage monitoring capability, but is influenced by regional latitude and physical conditions when the large-range crop growth condition is monitored, the difference of the growth condition exists, and larger error can be generated for the later remote sensing monitoring evaluation.
Because the crop growth condition remote sensing monitoring curves of all the years are affected by factors such as weather, sowing periods and the like, whether the growth periods corresponding to the initial, peak and end positions of the curves are not completely consistent, the crop climate differences of different areas can be regularly and uniformly eliminated, and the optimal year type can be obtained by matching.
Therefore, in the embodiment of the invention, a DTW (Dynamic Time Warping, DTW for short) algorithm is adopted to carry out dynamic time warping of the growth curve. Specifically, the current NDVI fitting curve and each historical NDVI fitting curve are respectively subjected to normalization processing by using a DTW algorithm, influences caused by factors such as climate, sowing period and the like are eliminated, and the current NDVI growth curve and each historical NDVI growth curve are obtained.
Calculating the shortest distance between the current NDVI growth curve and each historical NDVI growth curve, taking the historical year corresponding to the historical NDVI growth curve with the shortest distance as the optimal NDVI growth matching year, and indicating that the growth of the target crop in the current year is closest to the growth of the target crop in the optimal NDVI growth matching year, so that the growth of the target crop in the current year is predicted according to the growth condition of the target crop in the optimal NDVI growth matching year, and measures such as fertilization, weeding and the like are reasonably planned.
The embodiment of the invention provides a crop growth situation prediction method, which utilizes continuous monitoring information of crop growth situations obtained by time sequence remote sensing data, fully considers the difference of physical conditions existing in the distribution of crop areas, establishes a unified growth situation dynamic curve regulation method, enables remote sensing growth situation curves of all complete years to optimally correspond according to physical condition response through a DTW dynamic time regulation algorithm, and sequentially judges that the difference of the growth situation curve of a current year target crop and the growth situation curve of a historical year target crop in each growth period is minimum by adopting a Euclidean distance method, wherein the minimum difference is the best matching year. The user can predict the growth vigor of the target crops in the later period according to the obtained best matching year, so as to guide the crop management.
On the basis of the foregoing embodiment, preferably, the calculating the shortest distance between the current NDVI growth curve and each historical NDVI growth curve specifically includes:
step one: the sequence distance matrix D is calculated using the following formula M * N ；
D(i,j)＝|R i -T j |，i＝1,2,…,M,j＝1,2,…,N，
Wherein D (i, j) represents Euclidean distance, R represents the current NDVI growth curve, and T represents any historical NDVI growth curve;
step two: calculated according to the following formula:
Where g (i, j) represents the distance between the i component in R and the j component in T, and D (i, j) represents the value of the j-th element of the i-th row in matrix D.
The main idea of DTW is: assuming that a standard reference template R is present, it is an M-dimensional vector, i.e., r= { R (1), R (2), …, R (M), …, R (M) }, each component may be a number or a multidimensional vector. Now there is a template T to be tested for matching, which is an N-dimensional vector, i.e. t= { T (1), T (2), …, T (N), …, T (N) }, again each component may be a number or a multidimensional vector, note that M is not necessarily equal to N, but the dimensions of each component should be the same.
Since M is not necessarily equal to N, it is difficult to measure the former euclidean distance determination to calculate which part of T is the most similar to R, i.e. determine the similarity between the current and the historical growth remote sensing data.
Therefore, in the embodiment of the invention, the current NDVI growth curve and each historical NDVI growth curve are aligned one by one, and the similarity is calculated. The specific calculation process is as follows:
the first step: calculating a sequence distance matrix D M * N ；
Using the formula D (i, j) = |r i -T j Calculating the distance between any two points in the sequence of T and R to form the sequence distance matrix D is calculated by i=1, 2, …, M, j=1, 2, …, N M*N Wherein D (i, j) is the euclidean distance.
And a second step of: the matching path with the shortest distance is found according to D (i, j), when the matching path is from one square lattice ((i-1, j-1) or (i-1, j) or (i, j-1)) to the next square lattice (i, j), if the matching path is D (i, j) in the horizontal or vertical direction, the diagonal distance is 2D (i, j), and the constraint condition is as follows:
where g (i, j) denotes that all 2 templates are successively matched from the start component, the i component in R and the j component in T have been reached, and the distance between 2 templates is matched to this step. And d (i, j) or 2d (i, j) is added to the result of the previous matching, and then the minimum value is taken.
On the basis of the foregoing embodiment, preferably, the obtaining, according to each current growth condition remote sensing data of the target crop in the current year, a normalized vegetation index corresponding to each current growth condition remote sensing data in the current year further includes:
and periodically acquiring current growth condition remote sensing data of the target crops in the preset time period of the current year.
Specifically, before each piece of current growth condition remote sensing data is acquired, the method further comprises the following steps:
and periodically acquiring remote sensing data representing the growth vigor of the target crops in a preset time period of the current year, and taking the remote sensing data as the current growth vigor remote sensing data of the target crops.
In the embodiment of the invention, the prediction of the growth vigor of winter wheat is exemplified by 2020, the growth remote sensing data of winter wheat is obtained at regular intervals in the whole growth period time of winter wheat, for example, 3 months to 6 months, and the specific interval time can be adjusted according to actual needs, and the growth remote sensing data obtained at regular intervals is used as current growth remote sensing data.
On the basis of the foregoing embodiment, preferably, the normalized vegetation index corresponding to each current growth condition remote sensing data of the current year is obtained according to each current growth condition remote sensing data of the current year target crop, and a specific calculation formula is as follows:
wherein NDVI represents the normalized vegetation index, ρ NIR Representing the reflectivity in the near infrared band ρ RED Representing the reflectivity of the red band.
Specifically, the normalized vegetation index may be calculated according to the above formula.
On the basis of the foregoing embodiment, preferably, the fitting reconstruction is performed on the normalized vegetation index corresponding to each current growth remote sensing data in the current year to obtain a current NDVI fitting curve, which specifically includes:
and adopting an SG filtering algorithm to fit and reconstruct the normalized vegetation index corresponding to each current growth remote sensing data in the current year, and obtaining a current NDVI fitting curve.
Specifically, the normalized vegetation index corresponding to each current growth remote sensing data of the current year is fitted and reconstructed through an SG filtering algorithm, and a current NDVI fitting curve is obtained.
And similarly, fitting and reconstructing the normalized vegetation index corresponding to the historical year through an SG filtering algorithm to obtain a historical NDVI fitting curve corresponding to the historical year. And obtaining a history NDVI fitting curve corresponding to each history year according to the same method.
The crop growth condition prediction method provided by the embodiment of the invention has the following effects:
(1) The crop growth year type using remote sensing time sequence monitoring is provided for the first time, and the advantages of time sequence remote sensing monitoring are fully exerted.
(2) And the DTW method is adopted to perform unified treatment on the time sequence data of the remote sensing monitoring of the growth vigor of the crops in many years, so that the difference of the physical conditions of the crop growth in different areas is eliminated.
(3) The optimal growth and year type matching is realized by adopting a minimum distance method, the correlation of the growth and year in the continuous growth period is fully considered, and the defect that only a single growth period or a part of growth period is considered in the past is overcome.
Fig. 2 is a flowchart of a method for predicting crop growth according to still another embodiment of the present invention, as shown in fig. 2, the method includes:
S1, acquiring an enhanced vegetation index corresponding to each current growth condition remote sensing data of a target crop in a current year according to each current growth condition remote sensing data of the target crop in the current year, and acquiring an enhanced vegetation index corresponding to each historical growth condition remote sensing data of each historical year according to each historical growth condition remote sensing data of the target crop in a plurality of historical years;
s2, fitting reconstruction is carried out on the enhanced vegetation indexes corresponding to each current growth remote sensing data of the current year, a current EVI fitting curve is obtained, fitting reconstruction is carried out on the enhanced vegetation indexes corresponding to each historical growth remote sensing data of each historical year, and each historical EVI fitting curve is obtained;
s3, performing normalization processing on the current EVI fitting curve and each historical EVI fitting curve by using a DTW algorithm to obtain a current EVI growth curve and each historical EVI growth curve;
s4, calculating the shortest distance between the current EVI growth curve and each historical EVI growth curve, and taking the year corresponding to the historical EVI growth curve with the smallest distance as the optimal EVI growth matching year;
s5, predicting the growth condition of the target crop in the current year according to the growth condition of the target crop in the optimal EVI growth condition matching year.
In order to predict growth vigor of a target crop in a current year, the current year refers to a year in which growth monitoring is required, remote sensing data from a sensor is first acquired, in the embodiment of the invention, remote sensing data obtained by shooting at a plurality of different time points is acquired and taken as a plurality of current growth vigor remote sensing data of the target crop in the current year, and an enhanced vegetation index corresponding to each current growth vigor remote sensing data is acquired according to each current growth vigor remote sensing data.
In the prior art, the growth vigor of the target crops is usually predicted only according to one remote sensing data, when the limited growth period is compared and analyzed, the difference of weather and physical conditions among different years is ignored, and when the conditions such as air temperature, precipitation and the like are obviously different, the sowing period and the growth condition of the crops are obviously influenced. Therefore, when the growth of the target crop is predicted based on only one remote sensing data, the influence of the weather and the weather on the growth of the target crop cannot be avoided, thereby causing errors in prediction.
Therefore, in the embodiment of the invention, a plurality of current growth condition remote sensing data are adopted, the growth condition of the target crops is predicted based on the data, and the prediction error caused by a single growth period is overcome.
In addition, it is also necessary to acquire remote sensing data of a target crop in a plurality of historical years before the current year, generally, if the current year is 2020, the target crop is wheat, in order to predict the growth vigor of the wheat in 2020, it is necessary to acquire historical growth remote sensing data of different time points in the whole growth period of the wheat in 2009 by taking 2009 as an example according to the remote sensing data of the wheat in 10 years from 2009 to 2019, and the historical growth remote sensing data of the different time points is each historical growth remote sensing data of the target crop, and the corresponding enhanced vegetation index is calculated for each historical growth remote sensing data.
And then, fitting and reconstructing each enhanced vegetation index according to the enhanced vegetation index corresponding to each current growth remote sensing data, wherein a curve obtained by fitting and reconstructing is called a current EVI fitting curve.
And fitting and reconstructing the enhanced vegetation indexes according to the enhanced vegetation indexes corresponding to each historical growth condition remote sensing data of one historical year to obtain a historical EVI fitting curve corresponding to the historical year, and obtaining the historical EVI fitting curve corresponding to each historical year according to the method.
As the remote sensing monitoring has large-area instantaneous coverage monitoring capability, but is influenced by regional latitude and physical conditions when the large-range crop growth condition is monitored, the difference of the growth condition exists, and larger error can be generated for the later remote sensing monitoring evaluation.
Because the crop growth condition remote sensing monitoring curves of all the years are affected by factors such as weather, sowing periods and the like, whether the growth periods corresponding to the initial, peak and end positions of the curves are not completely consistent, the crop climate differences of different areas can be regularly and uniformly eliminated, and the optimal year type can be obtained by matching.
Therefore, in the embodiment of the invention, a DTW (Dynamic Time Warping, DTW for short) algorithm is adopted to carry out dynamic time warping of the growth curve. Specifically, the DTW algorithm is utilized to respectively carry out normalization processing on the current EVI fitting curve and each historical EVI fitting curve, so as to eliminate the influence caused by factors such as climate, sowing period and the like, and obtain the current EVI growth curve and each historical EVI growth curve.
Calculating the shortest distance between the current EVI growth curve and each historical EVI growth curve, taking the historical year corresponding to the historical EVI growth curve with the shortest distance as the optimal EVI growth matching year, and indicating that the growth of the target crop in the current year is closest to the growth of the target crop in the optimal EVI growth matching year, so that the growth of the target crop in the current year is predicted according to the growth condition of the target crop in the optimal EVI growth matching year, and measures such as fertilization, weeding and the like are reasonably planned.
The embodiment of the invention provides a crop growth situation prediction method, which utilizes continuous monitoring information of crop growth situations obtained by time sequence remote sensing data, fully considers the difference of physical conditions existing in the distribution of crop areas, establishes a unified growth situation dynamic curve regulation method, enables remote sensing growth situation curves of all complete years to optimally correspond according to physical condition response through a DTW dynamic time regulation algorithm, and sequentially judges that the difference of the growth situation curve of a current year target crop and the growth situation curve of a historical year target crop in each growth period is minimum by adopting a Euclidean distance method, wherein the minimum difference is the best matching year. The user can predict the growth vigor of the target crops in the later period according to the obtained best matching year, so as to guide the crop management.
On the basis of the foregoing embodiment, preferably, the obtaining, according to each current growth condition remote sensing data of the target crop in the current year, an enhanced vegetation index corresponding to each current growth condition remote sensing data in the current year specifically includes:
wherein EVI represents the enhanced vegetation index, ρ NIR Representing the reflectivity in the near infrared band ρ RED Representing the reflectance of the red band ρ BLUE Indicating the reflectivity in the blue band.
Other portions of this embodiment are the same as those described above, and reference is made to the above embodiments for details.
In another embodiment of the present invention, a method for predicting crop growth is provided, wherein winter wheat is a target crop, remote sensing data is from MODIS, and the method specifically comprises:
firstly, acquiring each current growth condition remote sensing data of winter wheat in the current year, and simultaneously acquiring a corresponding normalized vegetation index and an enhanced vegetation index according to each current growth condition remote sensing data; and simultaneously acquiring a normalized vegetation index and an enhanced vegetation index corresponding to each historical growth condition remote sensing data in each historical year according to the historical growth condition remote sensing data corresponding to each historical year.
Step two: fitting and reconstructing according to each normalized vegetation index in the current year to obtain a current NDVI fitting curve, and fitting and reconstructing each enhanced vegetation index in the current year to obtain a current EVI fitting curve; fitting reconstruction is carried out according to each normalized vegetation index in each historical year to obtain a historical NDVI fitting curve corresponding to each historical year, and fitting reconstruction is carried out according to each enhanced vegetation index in each historical year to obtain a historical EVI fitting curve corresponding to each historical year.
And calculating a 3-month-6-month wheat growth potential dynamic curve through the two vegetation indexes once every 8 days, carrying out fitting reconstruction on a time sequence curve by using an S-G filtering method, wherein the total of the remote sensing growth potential spectrum monitoring results is 20 times. Fig. 3 is a schematic diagram of a current NDVI fitting curve and a current EVI fitting curve in the embodiment of the present invention, where, as shown in fig. 3, the NDVI fitting growth curve is the current NDVI fitting curve, and the EVI fitting growth curve is the current EVI fitting growth curve.
Calculating a crop growth curve monitored by a historical multi-year remote sensing time sequence: year selection is at least 10 years or more, e.g., the current year of the latest monitoring is 2012, the historical year starts at least from 2003. The surface reflectivity data synthesized by MODIS 250 m 8 days is selected, the NDVI and EVI growth vigor spectrum indexes are calculated respectively, the time series curves of all years are fitted and reconstructed by adopting an S-G filtering method, and fig. 4 is a schematic diagram of a historical NDVI growth vigor curve and a historical EVI growth vigor curve in the embodiment of the invention, as shown in fig. 4.
Step three: and respectively carrying out normalization processing on the current NDVI fitting curve and the current EVI fitting curve through a DTW algorithm to obtain a current NDVI growth curve and a current EVI growth curve. And respectively carrying out normalization processing on each historical NDVI fitting curve and each historical EVI fitting curve through a DTW algorithm to obtain a historical NDVI growth curve and a historical EVI growth curve.
Step four: and calculating the shortest distance between the current NDVI growth curve and each historical NDVI growth curve, acquiring the year with the smallest distance as the optimal NDVI matching year, calculating the shortest distance between the current EVI growth curve and each historical EVI growth curve, and acquiring the year with the smallest distance as the optimal EVI matching year.
The lower graph is a MODIS NDVI growth condition remote sensing monitoring curve of winter wheat from 2003 to 2012, in order to obtain the best matching year with the weather curve of 2012, the DTW distances of the weather curves of 2012 and each year from 2003 to 2011 are calculated, and a corresponding path planning graph is obtained, and fig. 5 is a schematic diagram of shortest path calculation in the embodiment of the invention, as shown in fig. 5, the upper curve in the graph represents the current NDVI growth condition curve, and the lower curve represents the historical NDVI growth condition curve.
From fig. 5, the weather curve in 2012 and the DTW distance minimum in 2005 (DTW distance minimum: 0.012926) are derived, i.e. it is shown that the weather curve in 2012 is most similar to the weather curve in 2005, i.e. the remote sensing annual shape of the best matching crop in 2012 is 2005.
Step five: if the optimal NDVI matching year is the same as the optimal EVI matching year, predicting the growth vigor of the winter wheat according to the optimal NDVI matching year; if the optimal NDVI matching year is different from the optimal EVI matching year, predicting the growth vigor of the winter wheat according to the optimal NDVI matching year.
Fig. 6 is a schematic structural diagram of a crop growth prediction system according to an embodiment of the present invention, as shown in fig. 6, the system includes a remote sensing module 601, a fitting module 602, a normalization module 603, a shortest distance module 604, and a prediction module 605, where:
the remote sensing module 601 is configured to obtain a normalized vegetation index corresponding to each current growth condition remote sensing data of a target crop in a current year according to each current growth condition remote sensing data of the target crop in the current year, and obtain a normalized vegetation index corresponding to each historical growth condition remote sensing data of the target crop in a plurality of historical years according to each historical growth condition remote sensing data of the target crop in the current year;
the fitting module 602 is configured to perform fitting reconstruction on the normalized vegetation index corresponding to each current growth condition remote sensing data in the current year to obtain a current NDVI fitting curve, and perform fitting reconstruction on the normalized vegetation index corresponding to each historical growth condition remote sensing data in each historical year to obtain each historical NDVI fitting curve;
the normalization module 603 is configured to perform normalization processing on the current NDVI fitting curve and each historical NDVI fitting curve by using a DTW algorithm, so as to obtain a current NDVI growth curve and each historical NDVI growth curve;
The shortest distance module 604 is configured to calculate a shortest distance between the current NDVI growth curve and each historical NDVI growth curve, and take a year corresponding to the historical NDVI growth curve with the smallest distance as an optimal NDVI growth matching year;
the prediction module 605 is configured to predict the growth status of the target crop in the current year according to the growth status of the target crop in the optimal NDVI growth status matching year.
The specific implementation process of the embodiment of the present system is the same as that of the embodiment of the method, and please refer to the embodiment of the method for details, which is not described herein again.
The embodiment of the invention utilizes remote sensing time sequence data to judge the growth and year type of crops, realizes comprehensive consideration of comprehensive crop growth, weather and weather factors, and can utilize management experience under the condition of matching year type to reference by determining the growth and year type, thereby realizing prediction and guidance of later growth of crops. Fills the blank in the field and has innovation.
Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 7, an embodiment of the present invention provides an electronic device, including: a processor (processor) 701, a communication interface (Communications Interface) 702, a memory (memory) 703 and a communication bus 704, wherein the processor 701, the communication interface 702 and the memory 703 communicate with each other through the communication bus 704. The processor 701 may call a computer program on the memory 703 and executable on the processor 701 to perform the field seedling stage grass identifying method provided in the above embodiments, for example, including:
Acquiring normalized vegetation indexes corresponding to each current growth condition remote sensing data of a target crop in current years according to each current growth condition remote sensing data of the target crop in current years, and acquiring normalized vegetation indexes corresponding to each historical growth condition remote sensing data of each historical year according to each historical growth condition remote sensing data of the target crop in a plurality of historical years;
fitting and reconstructing the normalized vegetation indexes corresponding to each current growth condition remote sensing data in the current year to obtain a current NDVI fitting curve, and fitting and reconstructing the normalized vegetation indexes corresponding to each historical growth condition remote sensing data in each historical year to obtain each historical NDVI fitting curve;
performing normalization processing on the current NDVI fitting curve and each historical NDVI fitting curve by using a DTW algorithm to obtain a current NDVI long-term curve and each historical NDVI long-term curve;
calculating the shortest distance between the current NDVI growth curve and each historical NDVI growth curve, and taking the year corresponding to the historical NDVI growth curve with the smallest distance as the optimal NDVI growth matching year;
and predicting the growth condition of the target crop in the current year according to the growth condition of the target crop in the optimal NDVI growth condition matching year.
Further, the logic instructions in the memory 703 may be implemented in the form of software functional units and may be stored in a computer readable storage medium when sold or used as a stand alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method of the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The embodiment of the present invention also provides a non-transitory computer readable storage medium, on which a computer program is stored, which when executed by a processor, is implemented to perform the method for identifying grass in field seedling stage provided in the above embodiments, for example, including:
Acquiring normalized vegetation indexes corresponding to each current growth condition remote sensing data of a target crop in current years according to each current growth condition remote sensing data of the target crop in current years, and acquiring normalized vegetation indexes corresponding to each historical growth condition remote sensing data of each historical year according to each historical growth condition remote sensing data of the target crop in a plurality of historical years;
fitting and reconstructing the normalized vegetation indexes corresponding to each current growth condition remote sensing data in the current year to obtain a current NDVI fitting curve, and fitting and reconstructing the normalized vegetation indexes corresponding to each historical growth condition remote sensing data in each historical year to obtain each historical NDVI fitting curve;
performing normalization processing on the current NDVI fitting curve and each historical NDVI fitting curve by using a DTW algorithm to obtain a current NDVI long-term curve and each historical NDVI long-term curve;
calculating the shortest distance between the current NDVI growth curve and each historical NDVI growth curve, and taking the year corresponding to the historical NDVI growth curve with the smallest distance as the optimal NDVI growth matching year;
and predicting the growth condition of the target crop in the current year according to the growth condition of the target crop in the optimal NDVI growth condition matching year.
The above-described embodiments of electronic devices and the like are merely illustrative, in which elements illustrated as separate elements may or may not be physically separate, and elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on such understanding, the foregoing technical solutions may be embodied essentially or in part in the form of a software product, which may be stored in a computer-readable storage medium, such as a ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the various embodiments or some part of the methods of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. A method for predicting crop growth, comprising:
acquiring normalized vegetation indexes corresponding to each current growth condition remote sensing data of a target crop in current years according to each current growth condition remote sensing data of the target crop in current years, and acquiring normalized vegetation indexes corresponding to each historical growth condition remote sensing data of each historical year according to each historical growth condition remote sensing data of the target crop in a plurality of historical years;
fitting and reconstructing the normalized vegetation indexes corresponding to each current growth condition remote sensing data in the current year to obtain a current NDVI fitting curve, and fitting and reconstructing the normalized vegetation indexes corresponding to each historical growth condition remote sensing data in each historical year to obtain each historical NDVI fitting curve;
Performing normalization processing on the current NDVI fitting curve and each historical NDVI fitting curve by using a DTW algorithm to obtain a current NDVI long-term curve and each historical NDVI long-term curve;
calculating the shortest distance between the current NDVI growth curve and each historical NDVI growth curve, and taking the year corresponding to the historical NDVI growth curve with the smallest distance as the optimal NDVI growth matching year;
acquiring an enhanced vegetation index corresponding to each current growth condition remote sensing data of a target crop in a current year according to each current growth condition remote sensing data of the target crop in the current year, and acquiring an enhanced vegetation index corresponding to each historical growth condition remote sensing data of each historical year according to each historical growth condition remote sensing data of the target crop in a plurality of historical years;
fitting and reconstructing the enhanced vegetation indexes corresponding to each current growth condition remote sensing data in the current year to obtain a current EVI fitting curve, and fitting and reconstructing the enhanced vegetation indexes corresponding to each historical growth condition remote sensing data in each historical year to obtain each historical EVI fitting curve;
performing normalization processing on the current EVI fitting curve and each historical EVI fitting curve by using a DTW algorithm to obtain a current EVI growth curve and each historical EVI growth curve;
Calculating the shortest distance between the current EVI growth curve and each historical EVI growth curve, and taking the year corresponding to the historical EVI growth curve with the smallest distance as the optimal EVI growth matching year;
predicting the growth condition of the target crop in the current year according to the growth condition of the target crop in the optimal NDVI growth condition matching year;
the predicting the growth condition of the target crop in the current year according to the growth condition of the target crop in the optimal NDVI growth condition matching year comprises:
and if the optimal NDVI growth condition matching year is the same as the optimal EVI growth condition matching year, predicting the growth condition of the target crop in the current year according to the optimal NDVI growth condition matching year.
2. The method according to claim 1, wherein calculating the shortest distance between the current NDVI growth curve and each historical NDVI growth curve comprises:
step one: the sequence distance matrix D is calculated using the following formula M*N ；
D(i,j)＝|R i -T j |，i＝1,2,…,M,j＝1,2,…,N，
Wherein D (i, j) represents Euclidean distance, R represents the current NDVI growth curve, and T represents any historical NDVI growth curve;
step two: calculated according to the following formula:
Where g (i, j) represents the distance between the i component in R and the j component in T, and D (i, j) represents the value of the j-th element of the i-th row in matrix D.
3. The method for predicting the growth vigor of crops according to claim 1, wherein the obtaining, according to each current growth vigor remote sensing data of the target crop in the current year, a normalized vegetation index corresponding to each current growth vigor remote sensing data in the current year further comprises:
and periodically acquiring current growth condition remote sensing data of the target crops in the preset time period of the current year.
4. The method for predicting the growth vigor of crops according to claim 1, wherein the normalized vegetation index corresponding to each current growth vigor remote sensing data of the target crop in the current year is obtained according to each current growth vigor remote sensing data of the target crop in the current year, and a specific calculation formula is as follows:
wherein NDVI represents the normalized vegetation index, ρ NIR Representing the reflectivity in the near infrared band ρ RED Representing the reflectivity of the red band.
5. The method for predicting crop growth vigor according to claim 1, wherein the fitting reconstruction is performed on the normalized vegetation index corresponding to each current growth vigor remote sensing data in the current year to obtain a current NDVI fitting curve, and specifically includes:
And adopting an SG filtering algorithm to fit and reconstruct the normalized vegetation index corresponding to each current growth remote sensing data in the current year, and obtaining a current NDVI fitting curve.
6. A crop growth prediction system for performing the crop growth prediction method according to any one of claims 1 to 5.
7. An electronic device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the crop growth prediction method according to any one of claims 1 to 5 when the program is executed.
8. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the crop growth prediction method of any of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010307610.1A CN111582554B (en) | 2020-04-17 | 2020-04-17 | Crop growth prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010307610.1A CN111582554B (en) | 2020-04-17 | 2020-04-17 | Crop growth prediction method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111582554A CN111582554A (en) | 2020-08-25 |
| CN111582554B true CN111582554B (en) | 2024-02-23 |
Family
ID=72111561
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010307610.1A Active CN111582554B (en) | 2020-04-17 | 2020-04-17 | Crop growth prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111582554B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112167035B (en) * | 2020-08-28 | 2022-05-03 | 北京农业智能装备技术研究中心 | Hydroponic leaf vegetable production management method and system |
| CN112101681B (en) * | 2020-09-25 | 2023-04-28 | 北京师范大学 | Method for monitoring winter wheat dry hot air disasters based on remote sensing NDPI time sequence |
| CN112304902B (en) * | 2020-11-02 | 2023-10-20 | 航天宏图信息技术股份有限公司 | Real-time monitoring method and device for crop weather |
| CN112632796A (en) * | 2020-12-31 | 2021-04-09 | 广州极飞科技有限公司 | Nitrogen content determination method, operation method, device, electronic device and storage medium |
| CN113076651B (en) * | 2021-04-12 | 2023-05-12 | 中山大学 | Method and related device for recovering bedrock stripping history based on universe causative nuclide |
| CN113822495B (en) * | 2021-10-20 | 2023-12-19 | 平安科技（深圳）有限公司 | Growth state prediction method, device, equipment and medium based on machine learning model |
| CN113984212B (en) * | 2021-10-27 | 2023-06-27 | 中国气象科学研究院 | Agricultural irrigation area extraction method and system |
| CN114266388A (en) * | 2021-12-08 | 2022-04-01 | 浙江大学 | Soybean yield prediction method based on historical vegetation index time series spectrum curve and yield mapping mode |
| CN114005039B (en) * | 2021-12-31 | 2022-04-26 | 成都国星宇航科技有限公司 | Crop growth assessment method and device based on remote sensing image and electronic equipment |
| CN114581401A (en) * | 2022-03-03 | 2022-06-03 | 平安科技（深圳）有限公司 | Method, system, equipment and medium for monitoring growth vigor of crops |
| CN115983503A (en) * | 2023-03-18 | 2023-04-18 | 杭州领见数字农业科技有限公司 | Crop maturity prediction method, equipment and storage medium |
| CN117151477B (en) * | 2023-10-31 | 2024-01-23 | 中化现代农业有限公司 | Crop anomaly identification method, device, electronic equipment and storage medium |
| CN117952497B (en) * | 2024-03-25 | 2024-05-31 | 江苏酷班科技有限公司 | Agricultural logistics management system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015188333A (en) * | 2014-03-27 | 2015-11-02 | 株式会社日立製作所 | Vegetation growth analyzing system and method |
| CN106096630A (en) * | 2016-06-03 | 2016-11-09 | 福州大学 | A kind of integrated pixel and the Oryza sativa L. method for detecting automatic variation of object |
| CN107014753A (en) * | 2017-03-06 | 2017-08-04 | 中国科学院遥感与数字地球研究所 | Crop condition monitoring method and system |
| CN109241077A (en) * | 2018-08-30 | 2019-01-18 | 东北大学 | Production target variation tendency visual query system and method based on similitude |
| CN109446962A (en) * | 2018-10-19 | 2019-03-08 | 中国科学院地理科学与资源研究所 | Land cover interannual variance detection method and system |
-
2020
- 2020-04-17 CN CN202010307610.1A patent/CN111582554B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2015188333A (en) * | 2014-03-27 | 2015-11-02 | 株式会社日立製作所 | Vegetation growth analyzing system and method |
| CN106096630A (en) * | 2016-06-03 | 2016-11-09 | 福州大学 | A kind of integrated pixel and the Oryza sativa L. method for detecting automatic variation of object |
| CN107014753A (en) * | 2017-03-06 | 2017-08-04 | 中国科学院遥感与数字地球研究所 | Crop condition monitoring method and system |
| CN109241077A (en) * | 2018-08-30 | 2019-01-18 | 东北大学 | Production target variation tendency visual query system and method based on similitude |
| CN109446962A (en) * | 2018-10-19 | 2019-03-08 | 中国科学院地理科学与资源研究所 | Land cover interannual variance detection method and system |
Non-Patent Citations (1)
| Title |
|---|
| 安徽省冬小麦长势遥感监测与评估方法研究;刘惠敏;何彬方;张宏群;;中国农学通报(第33期);摘要，第0、1.3、4节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111582554A (en) | 2020-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111582554B (en) | Crop growth prediction method and system | |
| US9652840B1 (en) | System and method for remote nitrogen monitoring and prescription | |
| US20180075546A1 (en) | Systems for determining agronomic outputs for a farmable region, and related methods and apparatus | |
| Pereira et al. | Crop evapotranspiration estimation with FAO56: Past and future | |
| US10564316B2 (en) | Forecasting national crop yield during the growing season | |
| US20220261928A1 (en) | Crop yield forecasting models | |
| Van Oijen et al. | Bayesian calibration, comparison and averaging of six forest models, using data from Scots pine stands across Europe | |
| US20160224703A1 (en) | Growth stage determination system and method | |
| US20220067614A1 (en) | Apparatus and method for crop yield prediction | |
| Bornn et al. | Efficient stabilization of crop yield prediction in the Canadian Prairies | |
| Waongo et al. | A crop model and fuzzy rule based approach for optimizing maize planting dates in Burkina Faso, West Africa | |
| Romera et al. | Use of a pasture growth model to estimate herbage mass at a paddock scale and assist management on dairy farms | |
| EP3719722A1 (en) | Forecasting national crop yield during the growing season | |
| Sultan et al. | Estimating the potential economic value of seasonal forecasts in West Africa: A long-term ex-ante assessment in Senegal | |
| Thorsen et al. | Modelling cold hardening and dehardening in timothy. Sensitivity analysis and Bayesian model comparison | |
| AU2021374236A1 (en) | Advanced crop manager for crops stress mitigation | |
| Singh et al. | Forecasting crop yield through weather indices through LASSO | |
| CN117455062A (en) | Crop yield prediction algorithm based on multi-source heterogeneous agricultural data | |
| Farbo et al. | Forecasting corn NDVI through AI-based approaches using sentinel 2 image time series | |
| CN109615150B (en) | Method and system for determining rice meteorological output | |
| Linker et al. | Concurrent data assimilation and model-based optimization of irrigation scheduling | |
| CN114936765A (en) | Agricultural drought index construction method considering spatial heterogeneity | |
| Warner et al. | Agricultural impacts of the 2015/2016 drought in Ethiopia using high-resolution data fusion methodologies | |
| Yang et al. | Seasonal prediction of crop yields in Ethiopia using an analog approach | |
| CN117236519B (en) | Water and fertilizer regulation and control method and device, electronic equipment and storage medium |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 1107, block a, Nongke building, No. 11, Shuguang garden middle road, Haidian District, Beijing, 100097 Applicant after: Information technology research center of Beijing Academy of agricultural and Forestry Sciences Address before: 1107, block a, Nongke building, No. 11, Shuguang garden middle road, Haidian District, Beijing, 100097 Applicant before: BEIJING RESEARCH CENTER FOR INFORMATION TECHNOLOGY IN AGRICULTURE |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |