JP2021026771A - Yield estimation program, method for estimating yield, and yield estimation device - Google Patents

Abstract

To estimate the yield of crops.SOLUTION: A biological information acquisition unit 30 acquires biological information of crops. An environmental information acquisition unit 32 acquires environmental information on an environment under which crops grow. A yield estimation unit 34 estimates the state of fruits of the crops on the basis of the acquired biological information and the environmental information and estimates the yield of the crops on the basis of the estimated state of the fruits, thereby accurately estimating the yield of the crops.SELECTED DRAWING: Figure 3

Description

The present invention relates to a yield estimation program, a yield estimation method and a yield estimation device.

If the yield can be estimated to some extent before harvesting the crop, the number of workers required at the time of harvesting, the fuel for transportation, the quantity of packing materials, the equipment for harvesting, etc. can be estimated, so it is possible to improve the efficiency in production and distribution. is there. However, in the past, the yield estimation of crops was only performed based on past yield data and experience after the manager and the like grasped the cultivation situation.

On the other hand, recently, a technique for predicting the yield of crops from the light reflectance and NDVI of the target area obtained from remote sensing data such as satellite data, or GNDVI (see, for example, Patent Document 1), and the growth of water temperature Techniques related to production prediction of dependent useful organisms (for example, algae) (see, for example, Patent Document 2 and the like) are known. In addition, a technique for predicting yield using aerial images and time-series meteorological data is also known (see, for example, Patent Document 3 and the like).

JP-A-2010-166851 Japanese Unexamined Patent Publication No. 2012-203875 JP 2015-49

However, the techniques of Patent Documents 1 to 3 and the like cannot be applied to the estimation of yield in the cultivation of fruit vegetables such as tomatoes, and are not general purpose.

An object of the present invention is to provide a yield estimation program, a yield estimation method, and a yield estimation device capable of accurately estimating the yield of a crop.

The yield estimation program of the present invention acquires biological information of a crop, acquires environmental information on which the crop grows, and estimates from at least one of the biological information, the environmental information, the biological information, and the environmental information. It is a program for causing a computer to perform a process of estimating the yield of the crop based on the state of the fruit of the crop.

The yield estimation program, the yield estimation method, and the yield estimation device of the present invention have the effect of being able to accurately estimate the yield of a crop.

It is a figure which shows the structure of the agricultural system which concerns on one Embodiment. FIG. 2A is a diagram showing the hardware configuration of the server, and FIG. 2B is a diagram showing the hardware configuration of the user terminal. It is a functional block diagram of a server. It is a flowchart which shows the processing of a server. It is a flowchart which shows the detailed process of step S26 of FIG. It is a figure which shows the estimation procedure of the yield of a crop based on a photosynthetic characteristic. It is a figure (the 1) which shows the table used in the process of FIG. It is a figure (the 2) which shows the table used in the process of FIG. It is a figure (the 3) which shows the table used in the process of FIG. It is a figure which shows the graph used in step S48 of FIG. FIG. 11A is a diagram showing a data structure of the estimated yield DB, and FIG. 11B is a diagram showing an output example by the output unit. 12 (a) and 12 (b) are diagrams for explaining an example of tomato. 13 (a) and 13 (b) are diagrams for explaining an embodiment of cucumber. It is a figure for demonstrating the Example of paprika. 15 (a) and 15 (b) are diagrams for explaining a tomato cultivation example of another embodiment (No. 1). It is a figure for demonstrating the cultivation example of paprika of another embodiment (the 1). It is a figure for demonstrating another embodiment (the 2).

Hereinafter, one embodiment of the agricultural system will be described in detail with reference to FIGS. 1 to 11. FIG. 1 schematically shows the configuration of the agricultural system 100 according to one embodiment. The agricultural system 100 of the present embodiment is a system that estimates the yield of crops in a large-scale facility (for example, a house) for cultivating crops such as tomatoes, and controls the equipment in the facility so that the estimated yield is improved. ..

As shown in FIG. 1, the agricultural system 100 includes a server 10, a user terminal 70, an environmental information acquisition device 72, and a control target device 74. The server 10, the user terminal 70, the environment information acquisition device 72, and the control target device 74 are connected to a network 80 such as the Internet.

The server 10 is an information processing device installed in a data center or the like, and estimates the yield of crops based on the environmental information acquired by the environmental information acquisition device 72 and the information input from the user terminal 70. Further, the server 10 outputs the estimated yield information to the user terminal 70, and outputs the control information for controlling the controlled target device 74 based on the estimated yield and the like. The details of the configuration and processing of the server 10 will be described later.

The user terminal 70 is a terminal such as a PC (Personal Computer) that can be used by workers, managers, etc., and receives input of biological information of crops by the manager, etc. and sends it to the server 10 or a server. Information on the yield of the crop estimated by 10 is received and displayed. The user terminal 70 has a hardware configuration as shown in FIG. 2 (b). That is, as shown in FIG. 2B, the user terminal 70 includes a CPU (Central Processing Unit) 190, a ROM (Read Only Memory) 192, a RAM (Random Access Memory) 194, and a storage unit (here, an HDD (Hard)). Disk Drive)) 196, a network interface 197, a display unit 193, an input unit 195, a portable storage medium drive 199 capable of reading the portable storage medium 191 and the like. Each component of the user terminal 70 is connected to the bus 198. The display unit 193 includes a liquid crystal display and the like, and the input unit 195 includes a keyboard, a mouse, a touch panel and the like.

Returning to FIG. 1, the environmental information acquisition device 72 _{includes a sensor for measuring the air temperature, the amount of solar radiation, and the CO 2} concentration, and has a function of transmitting the measurement result of the sensor to the server 10. Here, the environmental information acquisition device 72 measures the air temperature, the amount of solar radiation, and the CO ₂ concentration, for example, every 5 minutes, and transmits the average value or the integrated value of the measurement results measured during the day to the server 10. To do. The environment information acquisition device 72 may transmit the measurement result to the server 10 immediately after the measurement. In this case, the server 10 may use the received measurement results to obtain the average value or the integrated value of the measurement results measured during the day.

The controlled device 74 includes, for example, _{an air conditioner for adjusting the temperature and CO 2} concentration in the house, and an insolation amount adjusting device for adjusting the amount of solar radiation. When the control target device 74 receives the control information from the server 10, the control target device 74 adjusts the growing environment of the crop in the house based on the control information.

(About server 10)
FIG. 2A shows the hardware configuration of the server 10. As shown in FIG. 2A, the server 10 includes a CPU 90, a ROM 92, a RAM 94, a storage unit (here, an HDD) 96, a network interface 97, a drive 99 for a portable storage medium, and the like as a computer. Each component of the server 10 is connected to the bus 98. In the server 10, the CPU 90 executes a program (including a yield estimation program) stored in the ROM 92 or HDD 96, or a program (including a yield estimation program) read from the portable storage medium 91 by the portable storage medium drive 99. By doing so, the functions of each part shown in FIG. 3 are realized. The functions of each part in FIG. 3 may be realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

FIG. 3 shows a functional block diagram of the server 10. In the server 10, when the CPU 90 executes the program, as shown in FIG. 3, the biological information acquisition unit 30 as the first acquisition unit, the environmental information acquisition unit 32 as the second acquisition unit, and the yield as the estimation unit. It functions as an estimation unit 34, an output unit 36, and a correction reception unit 38. Note that FIG. 3 also shows an estimated yield DB 28 stored in the HDD 96 or the like of the server 10.

The biological information acquisition unit 30 acquires the biological information of the crop input from the user terminal 70 and transmits it to the yield estimation unit 34. In this embodiment, the biological information includes the leaf length and width of the crop and the planting density. The worker identifies a leaf having an average size and shape among the leaves possessed by the crop, measures the leaf length and leaf width of the specified leaf, and inputs the leaves to the user terminal 70. In addition, the worker inputs the planting density determined at the time of planting the crop to the user terminal 70. Here, the leaf length means the length of the leaf blade of an average size, and the leaf width means the dimension of the part where the leaf blade is the widest. The planting density means the number of plants planted per unit land area (1 m ^2).

The environmental information acquisition unit 32 acquires the environmental information transmitted from the environmental information acquisition device 72 and transmits it to the yield estimation unit 34. Environmental information includes average temperature, cumulative amount of solar radiation, and average CO ₂ concentration.

The yield estimation unit 34 estimates the yield of the crop based on the information acquired from the biological information acquisition unit 30 and the environmental information acquisition unit 32 in consideration of the photosynthetic characteristics of the crop. The yield estimation unit 34 stores the estimated yield information in the estimated yield DB 28. The specific processing of the yield estimation unit 34 and the details of the data structure of the estimated yield DB 28 will be described later.

The output unit 36 reads the information stored in the estimated yield DB 28 and transmits it to the user terminal 70, for example, in response to a request from the user terminal 70.

When the information on the actual yield is input from the user terminal 70, the correction reception unit 38 corrects the estimated yield stored in the estimated yield DB 28 with the actual yield.

(About the processing of server 10)
Hereinafter, the processing of the server 10 will be described in detail with reference to the flowcharts of FIGS. 4 and 5 and FIG. FIG. 6 is a diagram showing a procedure for estimating crop yield based on photosynthetic characteristics. In FIG. 6, the data shown in the broken line frame is the biometric information acquired by the biometric information acquisition unit 30 from the user terminal 70, and the data shown in the gray frame is the environmental information acquisition unit. 32 is the environmental information acquired from the environmental information acquisition device 72. Further, the data shown by the alternate long and short dash line frame is preset information, and the data shown by the solid line frame is information obtained by the yield estimation unit 34 by calculation. In FIG. 6, the step numbers used in FIGS. 4 and 5 are displayed at the locations corresponding to the processes of FIGS. 4 and 5.

It is assumed that the process of FIG. 4 is executed at a predetermined time of the day, for example. At the stage when the processing of FIG. 4 is started, the biological information (average leaf length and width, planting density) of the crop on the day (nth day after planting) is input from the user terminal 70. It is assumed that the biometric information acquisition unit 30 has acquired the biometric information. Further, it is assumed that the environmental information acquisition device 72 acquires the environmental information on the day (nth day after planting), and the environmental information acquisition unit 32 acquires the environmental information.

In the process of FIG. 4, first, in step S12, the yield estimation unit 34 is input from the user terminal 70, and the leaf length (mm / leaf) and leaf width (mm / leaf) acquired by the biological information acquisition unit 30. Obtain information on planting density (plants / m ^2). The biological information is not limited to the case where the worker manually inputs the biometric information to the user terminal 70, and the biometric information may be acquired by analyzing the image taken by the camera.

Next, in step S14, the yield estimation unit 34 calculates the number of expanded leaves based on the average temperature acquired from the environmental information acquisition unit 32. The number of expanded leaves means the number of expanded (expanded) leaves, and the current number of expanded leaves is calculated from the data showing the relationship between the number of expanded leaves in the past and the average temperature and the acquired average temperature value. Can be (estimated). As the number of expanded leaves, a value that the worker actually counts the number of leaves and inputs to the user terminal 70 may be used. In this case, the environmental information acquisition unit 32 does not have to acquire the information on the average temperature.

Next, in step S16, the yield estimation unit 34 calculates the individual leaf area (the area of one leaf having an average size and shape) from the leaf length and the leaf width. ^{In this case, the yield estimation unit 34 can set the individual leaf area (m 2} / leaf) as a value obtained by multiplying the product of the leaf length and the leaf width by a predetermined coefficient. The predetermined coefficient may be obtained in advance from the leaf data obtained in the past.

^{Next, in step S18, the yield estimation unit 34 calculates the leaf area (m 2} / plant) per individual from the number of developed leaves and the individual leaf area. In this case, the yield estimation unit 34 sets the product of the number of developed leaves and the individual leaf area as the leaf area per individual. Next, in step S20, the yield estimation unit 34 calculates a leaf area index (LAI: Leaf Area Index) from the leaf area per individual and the planting density. Here, leaf area index refers to the total leaf area of the crop per unit land area ^{(1m 2) (m 2)} . That is, it can be said that the leaf area index (m ² / m ² ) is the product of the leaf area and the planting density per individual.

Next, in step S22, the yield estimation unit 34 calculates the daily integrated light receiving amount from the leaf area index (LAI), the integrated solar radiation amount (MJ / m ^{2), and the absorption coefficient.} Specifically, the yield estimation unit 34 calculates the daily cumulative light receiving amount (MJ / (m ² · d)) based on the following equation (1). _{In addition, "IL n} " of the following formula (1) is the integrated light receiving amount on the nth day after planting, "k" is the absorption coefficient, and "LAI _n " is the leaf area on the nth day after planting. is an index, "Sr _n" is an outdoor all-sky solar radiation of planting after the n-th day.
IL _n = (1-e ^{-k ・ LAIn} ) ・ 0.55 ・ 0.5 ・ Sr _n … (1)

Here, 0.55 means the light transmission coefficient in the facility (inside the house), and 0.5 means the coefficient for converting into photosynthetically active radiation (PAR).

Next, in step S24, the yield estimation unit 34 calculates the light utilization efficiency from _{the average CO 2 concentration.} Specifically, the yield estimation unit 34 calculates the light utilization efficiency (g / MJ) based on the following equation (2). In the following equation (2), "LUE _n " is the light utilization efficiency on the nth day, and "CO _2n " is the daytime CO ₂ concentration on the nth day (average CO ₂ concentration on the nth day). is there. Further, "m" and "o" are coefficients obtained from the measured values.
LUE _n = m · CO _2n −o… (2)

Next, in step S26, the yield estimation unit 34 executes a process of estimating the daily yield. In step S26, the process according to the flowchart of FIG. 5 is executed.

Here, the yield estimation unit 34 uses a table as shown in FIGS. 7 to 9 when executing the process of step S26. Hereinafter, the tables of FIGS. 7 to 9 will be described.

The tables of FIGS. 7 to 9 are tables for storing various information in association with the number of days from the start of cultivation. Specifically, in the table, "flowering fruit bunch", "sun-dried product production amount", "fruit distribution amount (A)", information on each fruit in each fruit bunch ("accumulated temperature", "maximum for each fruit" "Growable weight (B)", "Daily growth amount (D)", "Integrated fruit weight (E)"), "Total maximum growable weight in one individual (C)", "Dry fruit yield", "Fruit dry matter rate" and "yield" can be stored.

The "Flowering Fruit Bunch" column stores the number of fruit clusters that are expected to have already bloomed on each day. In the column of "daily dry matter production amount", the total daily dry matter production amount calculated from the daily cumulative light receiving amount and the like for each day is stored. The "fruit distribution amount (A)" stores the dry matter production amount distributed to the fruits out of the total daily dry matter production amount. In the "Integrated temperature" column, the accumulated temperature (total daily average temperature of each day) after each fruit blooms is stored, and in the "Maximum growthable weight (B) for each fruit" column, The maximum daily growth weight of each fruit calculated from the accumulated temperature is stored. Further, in the column of "daily growth amount (D)", the weight of each fruit grown in one day is stored. Specifically, the maximum growth weight (B) itself for each fruit or the maximum growth for each fruit is stored. A value calculated from the possible weight (B) and the fruit distribution amount (A) is stored. In the "accumulated fruit weight (E)" column, a value obtained by converting the daily growth amount (D) of each fruit after flowering into a weight per unit land area is stored. The total value of the maximum growthable weight (B) of each fruit cluster is stored in the column of "total maximum growthable weight (C) in one individual as a whole". In the "dry fruit yield" column, the total value of the accumulated fruit weights (E) of the fruits at the harvest timing is stored. The "fruit dry matter ratio" column stores the percentage of dry matter in the fruit, and the "yield" column stores the estimated daily yield.

In the process of FIG. 5, first, in step S40, the yield estimation unit 34 determines whether or not the day (nth day) is the fruit cluster appearance time based on the number of expanded leaves. Specifically, in the yield estimation unit 34, the first fruit cluster appears when the number of leaves exceeds the predetermined number S1 (for example, 15), and thereafter, the number of leaves is S2 (for example, 3). ), It is determined whether or not the fruit cluster appears on the nth day based on the logic that the fruit cluster appears each time. When the yield estimation unit 34 determines that the fruit cluster appears, the number in the column of "flowering fruit cluster" in the tables of FIGS. 7 to 9 is increased by 1 from the previous day.

Next, in step S42, the yield estimation unit 34 calculates the total daily dry matter production amount from the _{daily integrated light receiving amount IL n} and the light utilization efficiency LUE _{n. Specifically, the yield estimation unit 34 calculates the total dry matter production amount DM n} (g / (m ² · d)) for one day (nth day) based on the following equation (3).
DM _n = IL _n · LUE _n … (3)
Then, the yield estimation unit 34 _{multiplies DM n} by the fruit distribution rate to calculate the daily fruit distribution amount (A). For example, in the examples of FIGS. 7 to 9, the fruit distribution rate is calculated as 0.65. Here, the fruit distribution rate can be calculated based on the past data of the same variety. The yield estimation unit 34 calculated the total daily dry matter production in the columns corresponding to the nth day in the columns of "daily dry matter production" and "(A)" in the tables of FIGS. 7 to 9. Enter the numerical values of the amount and the daily fruit distribution amount (A).

Next, in step S44, the yield estimation unit 34 determines whether or not it is the flowering date of each fruit based on the average daily temperature. In the present embodiment, for example, it is assumed that the first fruit (one fruit) blooms at the same time as the fruit cluster appears. Then, when the integrated temperature after flowering of one fruit (the integrated average temperature of each day after flowering) reaches a predetermined value (for example, 140 ° C.), the next fruit (two fruits) blooms. It shall be. After that, similarly, it is assumed that 3 fruits and 4 fruits bloom each time the integrated temperature increases by a predetermined value. In this embodiment, it is assumed that 1 to 4 fruits bloom from one fruit cluster. In the tables of FIGS. 7 to 9, the fruit after flowering is shown by a thick line frame. For example, one fruit in one fruit cluster blooms on the 23rd day, and two fruits, three fruits and four fruits in one fruit cluster bloom on the 28th, 34th and 39th days. In addition, one fruit of the two fruit clusters is in bloom on the 31st day.

Next, in step S46, the yield estimation unit 34 integrates the daily average air temperature for each fruit after flowering and determines whether or not it is the harvest date. For example, the yield estimation unit 34 determines that the day when the accumulated temperature of a certain fruit reaches a predetermined value (for example, 1080 ° C.) is the harvest day of the fruit. For example, in the case of one fruit in one fruit cluster of FIGS. 7 to 9, since the accumulated temperature exceeds 1080 ° C. on the 70th day, it is determined that the harvest date of one fruit in the one fruit cluster is on the 70th day. .. It should be noted that the actual harvesting by the worker is not necessarily the day determined to be the harvesting date.

Then, in step S48, the yield estimation unit 34 calculates the maximum growthable weight for each fruit. In the present embodiment, the yield estimation unit 34 calculates the maximum growthable weight (B) for each fruit by using a graph as shown in FIG. 10 prepared in advance for each variety. The graph of FIG. 10 is a graph in which the cumulative temperature after flowering is on the horizontal axis and the daily growthable weight is on the vertical axis. From the graph of FIG. 10, it can be seen that the daily growthable weight increases until the cumulative temperature after flowering reaches about 400 ° C, but the daily growthable weight gradually decreases after about 400 ° C. Understand. In addition, the yield estimation unit 34 obtained the maximum growthable weight (B) corresponding to the integrated temperature of each fruit on the nth day from the graph of FIG. 10, and the corresponding portion (“(B)) in the table of FIGS. 7 to 9. Store in the line).

Next, in step S50, the yield estimation unit 34 calculates the total maximum growthable weight of one individual as a whole. Specifically, the yield estimation unit 34 integrates the values stored in the row (B) of the tables of FIGS. 7 to 9 to obtain the total (C). In addition, the yield estimation unit 34 stores the obtained total (C) in the column corresponding to the nth day in the column of "(C)" in the tables of FIGS. 7 to 9.

Next, in step S52, the yield estimation unit 34 finds that the daily fruit distribution amount (A) calculated in step S42 is equal to or greater than the total maximum growthable weight (C) of one individual calculated in step S50. Judge whether or not. That is, it is determined whether or not the weight of the fruit of the whole individual can be increased by the maximum growthable weight.

If the determination in step S52 is affirmed, the process proceeds to step S54, and the yield estimation unit 34 sets the value of the maximum growthable weight for each fruit as the daily growth amount (D).

On the other hand, if the determination in step S52 is denied, the process proceeds to step S56, and the yield estimation unit 34 calculates the daily growth amount (D) for each fruit based on the following equation (4).
(D) = (A) x (B) / (C) ... (4)
In the above formula (4), the daily fruit distribution amount (A) is distributed to each fruit according to the size of the maximum growthable weight (B) of each fruit, and the daily growth amount (D) for each fruit is used. It is an expression to do. The yield estimation unit 34 stores the daily growth amount (D) for each fruit in the column corresponding to the nth day in the row of "(D)" in the table of FIGS. 7 to 9.

In the examples of FIGS. 7 to 9, the process of step S54 is executed from the 0th day to the 41st day, and the process of step S56 is executed on the 42nd day of FIG. 9 (FIG. 7). Refer to the part painted in gray on the 42nd day of 9).

After step S54 or step S56, the process proceeds to step S58, and the yield estimation unit 34 integrates the daily growth amount (D) for the period after flowering for each fruit, and ^{per unit land area (1 m 2} ). The value converted into the weight is defined as the integrated fruit weight (E). The yield estimation unit 34 stores the obtained integrated fruit weight (E) in the column corresponding to the nth day in the row (E) of the table of FIGS. 7 to 9.

Next, in step S60, if there is a fruit on the harvest date, the yield estimation unit 34 divides the fruit cumulative weight (E) by the fruit dry matter ratio to obtain the yield (estimated yield). The dry fruit ratio is a predetermined value for each number of days after planting. The yield estimation unit 34 stores the calculated estimated yield value in the column corresponding to the nth day of the “yield” row in the table of FIGS. 7 to 9.

The yield information estimated as described above is stored in the estimated yield DB 28. Here, the estimated yield DB 28 has a data structure as shown in FIG. 11 (a). Specifically, the estimated yield DB28 is used or calculated when calculating the fresh fruit yield (estimated yield) in addition to the "house name", "date", and "estimated yield". The values (average temperature, average CO ₂ concentration, cumulative amount of solar radiation, number of expanded leaves, LAI, light utilization efficiency) are stored.

As a result, the processing of FIGS. 4 and 5 by the yield estimation unit 34 is completed.

Here, it is assumed that the administrator or the like inputs an instruction to display the estimated yield to the user terminal 70. In this case, when the output unit 36 receives the instruction to that effect from the user terminal 70, the output unit 36 reads the data from the estimated yield DB 28 and transmits it to the user terminal 70. For example, when an instruction to display the estimated yield of House A from April 6 to 13, 2018 is input, the output unit 36 outputs the information of the date from the estimated yield DB 28 (FIG. 11 (FIG. 11). The data for eight lines of a) is read out to generate a screen as shown in FIG. 11B, which is transmitted to the user terminal 70.

In this case, for example, on the screen shown in FIG. 11B, the administrator or the like may modify some information. For example, if the actual yield differs from the estimated yield, the value of "estimated yield" may be changed. In this case, the correction reception unit 38 acquires the corrected information and updates the estimated yield DB 28.

In addition, the yield estimation unit 34 also has a function of simulating how the estimated yield changes when, for example, the temperature inside the greenhouse is changed or the CO _{2 concentration is changed.} For example, the yield estimation unit 34 can simulate the yield on the assumption that the environmental information of the next day is the same as the environmental information of the previous day. In this case, the yield estimation unit 34 describes, for example, when the CO ₂ concentration is increased by a predetermined concentration, when the temperature is increased by a predetermined temperature, when the CO ₂ concentration and the temperature are increased, and the like. It can be simulated by the same processing. For example, the output unit 36 outputs the simulation result to the user terminal 70 to provide the simulation result to the administrator or the like. Then, when the administrator or the like selects one of the simulation results, the output unit 36 sets the control target device 74 so that the environment in the house on the next day becomes the environment corresponding to the selected simulation result. Outputs control information (issues control instructions). As a result, the environment in the house can be adjusted so that the yield desired by the manager or the like is obtained. The output unit 36 may specify the environment in which the yield (estimated value) is the largest among the simulation results, and output the control information to the control target device 74 so as to obtain the specified environment.

As described in detail above, according to the present embodiment, the biological information acquisition unit 30 acquires the biological information of the crop, and the environmental information acquisition unit 32 acquires the environmental information on which the crop grows, and the yield estimation unit 34. However, the state of the fruit of the crop is estimated based on the acquired biological information and the environmental information, and the yield of the crop is estimated based on the estimated state of the fruit and the biological information and the environmental information (S14 to S26). As a result, in the present embodiment, the state of the fruit is estimated based on the photosynthetic characteristics, and the yield of the crop is estimated based on the estimated state of the fruit, so that the yield can be estimated accurately. .. Further, in the present embodiment, the yield can be easily estimated only by the manager or the like inputting the leaf length, leaf width, and planting density. In addition, since the yield can be estimated accurately, it is possible to accurately estimate the number of workers required at the time of harvesting, the fuel for transportation, the quantity of packing materials, the equipment for harvesting, and the like.

Further, in the present embodiment, the yield estimation unit 34 determines whether or not the fruit bunches appear at the time of appearance based on the number of developed leaves of the crop (S40), and the fruit bunches are based on the environmental information after the fruit bunches appear. Determine the state. As a result, the yield estimation unit 34 can accurately estimate the yield based on the state of the fruit (harvest time and weight).

Further, in the present embodiment, since the yield estimation unit 34 calculates the number of expanded leaves based on the integrated temperature, the amount of work of the manager or the like can be reduced as compared with the case where the number of expanded leaves is manually input. ..

Further, in the present embodiment, the yield estimation unit 34 calculates the cumulative temperature after flowering of each fruit, and determines that the fruit whose calculated cumulative temperature is equal to or higher than a predetermined value is a fruit that can be harvested (S46). As a result, the yield estimation unit 34 can accurately determine the harvest time of the fruit.

Further, in the present embodiment, the yield estimation unit 34 determines the flowering date (flowering timing) of each fruit in the fruit cluster based on the accumulated temperature after the fruit cluster appears (S44). As a result, the flowering timing of each fruit can be appropriately predicted without visually confirming the state of each fruit.

Further, in the present embodiment, the biological information includes information (leaf length and leaf width) for calculating the leaf area, and the yield estimation unit 34 is based on the leaf length and leaf width and the cumulative amount of solar radiation. The cumulative light-receiving amount in the crop is calculated, and the weight of the fruit at the time of harvest (that is, the yield of the crop) is estimated based on the calculated cumulative light-receiving amount. As a result, in the present embodiment, the yield is estimated based on the photosynthetic characteristics based on the state of the leaves of the crop and the amount of solar radiation on the leaves, so that the yield of the crop can be estimated accurately.

Further, in the present embodiment, the yield estimation unit 34 calculates the leaf area of the crop based on the leaf length and the leaf width, so that the manager or the like does not have to measure the leaf area. You can save time and effort.

Further, in the present embodiment, the yield estimation unit 34 has a function of simulating the yield by changing the environmental information. This makes it possible to confirm how the yield changes when the CO _{2 concentration, temperature, etc. are changed.} Further, since the output unit 36 outputs the control information of the control target device 74 based on the simulation result, it is possible to control the control target device 74 so as to increase the yield.

In the above embodiment, the case where the yield is estimated every day has been described, but for example, the yield may be estimated every half day or every predetermined time in the same manner as described above.

The yield estimation method described in the above embodiment is an example. That is, a part of the above formula may be modified. Further, the value obtained by calculation in the above embodiment may be actually measured.

In the above embodiment, the case where the server 10 estimates the yield has been described, but the present invention is not limited to this. For example, each user terminal 70 may have the function of the server 10 (the function of FIG. 3).

(Example)
Hereinafter, examples will be described. The invention of the present application is not limited to the following examples.

FIG. 12A shows the result (predicted yield) of predicting the yield when tomatoes are densely planted in a low stage by the method of the above embodiment using the environmental information (actual measurement value) in the past predetermined period, and actually. It is a graph comparing with the yield (measured yield) obtained as a result of low-stage dense planting cultivation of tomatoes in a predetermined period. Further, FIG. 12B shows the result (predicted yield) of predicting the yield when tomatoes are cultivated in multiple stages for a long period of time by the method of the above embodiment using the environmental information (measured value) in the past predetermined period, and the actual result. It is a graph comparing with the yield (measured yield) obtained as a result of long-term multi-stage cultivation of tomatoes in a predetermined period. As shown in these graphs, it was possible to accurately predict the yield in both the low-stage dense planting cultivation and the long-term multi-stage cultivation.

FIG. 13A shows the result (predicted value) of predicting the total dry matter production amount of cucumber by the method of the above embodiment using the environmental information (actual measurement value) in the past predetermined period, and the actual cucumber in the predetermined period. It is a graph comparing with the total dry matter production amount (measured value) obtained as a result of cultivating. Further, FIG. 13B shows the result (predicted value) of predicting the yield when cultivating cucumber by the method of the above embodiment using the environmental information (actual measurement value) in the past predetermined period, and the actual predetermined value. It is a graph comparing with the yield (measured value) obtained as a result of cultivating cucumber in the period. As shown in these graphs, both the total dry matter production of cucumber and the yield could be predicted accurately.

FIG. 14 shows the result (predicted value) of predicting the weekly yield of paprika by the method of the above embodiment using the environmental information (actual measurement value) in the past predetermined period, and the result of actually cultivating paprika in the predetermined period. It is a graph comparing with the obtained weekly yield (measured value). The ratio described in the vicinity of the bar graph means a relative error (= (| predicted value-measured value | / predicted value) x 100%). As shown in FIG. 14, although there is a difference in the accuracy of short-term yield prediction due to unexpected influences such as pest outbreak, cultivation management problems, and harvest degree, as a whole, the tendency of the predicted value and the tendency of the measured value. Was able to match.

Considering these results, the future yield when tomatoes and crops other than tomatoes (for example, cucumber, paprika, etc.) are cultivated by various cultivation methods can be determined by using future environmental information (predicted values). It is considered that accurate prediction can be made by the method described in the form.

(Other Embodiments (Part 1))
When comparing the dry matter production amount per unit time (group photosynthesis amount) and the expected fruit growth amount per unit time (photosynthesis amount required for fruit growth), the dry matter production amount (group photosynthesis amount) If the amount is smaller, it means that the amount of photosynthesis required for fruit growth is insufficient. 15 (a) and 15 (b) are graphs showing the relationship between the dry matter production amount and the daily fruit growth amount on each day of the cultivation period in the tomato cultivation example. For example, the period A shown in FIG. 15A and the period B shown in FIG. 15B are periods in which the dry matter production amount (community photosynthesis amount) is smaller than the daily fruit growth amount. It can be said that these periods A and B are periods in which an improvement in yield can be expected by increasing the amount of photosynthesis.

Therefore, in this example, in the server 10, the maximum growthable weight of the entire individual in which the dry matter production amount (FIG. 5: S42) predicted by the method similar to the above embodiment is predicted by the same method as the above embodiment. When it is less than the total (C) (FIG. 5: S50), a warning (a message indicating that countermeasures are required) is issued to the user terminal 70. For example, by warning the worker that the dry matter production of the next day or the next week is likely to be less than the daily fruit growth, the worker raises the temperature and CO ₂ concentration in the next day or the next week. It is possible to perform cultivation management such as controlling the environment of carbon dioxide and increasing the number of leaves. By doing so, the amount of photosynthesis can be increased and the yield can be improved.

FIG. 16 is a graph showing the relationship between the daily dry matter production amount and the daily fruit growth amount in the cultivation example of paprika. For example, the period C shown in FIG. 16 is a period in which the dry matter production amount (community photosynthesis amount) is smaller than the daily fruit growth amount. It can be said that this period C is a period in which an improvement in yield can be expected if the amount of photosynthesis is increased.

Therefore, in this example, the server 10 warns that there will be a period in the future, such as period C, in which the amount of photosynthesis required for the fruit will be overwhelmingly insufficient, based on the prediction result. If the worker determines that the fruit set load is large, it is possible to perform fruit thinning (adjustment of the number of fruit set), stabilize the enlargement of the fruit, and improve the quality. In addition, if the worker determines that the amount of photosynthesis is insufficient, it is possible to increase the amount of photosynthesis and improve the yield by performing environmental control such as increasing the _{temperature and CO 2 concentration.}

(Other Embodiments (Part 2))
Even if the yield is predicted as shown in FIG. 4, the difference between the predicted yield and the actual yield suddenly increases from the state where a certain range is maintained (the expected yield cannot be obtained suddenly). )Sometimes. For example, as shown in FIG. 17, although the difference between the measured value and the predicted value of the integrated yield was within a predetermined allowable range in the period D, the difference sharply increased in the period E, and thereafter. A large difference may be maintained during period F. Normally, the predicted yield is calculated based on the measured environmental information and growth information, so it should reflect the influence of the environment such as solar radiation and temperature. Therefore, it is highly possible that such changes occur due to other factors (such as failure of nutrient water management and outbreak of pests).

In this example, the server 10 issues a warning from the user terminal 70 when there is a change (a sudden change in difference) as shown in the period E. As a result, the worker can check the cultivation management status (water supply management, pest outbreak, etc.) and eliminate the risk of affecting the yield at an early stage. When issuing a warning, the server 10 may also output a message to the effect that the cultivation management status (water nutrient management, pest outbreak, etc.) should be checked (prompting confirmation).

The above processing function can be realized by a computer. In that case, a program that describes the processing content of the function that the processing device should have is provided. By executing the program on a computer, the above processing function is realized on the computer. The program describing the processing content can be recorded on a computer-readable storage medium (excluding the carrier wave).

When a program is distributed, it is sold in the form of a portable storage medium such as a DVD (Digital Versatile Disc) or a CD-ROM (Compact Disc Read Only Memory) on which the program is recorded. It is also possible to store the program in the storage device of the server computer and transfer the program from the server computer to another computer via the network.

The computer that executes the program stores, for example, the program recorded on the portable storage medium or the program transferred from the server computer in its own storage device. Then, the computer reads the program from its own storage device and executes the processing according to the program. The computer can also read the program directly from the portable storage medium and execute the process according to the program. In addition, the computer can sequentially execute processing according to the received program each time the program is transferred from the server computer.

The embodiments described above are examples of preferred embodiments of the present invention. However, the present invention is not limited to this, and various modifications can be made without departing from the gist of the present invention.

10 servers (yield estimation device)
30 Biological Information Acquisition Department (1st Acquisition Department)
32 Environmental Information Acquisition Department (2nd Acquisition Department)
34 Yield estimation part (estimation part)

Claims (14)

Acquire biological information of crops,
Acquire environmental information on which crops grow,
The yield of the crop is estimated based on the biological information, the environmental information, and the fruit state of the crop estimated from at least one of the biological information and the environmental information.
A yield estimation program that lets a computer perform the process. In the estimation process, the appearance timing of the fruit cluster is specified based on the number of developed leaves of the crop, and the state of the fruit in the fruit cluster is estimated based on the environmental information after the fruit cluster appears. The yield estimation program according to claim 1. The yield estimation program according to claim 2, wherein in the estimation process, the number of developed leaves is calculated based on the integrated air temperature. The yield estimation program according to claim 2 or 3, wherein in the estimation process, the flowering timing of the fruit in the fruit cluster is specified based on the accumulated temperature after the fruit cluster appears. The estimation process according to claim 1 to 4, wherein the integrated temperature after flowering of each fruit is calculated, and the fruit whose integrated temperature is equal to or higher than a predetermined value is estimated as a harvestable fruit. The yield estimation program according to any one item. The biological information includes information on the leaf size of the crop.
In the estimation process, the integrated light receiving amount in the crop was calculated based on the information on the leaf size and the accumulated solar radiation amount, and it was estimated that the harvest was possible based on the calculated integrated light receiving amount. The yield estimation program according to claim 5, wherein the weight of each fruit is estimated. The biological information includes measurement results of leaf length and width of the crop.
The estimation process is characterized in that the area per leaf calculated based on the measurement results of the leaf length and width of the crop is used for estimating the weight of each of the fruits estimated to be harvestable. The yield estimation program according to claim 6. The estimation is characterized in that the light utilization efficiency calculated based on the carbon dioxide concentration in the air contained in the environmental information is used for estimating the weight of each of the fruits estimated to be harvestable. Item 5. The yield estimation program according to any one of Items 5 to 7. In the estimation process, in order to estimate the yield of the crop, the amount of dry matter produced per unit time in the crop and the estimated amount of fruit growth per unit time in the crop are estimated.
On the computer
The yield estimation program according to any one of claims 1 to 8, further performing a process of outputting a comparison result of the dry matter production amount and the assumed fruit growth amount. The process according to claim 9, wherein in the process of outputting the comparison result, a message indicating that countermeasures are necessary is output when the dry matter production amount is smaller than the assumed fruit growth amount. Yield estimation program. The present invention according to any one of claims 1 to 10, wherein it is determined whether the difference between the estimated yield of the crop and the actual yield is equal to or greater than a predetermined value, and the determination result is output, and the computer further executes the process. Yield estimation program. The yield estimation program according to claim 11, wherein a message prompting confirmation of the cultivation management status is output when the determination result that the difference is equal to or greater than a predetermined value is output. Acquire biological information of crops,
Acquire environmental information on which crops grow,
The yield of the crop is estimated based on the biological information, the environmental information, and the fruit state of the crop estimated from at least one of the biological information and the environmental information.
A yield estimation method characterized by a computer performing the process. The first acquisition department that acquires biological information of crops,
The second acquisition department that acquires environmental information on which crops grow,
The yield of the crop is estimated based on the biological information, the environmental information, and the fruit state of the crop estimated from at least one of the biological information and the environmental information.
A yield estimation device including an estimation unit.

Images