CN115860285A - Method and device for predicting optimal transplanting period of tobacco - Google Patents
Method and device for predicting optimal transplanting period of tobacco Download PDFInfo
- Publication number
- CN115860285A CN115860285A CN202310183279.0A CN202310183279A CN115860285A CN 115860285 A CN115860285 A CN 115860285A CN 202310183279 A CN202310183279 A CN 202310183279A CN 115860285 A CN115860285 A CN 115860285A
- Authority
- CN
- China
- Prior art keywords
- time
- tobacco
- data set
- prediction
- data
- 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.)
- Granted
Links
- 235000002637 Nicotiana tabacum Nutrition 0.000 title claims abstract description 109
- 241000208125 Nicotiana Species 0.000 title claims abstract description 103
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000009331 sowing Methods 0.000 claims abstract description 16
- 238000011156 evaluation Methods 0.000 claims description 40
- 238000004364 calculation method Methods 0.000 claims description 21
- 230000001186 cumulative effect Effects 0.000 claims description 19
- 230000008569 process Effects 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 18
- 238000001556 precipitation Methods 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000010899 nucleation Methods 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 238000002310 reflectometry Methods 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000000638 solvent extraction Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 claims description 2
- 238000005520 cutting process Methods 0.000 claims description 2
- 230000002123 temporal effect Effects 0.000 claims description 2
- 238000011160 research Methods 0.000 abstract description 6
- 101100511466 Caenorhabditis elegans lon-1 gene Proteins 0.000 description 10
- 101150095230 SLC7A8 gene Proteins 0.000 description 10
- 101150044140 Slc7a5 gene Proteins 0.000 description 10
- 101150085091 lat-2 gene Proteins 0.000 description 10
- 239000010410 layer Substances 0.000 description 9
- 230000008859 change Effects 0.000 description 7
- 238000009826 distribution Methods 0.000 description 7
- 244000061176 Nicotiana tabacum Species 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000011161 development Methods 0.000 description 5
- 239000002344 surface layer Substances 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 239000002689 soil Substances 0.000 description 4
- 238000005286 illumination Methods 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000701 chemical imaging Methods 0.000 description 1
- 235000019504 cigarettes Nutrition 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a method and a device for predicting the optimal transplanting period of tobacco, which belong to the field of tobacco planting management and comprise the following steps: combining the sentinel-2 remote sensing image and various meteorological data, constructing a multi-factor data set for predicting the tobacco transplanting period, combining data such as historical records and the like, determining the most suitable transplanting period judgment standard in a mode of stacking the accumulated values of multiple factors, and predicting the factors through an LSTM prediction model, thereby realizing the dynamic prediction of the most suitable transplanting period of the tobacco. The method determines the final most suitable transplanting period judgment standard by using a mode of superposing accumulated values of multiple factors from the sowing period to the most suitable transplanting period, and effectively improves the judgment accuracy and the anti-interference capability compared with the mode of determining by adopting a single or multiple factor value threshold value in the prior research.
Description
Technical Field
The invention belongs to the field of tobacco planting management, and particularly relates to a method and a device for predicting an optimal transplanting period of tobacco.
Background
The quality of the tobacco leaves has a decisive influence on the quality of cigarette products, and the production of high-quality tobacco leaves not only needs suitable ecological conditions, but also needs to fully utilize limited natural resources according to the growth and development characteristics of the tobacco. The distribution conditions of the climate factors in different growth periods in the growth period of the tobacco field play a crucial role in the production of high-quality tobacco, the climate conditions mainly comprise temperature, rainfall and illumination, and the appropriate climate conditions are necessary for the tobacco to complete normal growth and development. In addition, the relative humidity can affect the tobacco morbidity, and the tobacco field morbidity is obviously increased due to the fact that the relative humidity is too high in the early stage of the growth period of the tobacco field.
The transplanting period is an important link in tobacco cultivation measures, and has obvious influence on the field characters, yield and quality of tobacco. The tobacco plants in different transplanting periods have different climatic conditions such as temperature, illumination, rainfall and the like in each growth period, thereby having great influence on the growth and development and the production quality of the tobacco plants. Transplanting is a key link of tobacco production, if the transplanting is too early, the normal growth and development of tobacco plants can be seriously influenced even early blossoming can occur when the tobacco plants are under the low-temperature and low-illumination condition for a long time after the transplanting; if the tobacco plants are transplanted too late and are under the relatively high temperature and high humidity condition in the early stage after the transplanting, the growth and development speed of the tobacco plants is too high, dry matters are not accumulated enough, the leaves are thin, the normal maturity of the leaves is influenced by the temperature reduction in the later growth stage, and the yield and quality of the tobacco leaves are reduced. Therefore, the proper transplanting period is one of the key factors for high quality and high yield of tobacco.
A method and a system for determining the tobacco transplanting date in Fujian tobacco district are disclosed (the patent application number is CN 201910445302.2), comprising the following steps: fitting a function of the daily average temperature of the previous year changing along with the date according to the daily average temperature data of the previous natural year; establishing a prediction function of annual average daily temperature of the agriculture along with date change according to the fitted function of the average daily temperature along with date change; and determining the tobacco transplanting date based on a specific rule according to a prediction function of annual average daily temperature of the agriculture along with date change. The scheme adopts a single factor (temperature) mode to determine the tobacco transplanting period, is easily interfered by other factors, and has poor anti-interference capability and low accuracy.
The method comprises the steps of establishing a simulation method of a space-time variation pattern of weather and soil moisture every ten days in the tobacco area by utilizing MODIS remote sensing image data and DEM elevation data, combining ground observation data of the tobacco area and mathematical modeling, extracting space-time distribution patterns of main weather elements and soil moisture, and determining the space-time distribution pattern of the optimum transplanting time of the tobacco area by combining the optimum weather factors and the soil moisture range required by tobacco transplanting. According to the scheme, MODIS remote sensing image data are used for data processing, but the data are generally used for global or national large-scale research, the data products are not suitable for regional small-scale range research, the results lack effectiveness, and the transplanting period prediction results of high spatial resolution and spatial continuous distribution cannot be well generated.
Disclosure of Invention
The application provides a method and a device for predicting the optimal transplanting period of tobacco, and aims to solve the problems that the method for determining the transplanting period of tobacco by adopting a single factor mode is easily interfered by other factors, has poor anti-jamming capability and low accuracy and cannot well generate the transplanting period prediction result with high spatial resolution and spatial continuous distribution.
In order to achieve the purpose, the invention adopts the following technical scheme that:
acquiring meteorological data and remote sensing image data of a tobacco field to be detected, and performing first preprocessing to obtain a first historical data set and a second prediction data set which are divided according to time attributes;
acquiring the past annual sowing time and the optimum transplanting period of tobacco in a tobacco field to be detected to obtain a first time interval, intercepting a first historical data set based on the first time interval and carrying out second pretreatment to obtain an evaluation standard of the optimum transplanting period of the tobacco;
establishing an LSTM prediction model by respectively constructing prediction models for various factors in the first historical data set based on the first historical data set and adopting a mode of multi-time point input to multi-time point output, wherein the various factors are air temperature, precipitation, sunshine hours and surface moisture content indexes;
inputting the second prediction data set into an LSTM prediction model for calculation to obtain the predicted values of all factors of R days after the current time node, calculating the first accumulated value of all factors between the seeding time of the current year and the prediction time node of the last day according to the predicted values of all factors, comparing and analyzing the first accumulated value with an evaluation standard to obtain first prediction time and second prediction time, and obtaining the prediction result of the optimal transplanting period of the tobacco in the tobacco field to be tested by taking the first prediction time as a starting point and the second prediction time as an end point, wherein R is a natural number.
Preferably, the first pretreatment specifically comprises:
sequentially carrying out temporal screening, spatial screening and cutting, cloud removing processing and abnormal value removal on the remote sensing image data to obtain processed remote sensing image data;
calculating a surface moisture content index based on the processed remote sensing image data to obtain SCWI time sequence data, and performing time sequence reconstruction on the SCWI time sequence data by using an S-G filtering algorithm to obtain space-time continuous SCWI data, wherein the calculation formula of the surface moisture content index is
Wherein SCWI is a surface moisture content index, and b11 and b12 respectively correspond to the reflectivities of the 11 th wave band and the 12 th wave band of the Sentinel-2;
the method comprises the steps of dividing meteorological DATA and space-time continuous SCWI DATA according to N-1 years and N years to obtain meteorological DATA, surface moisture content indexes of the N-1 years, meteorological DATA and surface moisture content indexes of the N years respectively, combining the DATA of the N-1 years to obtain a DATA set DATA1, carrying out Kriging interpolation processing on the meteorological DATA of the N years in space and combining the surface moisture content indexes of the N years to obtain a DATA set DATA2, wherein N is the current year, N-1 is the past year, the DATA set DATA1 is a first historical DATA set, the DATA set DATA2 is a second prediction DATA set, and the meteorological DATA comprise air temperature, precipitation and sunshine hours.
Preferably, the second pretreatment specifically comprises:
sequentially calculating the accumulated values of various factors in a first time interval of each year by using the intercepted first historical data set, and summarizing to obtain a second accumulated value;
respectively carrying out summary statistics on the second accumulated values according to the types of the factors to obtain confidence intervals of the accumulated values of the factors;
carrying out superposition analysis on the confidence intervals of the accumulated values of the factors to obtain an intersection in time;
and obtaining the accumulated value range of each factor based on the intersection in time so as to establish the evaluation standard of the optimal transplanting period of the tobacco.
Preferably, the calculation formula in the second preprocessing process is
Wherein Ax represents the cumulative value set of each site in ts to te time in each year in the past N-1 years before x factor, N is the current year, N-1 is the past year, ts is the sowing time, te is the most suitable transplanting period, and>
represents the value of the x factor at day t, y represents the y year in the previous N-1 year, i represents the ith weather station, </or >>
And &>
Respectively representing the mean value and standard deviation of the x factor cumulative value, bAx and pAx respectively representing the lower limit and the upper limit of the confidence interval of the x factor cumulative value, T bAx And T pAx Respectively representing the time corresponding to the lower limit and the upper limit of the confidence interval of the accumulated value of each factor, at is the air temperature, pr is the precipitation, su is the sunshine duration, wa is the surface moisture content index, T b And Tp is the intersection of the upper and lower time limits, and the x factor is one of the factors.
Preferably, the first historical data set is divided into a training data set and a testing data set, and the training data set and the testing data set are respectively used for constructing and checking the LSTM prediction model.
Preferably, the first accumulated value is compared with the evaluation criterion to obtain a first predicted time and a second predicted time, specifically:
comparing the first accumulated value with the evaluation standard, recording a first time point when the first accumulated values are all within the range of the evaluation standard, and recording a second time point when the first accumulated value of any factor is greater than the upper limit of the evaluation standard;
and obtaining a first predicted time and a second predicted time based on the first time point and the second time point.
Preferably, the first accumulated value of each factor is obtained by daily superposition of the accumulated value of each factor of the current time node and the predicted value of each factor of R consecutive days.
A device for predicting the optimal transplanting period of tobacco comprises:
a data set partitioning module: the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring meteorological data and remote sensing image data of a tobacco field to be detected and performing first preprocessing to obtain a first historical data set and a second prediction data set which are divided according to time attributes;
an evaluation standard establishing module: the method comprises the steps of obtaining the past annual sowing time and the most suitable transplanting period of tobacco in a tobacco field to be tested to obtain a first time interval, intercepting a first historical data set based on the first time interval and carrying out second pretreatment to obtain an evaluation standard of the most suitable transplanting period of the tobacco;
a prediction model construction module: the method comprises the steps of establishing a prediction model for each factor in a first historical data set based on the first historical data set by adopting a multi-time point input and multi-time point output mode, and establishing an LSTM prediction model, wherein each factor is air temperature, precipitation, sunshine hours and surface moisture content index;
the most suitable transplanting period calculation module: and inputting the second prediction data set into an LSTM prediction model for calculation to obtain the predicted values of all factors of R days after the current time node, calculating the first accumulated value of all factors between the seeding period of the current year and the prediction time node of the last day according to the predicted values of all factors, comparing and analyzing the first accumulated value with an evaluation standard to obtain a first prediction time and a second prediction time, and obtaining the prediction result of the optimal transplanting period of the tobacco in the tobacco field to be tested by taking the first prediction time as a starting point and the second prediction time as an end point, wherein R is a natural number.
An electronic device comprising a memory and a processor, the memory for storing one or more computer instructions, wherein the one or more computer instructions are executable by the processor to implement a method of predicting an optimal transplanting period for tobacco as described in any one of the above.
A computer readable storage medium storing a computer program which, when executed by a computer, implements a method of predicting an optimal transplanting period for tobacco as described in any one of the above.
The invention has the following beneficial effects:
(1) The 11 and 12 wave bands of the Sentinel-2 data used in the scheme have 20m spatial resolution, the plot scale of an area-level small-scale range can be achieved by interpolating the meteorological site data, more refined prediction is realized, and a transplanting period prediction result with high spatial resolution and spatial continuous distribution can be generated;
(2) According to the scheme, a large number of related researches are referred, a plurality of factors (temperature, rainfall, sunshine hours and surface layer moisture content indexes) related to the tobacco transplanting period are screened, and the transplanting period of the tobacco is comprehensively predicted by adopting multiple factors, so that the result is considered more comprehensively and reliably;
(3) In the aspect of evaluation criteria suitable for the transplanting period, the final most suitable transplanting period judgment criteria is determined by using a mode of superposition of accumulated values of multiple factors from the sowing period to the most suitable transplanting period, and compared with the existing mode of determining by adopting a single or multiple factor value threshold value, the method effectively improves the judgment accuracy and the anti-interference capability;
(4) The method uses the perennial time sequence data and adopts an LSTM model to capture the stable information of the perennial change process of multiple factors during the period from the sowing to the transplanting of the tobacco, thereby more accurately realizing the prediction of the factors, reducing the interference of uncontrollable accidental factors and enhancing the prediction accuracy of the most suitable transplanting period.
Drawings
FIG. 1 is a flow chart of a method for predicting the optimal transplanting period of tobacco in the present invention;
FIG. 2 is a diagram showing the concept of the embodiment of the present invention in example 1;
FIG. 3 is a schematic diagram of time-series reconstruction in embodiment 1 of the present invention;
FIG. 4 is a schematic view showing a process for determining the optimum transplanting period of tobacco in example 1 of the present invention;
FIG. 5 is a schematic structural diagram of a device for predicting the optimal transplanting period of tobacco in the present invention.
Detailed Description
Example 1
As shown in fig. 1, a method for predicting the optimal transplanting period of tobacco comprises the following steps:
s11, acquiring meteorological data and remote sensing image data of a tobacco field to be detected, and performing first preprocessing to obtain a first historical data set and a second prediction data set which are divided according to time attributes;
s12, obtaining the past annual seeding time and the most suitable transplanting period of tobacco in a tobacco field to be tested to obtain a first time interval, intercepting a first historical data set based on the first time interval and carrying out second pretreatment to obtain an evaluation standard of the most suitable transplanting period of the tobacco;
s13, constructing prediction models for various factors in the first historical data set respectively based on the first historical data set and by adopting a mode of multi-time point input and multi-time point output, and establishing an LSTM prediction model, wherein the various factors are air temperature, precipitation, sunshine hours and surface moisture content indexes respectively;
s14, inputting the second prediction data set into an LSTM prediction model for calculation to obtain predicted values of all factors of R days after the current time node, calculating a first accumulated value of all factors between the current year sowing period and the last day prediction time node according to the predicted values of all factors, comparing and analyzing the first accumulated value with an evaluation standard to obtain a first prediction time and a second prediction time, and obtaining a prediction result of the optimal tobacco transplanting period in the tobacco field to be tested by taking the first prediction time as a starting point and the second prediction time as an end point, wherein R is a natural number.
In the scheme of the embodiment, a multi-factor data set for predicting the tobacco transplanting period is constructed by combining the sentinel-2 remote sensing image and various meteorological data, an optimum transplanting period judgment standard is determined by combining data such as historical records and the like in a multi-factor accumulated value superposition mode, and various factors are predicted through an LSTM model, so that the dynamic prediction of the optimum transplanting period of the tobacco is realized. The thinking guide diagram is shown in fig. 2, and the specific flow is as follows:
1. data acquisition and processing
1.1 Meteorological data
The meteorological data is derived from official meteorological site data (the number of meteorological sites is multiple) of the China meteorological office, and the meteorological data comprises day-by-day air temperature, precipitation and sunshine duration data.
1.2sentinel-2
Sentinel-2 is a multispectral imaging satellite and is divided into two satellites 2A and 2B, wherein 2A is launched and lifted off by a carrier rocket of 'ladies' at 23.01.6.2015 at 52 UTC, and 2B is launched and lifted off by a carrier rocket of 'ladies' at 9.49 times of beijing at 07.3.3.2017 at 49. The revisit period of one satellite is 10 days, the two satellites are complementary, and the revisit period is 5 days. The Sentinel-2 satellite carries a multi-spectral instrument (MSI) which can cover 13 spectral bands from visible light to short-wave infrared, and the ground resolution is 10m, 20m and 60m respectively. According to the scheme, a Level-2A product is selected as one of basic data of subsequent work, and the product is atmospheric bottom layer reflectivity data corrected by atmosphere.
In order to reduce the data processing time to the maximum extent and improve the working efficiency. According to the scheme, the GEE (Google earth engine) remote sensing cloud computing platform is used for finishing the data acquisition and processing work. In the aspect of data acquisition, firstly, sentinel-2 L2A data of each year is temporally screened by a specific time range (described later), then, the data is spatially screened and cut by using vector data of a research area range, then, a cloud mask is constructed by using a QA60 band of an image, and the image is subjected to cloud removal. Related researches prove that the surface moisture content index (SCWI) is sensitive to soil moisture change, the scheme adopts SCWI to describe the tobacco field moisture content, and the calculation formula 1 is as follows
Wherein SCWI is the surface moisture content index, and b11 and b12 correspond to the reflectivities of the 11 th and 12 th bands of Sentinel-2, respectively.
In order to avoid the interference of the preprocessed null value area on the integrity expression of the SCWI time sequence data, the scheme carries out time sequence reconstruction processing on the calculated SCWI time sequence data through S-G filtering. The time series reconstruction diagram is shown in fig. 3, in which the square data points represent the original SCWI values (i.e. the calculated SCWI time series data), and the circular data points represent the reconstructed SCWI values, which are continuous after reconstruction. The S-G filtering is an algorithm which is firstly proposed by Savizky and Golay and then widely applied to reconstruction of time sequence data, and the value of the time to be reconstructed is obtained by setting the size of a time window with a certain length and carrying out weighted average on the value in the window in a sliding window mode. The basic formula is shown in formula 2:
wherein,
represents the fitted value, which represents the ith time SCWI>
Representing the original value of SCWI at the i + j moment, where N is the window size and satisfies N =2m +1; />
The values of the coefficients representing the S-G polynomial fit depend on the degree of least squares fit of a given higher order polynomial within a filter window.
In a specific reconstruction process, only the data missing position is obtained through a mask mode, then time sequence reconstruction is carried out, interference on original data values of other positions is reduced as much as possible, and annual space-time continuous SCWI data are obtained after processing.
1.3 data integration
All data is divided into two parts (previous N-1 year and current year N) according to the time attribute. For the DATA of the previous N-1 years, firstly, the spatial position information of a station (station number M) is utilized, the surface layer moisture content index value of the station position is obtained by combining the surface layer moisture content index DATA, and then the air temperature, precipitation and sunshine hours DATA of the station position are combined to form a DATA set DATA1 (namely a first historical DATA set) together, the DATA expression form of the DATA set DATA1 is shown in the table 1, and the DATA are mainly used for training prediction models of the air temperature, precipitation, sunshine hours and surface layer moisture content index factors (air temperature: at; precipitation: pr; sunshine hours: su; surface layer moisture content index: wa) and establishing an evaluation standard of the optimal transplanting period by combining the DATA of the historical transplanting period. For the DATA of the N year, kriging (Kriging) interpolation is carried out on the air temperature, precipitation and sunshine duration DATA of a meteorological site in space, the grid of the interpolation is captured to a grid layer of a surface moisture content index, and the grid of the surface moisture content index is sampled to be consistent in spatial resolution, the DATA set DATA2 (namely a second prediction DATA set) is formed by the DATA set DATA1, the representation form of the DATA set is the same as that of the DATA set DATA1, the DATA set is continuous in space only due to interpolation, the DATA set is used for predicting various factors in an unknown time period of the N year, and the optimum transplanting period is determined by combining the prediction result and an evaluation standard of the optimum transplanting period.
TABLE 1 data integration schematic table of various factors
| Site | Site location | Year of year | Tian (t) | Air temperature | Precipitation | Sunshine hours | Surface moisture content index |
| D1 | (Lon1, Lat1) | 1 | t1 | at1 | pr1 | su1 | wa1 |
| D1 | (Lon1, Lat1) | 1 | t2 | at2 | pr2 | su2 | wa2 |
| D1 | (Lon1, Lat1) | 1 | … | … | … | … | … |
| D1 | (Lon1, Lat1) | 2 | … | … | … | … | |
| D1 | (Lon1, Lat1) | 2 | … | … | … | … | |
| D1 | (Lon1, Lat1) | 2 | … | … | … | … | |
| D1 | (Lon1, Lat1) | … | … | … | … | … | |
| D1 | (Lon1, Lat1) | N-1 | … | … | … | … | |
| D1 | (Lon1, Lat1) | N-1 | |||||
| D1 | (Lon1, Lat1) | N-1 | |||||
| D2 | (Lon2, Lat2) | 1 | … | … | … | … | … |
| D2 | (Lon2, Lat2) | 1 | … | … | … | … | … |
| D2 | (Lon2, Lat2) | 1 | … | … | … | … | … |
| D2 | (Lon2, Lat2) | 2 | … | … | … | … | … |
| D2 | (Lon2, Lat2) | 2 | … | … | … | … | … |
| D2 | (Lon2, Lat2) | 2 | … | … | … | … | … |
| D2 | (Lon2, Lat2) | … | … | … | … | … | … |
| D2 | (Lon2, Lat2) | N-1 | … | … | … | … | … |
| D2 | (Lon2, Lat2) | N-1 | … | … | … | … | … |
| D2 | (Lon2, Lat2) | N-1 | … | … | … | … | … |
| … | … | … | … | … | … | … | … |
| DM | (LonM, LatM) | 1 | … | … | … | … | … |
| DM | (LonM, LatM) | 1 | … | … | … | … | … |
| DM | (LonM, LatM) | 1 | … | … | … | … | … |
| DM | (LonM, LatM) | 2 | … | … | … | … | … |
| DM | (LonM, LatM) | 2 | … | … | … | … | … |
| DM | (LonM, LatM) | 2 | … | … | … | … | … |
| DM | (LonM, LatM) | … | … | … | … | … | … |
| DM | (LonM, LatM) | N-1 | … | … | … | … | … |
| DM | (LonM, LatM) | N-1 | … | … | … | … | … |
| DM | (LonM, LatM) | N-1 | … | … | … | … | … |
The schemes 1.2 and 1.3 are specific processes of the first pretreatment.
2. Evaluation standard of optimum transplanting period (for different tobacco and tobacco field vector range)
The accumulated value of each factor between the sowing period and the optimum transplanting period is used as the evaluation standard of the optimum transplanting period.
According to historical record DATA and relevant literature DATA, in the previous N-1 year, the sowing time ts and the optimum transplanting period te of a certain tobacco C in each year are obtained, a DATA set DATA1 in the time range of the year is intercepted by using the time range from ts to te (namely, a first time interval), and then the accumulated value of each factor in the time range from ts to te in each year is calculated by using the intercepted DATA1 DATA; the same method calculates the accumulated value of each factor of all the previous N-1 years, namely the second accumulated value, and the calculation process is shown as formula 3; then, respectively carrying out summary statistics on the accumulated values of all factors of all weather stations in all years to obtain confidence intervals of the accumulated values of all factors, wherein the calculation process is shown as a formula 4; then further acquiring the intersection of the confidence intervals of the accumulated values of the factors in time, wherein the calculation process is shown as a formula 5; and finally, obtaining the accumulated value range of each factor corresponding to the time intersection as the evaluation standard of the most suitable transplanting period of the tobacco of the variety, wherein the calculation process is shown as a formula 6. Fig. 4 visually shows the determination process of the optimum transplanting period, which is an exemplary diagram of any factor in the factors, that is, the optimal transplanting time of a single factor is determined by finding the range from the maximum cumulative value to the minimum cumulative value (the range is the confidence interval of the factor), then all the factors are repeated to obtain the optimal transplanting time of each factor, and then the intersection of all the optimal transplanting times is taken to obtain the evaluation criterion of the optimum transplanting period.
Wherein Ax represents the cumulative value set of sites in ts to te time in each year in the past year N-1 years before x factor, N is the current year, N-1 is the past year, ts isThe sowing time, te is the optimum transplanting period,
represents the value of the x factor at day t, y represents the y year in the previous N-1 year, i represents the ith weather station, </or >>
And &>
Respectively representing the mean value and standard deviation of the x factor cumulative value, bAx and pAx respectively representing the lower limit and the upper limit of the confidence interval of the x factor cumulative value, T bAx And T pAx Respectively representing the time corresponding to the lower limit and the upper limit of the confidence interval of the accumulated value of each factor, at is the air temperature, pr is the precipitation, su is the sunshine duration, wa is the surface moisture content index, T b And Tp is the intersection of the upper and lower time limits, and the x factor is one of the factors.
The above-mentioned process of processing the DATA set DATA1 (first history DATA set) to obtain the evaluation criterion of the optimum transplanting period of tobacco is a specific process of the second pretreatment, and the above-mentioned formulas 3, 4, 5, and 6 are calculation formulas used for calculation in the second pretreatment process.
3. LSTM prediction model
The LSTM is an excellent time series prediction model derived on the basis of a traditional Recurrent Neural Network (RNN), the problems of gradient disappearance, long-term dependence and the like existing when the RNN processes data are solved, the change rule of the data can be well grasped in processing data such as meteorological factors of long-term sequences, and a more accurate prediction result is given.
The construction of the LSTM prediction model of the four factors related by the scheme is mainly carried out in four steps: (1) The DATA1 DATA set in 1.3 is further sorted into an input DATA set and divided into a training DATA set DATA1_ Train and a Test DATA set DATA1_ Test; (2) Constructing an LSTM network model, and confirming parameters and targets required in model training and prediction; (3) Training the model by using the training data, and establishing a prediction model of each factor; and (4) testing the model by using the test data set.
In order to predict the DATA of each factor day by day, the scheme adopts a mode of inputting multiple time points and outputting multiple time points to respectively construct models for different factors, DATA1_ Train time sequence numbers containing each factor are respectively arranged into m groups of input sequence DATA and input DATA are standardized, DATA with fixed length in front of each group of DATA are used as input parts of a network, and DATA of time points needing prediction are used as output values of the model theory. The double-layer LSTM and Dense full-connection layers are combined together to form a hidden layer, so that the influence of large-range dynamics of data is weakened as much as possible. Because the models of various factors are trained respectively in the scheme, the input and output feature dimensions of the prediction model of each factor are both 1. The learning rate is adjusted in fine after the magnitude is confirmed from the change of the loss value (loss) during the period from 0.1 to 0.000001. The number of training is determined according to the convergence of the loss value with the increase of the number of training. The number of nodes of the hidden layer is then determined according to empirical formula 7 derived from prior studies.
Wherein,
that is, the number of hidden layer nodes, where α and β are the number of input and output layer nodes, respectively>
Taking an integer between 0 and 9, and finding the corresponding ^ or/and/or the corresponding maximum RMSE by using a traversal optimization method>
The value is obtained.
And in the process of training data, continuously updating the weight of the network model by using the determined parameters and the gradient descent algorithm to obtain a hidden layer network. And finally, predicting the Test DATA set DATA1_ Test by using the trained network, standardizing, outputting a predicted value of a predicted time point, comparing with an actual value, and checking the effect of the model.
4. Optimum spatial distribution in the transplanting period
Using DATA set DATA2 (second prediction DATA set) as input DATA of the LSTM prediction model trained in section 3, predicting values of each factor for R consecutive days after the current time node, then calculating the cumulative value Ax (i.e. first cumulative value) of each factor between the seeding time of the year (nth year) and the predicted time node of the last day, comparing the first cumulative value Ax with the range of the cumulative value of each factor for the optimal transplanting period obtained in section 2 (i.e. evaluation criterion), and obtaining two prediction days R1 and R2, R2> R1 under the condition that all values of Ax are within the range shown in formula 6 and one value of Ax is greater than the upper limit of formula 6, the optimal transplanting period is closer to the current date within the days R1 to R2 from the beginning of the current date, and the prediction result is more accurate.
The process is as follows: comparing the first cumulative value with the evaluation standard, recording a first time point when the first cumulative value is within the range of the evaluation standard, and recording a second time point when the first cumulative value of any factor is greater than the upper limit of the evaluation standard; the first time point is R1, and the second time point is R2;
and obtaining a first predicted time and a second predicted time based on the first time point and the second time point. The first predicted time is the current date plus the first time point R1, and the second predicted time is the current date plus the second time point R2.
The R day is an uncertain time, the last day predicted time node is a pronoun, which means when the accumulated value Ax meets the above two conditions, and when the accumulated value Ax is the last day, that is, the time reaching the transplanting date standard is determined according to the values of various factors predicting the future.
The first accumulated value of each factor is obtained by sequentially overlapping from the predicted time node, so that when the two conditions are met in the overlapping process of the accumulated values, two time points appear, and the optimal transplanting date is calculated.
Example 2
As shown in fig. 5, an apparatus for predicting an optimal transplanting period of tobacco includes:
data set partitioning module 10: the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring meteorological data and remote sensing image data of a tobacco field to be detected and performing first preprocessing to obtain a first historical data set and a second prediction data set which are divided according to time attributes;
evaluation criterion establishing module 20: the method comprises the steps of obtaining the past annual sowing time and the most suitable transplanting period of tobacco in a tobacco field to be tested to obtain a first time interval, intercepting a first historical data set based on the first time interval and carrying out second pretreatment to obtain an evaluation standard of the most suitable transplanting period of the tobacco;
prediction model construction module 30: the method comprises the steps of establishing an LSTM prediction model by respectively constructing prediction models for various factors in a first historical data set based on the first historical data set and adopting a mode of multi-time point input and multi-time point output, wherein the various factors are air temperature, precipitation, sunshine hours and surface moisture content indexes;
the most suitable transplanting period calculating module 40: and inputting the second prediction data set into an LSTM prediction model for calculation to obtain the predicted values of all factors of R days after the current time node, calculating the first accumulated value of all factors between the current year sowing period and the last day prediction time node according to the predicted values of all factors, comparing and analyzing the first accumulated value with an evaluation standard to obtain first prediction time and second prediction time, and obtaining the prediction result of the optimal tobacco transplanting period in the tobacco field to be tested by taking the first prediction time as a starting point and the second prediction time as an end point, wherein R is a natural number.
One embodiment of the above device is that in the data set dividing module 10, the meteorological data and the remote sensing image data of the tobacco field to be measured are obtained and are subjected to first preprocessing, a first historical data set and a second prediction data set which are divided according to time attributes are obtained, in the evaluation criterion establishing module 20, the seeding time and the most suitable transplanting period of the tobacco in the tobacco field to be measured in the past each year are obtained, a first time interval is obtained, the first historical data set is intercepted and subjected to second preprocessing based on the first time interval, the evaluation criterion of the most suitable transplanting period of the tobacco is obtained, in the prediction model establishing module 30, the prediction models are respectively established for each factor in the first historical data set based on the first historical data set and by adopting a multi-time-point input and multi-time-point output mode, establishing an LSTM prediction model, wherein each factor is air temperature, rainfall, sunshine hours and surface moisture content index, inputting a second prediction data set into the LSTM prediction model in an optimum transplanting period calculation module 40 for calculation to obtain a prediction value of each factor of R days after the current time node, calculating a first accumulation value of each factor between the current annual sowing period and the last day prediction time node according to the prediction value of each factor, comparing and analyzing the first accumulation value with an evaluation standard to obtain a first prediction time and a second prediction time, and obtaining a prediction result of the optimum transplanting period of the tobacco in the tobacco field to be tested by taking the first prediction time as a starting point and the second prediction time as an end point, wherein R is a natural number.
Example 3
On the basis of the above embodiments, the present embodiment provides an electronic device.
Example 4
On the basis of the above embodiments, the present embodiment provides a storage medium.
The above description is only an embodiment of the present invention, but the technical features of the present invention are not limited thereto, and any changes or modifications within the technical field of the present invention by those skilled in the art are covered by the claims of the present invention.
Claims (10)
1. A method for predicting the optimal transplanting period of tobacco is characterized by comprising the following steps:
acquiring meteorological data and remote sensing image data of a tobacco field to be detected, and performing first preprocessing to obtain a first historical data set and a second prediction data set which are divided according to time attributes;
acquiring the past annual sowing time and the optimum transplanting period of tobacco in a tobacco field to be detected to obtain a first time interval, intercepting a first historical data set based on the first time interval and carrying out second pretreatment to obtain an evaluation standard of the optimum transplanting period of the tobacco;
establishing an LSTM prediction model by respectively constructing prediction models for various factors in the first historical data set based on the first historical data set and adopting a mode of multi-time point input to multi-time point output, wherein the various factors are air temperature, precipitation, sunshine hours and surface moisture content indexes;
inputting the second prediction data set into an LSTM prediction model for calculation to obtain the predicted values of all factors of R days after the current time node, calculating the first accumulated value of all factors between the seeding time of the current year and the prediction time node of the last day according to the predicted values of all factors, comparing and analyzing the first accumulated value with an evaluation standard to obtain first prediction time and second prediction time, and obtaining the prediction result of the optimal transplanting period of the tobacco in the tobacco field to be tested by taking the first prediction time as a starting point and the second prediction time as an end point, wherein R is a natural number.
2. The method for predicting the optimal transplanting period of tobacco according to claim 1, wherein the first pretreatment specifically comprises:
sequentially carrying out temporal screening, spatial screening and cutting, cloud removing processing and abnormal value removal on the remote sensing image data to obtain processed remote sensing image data;
calculating a surface moisture content index based on the processed remote sensing image data to obtain SCWI time sequence data, and performing time sequence reconstruction on the SCWI time sequence data by using an S-G filtering algorithm to obtain space-time continuous SCWI data, wherein the calculation formula of the surface moisture content index is
Wherein SCWI is a surface moisture content index, and b11 and b12 respectively correspond to the reflectivities of the 11 th wave band and the 12 th wave band of the Sentinel-2;
dividing meteorological DATA and space-time continuous SCWI DATA according to N-1 year and N year to respectively obtain meteorological DATA, surface moisture content index, meteorological DATA of N year and surface moisture content index of N year, combining the DATA of N-1 year to obtain a DATA set DATA1, carrying out Kergin interpolation processing on the meteorological DATA of N year in space and combining the surface moisture content index of N year to obtain a DATA set DATA2, wherein N is the current year, N-1 is the past year, the DATA set DATA1 is a first historical DATA set, the DATA set DATA2 is a second prediction DATA set, and the meteorological DATA comprises air temperature, precipitation and sunshine hours.
3. The method for predicting the optimal transplanting period of tobacco according to claim 1, wherein the second pretreatment comprises:
sequentially calculating the accumulated values of various factors in a first time interval of each year by using the intercepted first historical data set, and summarizing to obtain a second accumulated value;
respectively carrying out summary statistics on the second accumulated values according to the types of the factors to obtain confidence intervals of the accumulated values of the factors;
carrying out superposition analysis on the confidence intervals of the accumulated values of the factors to obtain an intersection in time;
and obtaining the accumulated value range of each factor based on the intersection in time so as to establish the evaluation standard of the optimal transplanting period of the tobacco.
4. The method for predicting the optimal transplanting period of tobacco as claimed in claim 3, wherein the calculation formula in the second preprocessing process is
Wherein Ax represents the accumulated value set of the sites in ts to te time in N-1 years before x factor, namely in the past year, N is the current year, N-1 is the past year, ts is the sowing time, te is the optimum transplanting period, and>
represents the value of the x factor at day t, y represents the y year in the previous N-1 year, i represents the ith weather station, </or >>
And &>
Respectively representing the mean value and standard deviation of the x factor cumulative value, bAx and pAx respectively representing the lower limit and the upper limit of the confidence interval of the x factor cumulative value, T bAx And T pAx Respectively representing the time corresponding to the lower limit and the upper limit of the confidence interval of the accumulated value of each factor, at is the air temperature, pr is the precipitation, su is the sunshine duration, wa is the surface moisture content index, T b And Tp is the intersection of the upper and lower time limits, and the x factor is one of the factors.
5. The method of claim 1, wherein the first historical data set is divided into a training data set and a testing data set, and the training data set and the testing data set are respectively used for constructing and testing an LSTM prediction model.
6. The method for predicting the optimal transplanting period of tobacco as claimed in claim 1, wherein the first accumulated value is compared with the evaluation criterion to obtain a first predicted time and a second predicted time, and the method comprises:
comparing the first accumulated value with the evaluation standard, recording a first time point when the first accumulated values are all within the range of the evaluation standard, and recording a second time point when the first accumulated value of any factor is greater than the upper limit of the evaluation standard;
and obtaining a first predicted time and a second predicted time based on the first time point and the second time point.
7. The method of claim 6, wherein the first cumulative value of each factor is obtained by daily overlapping the cumulative value of each factor at the current time node with the predicted value of each factor for R consecutive days.
8. A prediction device for an optimal tobacco transplanting period is characterized by comprising:
a data set partitioning module: the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring meteorological data and remote sensing image data of a tobacco field to be detected and performing first preprocessing to obtain a first historical data set and a second prediction data set which are divided according to time attributes;
an evaluation standard establishing module: the method comprises the steps of obtaining the past annual sowing time and the most suitable transplanting period of tobacco in a tobacco field to be tested to obtain a first time interval, intercepting a first historical data set based on the first time interval and carrying out second pretreatment to obtain an evaluation standard of the most suitable transplanting period of the tobacco;
a prediction model construction module: the method comprises the steps of establishing an LSTM prediction model by respectively constructing prediction models for various factors in a first historical data set based on the first historical data set and adopting a mode of multi-time point input and multi-time point output, wherein the various factors are air temperature, precipitation, sunshine hours and surface moisture content indexes;
the most suitable transplanting period calculation module: and inputting the second prediction data set into an LSTM prediction model for calculation to obtain the predicted values of all factors of R days after the current time node, calculating the first accumulated value of all factors between the seeding period of the current year and the prediction time node of the last day according to the predicted values of all factors, comparing and analyzing the first accumulated value with an evaluation standard to obtain a first prediction time and a second prediction time, and obtaining the prediction result of the optimal transplanting period of the tobacco in the tobacco field to be tested by taking the first prediction time as a starting point and the second prediction time as an end point, wherein R is a natural number.
9. An electronic device, comprising a memory and a processor, wherein the memory is configured to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method for predicting an optimal transplanting period of tobacco as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a computer, implements a method for predicting an optimal transplanting period of tobacco according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310183279.0A CN115860285B (en) | 2023-03-01 | 2023-03-01 | Prediction method and device for optimal transplanting period of tobacco |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310183279.0A CN115860285B (en) | 2023-03-01 | 2023-03-01 | Prediction method and device for optimal transplanting period of tobacco |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115860285A true CN115860285A (en) | 2023-03-28 |
| CN115860285B CN115860285B (en) | 2023-10-31 |
Family
ID=85659488
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310183279.0A Active CN115860285B (en) | 2023-03-01 | 2023-03-01 | Prediction method and device for optimal transplanting period of tobacco |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115860285B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117313993A (en) * | 2023-09-15 | 2023-12-29 | 湖南省烟草公司湘西自治州公司 | Flue-cured tobacco cultivation management method based on temperature and altitude |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104851048A (en) * | 2015-05-28 | 2015-08-19 | 四川农业大学 | Method for determining spatial distribution of suitable transplanting period of flue-cured tobacco in complicated hilly area |
| CN108564309A (en) * | 2018-05-07 | 2018-09-21 | 江西省农业科学院农业经济与信息研究所（江西省农业工程咨询中心、江西省农业科技图书馆） | A kind of Weather Risk appraisal procedure of tobacco leaf planting |
| CN110150078A (en) * | 2019-05-27 | 2019-08-23 | 福建中烟工业有限责任公司 | A kind of method and system on determining northwestern Fujian tobacco transplant date |
| CN111275569A (en) * | 2020-03-13 | 2020-06-12 | 中国农业科学院烟草研究所 | Method and system for determining ecological characteristics of flue-cured tobacco producing area, storage medium and terminal |
| CN111837863A (en) * | 2020-07-28 | 2020-10-30 | 福建中烟工业有限责任公司 | Transplanting period-based cultivation method and system for Fujian fresh, sweet and fragrant high-quality tobacco leaves |
| CN112749627A (en) * | 2020-12-09 | 2021-05-04 | 北京星衡科技有限公司 | Method and device for dynamically monitoring tobacco based on multi-source remote sensing image |
| WO2021180925A1 (en) * | 2020-03-13 | 2021-09-16 | Basf Agro Trademarks Gmbh | Method and system for determining a plant protection treatment plan of an agricultural plant |
| CN114186423A (en) * | 2021-12-14 | 2022-03-15 | 湖北省烟草科学研究院 | Method and system for predicting and evaluating suitable planting area of cigar smoking product |
| CN115376006A (en) * | 2022-08-10 | 2022-11-22 | 中联智慧农业股份有限公司 | Method, storage medium, and processor for predicting crop harvest date |
| CN115545305A (en) * | 2022-10-08 | 2022-12-30 | 中化现代农业有限公司 | Crop transplanting period time prediction method and system |
| CN115688997A (en) * | 2022-10-21 | 2023-02-03 | 浙江领见数智科技有限公司 | Accumulated temperature-based tea leaf picking period prediction method and system |
-
2023
- 2023-03-01 CN CN202310183279.0A patent/CN115860285B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104851048A (en) * | 2015-05-28 | 2015-08-19 | 四川农业大学 | Method for determining spatial distribution of suitable transplanting period of flue-cured tobacco in complicated hilly area |
| CN108564309A (en) * | 2018-05-07 | 2018-09-21 | 江西省农业科学院农业经济与信息研究所（江西省农业工程咨询中心、江西省农业科技图书馆） | A kind of Weather Risk appraisal procedure of tobacco leaf planting |
| CN110150078A (en) * | 2019-05-27 | 2019-08-23 | 福建中烟工业有限责任公司 | A kind of method and system on determining northwestern Fujian tobacco transplant date |
| CN111275569A (en) * | 2020-03-13 | 2020-06-12 | 中国农业科学院烟草研究所 | Method and system for determining ecological characteristics of flue-cured tobacco producing area, storage medium and terminal |
| WO2021180925A1 (en) * | 2020-03-13 | 2021-09-16 | Basf Agro Trademarks Gmbh | Method and system for determining a plant protection treatment plan of an agricultural plant |
| CN111837863A (en) * | 2020-07-28 | 2020-10-30 | 福建中烟工业有限责任公司 | Transplanting period-based cultivation method and system for Fujian fresh, sweet and fragrant high-quality tobacco leaves |
| CN112749627A (en) * | 2020-12-09 | 2021-05-04 | 北京星衡科技有限公司 | Method and device for dynamically monitoring tobacco based on multi-source remote sensing image |
| CN114186423A (en) * | 2021-12-14 | 2022-03-15 | 湖北省烟草科学研究院 | Method and system for predicting and evaluating suitable planting area of cigar smoking product |
| CN115376006A (en) * | 2022-08-10 | 2022-11-22 | 中联智慧农业股份有限公司 | Method, storage medium, and processor for predicting crop harvest date |
| CN115545305A (en) * | 2022-10-08 | 2022-12-30 | 中化现代农业有限公司 | Crop transplanting period time prediction method and system |
| CN115688997A (en) * | 2022-10-21 | 2023-02-03 | 浙江领见数智科技有限公司 | Accumulated temperature-based tea leaf picking period prediction method and system |
Non-Patent Citations (2)
| Title |
|---|
| 冉法芬;裴洲洋;朱启法;刘国侠;: "皖南烟区不同移栽期气象因子与农艺性状的关系分析", 安徽农学通报, no. 02 * |
| 杨亚;朱列书;朱静娴;杨威;冯连军;刘伟;邓亚飞;: "移栽期对烤烟生长发育及品质的影响", 作物研究, no. 02 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117313993A (en) * | 2023-09-15 | 2023-12-29 | 湖南省烟草公司湘西自治州公司 | Flue-cured tobacco cultivation management method based on temperature and altitude |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115860285B (en) | 2023-10-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110751094B (en) | Crop yield estimation method based on GEE comprehensive remote sensing image and deep learning method | |
| CN108921885B (en) | Method for jointly inverting forest aboveground biomass by integrating three types of data sources | |
| CN111727443B (en) | Soil available nutrient inversion method based on deep neural network | |
| CN109711102B (en) | Method for rapidly evaluating crop disaster loss | |
| CN111738066B (en) | Grid late rice sheath blight disease habitat evaluation method integrating multisource remote sensing information | |
| CN110633841B (en) | Provincial range plot scale data assimilation yield prediction method based on set sampling | |
| CN109800921B (en) | Regional winter wheat yield estimation method based on remote sensing phenological assimilation and particle swarm optimization | |
| CN102651096A (en) | Method for estimating yield of winter wheat by assimilating characteristics of leaf area index time-sequence curve | |
| CN109657988B (en) | Tobacco leaf quality partitioning method based on HASM and Euclidean distance algorithm | |
| CN114062439A (en) | Method for jointly estimating salinity of soil profile by using time series remote sensing images | |
| CN104143043B (en) | A kind of Multifunctional climate data capture method | |
| CN113222242A (en) | Forest fire danger grade forecasting method and device, computer equipment and storage medium | |
| CN115860285B (en) | Prediction method and device for optimal transplanting period of tobacco | |
| CN114120137A (en) | Wetland element space-time evolution monitoring method based on time sequence main remote sensing image | |
| CN115018105A (en) | Winter wheat meteorological yield prediction method and system | |
| CN118072178B (en) | Corn yield estimation method and system based on classified percentage data assimilation | |
| CN117556695B (en) | Crop root soil water content simulation method based on deep learning | |
| Bhanose et al. | Crop and yield prediction model | |
| CN118364975A (en) | Wheat yield prediction method of multi-source data-driven hybrid mechanism learning model | |
| CN117520783A (en) | Crop yield prediction method | |
| CN111737876A (en) | Tea leaf mining period and picking time prediction method with space-time distribution characteristics | |
| Saatchi et al. | Mapping landscape scale variations of forest structure, biomass, and productivity in Amazonia | |
| Sharma et al. | NGFS rainfall forecast verification over India using the contiguous rain area (CRA) method | |
| CN116297058A (en) | 10-minute-level atmospheric particulate monitoring method and system based on remote sensing data | |
| Jagannathan et al. | Time Series Analyzation and Prediction of Climate using Enhanced Multivariate Prophet |
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 |