JP7176980B2 - Crop management system and crop management method - Google Patents

Description

The present invention relates to a system and method for managing crop growth, harvest, and the like.

In large-scale farms, it is difficult to grasp details on site, and a management method using GIS (Geographical Information System) or satellites is required. In order to achieve constant monitoring, cost reduction and early yield prediction, analytical methods such as satellite imagery or images taken by drones are used. For example, Japanese Unexamined Patent Application Publication No. 2016-123369 (Patent Document 1) describes, "A plant growth analysis system for analyzing plant growth based on remote sensing images, in which time indicating the elapsed time from a predetermined time of the plant Feature values are calculated based on a plant growth model in which changes in plant growth feature values are registered in response to information and images corresponding to multiple plant growth locations that are part of the remote sensing image. a feature amount calculation unit, a growth difference correction unit that refers to the plant growth model, corrects the feature amount of the plurality of growth locations to a feature amount corresponding to the reference time information, and corrects the growth difference of the plurality of growth locations; and an image generation unit that generates a new image so that the image corresponding to the plurality of growing places, which is part of the sensing image, becomes the feature amount after correction." there is

JP 2016-123369 A

Based on the GIS data, when the farm is managed by displaying the field on a map and mapping the field data, there is a variation in the growth stage due to the difference in the planting date of the crop, which is analyzed and predicted. Such observation management is becoming difficult.

On the other hand, at present, early yield predictions are made and harvest plans are prepared, but the harvest time depends on the experience of the farmers. Crops usually have an optimal harvest point, beyond which yields usually decline. In addition, due to the planning of the harvesting order, the standby consumption of the harvesting equipment is large, which is costly.

The above-mentioned Patent Document 1 describes correcting the feature amount calculated from the remote sensing image in the analysis of the growth of a plant with a deviation in the growth stage. Correcting the model is not mentioned.

A brief outline of typical inventions disclosed in the present application is as follows. That is, a crop management system comprising a processor and a storage device accessed by the processor, wherein the storage device stores image data including a plurality of images of a plurality of plots of a farm taken at different times in the past. , meteorological data for each section measured at different times in the past, and the processor calculates an index indicating the growth status of crops for each hour based on the meteorological data, and Obtaining the temperature, and estimating an index indicating the growth state of the crop with respect to the integrated temperature based on the index indicating the growth state of the crop for each hour and the temperature for each hour . based on the image data , estimating a mathematical relationship between the spectral feature value obtained from the image data and an index indicating the growth status of the crop for each section, converting the curve of the spectral feature quantity into an index curve indicating the growth status of the crop, and converting the converted index curve indicating the growth status of the crop to the index curve indicating the growth status of the crop in the generated growth model; The growth model is corrected by curve fitting .

According to one aspect of the present invention, a growth stage unified image can be generated, the growth stages of crops can be corrected, variations in feature amounts of crops in the image are no longer affected by growth stage shifts, and the accuracy of analysis can be improved. , the accuracy of management is also improved.

Problems, configurations, and effects other than those described above will be clarified by the following description of the embodiments.

1 is a block diagram showing the configuration of a crop management and harvesting system according to an embodiment of the present invention; FIG. 1 is a block diagram showing the overall hardware configuration of a crop management and harvesting system according to an embodiment of the present invention; FIG. It is a flow chart explaining an example of processing of the whole crop management harvesting system in the example of the present invention. It is explanatory drawing showing the process of growth model generation in the Example of this invention. It is explanatory drawing showing the process of growth stage extraction in the Example of this invention. FIG. 4 is an explanatory diagram showing growth stage analysis processing in the embodiment of the present invention; It is explanatory drawing showing the process of growth model correction|amendment in the Example of this invention. It is a flow chart showing processing of growth difference calculation in the example of the present invention. FIG. 4 is an explanatory diagram showing a first example of growth difference correction processing in the embodiment of the present invention; FIG. 7 is an explanatory diagram showing a second example of growth difference correction processing in the embodiment of the present invention; FIG. 11 is an explanatory diagram showing a third example of growth difference correction processing in the embodiment of the present invention; FIG. 11 is an explanatory diagram showing a fourth example of growth difference correction processing in the embodiment of the present invention; It is explanatory drawing showing each case of the process of growth difference correction|amendment in the Example of this invention. FIG. 4 is an explanatory diagram showing an example of a database in an embodiment of the present invention; FIG. FIG. 4 is an explanatory diagram showing an example of time-series satellite image data stored in a database in the embodiment of the present invention; FIG. 3 is an explanatory diagram showing an example of GIS data stored in a database in an embodiment of the present invention; FIG. FIG. 4 is an explanatory diagram showing an example of plant growth data stored in a database in the embodiment of the present invention; FIG. 4 is an explanatory diagram showing an example of weather data stored in a database in the embodiment of this invention; FIG. 4 is an explanatory diagram showing an example of soil and other correlation data stored in a database in an embodiment of the present invention; FIG. 4 is an explanatory diagram showing an example of processing parameters stored in a database in the embodiment of the present invention; It is explanatory drawing showing each case of the processing of the harvest map in the Example of this invention.

An embodiment to which the crop management system and method of the present invention are applied will be described below.

The crop management system of the present embodiment is a system for managing the cultivation, harvesting, etc. of crops, and outputs a new crop physiological feature amount map in which the target area of the time-series remote sensing image data and the growth stage of the field are corrected. 13 and 15 are schematic diagrams showing inputs and outputs in this embodiment. In this embodiment, the analysis unit is the field, but the analysis may be performed in other units.

A farm field is an example of a division of a farm. For example, each field may be separated by roads or waterways, but the size and shape of the field and how to determine the boundaries are not limited. Fields in the following description can be replaced with any plot.

FIG. 1 is a block diagram showing the configuration of a crop management system 100 in an embodiment of the invention.

The crop management system 100 includes an input data 101, a crop physiological/environmental data acquisition unit 102, a weather/GIS (Geographical Information System) data acquisition unit 103, a remote sensing image data acquisition unit 104, a growth model generation unit 105, and a growth stage extraction unit. 106 , a growth stage analysis unit 107 , a growth model correction unit 108 , a growth difference calculation unit 109 and a growth difference correction unit 110 . Input data 101 includes crop physiological data and environmental data (hereinafter referred to as crop physiological/environment data 101a), weather data and GIS data (hereinafter referred to as weather/GIS data 101b), and time-series remote sensing images. Contains data 101c.

The crop management system 100 acquires time-series remote sensing data of the crop growing season, weather/GIS data, and crop physiological/environmental data, and provides them to the database 115 . Remote sensing image data 101c, weather/GIS data 101b, and crop physiological/environmental data 101a will be described with reference to FIG. Also, the database 115 will be described with reference to FIG.

Data managed by the database 115 is provided to the growth stage unified image generation unit 111 and the crop harvest image generation unit 112 . The growth stage unified image generation unit 111 and the crop harvest image generation unit 112 use the provided information to generate a new analysis map (growth deviation correction map) in which deviations in the growth stages of the estimation target (field or region) are corrected. and a crop harvest image.

The new growth deviation correction map generated by the growth stage unified image generation unit 111 is provided to the growth analysis system usage unit and used for crop management. The crop harvest image generated by the crop harvest image generation unit 112 is provided to the distribution vehicle dispatch system usage unit and used for the crop harvest plan.

FIG. 2 is a block diagram showing the overall hardware configuration of the crop management system 100 according to the embodiment of the invention.

A state in which time-series remote sensing images are taken from the remote sensing observation device 120 is shown. Examples of the remote sensing observation device 120 include observation satellites or aircraft, and the type is not limited. A present Example demonstrates the example using the satellite image which the observation satellite acquired. FIG. 2 shows an example in which crop management system 100 is implemented in computer system 121 . That is, the main part of the crop management system 100 of FIG. 1 is processed by the computer system 121 . This computer system has a general hardware configuration such as a CPU (Central Processing Unit) 122, a RAM (Random Access Memory) 123 and a storage unit 124.

Returning to FIG. 1, the description continues. The input data 101 (crop physiology/environment data 101a, weather/GIS data 101b, and time-series remote sensing image data 101c) is remote sensing data, such as data from artificial satellites such as RapidEye, MODIS, or LandSat, or aerial photographs. is. In this embodiment, time-series remote sensing images are shown, but the type of data is not limited, and the input data 101 may be other types of data. Also, time series images in the same remote sensing image may be used. Note that the difference in resolution is a relative comparison.

The meteorological data may include AMeDAS data, MODIS surface temperature satellite data, meteorological station data, and the like, but the types are not limited. GIS data is essential data for sharing field data and satellite data, such as field polygons or GPS data. Crop physiological data is physiological characteristic data such as leaf area, stem weight, and biomass, but the type is not limited. Environmental data are data related to the environment of crop growth such as soil data and ecological data, but are not limited in kind. The data is stored in the database 115 after preprocessing. Details of the database will be described with reference to FIG.

Crop physiology/environment data acquisition unit 102, weather/GIS data acquisition unit 103, remote sensing image data acquisition unit 104, growth model generation unit 105, growth stage extraction unit 106, growth stage analysis unit 107, growth model correction unit 108, growth The difference calculation unit 109, the growth difference correction unit 110, the growth stage unified image generation unit 111, the crop harvest image generation unit 112, the growth analysis system use unit 113, and the physical distribution vehicle dispatch system use unit 114 perform each arithmetic processing. implemented as a combination of multiple CPUs and RAM divided into Each unit described above employs a hard disk, a USB memory, or the like as an external storage device.

For example, the crop physiology/environment data acquisition unit 102, weather/GIS data acquisition unit 103, remote sensing image data acquisition unit 104, growth model generation unit 105, growth stage extraction unit 106, growth stage analysis unit 107, and A growth model correction unit 108, a growth difference calculation unit 109, a growth difference correction unit 110, a growth stage unified image generation unit 111, a crop harvest image generation unit 112, a growth analysis system use unit 113 (described later), and a distribution vehicle allocation system use unit 114 ( described later) may be implemented by programs stored in the RAM 123 . For example, those programs may be stored in the storage unit 124 (eg, hard disk device, flash memory, etc.), and at least part of them may be read and stored in the RAM 123 as necessary. In other words, the processes executed by the respective units in the following description are actually executed by the CPU 122 (that is, the processor) according to the programs stored in the RAM 123 .

Similarly, the database 115 may be stored in the storage unit 124 , at least part of which may be read out as needed and stored in the RAM 123 .

FIG. 3 is a flow chart illustrating an example of overall processing of the crop management system 100 according to the embodiment of the present invention.

When the process is started (S301), first, in S302, the time-series remote sensing image data 101c is sent to the remote sensing image data acquisition unit 104, the weather/GIS data 101b is sent to the weather/GIS data acquisition unit 103, and crop physiology/ The environmental data are input to the crop physiological/environmental data acquisition unit 102, respectively. In this embodiment, the weather data is surface temperature data of the field, but temperature data measured by other methods may be used.

Time-series remote sensing image data, temperature data, crop physiological data, and environmental data are provided to database 115 in association with GIS data. The GIS data includes positional information and shape information, and the remote sensing data is masked by the position and shape of the field. A masking field is extracted and the remote sensing data and surface temperature of the field are generated from the database generator and provided to the database 115 .

In S303, the growth model generation unit 105 performs masking processing from the position information and shape information of the GIS data stored in the database 115, and from the resulting crop physiological data, environmental data, and surface temperature data of each field. A crop physiological feature amount and effective integrated temperature data for each hour are calculated and stored in the database 115 .

In S304, the crop physiological feature values and the effective cumulative temperature data stored in the database 115 are provided to the growth model generation unit 105, and the growth model generation unit 105 converts them into a coordinate system curve of the crop feature values and the effective cumulative temperature (for example, , with the horizontal axis as the effective cumulative temperature and the vertical axis as the crop feature value). Details of the calculation of the crop characteristic quantity and the effective integrated temperature data in S304 and the generation of the growth curve in S305 will be described later with reference to FIG.

In S305, the transition model of the crop feature amount and effective cumulative temperature stored by the growth model generation unit 105 is provided to the growth stage extraction unit 106, and the growth stage extraction unit 106 extracts the growth stage of the crop from the cultivation characteristics of the crop. do. Details of crop growth stage extraction in S305 will be described later with reference to FIG.

In S306, the growth stage extraction unit 106 provides the growth stage analysis unit 107 with the crop feature amount and the effective cumulative temperature transition model stored in the growth stage extraction unit 106, and the growth stage analysis unit 107 analyzes organisms at each stage of the crop. Analyze the growth model of each stage according to the characteristics. Details of the parameterization of the growth model for each stage according to the biological characteristics of the crop stage at S306 will be described later with reference to FIG.

Then, in S307, the growth stage analysis unit 107 analyzes the growth stage extracted by the growth stage extraction unit 106 with respect to the crop growth curve model generated by the growth model generation unit 105 by the growth model correction unit 108. Using the parameters calculated based on , correct the distribution of the spectral feature quantity/effective cumulative temperature extracted from the time-series remote sensing image data. Details of the growth model correction in S307 will be described later with reference to FIG.

In S308, the growth difference calculation unit 109 calculates GIS field masking and crop physiological feature values for the high-resolution remote sensing image data. is used as the reference to calculate the difference in growth stage between the other fields and the reference field. Details of the growth difference calculation in S308 will be described later with reference to FIG.

In S309, the growth difference correction unit 110 compares the parameters of each field calculated by the growth stage analysis unit 107 and the growth model correction unit 108 and the growth difference of each field with respect to the reference field calculated by the growth difference calculation unit 109. are used to correct the crop physiological feature values. Details of the growth difference correction in S309 will be described later with reference to FIGS. 9, 10, 11 and 12. FIG.

In S<b>310 , the growth stage unified image generation unit 111 generates a growth deviation correction map for fields having corrected crop physiological feature values calculated for each field by the growth difference correction unit 110 . Details of the growth stage unified image generation in S310 will be described later with reference to FIG.

In S311, the growth analysis system usage unit 113 performs crop growth management using the growth stage unified image generated in S310.

In S312, the crop harvest image generation unit 112 uses the crop growth model corrected by the growth model correction unit 108 to generate a crop harvest image. Details of crop harvest image generation in S312 will be described later with reference to FIG.

In S313, the physical distribution vehicle allocation system usage unit 114 performs physical distribution vehicle allocation optimization using the crop harvest image generated in S312.

All data is stored in database 115 . An example of database 115 is shown in FIG.

The details of the above processing will be described below.

The crop physiological/environmental data acquisition unit 102 acquires the crop physiological/environmental data 101 a and provides it to the database 115 .

The weather/GIS data acquisition unit 103 acquires the weather/GIS data 101 b and provides it to the database 115 .

The remote sensing image data acquisition unit 104 acquires the remote sensing image data 101c and provides the database 115 with the remote sensing image data 101c.

Next, the growth model generation unit 105 uses the crop physiological feature data and the surface temperature data (included in the weather/GIS data 101b) of the field stored in the database 115 to generate each analysis target (field, region, etc.). ) to create a crop physiological feature value and an effective integrated temperature-growth curve.

The crop physiological feature value is a parameter indicating the growth state of the crop, such as a crop index. In the present embodiment, a description will be given using a crop physiological index. Crop physiological index is an index that reflects various crop growth conditions based on data taken from ground sensors in the field of agriculture. One of the most commonly used crop indicators is LAI (leaf area index), biomass, sugar content, etc. In this embodiment, LAI will be described as an example. However, other crop indicators may be used. The growth model generation unit 105 calculates the effective cumulative temperature (EAT) using Equation (1).

where _td is the average daily temperature. _t0 is the reference temperature of the effective integrated temperature, and varies depending on crops. In this example, _t0 is set to 15 degrees. i is the number of days.

EAT is the sum of the daily average temperatures for a certain period of time that exceed a certain reference value. EAT is used as a measure of the amount of heat required for plant growth, and as a reference value, for example, a value of 3° C. or higher for spring wheat and 13° C. or higher for maize is used.

In this embodiment, sugar cane is used as an example. Other varieties and plants may be used.

The crop index/effective cumulative temperature growth model is generated by accumulating the effective cumulative temperature from the date of the important period as a characteristic of the crop and setting the value on the horizontal axis of the coordinate system.

Then, the growth model generation unit 105 acquires the crop index for each season from the database 115, and sets the value on the vertical axis of the coordinate system. If there is a planting date date for the plant, a curve from the planting date is generated. However, since the planting date may not be known depending on the field area, it may be calculated from the flowering period or other important dates. Put the points of time in the data into a coordinate system and generate a curve based on all the points. One example of a curve generation method is quadratic approximation, but other methods such as spline interpolation may also be used.

FIG. 4 is an explanatory diagram showing the growth model generation process in the embodiment of the present invention.

The growth model generation unit 105 generates physiological data for the accumulated temperature based on the physiological data for each hour and the temperature data for each hour (Fig. 4(a)). Specifically, the growth model generation unit 105 calculates the integrated temperature from the day of the plant's important period, sets it on the horizontal axis, sets the corresponding crop index LAI on the vertical axis, and calculates the LAI/ An integrated thermoanalysis curve is generated (FIG. 4(b)). A critical season is a time when the growth phase of a crop changes.

In the case of the sugar cane of this example, there are growth stages R1, R2, R3 and R4. R1 is the time when the first flowers appear. R2 is the time when the stem grows. R3 is the time to accumulate sugar. R4 is the time when the leaves are more than 50% yellow and sugar content is reduced and harvested. For each critical period, there is an EAT required to reach this period, and the LAI value for that EAT period can be calculated.

The LAI used as a growth model can be created from a known vegetation growth model. For example, by inputting various physiological parameters and environmental parameters into the CANEGRO model, one cycle growth curve from planting to harvest can be estimated for each physiological feature of sugarcane.

Subsequently, the growth stage extraction unit 106 considers the cultivation growth characteristics of the plant based on the growth model of the corresponding area and field generated by the growth model generation unit 105, and extracts the growth stage.

FIG. 5 is an explanatory diagram showing growth stage extraction processing in the embodiment of the present invention.

The growth stage is extracted after considering the cultivation growth characteristics of the crop. For example, sugar cane has growth stages R1, R2, R3 and R4, and is divided into three growth stages R1-R2, R2-R3 and R3-R4. R1-R2 is the flowering period from when the flowers appear until the flowers are fully grown. R2-R3 is the time until the sugar cane stalk reaches maximum growth. R3-R4 is the time when the body stops growing and most of the sugar accumulates. After R4 is the time when the leaves turn yellow by 50% or more and the sugar content is reduced and harvested.

Data is obtained from farm or crop base growth data and stored in database 115 . As the basic growth data of crops, as already explained, there are cases where there are publicly known data regarding the number of days in each season and the required cumulative temperature.

When targeting other plants, the basic growth data of the crop changes, but the extraction principle remains the same. After examining the growth phase of the crop, the required accumulated temperature for each critical period can be calculated, and the LAI of the accumulated temperature can be calculated.

The growth stage analysis unit 107 analyzes the biological properties of each stage based on the cultivation and growth period of the crop extracted by the growth stage extraction unit, and decomposes the crop growth model of each stage.

FIG. 6 is an explanatory diagram showing growth stage analysis processing in the embodiment of the present invention.

For example, sugar cane has growth stages R1, R2, R3, and R4 (in other words, divisions of growth stages), and three growth stages R1-R2, R2-R3, and R3-R4 (that is, divisions of growth stages). divided into

The growth model correction unit 108 uses the parameters calculated based on the analysis of the growth stage analysis unit 107 for the growth stage extracted by the growth stage extraction unit 106 for the crop growth curve model generated by the growth model generation unit 105. Then, the distribution of NDVI (Normalized Difference Vegetation Index)/effective cumulative temperature extracted from the remote sensing image data (Fig. 6(a)) is corrected to obtain LAI_NDVI/effective cumulative temperature distribution (Fig. 6(b)). Generate. NDVI is calculated by Equation (2) below.

where R is the red reflectance in the visible region and IR is the reflectance in the near-infrared region. The reflectance for each of these regions can be extracted from satellite images.

FIG. 7 is an explanatory diagram showing growth model correction processing in the embodiment of the present invention.

The growth model correction unit 108 acquires remote sensing data and estimates the mathematical relationship between the spectral feature amount and the crop physiological feature amount in order to correct the growth model obtained from the crop physiological data. Then, the growth model correction unit 108 converts the spectral feature amount curve obtained from the observed remote sensing data into a crop physiological feature amount curve. The transformed crop physiological feature curve and the curve of the original crop growth model are fitted to correct the original crop growth model.

For example, when trying to use a growth model to know the growth status of a crop in a certain year (current year) when the crop is in the process of growing, the growth model correction unit 108 A growth model (FIGS. 4 and 5) generated based on meteorological data and the like may be corrected by LAI_NDVI (FIG. 6) obtained from remote sensing image data up to the present time of the year.

As an example of correction, in the case of sugarcane, the growth stages are divided into three stages R1-R2, R2-R3, and R3-R4, and the mathematical relational expressions between the spectral model and the crop physiological model are different at each stage. The growth model correction unit 108 calculates LAI_NDVI (FIG. 7(b)) from the NDVI (FIG. 7(a)) of each stage, and by fitting the result with the LAI, optimizes the parameters of the LAI curve ( FIG. 7(c)). By optimizing the parameters of the LAI curve, the crop physiological feature curve is corrected, and curves such as yield and sugar content can also be estimated. In the case of other plants or other crop features, the biological properties of each stage and the relationship reflected in the crop features from the biological properties are different, so by using them, the above analysis means are not limited to sugarcane can be applied.

The growth difference calculation unit 109 calculates GIS field masking and crop physiological feature values for the crop physiological data and the environmental data, and calculates a certain field among the fields of the remote sensing image data stored in the database 115 as a reference. and calculate the difference in growth stage between the other fields and the reference field.

FIG. 8 is a flow chart showing processing of growth difference calculation in the embodiment of the present invention.

The calculation method is as follows. Using the planting times or certain important times of each field stored in the database 115, the difference in accumulated temperature between the reference field and the planting times or certain important times of other fields is calculated. This difference is provided to the database 115 as the value of the correction standard for each field. There are two methods for selecting the reference field. When it is desired to generate an image of a specific time from a remote sensing image, the field of this time is used as the reference field. Otherwise, based on the accumulated temperature of each field with respect to the planting time or a certain important time, the field that minimizes the sum of the accumulated temperature differences may be used as a reference (for example, formula (3)). Alternatively, the reference field may be selected by another method.

The growth difference correction process S1060 is a process of calculating the growth difference of each field. In S1061, the growth difference calculation unit 109 calculates the integrated temperature value of each field. In S1062, the growth difference correction unit 110 selects the reference field by the method described above. In S1063, the growth difference correction unit 110 calculates the accumulated temperature difference between each field and the reference field. In S1063, the growth difference correction unit 110 stores the difference between the integrated temperature of each field and the integrated temperature of the reference field in the database 115 as a growth difference.

The growth difference correction unit 110 uses the parameters of each field calculated by the growth stage analysis unit 107 and the growth model correction unit 108 and the growth difference of each field with respect to the reference field calculated by the growth difference calculation unit 109 to calculate each field. corrects the crop features of

9, 10, 11 and 12 are explanatory diagrams showing first to fourth examples of growth difference correction processing according to the embodiment of the present invention, respectively.

In the correction of this example, the sugarcane growth stages are divided into three stages, R1-R2, R2-R3, and R3-R4, and there is a growth curve to calculate and correct for each stage. The growth curves shown in FIGS. 9-12 are all identical and show LAI corrected in the manner described with reference to FIG.

9 to 12, all of the reference fields are in the R2-R3 growth stage (that is, the integrated temperature of the reference fields is within the range of R2 to R3). On the other hand, the other field to be corrected (hereinafter also referred to as the relevant field) is the R2-R3 growth stage in the example of FIG. , R2-R3 on the right side of the reference field, in the example of FIG. 11 it is in the R3-R4 stage, and in the example of FIG. 12 it is in the R1-R2 stage. In the examples of FIGS. 9 and 12, the cumulative temperature of the relevant field is smaller than the cumulative temperature of the reference field (that is, the growth stage of the relevant field is later than the growth stage of the reference field). On the other hand, in the examples of FIGS. 10 and 11, the cumulative temperature of the relevant field is greater than the cumulative temperature of the reference field (that is, the growth stage of the relevant field is earlier than the growth stage of the reference field).

In the example of FIG. 9, the growth difference correction unit 110 corrects the crop feature amount of the relevant field in the positive direction of the horizontal axis (that is, the integrated temperature direction).

In FIG. 9, the black dots indicate the LAI corresponding to the accumulated temperature of the corresponding field in the corrected growth model of the corresponding field, and the white dots indicate the LAI corresponding to the accumulated temperature of the reference field. The LAI of the black dot is corrected to the LAI of the white dot. The difference between the two is the correction amount. The same applies to FIGS. 10 to 12 as well.

In the example of FIG. 10, the growth difference correction unit 110 corrects the crop feature amount of the relevant field in the negative direction of the horizontal axis (that is, the integrated temperature direction).

In the example of FIG. 11, the growth difference correction unit 110 divides the difference between the integrated temperature of the corresponding field and the integrated temperature of the reference field into the R2-R3 stage portion and the R3-R4 stage portion. Then, the growth difference correction unit 110 corrects the crop feature amount of the relevant field at the time point R6 using the parameters of the growth model function of the R3-R4 stages, and then uses the parameters of the growth model function of the R2-R3 stages. calculation to correct the integrated temperature of the reference field.

In the example of FIG. 12, the growth difference correction unit 110 divides the difference between the integrated temperature of the relevant field and the integrated temperature of the reference field into the R2-R3 stage portion and the R1-R2 stage portion. Then, the growth difference correction unit 110 corrects the crop feature amount of the relevant field at the R2 time point using the parameters of the R1-R2 stage growth model function, and then uses the R2-R3 stage growth model function parameters. calculation to correct the integrated temperature of the reference field.

When the reference field is in the R1-R2 stage or the R3-R4 stage, the growth difference correction unit 110 performs correction toward the reference field according to the stage where the field to be corrected is present, as in the above process. Calculate the crop feature value of the correction field.

Using the case of FIG. 11 as an example, Equation (4) shows a correction method based on the parameters of the growth model function of the stage and the accumulated temperature difference. In the case of other plant or other crop feature values, the relationship reflected in the crop feature values from the biological properties of each stage and the biological properties are different, so it may not be a linear function, and corrections are made according to the function parameters. conduct.

here,
(x ₁ , y ₁ ) is the data before correction (x ₂ , y ₂ ) is the data after correction x ₂ is the integrated temperature value of the reference field (known)
y ₂ is a calculation target (x _R3 , y _R3 ) is R3 data x _R3 is a known y _R3 is a calculation target.

The growth stage unified image generation unit 111 replaces each corresponding field in the remote sensing image with a field having the corrected crop physiological feature amount calculated by the growth difference correction unit 110, and generates a growth deviation correction map. .

For example, the growth stage unified image generation unit 111 calculates the correction amount of the crop physiological feature amount of each field other than the reference field (specifically, for example, the LAI of the black circle points and the white circle points in the examples of FIGS. ), the amount of change in the value of pixels in the polygon of each field may be determined, and the value of each pixel may be changed according to the amount of change. Since the correction value is calculated for each field, the same amount of change is applied to the pixels within the polygon corresponding to the field. As a result, it is possible to change the level of the pixel values of the entire polygon while maintaining the variation of the pixel values within the polygon corresponding to the variation of the crop physiological feature values in the field.

FIG. 13 is an explanatory diagram showing each case of growth difference correction processing in the embodiment of the present invention.

As shown in FIG. 13(a), the original image is a temporally unified image. On the other hand, the image after processing shown in FIG. 13(b) is an image in which the growth stages are unified although there is a time lag. Such an image may be generated, for example, by multiplying the correction values for each field over the pixels within the field to correct for growth differences.

The growth stage unified image generation unit 111 generates a field map by replacing the original image of each applicable field with a corresponding new image after correction, and provides it to the database 115 . The field map stored in the database 115 in this manner is then provided to the growth analysis system use section 113 and used for agricultural support analysis.

The crop harvest image generation unit 112 replaces each corresponding field in the remote sensing image with the field having the corrected crop physiological feature amount calculated by the growth difference correction unit 110, and generates a map of harvest time and yield. .

FIG. 15 is an explanatory diagram showing each case of harvest map processing in the embodiment of the present invention.

Both the original physiological characteristic growth map shown in FIG. 15(a) and the harvest map shown in FIG. 15(b) are temporally unified images. In the processed image shown in FIG. 15(b), each field is colored, and the colors indicate the order of harvesting and the amount of harvesting according to the harvesting time. The crop harvest image generation unit 112 generates a field map by replacing the original image of each applicable field with a corresponding new image after correction, and provides it to the database 115 . The farm field map stored in the database 115 in this way is then provided to the physical distribution vehicle allocation system use unit 114 and used to create a harvest plan.

FIG. 14A is an explanatory diagram showing an example of the database 115 in the embodiment of the invention.

The database 115 includes time-series satellite image data 1401, GIS data (position and shape data) 1402, plant growth data (data calculated from GIS data, satellite, and weather data in the database generation unit) 1403, weather data (this embodiment surface temperature data) 1404, soil and other correlation data 1405, and processing parameters 1406. Although illustration is omitted, the database 115 may include data other than the above (for example, disaster data, etc.).

FIG. 14B is an explanatory diagram showing an example of time-series satellite image data 1401 stored in the database 115 in the embodiment of the present invention.

The remote sensing image data 101c acquired by the remote sensing image data acquiring unit 104 is stored in the database 115 as time-series satellite image data 1401. FIG. The time-series satellite image data 1401 is a group of images of the same location (for example, a farm including a field managed by the crop management system 100) taken at different times. It may also include a sensing image.

The time-series satellite image data 1401 is used for correction of the growth model (S307) and generation of images with uniform growth stages (S308-S310).

FIG. 14C is an explanatory diagram showing an example of GIS data 1402 stored in database 115 in the embodiment of the present invention.

Of the weather/GIS data 101 b acquired by the weather/GIS data acquisition unit 103 , GIS data is stored in the database 115 as GIS data 1402 . Position data and shape data of each field are registered in the GIS data 1402 . GIS data 1402 includes field IDs, GPS data, and shape data. Identification information of a farm field is registered in the farm field ID. Latitude and longitude indicating the position of the field are registered in the GPS data. Data (field polygon) indicating the contour of the field is registered in the shape data.

By referring to the GIS data 1402, it is possible to extract field polygons, which are contours of field images, from the images included in the time-series satellite image data 1401. FIG.

FIG. 14D is an explanatory diagram showing an example of plant growth data 1403 stored in database 115 in the embodiment of the present invention.

The plant growth data 1403 includes vegetation index time-series data and crop growth reference data.

The vegetation index time-series data includes a feature amount (vegetation index) indicating the state of vegetation in each field. In this embodiment, NDVI is held as a feature amount. For example, the NDVI for each period of each field such as field 1 and field 2 is held as vegetation index time-series data.

The growth stage reference data 460 registers, for example, the accumulated temperature at which the soybean reaches each important time and the plant characteristics of each growth stage.

Crop growth reference data includes integrated temperature and plant characteristics for each growth stage. For example, the growth stages of soybeans include flowering, pod setting, seed maturity, and full ripeness, when more than 50% of the leaves turn yellow and the seeds are fully ripe. . Other crops, such as sugarcane, have their own growth stages as well. As the crop growth reference data, the integrated temperature until the target crop reaches each growth stage and the plant characteristics of each growth stage are held.

FIG. 14E is an explanatory diagram showing an example of weather data 1404 stored in database 115 in an embodiment of the present invention.

Weather data 1404 includes, for example, precipitation data and temperature data. Precipitation data for a predetermined period of time in a certain area (for example, an area including a managed farm) is stored. For the precipitation data, for example, precipitation data from the Japan Meteorological Agency can be used.

Also, as temperature data, the highest temperature and lowest temperature in a certain area for a predetermined period are held. For example, the maximum and minimum temperatures may be the surface temperatures of fields in a certain region. Air temperature data can use, for example, data from the MODIS surface temperature satellite.

Moreover, although omitted in FIG. 14E, the weather data 1404 may further include data on the amount of solar radiation and the like.

Air temperature data can be used to calculate the cumulative temperature. Also, when calculating the LAI using some model, temperature data, solar radiation data, rainfall data, etc. included in the weather data 1404 can be used.

FIG. 14F is an illustration showing an example of soil and other correlation data 1405 stored in database 115 in an embodiment of the present invention.

Soil and other correlated data 1405 shown in FIG. 14F includes soil data and crop cultivation data.

In the soil data, coefficients of components necessary for plant growth among soil components of each field in a certain region are registered. The soil data shown in FIG. 14F includes phosphate coefficients by field.

The time (for example, date) when the crops in each field reached a predetermined stage is registered in the crop cultivation data. The crop cultivation data shown in FIG. 14F includes planting time, flowering time, pod setting time and harvest time for each field. These times are registered according to the type of crops in each field (for example, soybeans or sugar cane). These times may be registered, for example, based on information obtained from farmers.

FIG. 14G is an explanatory diagram showing an example of processing parameters 1406 stored in database 115 in an embodiment of the present invention.

In the processing parameters 1406, parameters and the like regarding the growth model of each field are registered.

Processing parameters 1406 include growth stage parameters, growth differences, and correction values for each field. The growth stage parameter registers a parameter corresponding to the growth stage of the plant (for example, a parameter for expressing the growth model of each stage). In the growth difference, the difference between the integrated temperature of each field and the integrated temperature of the reference field is registered as the growth difference. A correction value is registered as the correction value for making the feature amount (for example, LAI) of each field correspond to the integrated temperature of the reference field.

The representative examples of the aspects of the present invention described above are summarized as follows. That is, the crop management system includes a processor (eg, CPU 122) and a storage device (eg, RAM 123 or storage unit 124) accessed by the processor, wherein the storage device stores a plurality of plots (eg, farm fields) of a farm in the past. Image data including a plurality of images taken at different times (for example, image data acquired by the remote sensing image data acquisition unit 104 and stored in the database 115), and meteorological data for each section measured at different times in the past (For example, the weather data acquired by the weather/GIS data acquisition unit 103 and stored in the database 115), and the processor, based on the weather data, a growth model for estimating an index indicating the growth situation of crops. (eg, S304), and the growth model may be corrected (eg, S307) for each plot based on the image data.

As a result, it is possible to obtain a highly accurate growth model that reflects the actual field conditions.

At this time, the processor calculates an index indicating the growth state of crops for each hour based on the weather data, obtains the temperature for each hour, and calculates the index for the growth state of crops for each hour and the temperature for each hour. Based on this, an index indicating the growth status of the crop with respect to the accumulated temperature is generated as a growth model, and based on the accumulated temperature, the division of the growth stage of the crop (for example, the growth stage divided by R1 to R4 in FIG. 5) is extracted. You may

This solves the problem of different growth conditions due to different planting times for the same kind of plants.

In addition, the processor may generate a function indicating the relationship between the integrated temperature and the index indicating the growth state of the crop for each growth stage division, and store the parameters of the function in the storage device as a growth model.

This makes it possible to express the growth situation mathematically, and the expressed growth situation can be used as the basis for generating images in which growth stages are unified.

In addition, the processor calculates a vegetation index indicating the amount and vitality of crops for each plot based on the image data, calculates an index indicating the growth status of the crops based on the vegetation index, and calculates The growth model may be corrected using the calculated index indicating the growth state of the crop (eg, S307, FIG. 7).

As a result, the actual vegetation situation obtained from the image is reflected, and the growth situation can be estimated with higher accuracy.

In addition, the index indicating the growth status of crops is either the leaf area index, biomass, or sugar content, and the vegetation index is the normalized difference vegetation based on the red reflectance in the visible region and the reflectance in the near-infrared region. It is an index, and the accumulated temperature may be an effective accumulated temperature based on a reference temperature according to the type of crop.

This makes it possible to obtain useful information for crop management.

The processor may also generate an image showing the growth status of crops in a plurality of plots with a unified growth stage based on the corrected growth model (eg, S310, FIG. 13(b)).

As a result, it is possible to visually grasp the growth state from which the influence of differences in planting times has been removed.

In addition, the processor selects a first section among the plurality of sections as a reference section (eg, S1062), and calculates the integration in a second section different from the first section among the plurality of sections at a first time point. The temperature-based growth phase (eg, the solid dot growth phase in FIGS. 9-12) and the integrated temperature-based growth phase in the first plot at the first time point (eg, the open dot growth phase in FIGS. 9-12). (e.g., S1063), and based on the growth model of the second plot and the calculated difference in growth stage, an index indicating the growth status of the crop in the second plot is calculated. , corrected to a value indicating the growth status of the crop in the second section at the time when the growth stage in the second section becomes the same as the growth stage in the first section (eg, S1064, FIGS. 9 to 12), Based on the value of the index indicating the growth status of the crops in the first section and the corrected value of the index indicating the growth status of the crops in the second section at time 1, the growth of crops in a plurality of sections An image showing the growth status may be generated (eg, S310).

At this time, the processor generates a function indicating the relationship between the integrated temperature and the index indicating the growth state of the crop for each growth stage division, holds the parameters of the function as a growth model in the storage device, and stores the first Using parameters of functions of all sections from the section containing the growth stage in the section to the section containing the growth stage in the second section, even if the index indicating the growth situation of the crop in the second section is corrected. good. This is because the LAI is corrected (equation (4)) using the R2-R3 growth stage functional parameters and the R3-R4 growth stage functional parameters in the example of FIG. 11, and the R1-R2 and the functional parameters of the R2-R3 growth stages are used to correct the LAI.

As a result, the value of the index indicating the growth state is accurately calculated so as to match the growth stage of the reference field.

Also, the processor may select a section having an accumulated temperature that satisfies a predetermined condition with respect to the accumulated temperatures of other sections as the reference section (for example, S1062, formula (3)).

This allows the selection of a suitable reference partition.

The processor may also generate an image showing crop growth in multiple plots by applying the same correction to multiple pixels within the polygon corresponding to the second plot.

As a result, the overall level can be corrected so as to remove the influence of the planting date difference while maintaining the variation in the pixel values within the polygon (for example, within the same field).

The processor may also generate an image showing the harvest order of the crops in the multiple plots based on the corrected growth model (eg, S312, FIG. 15).

As a result, harvest planning is facilitated, and an increase in costs due to waiting for harvesting equipment can be suppressed.

In addition, the crop management system, which is a representative example of the aspect of the present invention, includes a remote sensing image acquisition unit, a weather data acquisition unit, a remote sensing image acquired by the crop growth data environmental data, the temperature data, and the crop growth data environmental data. A growth model generation unit that stores crop data that can be used as a reference, and generates a change transition of crop physiological characteristics depending on the effective cumulative temperature using both crop growth, environmental data, and weather data, and an index for each effective cumulative temperature. A growth stage extraction unit that extracts the growth stages of crop growth based on change transitions, a growth stage analysis unit that analyzes the extracted growth stages and parameterizes the growth of each stage, and a growth model that uses remote sensing features. A growth stage correction unit that corrects, a growth difference calculation unit that calculates the growth difference for each field, a growth difference correction unit that corrects the growth difference, and a growth stage unification that generates a growth stage unified image according to the growth correction. An image generation unit, a crop harvest image generation unit according to the growth model correction, a growth analysis system use unit using the growth stage unified image, and a distribution vehicle dispatch system use unit using the crop harvest image. good.

The remote sensing image acquisition unit may acquire time-series remote sensing images and extract the crop feature amount reflecting the images. The weather data acquisition unit may acquire temperature data of the region or field to be analyzed. The crop growth/environmental data acquisition unit may acquire environmental data such as the physiological characteristic parameters of the crop itself and the soil to be analyzed. Then, in a crop management system that analyzes a target area using remote sensing images and crop growth and environmental data transmitted from a remote sensing observation device, images transmitted from the observation device may be stored in a database. good.

In addition, a crop management system that analyzes a target area using remote sensing images, crop growth, and environmental data transmitted from the observation device includes a database that stores the images transmitted from the observation device, and Among the stored remote sensing images, time-series images, crop growth, and environmental data are used to perform time-series arithmetic processing within a preset image acquisition period, and the temperature data is combined to generate a growth model. You may have a growth model generation part which carries out. In this system, the growth model generation unit uses both time data and temperature data, instead of the normal crop index/time change transition, to calculate the integrated value of the effective temperature every day from the planting time of the crop, and to understand the essence of the crop. It may be converted into an effective integrated temperature analysis model shown, and the change may be analyzed based on this integrated temperature. Since the effective cumulative temperature can reflect the growth stage of the same type of crops, the use of the effective cumulative temperature of the present invention solves the problem of different growth conditions due to differences in the planting time of plants of the same type. considered to be solvable.

Further, the above crop management system may have a growth stage extraction unit for extracting a growth stage from the change transition curve of the crop index/accumulated temperature generated by the growth model generation unit. In this system, the growth stage extractor reveals the stages of all homogenous crop growth characteristics, allowing for a more precise analysis.

Further, the above crop management system has a growth stage analysis unit that analyzes the stages extracted by the growth stage extraction unit, considers the relationship between the biological properties and the crop feature amount, and converts the growth model of each stage into a function parameter. may In this system, the growth stage analysis unit can combine the growth model with the essential crop growth characteristics to mathematically represent the growth situation, which can be used as the basis for generating a unified growth image.

In addition, the above crop management system analyzes the stages extracted by the growth stage extraction unit from the change transition curve of the crop index/accumulated temperature generated by the growth model generation unit, and considers the relationship between the biological characteristics and the crop feature amount. The growth model of the stage may be converted into a function parameter and corrected from the data of the current year. In this system, it is possible to create a more precise crop growth model by fusing past data and current year data, and to increase the accuracy of growth correction.

In addition, the crop management system calculates the growth difference between each analysis unit and the standard analysis unit using the corrected crop growth model generated as described above, corrects the growth difference to the standard analysis unit, A unified growth stage image and a unified growth model time harvest map may be generated by replacing each corrected analysis unit with the corresponding analysis unit of the original image. In this system, through the use of a crop growth model, it is possible to correct the growth of each analysis unit that has a growth deviation, generate a unified growth image, and obtain high accuracy and reliability through yield prediction and growth situation analysis.

In addition, the present invention is not limited to the above-described embodiments, and includes various modifications. For example, the above embodiments have been described in detail for better understanding of the present invention, and are not necessarily limited to those having all the configurations described. Also, it is possible to replace part of the configuration of one embodiment with the configuration of another embodiment, or to add the configuration of another embodiment to the configuration of one embodiment. Moreover, it is possible to add, delete, or replace a part of the configuration of each embodiment with another configuration.

Further, each of the above configurations, functions, processing units, processing means, and the like may be realized by hardware, for example, by designing a part or all of them using an integrated circuit. Moreover, each of the above configurations, functions, etc. may be realized by software by a processor interpreting and executing a program for realizing each function. Information such as programs, tables, files, etc. that realize each function is stored in storage devices such as non-volatile semiconductor memories, hard disk drives, SSDs (Solid State Drives), or computer-readable non-volatile memory such as IC cards, SD cards, DVDs, etc. It can be stored on a temporary data storage medium.

Also, the control lines and information lines indicate those considered necessary for explanation, and not necessarily all the control lines and information lines are indicated on the product. In fact, it may be considered that almost all configurations are interconnected.

100: Crop management system 101a: Crop growth data, environmental data 101b: Weather, GIS data 101c: Time-series remote sensing image data 102: Crop physiology, environmental data acquisition unit 103: Weather, GIS data acquisition unit 104: Remote sensing image data Acquisition unit 105: Growth model generation unit 106: Growth stage extraction unit 107: Growth stage analysis unit 108: Growth model correction unit 109: Growth difference calculation unit 110: Growth difference correction unit 111: Growth stage unified image generation unit 112: Crop harvest Image generation unit 113: Growth analysis system use unit 114: Distribution vehicle allocation system use unit

Claims (10)

A crop management system comprising a processor and a storage device accessed by the processor,
The storage device
image data including multiple images taken at different times in the past of multiple plots of a farm;
holding weather data for each section measured at different times in the past,
The processor
calculating an index indicating the growth state of crops for each hour based on the meteorological data, obtaining temperature for each hour, and based on the index indicating the growth state of crops for each hour and the temperature for each hour , generating an index indicating the growth state of the crop with respect to the integrated temperature as a growth model for estimating the index indicating the growth state of the crop;
extracting a growth stage category of the crop based on the integrated temperature;
Based on the image data , a mathematical relationship between the spectral feature amount obtained from the image data and an index indicating the growth state of the crop is estimated for each section, and a curve of the spectral feature amount is calculated for the crop. and fitting the converted index curve indicating the crop growth status with the index curve indicating the crop growth status of the generated growth model, A crop management system characterized by correcting a growth model. A crop management system according to claim 1,
The processor generates a function indicating a relationship between the accumulated temperature and an index indicating the growth status of the crop for each of the growth stages, and stores parameters of the function as the growth model in the storage device. A crop management system characterized by: A crop management system according to claim 1,
The index indicating the growth status of the crop is either leaf area index, biomass or sugar content,
The crop management system, wherein the accumulated temperature is an effective accumulated temperature based on a reference temperature corresponding to the type of the crop. A crop management system according to claim 1,
The crop management system, wherein the processor generates an image showing the growth status of the crops in the plurality of plots with a unified growth stage based on the corrected growth model. A crop management system according to claim 4,
The processor
selecting a first partition from the plurality of partitions as a reference partition;
a growth stage based on accumulated temperature in a second section of said plurality of sections different from said first section at a first point in time; and based on accumulated temperature in said first section at said first point in time. Calculate the difference with the growth stage,
Based on the growth model of the second plot and the calculated difference in the growth stage, an index indicating the growth status of the crop in the second plot is calculated based on the growth stage in the second plot. Correcting to a value indicating the growth status of the crop in the second section at the same time as the growth stage in the first section,
Based on the value of the index indicating the growth state of the crop in the first section and the corrected value of the index indicating the growth state of the crop in the second section at the first time point, A crop management system, wherein an image showing the growth status of the crops in the plurality of sections is generated. A crop management system according to claim 5,
The processor
generating a function indicating the relationship between the integrated temperature and an index indicating the growth status of the crop for each of the growth stages, and storing the parameters of the function as the growth model in the storage device;
using the parameters of the function for all the segments from the segment containing the growth stage in the first compartment to the segment containing the growth stage in the second compartment, the A crop management system characterized by correcting an index indicating a crop growth situation. A crop management system according to claim 5,
The crop management system, wherein the processor selects, as the reference section, a section having an accumulated temperature that satisfies a predetermined condition with respect to the accumulated temperatures of other sections. A crop management system according to claim 5,
Crop management, wherein the processor generates an image showing the growth status of the crop in the plurality of sections by performing the same correction on the plurality of pixels within the polygon corresponding to the second section. system. A crop management system according to claim 1,
The crop management system, wherein the processor generates an image showing the harvest order of the crops in the plurality of plots based on the corrected growth model. A crop management method executed by a computer system having a processor and a storage device accessed by the processor,
The storage device
image data including multiple images taken at different times in the past of multiple plots of a farm;
holding weather data for each section measured at different times in the past,
The crop management method includes:
The processor calculates, based on the weather data, an index indicating the growth state of crops for each hour, obtains temperature for each hour, and calculates the index indicating the growth state of crops for each hour and the hourly index for crop growth. a step of generating an index indicating the growth state of the crop with respect to the integrated temperature as a growth model for estimating the index indicating the growth state of the crop based on the temperature;
a step in which the processor extracts a growth stage segment of the crop based on the integrated temperature;
The processor, based on the image data, estimates a mathematical relationship between the spectral feature amount obtained from the image data and an index indicating the growth state of the crop for each section, and estimates the spectral feature amount. The curve is converted into an index curve indicating the growth status of the crop, and the converted index curve indicating the growth status of the crop is fitted to the index curve indicating the growth status of the crop in the generated growth model. and a step of correcting said growth model by:

Images