Growth condition prediction method, growth condition prediction program, and information processing device
A computer-based growth prediction model using temperature and solar radiation parameters accurately forecasts vegetable growth states, addressing supply chain inefficiencies by enabling timely management of vegetable production.
Patent Information
- Application Number
- JP2021076351
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Priority Date
- 2020-05-07
- Filing Date
- 2021-04-28
- Publication Date
- 2024-11-07
- Estimated Expiration
- 2041-04-28
AI Technical Summary
Existing methods struggle to accurately predict the growth state of vegetables such as green onions, head vegetables, and flower vegetables, making it difficult for intermediary businesses to manage supply and demand due to weather fluctuations, leading to inefficiencies in procurement and disposal.
A growth state prediction method using a computer model that determines parameters based on temperature and solar radiation to predict the growth state of vegetables, incorporating different stages of cultivation and regeneration, allowing for accurate forecasting of harvest time and amount.
Enables precise prediction of vegetable growth states, enabling intermediary businesses to take appropriate measures such as securing procurement sources and shipping destinations, reducing waste and improving operational efficiency.
Smart Images

Figure 0007578980000001 
Figure 0007578980000002 
Figure 0007578980000003
Abstract
Description
[Technical field]
[0001] The present invention relates to a growth state prediction method, a growth state prediction program, and an information processing device. [Background technology]
[0002] Leafy vegetables such as green onions, head vegetables such as cabbage and lettuce, and flower vegetables such as broccoli, which are seeing growing demand for processing and commercial use, are grown outdoors and are therefore susceptible to the effects of weather. For this reason, intermediate businesses that handle these vegetables make contracts with multiple producing areas to adjust shipments to ensure a fixed and fixed supply to actual users in response to surpluses and shortages in shipments caused by weather changes.
[0003] However, production information for each production area is often not available until a few days in advance. For example, in the cultivation of green onions, in addition to the fixed planting cultivation in which seedlings are generally planted and cultivated, regeneration cultivation is also carried out in which only the above-ground parts of the plants that have reached the optimum harvesting period are harvested, and the regenerated parts from the remaining base are harvested again, making the cultivation complicated. For this reason, in large-scale management with many fields, it is difficult to accurately forecast the shipping situation for the entire management.
[0004] Intermediate businesses are forced to procure the shortfall if the actual shipping volume falls short of the contracted volume, and producers are forced to abandon farmland if the actual shipping volume far exceeds the contracted volume. [Prior art documents] [Non-patent literature]
[0005] [Non-Patent Document 1] "Development of a growth model for Kujo-type green onions (Part 1) Growth prediction based on estimated solar radiation utilization efficiency of green onion communities", Kazutoshi Nagasawa, Fumio Sato, Koji Sugawara, Yukitoshi Hemmi, Ryo Kamo, Kunihiko Okada, Horticultural Research 17 (supplement 1) 160.2017. [Non-Patent Document 2] "Development of a growth model for Kujo-type green onions (Part 2) Analysis of the relationship between leaf area, temperature and solar radiation in green onion communities in different growing seasons", Kazutoshi Nagasawa, Fumio Sato, Koji Sugawara, Yukitoshi Hemmi, Ryo Kamo, Kunihiko Okada, Horticultural Research 17(Extra 2) 224.2017. Summary of the Invention [Problem to be solved by the invention]
[0006] In the situation described above, if it were possible to predict harvest times and yields two weeks to one month in advance, it would enable intermediate businesses and local producers to take appropriate measures (such as securing new suppliers and shipping destinations). Therefore, there is a need for technology that can accurately predict the growth conditions of vegetables.
[0007] Therefore, an object of the present invention is to provide a growth condition prediction method, a growth condition prediction program, and an information processing device that can accurately predict the growth condition of vegetables that can be grown by fixed planting or regenerated after fixed planting. [Means for solving the problem]
[0008] The growth state prediction method of the present invention includes the steps of: fixed A method for predicting the growth state of a vegetable that can be regenerated after planting, comprising: A plurality of stages included in the first period of the fixed planting cultivation and a second period of the regeneration cultivation Any of the multiple stages included in Stage the stage being determined, parameters of a model for predicting the growth state of the vegetable to be predicted based on temperature and solar radiation are determined based on the determined stage, and the growth state of the vegetable to be predicted is predicted using the model in which the determined parameters are set. Effect of the Invention
[0009] It is possible to accurately predict the growth state of vegetables that can be grown by fixed planting or that can be regenerated after fixed planting. [Brief description of the drawings]
[0010] [Figure 1] FIG. 1 shows a cultivation system for green onions in one field. [Diagram 2] FIG. 2(a) is a diagram showing the hardware configuration of a terminal, and FIG. 2(b) is a functional block diagram of the terminal. [Diagram 3] FIG. 1 is a diagram showing a growth model that is the basis of a growth model used to predict the growth state of green onions. [Figure 4] FIG. 2 is a diagram showing a growth model of green onions and the like according to one embodiment. [Diagram 5] FIG. 2 is a diagram for explaining the growth stages of green onions. [Figure 6] 13 is a table showing parameter combinations for each stage. [Figure 7] FIG. 7(a) is a table showing the planting dates and the harvesting and regrowth start dates in the cropping season shifting test, and FIG. 7(b) is a diagram for explaining an overview of the cropping season shifting test. [Figure 8] 1 is a graph showing the canopy solar radiation shading rate characteristics. [Figure 9] FIG. 9(a) is a graph showing the growth of plants during fixed planting cultivation in each cultivation season, and FIG. 9(b) is a graph showing the relationship between the dry weight of the stems and leaves and the accumulated amount of solar radiation received during fixed planting cultivation. [Figure 10] FIG. 1 is a graph showing the relationship between solar radiation utilization efficiency and air temperature during the early and mature stages of planting cultivation. [Figure 11] FIG. 1 is a diagram showing the results of plotting the relationship between the dry matter weight of the stem and leaf and the dry matter partitioning rate to the leaf blade. [Figure 12] FIG. 13 is a graph showing the relationship between air temperature and the dry matter partitioning rate to the leaf blade during the early and mature stages of planting cultivation. [Figure 13] FIG. 1 is a diagram showing the results of plotting the relationship between the dry matter weight of the stem and leaf and the dry matter percentage of the leaf blade. [Figure 14] FIG. 1 is a graph showing the relationship between the leaf blade dry matter percentage and air temperature during the early and mature stages of planting cultivation. [Figure 15]FIG. 13 is a diagram showing the results of plotting the relationship between the dry matter weight of the stem and leaf and the dry matter percentage of the leaf sheath. [Figure 16] FIG. 13 is a graph showing the relationship between the dry matter percentage of the leaf sheath and air temperature during the early and mature stages of planting cultivation. [Figure 17] FIG. 1 is a graph showing the relationship between the fresh weight of the leaf blade and the leaf area / fresh weight ratio of the leaf blade. [Figure 18] 1 is a graph showing the growth of plants (changes in dry weight of stems and leaves) during regeneration cultivation in each cultivation season. [Figure 19] Figure 19(a) is a graph showing the change in dry matter weight of the leaf blade during regeneration cultivation in each cultivation season, and Figure 19(b) is a graph showing the change in dry matter weight of the leaf sheath during regeneration cultivation in each cultivation season. [Figure 20] 1 is a graph showing the relationship between temperature and the number of days from day 0 after harvest until the dry weight of the leaf sheath begins to increase. [Figure 21] Figure 21(a) is a graph showing the relationship between the cumulative amount of solar radiation received (MJ / plant) and the dry matter weight of the stems and leaves (g / plant), and Figure 21(b) is a graph showing the relationship between the solar radiation utilization efficiency and air temperature in each growing season. [Figure 22] This is a plot of the relationship between the dry matter weight of the stem and leaves (g / plant) and the dry matter distribution rate (%) to the leaf blade during regeneration cultivation. [Figure 23] This is a graph showing the relationship between temperature and the dry matter partitioning rate (%) to the leaf blade during the early growth period (including the internal translocation period) and the mature growth period of regenerative cultivation. [Figure 24] This is a plot of the relationship between the dry matter weight of the stem and leaves (g / plant) and the dry matter rate of the leaf blade (%) in regeneration cultivation. [Diagram 25] This is a graph showing the relationship between the leaf blade dry matter percentage and temperature during the early growth stage (including the internal translocation stage) and the mature growth stage of regeneration cultivation. [Figure 26] This is a plot of the relationship between the dry matter weight of the stem and leaves (g / plant) and the dry matter rate (%) of the leaf sheath in regeneration cultivation. [Figure 27] This is a graph showing the relationship between the dry matter content of the leaf sheath and temperature during the early growth period (including the internal translocation period) and the peak growth period of regenerative cultivation. [Figure 28]1 is a graph showing the ratio of leaf area / fresh weight of the leaf blade to the fresh weight of the leaf blade at the early growth stage of regeneration cultivation and at the peak growth stage of regeneration cultivation. [Figure 29] 13 is a flowchart showing a process of the terminal. [Diagram 30] 30(a) and 30(b) are diagrams for explaining prediction results. [Diagram 31] FIG. 31(a) to FIG. 31(d) are diagrams for explaining the prediction results. [Diagram 32] 32(a) and 32(b) are diagrams for explaining prediction results. [Diagram 33] FIG. 2 is a diagram showing a growth model of flower vegetables according to one embodiment. [Diagram 34] FIG. 34(a) is a diagram for explaining the growth stages of flower vegetables, and FIG. 34(b) is a table showing combinations of parameters for each growth stage of flower vegetables. [Diagram 35] FIG. 35(a) is a table showing planting dates in the broccoli cropping season shifting test, and FIG. 35(b) is a diagram for explaining an overview of the broccoli cropping season shifting test. [Diagram 36] FIG. 36(a) is a graph showing the growth of broccoli plants in each cultivation season, and FIG. 36(b) is a graph showing the relationship between the above-ground dry weight of broccoli plants and the integrated amount of solar radiation received. [Figure 37] FIG. 1 is a graph showing the relationship between the solar radiation use efficiency of broccoli and air temperature. [Figure 38] FIG. 1 is a plot of the relationship between the above-ground dry weight of broccoli and the number of days after planting. [Figure 39] FIG. 1 is a plot of the relationship between the dry matter partitioning rate of broccoli florets and the accumulated temperature during the cultivation period. [Diagram 40] FIG. 40(a) is a plot of the relationship between the dry matter weight and dry matter rate of the outer leaves of broccoli, and FIG. 40(b) is a plot of the relationship between the dry matter rate of the outer leaves of broccoli and air temperature. [Diagram 41]FIG. 41(a) is a plot of the relationship between the dry matter weight of the broccoli flower bud and the dry matter rate of the flower bud, and FIG. 41(b) is a plot of the relationship between the dry matter rate of the flower bud and the temperature. [Diagram 42] FIG. 2 is a diagram showing a growth model of head vegetables according to one embodiment. [Diagram 43] FIG. 43(a) is a diagram for explaining the growth stages of heading vegetables, and FIG. 43(b) is a table showing combinations of parameters for each growth stage of heading vegetables. [Diagram 44] FIG. 44(a) is a table showing planting dates in the cabbage cropping season shift test, and FIG. 44(b) is a diagram for explaining an overview of the cabbage cropping season shift test. [Diagram 45] FIG. 45(a) is a diagram for explaining the projected leaf area, and FIG. 45(b) is a diagram plotting the relationship between the number of days after planting of cabbage and the projected leaf area. [Figure 46] FIG. 46(a) is a graph showing the growth of cabbage plants in each growing season, and FIG. 46(b) is a graph showing the relationship between the above-ground dry weight of cabbage and the integrated amount of solar radiation received. [Figure 47] FIG. 1 is a plot of the relationship between above-ground dry weight of cabbage and the number of days after planting. [Figure 48] This is a plot of the relationship between the dry matter distribution rate in the head of cabbage and the accumulated temperature during the cultivation period. [Figure 49] The results are shown plotting the relationship between the dry matter weight of the head of cabbage and the dry matter percentage of the head. [Figure 50] FIG. 1 is a graph showing the relationship between the projected leaf area / outer leaf dry matter weight ratio and outer leaf dry matter weight of cabbage. [Figure 51] 13 is a flowchart showing an example of processing executed by a terminal when predicting the growth state of flower vegetables or heading vegetables for each day. [Figure 52] 52(a) and 52(b) are diagrams for explaining the prediction results for broccoli. [Figure 53] 53(a) and 53(b) are diagrams for explaining the prediction results for cabbage. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0011] A method for predicting the growth state of leaf onions according to one embodiment will be described in detail below. FIG. 1 is a diagram that shows a schematic diagram of a cultivation system for leaf onions in one farm field. As shown in FIG. 1, leaf onions are sown in cell trays or the like, and then grown as seedlings, which are then planted in a farm field. Then, the seedlings are grown for 2 to 3 months after planting, and harvested when the fresh weight of the stalk reaches a predetermined weight. If the leaf onions are harvested while leaving the roots (sprouts) intact, regeneration cultivation is performed in which stalks regenerate from the remaining roots and are grown for 1 to 2 months.
[0012] Fig. 2(a) shows the hardware configuration of a terminal 70 as an information processing device for predicting the growth state of green onions. As shown in Fig. 2(a), the terminal 70 includes a CPU (Central Processing Unit) 190, a ROM (Read Only Memory) 192, a RAM (Random Access Memory) 194, a storage unit (here, a HDD (Hard Disk Drive)) 196, a network interface 197, a display unit 193, an input unit 195, and a portable storage medium drive 199 capable of reading the portable storage medium 191. These components of the terminal 70 are connected to a 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. In the terminal 70, the functions of each part shown in FIG. 2(b) are realized by the CPU 190 executing a program (including a growth condition prediction program) stored in the ROM 192 or the HDD 196, or a program (including a growth condition prediction program) read from the portable storage medium 191 by the portable storage medium drive 199.
[0013] Fig. 2(b) shows a functional block diagram of the terminal 70. In the terminal 70, the CPU 190 executes a program to realize functions as the stage determination unit 20, the prediction unit 22, and the display control unit 24 shown in Fig. 2(b). Details of the units 20, 22, and 24 will be described later. Details of the prediction DB 30 shown in Fig. 2(b) will also be described later.
[0014] FIG. 3 shows the growth model that is the basis for the growth model used to predict the growth state of green onions in this embodiment. The growth model in FIG. 3 is based on a matter production model, and is a model in which crops repeat compound growth and expansion based on dry matter production through photosynthesis in leaves caused by receiving solar radiation. When predicting the fresh weight (g / plant) of the crop on the day (the predicted day) using the growth model in FIG. 3, the leaf area (m 2 / share) and the daily accumulated solar radiation (MJ / m 2 ), the daily accumulated amount of solar radiation shading (MJ / plant) is calculated, and the dry matter production (g / plant) for that day is calculated from the calculated daily accumulated amount of solar radiation shading (MJ / plant). The calculated dry matter production (g / plant) for that day and the dry matter weight (g / plant) for the previous day are summed to determine the dry matter weight (g / plant) for that day, and the fresh weight for that day is calculated from the dry matter weight (g / plant) for that day and a predetermined dry matter rate. The leaf area for the next day is also calculated from the dry matter weight for that day. The calculated leaf area can be used to predict the fresh weight for the next day.
[0015] The present inventors have created a growth model for vegetables (such as green onions) based on the growth model in Figure 3. The growth model created by the present inventors is shown in Figure 4. The growth model for green onions shown in Figure 4 was developed based on knowledge gained as a result of an analysis of the matter production characteristics of green onions through an investigation of the cropping season shift test described below.
[0016] Below, an overview of the growth model in Fig. 4 will be described. The growth model in Fig. 4 is held by the prediction unit 22 in Fig. 2(b), and the prediction unit 22 predicts the growth state of the green onion based on the growth model.
[0017] When calculating the fresh weight as the growth state on a certain day (a day to be predicted) using the growth model of FIG. 4, the prediction unit 22 first calculates the leaf area (m 2 / stock) and the daily accumulated solar radiation (MJ / m 2 ) and the external input condition planting density (plants / m 2 ) and calculates the daily accumulated solar radiation shading amount (MJ / plant). If it is immediately after planting, the user may manually input the initial value of the leaf area, or a value determined in advance as the initial value of the leaf area may be used. Instead of manually inputting the initial value of the leaf area, the user may manually input the fresh weight of the stems and leaves. In this case, the prediction unit 22 calculates the leaf area by multiplying the manually input fresh weight of the stems and leaves by a predetermined coefficient.
[0018] Next, in step S12, the prediction unit 22 calculates the daily dry matter production (g / stock) on the predicted day from the calculated daily integrated solar radiation shading amount (MJ / stock). In calculating this daily dry matter production, the solar radiation use efficiency (g / MJ) is used.
[0019] Next, in step S14, the prediction unit 22 calculates the dry matter weight of the plant (g / plant) by adding the daily dry matter production amount (g / plant) calculated in step S12 to the dry matter weight up to the previous day.
[0020] Next, in step S16, the prediction unit 22 calculates the dry matter weight of the leaf blade (g / plant) and the dry matter weight of the leaf sheath (g / plant) using the dry matter weight of the plant (g / plant) and the leaf blade dry matter distribution rate (%).
[0021] Next, in step S18, the prediction unit 22 calculates the fresh weight of the leaf blade (g / plant) based on the leaf blade dry matter weight (g / plant) and the leaf blade dry matter rate (%) calculated in step S16. In addition, in step S20, the prediction unit 22 calculates the fresh weight of the leaf sheath (g / plant) based on the leaf sheath dry matter weight (g / plant) and the leaf sheath dry matter rate (%) calculated in step S16.
[0022] Then, in step S22, the prediction unit 22 calculates the sum of the leaf blade fresh weight (g / plant) and the leaf sheath fresh weight (g / plant), and sets this as the fresh weight of the plant (g / plant).
[0023] In step S24, the prediction unit 22 multiplies the ratio of the leaf area to the fresh weight of the leaf blade by the fresh weight of the leaf blade (g / plant) to obtain the leaf area (m 2 / Stock) to update.
[0024] Thereafter, by repeating the process of FIG. 4, it is possible to predict changes in the growth state of the green onions (changes in fresh weight) over a specified period of time.
[0025] Here, the inventors analyzed the results of the cropping season shift test described below and found that leaf onions have growth stages as shown in Fig. 5. More specifically, the cultivation of leaf onions includes a fixed planting cultivation period (first period) and a regrowth cultivation period after harvesting (cutting) (second period), and it was found that the fixed planting cultivation period is divided into an "early growth period (establishment period)" stage and a "vigorous growth period" stage, and that the regrowth cultivation period is divided into an "internal translocation period" stage, an "early growth period (transition period)" stage, and a "vigorous growth period" stage.
[0026] Furthermore, the present inventors have found from the results of the cropping season shift test that when predicting the growth state of leaf onions, by varying the parameters used in the growth model of FIG. 4 according to the stage to which the leaf onions belong, the growth state can be predicted with high accuracy regardless of the stage to which the leaf onions belong. Note that parameter combinations are prepared in advance for each stage as shown in FIG. 6. Furthermore, each parameter is set for each variety and item based on the results of the cropping season shift test described below.
[0027] (Regarding the crop season shift test) For the crop shifting experiment, planting and regrowth cultivation were carried out on the planting dates and harvesting and regrowth start dates shown in Figure 7(a). During the cultivation period, multiple plants were sampled several times as survey subjects, as shown in the left diagram of Figure 7(b), and plant height, leaf area, stem and leaf fresh weight, stem and leaf dry weight, and images (projected images of the plant) were obtained for each plant, as shown in the center diagram of Figure 7(b). In addition, for the growth survey of the crop shifting experiment, each plant was divided into individual units, as shown in the right diagram of Figure 7(b), and each plant was divided into the leaf blade, which performs photosynthesis, and the leaf sheath, which stores nutrients.
[0028] (Analysis of the solar radiation shading properties of green onion leaves) First, the present inventors conducted a study to clarify the canopy solar radiation shading rate, i.e., what percentage of sunlight falling on a certain area is received at each growth stage.
[0029] The amount of solar radiation shaded by the canopy was measured by taking one row of planted green onions as one unit, measuring the proportion of the amount of solar radiation reaching the ground surface within the canopy out of the amount of solar radiation outside the canopy for each section, and calculating the average value. The amount of solar radiation was measured using the standard type of the simple integrated solar radiation measurement film "Optleaf (registered trademark)".
[0030] By plotting the relationship between the leaf area index and the solar shading factor, the inventor was able to find the canopy solar shading factor characteristics shown in Figure 8. This characteristic is considered to be a common characteristic between fixed planting cultivation and regeneration cultivation.
[0031] <Analysis of fixed planting cultivation> ((1) Growth characteristics and modeling in fixed planting cultivation) Figure 9(a) is a graph showing the growth of plants during fixed planting cultivation in each growing season (change in stem and leaf dry matter weight (g / plant)). Figure 9(a) shows that the rate of increase in stem and leaf dry matter weight differs depending on the growing season. It was also found that in each growing season, there is an early growth period in which the increase in stem and leaf dry matter weight is slow, followed by a period of rapid growth in which the increase in stem and leaf dry matter weight is vigorous.
[0032] ((2) Dry matter increase per unit of solar radiation received in fixed-plant cultivation (solar radiation utilization efficiency) Figure 9(b) shows the relationship between the dry weight of the stems and leaves and the cumulative amount of solar radiation received during planting cultivation. Although a linear relationship was observed between the dry weight of the stems and leaves and the cumulative amount of solar radiation received in all growing seasons, it was found that the slope (solar radiation use efficiency) differed depending on the growing season. In other words, Figure 9(b) suggests that it is highly likely that solar radiation use efficiency is affected by temperature.
[0033] ((3) Relationship between solar radiation efficiency and temperature) From the results of Figures 9(a) and 9(b), in order to analyze the influence of temperature on solar radiation use efficiency, the relationship between solar radiation use efficiency and temperature for each growing season was confirmed. As a result, as shown in Figure 10, different relationship curves were found for the early growth stage and the full growth stage. Therefore, it was decided to incorporate the influence of temperature in the early growth stage and the full growth stage into the solar radiation use efficiency, and the curve shown by the dashed line in Figure 10 was set as parameter A, which is used as the solar radiation use efficiency in the early growth stage, and the curve shown by the solid line was set as parameter B, which is used as the solar radiation use efficiency in the full growth stage (see Figure 6).
[0034] ((4) Characteristics of dry matter partitioning to leaf blades in planted cultivation) The relationship between the dry matter weight of the stem and leaves (g / plant) and the dry matter partitioning rate to the leaf blade (%) is plotted in Figure 11. The dry matter partitioning rate to the leaf blade differed between the early and mature stages of growth, and in the mature stage, the difference due to the cropping season was clearly observed.
[0035] When we looked at the relationship between the dry matter partitioning rate to the leaf blade and temperature, we found that there was a different relationship between the dry matter partitioning rate and temperature in the early growth stage and the full growth stage, as shown in Figure 12. Therefore, we decided to incorporate the effect of temperature into the dry matter partitioning rate to the leaf blade in both the early growth stage and the full growth stage using separate equations. The curve shown by the solid line in Figure 12 was set as parameter C used as the dry matter partitioning rate to the leaf blade in the early growth stage of planting cultivation, and the curve shown by the dashed line was set as parameter D used as the dry matter partitioning rate to the leaf blade in the full growth stage of planting cultivation (see Figure 6).
[0036] ((5) Characteristics of leaf dry matter content in planted cultivation) Figure 13 shows the plot of the relationship between the dry matter weight of the stem and leaves (g / plant) and the dry matter percentage of the leaf blade (%). The dry matter percentage of the leaf blade also differed between the early and the full growth stage, and the difference between the growing seasons was clearly observed during the full growth stage. When the relationship between the dry matter percentage of the leaf blade and the temperature during the full growth stage was examined, as shown in Figure 14, the relationship between the dry matter percentage of the leaf blade and the temperature was different between the early and the full growth stage. Therefore, it was decided to incorporate the influence of temperature into the dry matter percentage of the leaf blade in both the early and the full growth stages using separate equations. The curve shown by the dashed line in Figure 14 was taken as the parameter E used to represent the dry matter percentage of the leaf blade in the early growth stage of the planting cultivation, and the curve shown by the solid line was taken as the parameter F used to represent the dry matter percentage of the leaf blade in the full growth stage of the planting cultivation (see Figure 6).
[0037] ((6) Characteristics of dry matter content of leaf sheath in fixed planting cultivation) Figure 15 shows the plot of the relationship between the dry matter weight of the stem and leaves (g / plant) and the dry matter percentage of the leaf sheath (%). The dry matter percentage of the leaf sheath also differed between the early and the full growth period, and the difference in the full growth period was clearly observed depending on the cropping season. When the relationship with temperature was examined for the early and the full growth periods, different relationships were observed between the early and the full growth periods, as shown in Figure 16. Therefore, it was decided to incorporate the effect of temperature into the leaf sheath dry matter percentage in both the early and the full growth periods using separate equations. The curve shown by the dashed line in Figure 16 was taken as the parameter G used for the leaf sheath dry matter percentage in the early growth period of planting cultivation, and the curve shown by the solid line was taken as the parameter H used for the leaf sheath dry matter percentage in the full growth period of planting cultivation (see Figure 6).
[0038] ((7) Conversion of leaf blade fresh weight to leaf area) In order to repeatedly use the growth model in FIG. 4 to predict the growth state for each day, it is necessary to derive the leaf area from the fresh weight of the leaf blade that has increased due to dry matter production (step S26 in FIG. 4). As shown in FIG. 17, the change in the ratio of the leaf area / fresh weight of the leaf blade to the fresh weight of the stem and leaf was plotted, and it was found that there was a certain tendency in planting cultivation. The "ratio of the leaf area / fresh weight of the leaf blade" is a parameter used when calculating the leaf area of the leaf blade from the fresh weight of the leaf blade.
[0039] Therefore, in this embodiment, it was determined that in fixed planting cultivation, when calculating the leaf area of the leaf blade based on the fresh weight of the leaf blade, it is not necessary to incorporate the temperature factor.
[0040] The relationship shown in FIG. 17 was used as parameter I (see FIG. 6) to be used when calculating the leaf area of the leaf blade from the fresh weight of the leaf blade.
[0041] <Analysis of regenerative cultivation> ((1) Growth characteristics of regenerative cultivation) Figure 18 is a graph showing the growth of plants during regeneration cultivation in each crop season (changes in stem and leaf dry matter weight (g / plant)). In regeneration cultivation, the initial growth period is slow, just like in planting cultivation.
[0042] Figure 19(a) shows the change in dry weight of the leaf blade during regrowth cultivation in each crop season, and Figure 19(b) shows the change in dry weight of the leaf sheath during regrowth cultivation in each crop season. Figures 19(a) and 19(b) show a different trend from Figure 9(a).
[0043] That is, immediately after harvest, there is no leaf blade, and the plant grows using the nutrients in the leaf sheath base (shoots) that remain after harvesting. During the period when the leaf blade is using only the nutrients in the leaf sheath, it can be seen in FIG. 18 that the dry weight does not increase. On the other hand, it can be seen that the leaf sheath dry weight temporarily decreases immediately after harvest. In this embodiment, the period from when the leaf sheath dry weight decreases until it starts to increase is defined as the "internal translocation period" (see FIG. 18 and FIG. 19(b)).
[0044] ((2) Growth characteristics during internal translocation in regenerative cultivation Figure 19(b) shows that the time when the leaf sheath dry weight starts to increase differs depending on the crop season. Because most of the stem and leaf parts are below the ground level where they are less exposed to light, it is assumed that the change in the time when the leaf sheath dry weight starts to increase is due to temperature. As shown in Figure 20, the vertical axis represents the number of days from day 0 after harvest until the leaf sheath dry weight starts to increase, and the horizontal axis represents the average temperature for a certain period at the time of harvest, and a relationship was confirmed. Based on this relationship, the period when the plant transitions from the internal translocation stage to the early growth stage was defined. The solar radiation utilization coefficient during this internal translocation stage was designated as parameter J (see Figure 6).
[0045] ((3) Dry matter increase per unit of solar radiation received in regenerative cultivation (solar radiation utilization efficiency) Figure 21(a) shows a graph plotting the relationship between the cumulative amount of solar radiation received and the dry matter weight of the stems and leaves. In regenerative cultivation, a linear relationship can be confirmed for all growing seasons, regardless of whether they are in the early or mature stages, but the slope differs depending on the growing season. This suggests that the solar radiation utilization efficiency may be affected by temperature.
[0046] ((4) Relationship between solar radiation efficiency and temperature) As mentioned above, since the solar radiation use efficiency may be affected by the temperature, the relationship between the solar radiation use efficiency and the temperature in each growing season was confirmed as shown in Figure 21(b). In regenerative cultivation, the solar radiation use efficiency was determined from the relationship in Figure 21(b). As mentioned above, since there is no difference in the solar radiation use efficiency between the early growth stage and the full growth stage of regenerative cultivation, the relationship in Figure 21(b) was used in both the early growth stage and the full growth stage. In Figure 6, the quadratic curve shown in Figure 21(b) is shown as the parameter K used to calculate the solar radiation use efficiency in the early growth stage and the full growth stage of regenerative cultivation.
[0047] ((5) Definition of the early growth stage in regenerative cultivation Figure 22 shows the relationship between the dry matter weight of the stem and leaves (g / plant) in regenerative cultivation and the dry matter partitioning rate (%) to the leaf blade. Looking at the change in the dry matter partitioning rate to the leaf blade as the dry matter weight increases in regenerative cultivation, it can be seen that the partitioning rate tends to consistently increase when the dry matter weight is low. This trend is thought to indicate the process of returning to a dry matter partitioning rate that reflects the original appearance of the leaf onion, with the formation of the leaf blade by translocation from the leaf sheath remaining after harvesting (internal translocation period) and the formation of the leaf blade by photosynthetic products from the formed leaf blade.
[0048] The period from the end of the internal translocation period to when the increase in the dry matter partitioning rate to the leaf blade subsides was defined as the "early growth period." Note that the early growth period in regeneration cultivation is considered to be a period in which the effect of internal translocation is still large, so it is treated separately from the full growth period.
[0049] (6) Temperature dependence of dry matter partitioning rate to leaf blades in regenerative cultivation FIG. 23 shows the relationship between temperature and the dry matter partitioning rate (%) to the leaf blade during the early growth period (including the internal translocation period) and the mature growth period.
[0050] As shown in Figure 23, the relationship between dry matter partitioning rate and temperature during the early growth period (and internal translocation period) and the full growth period of regenerative cultivation can be represented as different curves.
[0051] The dashed curve in Figure 23 is the parameter L used as the dry matter distribution rate to the leaf blade during the internal translocation period and early growth stage of regeneration cultivation, and the solid curve is the parameter M used as the dry matter distribution rate to the leaf blade during the full growth stage of regeneration cultivation (see Figure 6).
[0052] (7) Temperature characteristics of leaf dry matter percentage in regenerative cultivation The relationship between the dry matter weight of the stem and leaves (g / plant) and the dry matter ratio of the leaf blade (%) in regenerative cultivation is shown in Figure 24. Analysis of the relationship between these data and temperature revealed the relationship between the dry matter ratio of the leaf blade and temperature, which differs depending on the growth stage, as shown in Figure 25.
[0053] Therefore, the dashed curve shown in Figure 25 was set as parameter N used as the dry matter rate of the leaf blade during the internal translocation period and early growth stage of regeneration cultivation, and the solid curve was set as parameter O used as the dry matter rate of the leaf blade during the full growth stage of regeneration cultivation (see Figure 6).
[0054] (8) Temperature characteristics of leaf sheath dry matter percentage in regenerative cultivation The relationship between the dry matter weight of the stem and leaves (g / plant) and the dry matter percentage of the leaf sheath (%) in regenerative cultivation is shown in Figure 26. Analysis of the relationship between these data and temperature revealed the relationship between the dry matter percentage of the leaf sheath and temperature, which differs depending on the growth stage, as shown in Figure 27.
[0055] Therefore, the dashed curve shown in Figure 27 was set as parameter P to be used as the dry matter rate of the leaf sheath during the internal translocation period and early growth stage of regeneration cultivation, and the solid curve was set as parameter Q to be used as the dry matter rate of the leaf blade during the peak growth stage of regeneration cultivation (see Figure 6).
[0056] ((9) Conversion of fresh weight of leaf blade to leaf area of leaf blade) In regeneration cultivation, the leaf blade is thicker in the early growth stage compared to the mature growth stage, so the relationship between the fresh weight of the leaf blade (gFW / plant) and the ratio of leaf area / fresh weight of the leaf blade must be considered separately for the early growth stage (and internal translocation stage) and the mature growth stage. Figure 28 shows the ratio of leaf area / fresh weight of the leaf blade to the fresh weight of the leaf blade in the early growth stage (and internal translocation stage) and mature growth stages. Based on these results, it was decided to use different functions for the "ratio of leaf area / fresh weight of the leaf blade" in the early growth stage (and internal translocation stage) of regeneration cultivation.
[0057] In addition, the relationship shown by the dashed line in Figure 28 is the parameter R used when calculating the leaf area of the leaf blade from the fresh weight of the leaf blade during the early growth period of regeneration cultivation (and the internal translocation period), and the relationship shown by the solid line is the parameter S used when calculating the leaf area of the leaf blade from the fresh weight of the leaf blade during the peak growth period of regeneration cultivation (see Figure 6).
[0058] (Regarding the processing of terminal 70) In this embodiment, the terminal 70 predicts the growth state of the green onions on each day using the growth model of Fig. 4, but changes parameters as shown in Fig. 6 depending on the growth stage of the green onions on each day. Specifically, the terminal 70 predicts the growth state of the green onions on each day according to the flowchart shown in Fig. 29.
[0059] As a prerequisite for the processing of Fig. 29, the user of the terminal 70 inputs various conditions such as the planting density and planting date of the green onions, and inputs a command to start prediction. The terminal 70 predicts the growth state on a day-by-day basis using the growth model of Fig. 4 (S118), and displays the prediction results on the display unit 193 (S120). Then, when prediction for the entire period set in advance is completed, the processing ends.
[0060] In the process of FIG. 29, first, in step S100, the stage determination unit 20 determines whether the mowing switch has been turned ON. The mowing switch is turned ON when the user presses the mowing switch. For example, the user looks at the growth state of the green onions displayed on the display unit 193 and presses the mowing switch when they determine that it is time to mow. Note that this is not limited to this, and the mowing switch may be automatically pressed each time the fresh weight of the green onions reaches a predetermined value. Note that in the initial stage, the mowing switch is OFF, so the process proceeds to step S102.
[0061] In step S102, the stage determination unit 20 determines whether the dry weight is equal to or greater than a predetermined weight that divides the growth stages of the planting cultivation. If the determination is negative, that is, if the dry weight is less than the predetermined weight, the process proceeds to step S104.
[0062] When the process proceeds to step S104, the stage determination unit 20 determines that the growth stage of the green onion is the initial growth stage of fixed planting cultivation, and sets parameters. Specifically, the stage determination unit 20 sets the parameters to be used by referring to the table in Fig. 6. Then, the process proceeds to step S118.
[0063] On the other hand, if the determination in step S102 is positive, that is, if the dry weight is equal to or greater than the predetermined weight, the process proceeds to step S106, where the stage determination unit 20 determines that the planting cultivation is in the peak growth stage, and sets parameters based on Fig. 6. After that, the process proceeds to step S118.
[0064] On the other hand, if the determination in step S100 is positive, the process proceeds to step S108, where the stage determination unit 20 determines whether the dry matter weight is on an upward trend. If the determination in step S108 is negative, the process proceeds to step S110, where the stage determination unit 20 determines that the stage is in the internal translocation period of regeneration cultivation, and sets parameters based on Fig. 6. Then, the process proceeds to step S118. On the other hand, if the determination in step S108 is positive, the process proceeds to step S112.
[0065] In step S112, the stage determination unit 20 determines whether the dry matter weight is equal to or greater than a predetermined weight that divides the growth stage of regeneration cultivation. If the determination in step S112 is negative, the process proceeds to step S114, where the stage determination unit 20 determines that the stage is in the early growth stage of regeneration cultivation, and sets parameters based on Fig. 6. On the other hand, if the determination in step S112 is positive, the process proceeds to step S116, where the stage determination unit 20 determines that the stage is in the full growth stage of regeneration cultivation, and sets parameters based on Fig. 6. After the process in step S114 or step S116, the process proceeds to step S118.
[0066] When any one of steps S104, S106, S110, S114, and S116 is executed and the process proceeds to step S118, the prediction unit 22 predicts the growth state for one day from the prediction model using the set parameters, and stores the prediction state in the prediction DB 30. The growth state of the green onions for each day (the crop state variables in FIG. 4) is stored in the prediction DB 30. Note that the prediction unit 22 can use the daily average temperature and daily accumulated solar radiation predicted from past data, or the daily average temperature and daily accumulated solar radiation predicted by the Japan Meteorological Agency, etc., as the environmental conditions (daily average temperature and daily accumulated solar radiation).
[0067] Next, in step S120, the display control unit 24 displays the predicted growth state of the green onions. For example, the display control unit 24 displays information such as how many grams the fresh weight will be on what day on the display unit 193. Note that, when the user refers to the display unit 193 and determines that it is time to harvest, he or she can press the harvest switch.
[0068] Next, in step S122, the prediction unit 22 judges whether or not the process is finished. For example, if the prediction of the entire period set in advance is finished, the judgment in step S122 is affirmative, and the entire process in FIG. 29 is finished. On the other hand, if the judgment in step S122 is negative, the process returns to step S100. If the process returns to step S100, the above-mentioned process is repeatedly executed. Then, if the judgment in step S122 is affirmative, the entire process in FIG. 29 is finished.
[0069] Fig. 30(a) shows the results (predicted values) of the cultivation period until the weight at the time of sampling is reached, which is predicted by the method of this embodiment, for a total of 16 fields in three different regions, by using the planting date or the growth amount one month before the survey as the initial value, and inputting the daily amount of solar radiation and temperature of each region, in association with the actual measured values. Fig. 30(b) shows the results (predicted values) of the plant weight when cultivated for the period until sampling, which is predicted by the method of this embodiment, for a total of 16 fields in three different regions, by using the planting date or the growth amount one month before the survey as the initial value, and inputting the daily amount of solar radiation and temperature of each region, in association with the actual measured values.
[0070] By predicting the growth state of green onions as in this embodiment, it is possible to accurately predict the growth state, as shown in Figures 30(a) and 30(b).
[0071] As is clear from the above explanation, in this embodiment, the stage determination unit 20 realizes the functions of a determination unit that determines the stage to which the leaf onion belongs, and a determination unit that determines the parameters of a prediction model that predicts the growth state based on the stage.
[0072] 31(a) to 31(d) show the results of predicting the weight of green onions by the method of this embodiment (predicted values) for each number of days elapsed since the planting date for a total of four fields in two different regions, with the planting date set as the initial value and the amount of solar radiation and temperature for each region input. More specifically, Fig. 31(a) and Fig. 31(b) show the predicted values and actual measured values for two different fields in Region 1, and Fig. 31(c) and Fig. 31(d) show the predicted values and actual measured values for two different fields in Region 2.
[0073] It can be seen that by predicting the growth state of green onions as in this embodiment, it is possible to accurately predict the growth state at the time of planting cultivation, as shown in Figures 31(a) to 31(d).
[0074] In addition, Figures 32(a) and 32(b) show the results of predicting the weight of green onion plants (predicted values) and actual measured values for each number of days elapsed since the harvesting date for fields in two different regions, using the harvesting date as the initial value and inputting the daily solar radiation and temperature for each region, using the method of this embodiment.
[0075] By predicting the growth state of green onions in the manner described in this embodiment, it is possible to accurately predict the growth state during the regeneration cultivation period, as shown in Figures 32(a) and 32(b).
[0076] As described above in detail, according to this embodiment, the stage determination unit 20 determines which of a plurality of stages included in the cultivation period a vegetable (such as green onion) that can be cultivated by fixed planting or cultivated by fixed planting and then regenerated belongs to, and determines the parameters of the prediction model in FIG. 4 based on the stage (S104, S106, S110, S114, S116). Then, the prediction unit 22 predicts the growth state of the green onion using the prediction model (S118). As a result, in this embodiment, the parameters of the prediction model are made different depending on which stage the green onion to be predicted belongs to, so that the growth state of the green onion can be predicted with high accuracy. As a result, it becomes possible to predict the harvest time and harvest amount in advance (for example, 2 weeks to 1 month in advance), so that intermediate businesses and production area managers can take appropriate measures (such as securing new suppliers and shipping destinations) based on the prediction results.
[0077] In this embodiment, the stage determination unit 20 refers to the cutting switch, and if the cutting switch is OFF (S100: negative), it determines based on the dry weight of the green onion (S102) that the green onion belongs to either the early growth stage of planting cultivation or the full growth stage of planting cultivation (S104, S106). On the other hand, if the cutting switch is ON (S100: positive), the stage determination unit 20 determines based on the dry weight of the green onion (S108, S112) that the green onion belongs to either the internal translocation stage of regrowth cultivation, the early growth stage, or the full growth stage (S110, S114, S116). By determining the stage based on the cutting switch and the dry weight in this way, it is possible to accurately determine the stage to which the green onion belongs, taking into account the actual state of the green onion.
[0078] In this embodiment, the parameters A to S are set based on the results of a cultivation test (a cropping season shift test) conducted in advance, which allows appropriate functions and the like to be set as parameters for each cultivation style and variety.
[0079] In the above embodiment, the stage to which the vegetable to be predicted belongs is determined based on the dry weight. However, this is not limited to this, and the stage may be determined based on the accumulated temperature from the planting date, etc.
[0080] In the above embodiment, the case where the vegetable to be predicted is green onion has been described, but the present invention is not limited to this. That is, the vegetable to be predicted may be other vegetables that can be cultivated by fixed planting or cultivated by regeneration after fixed planting (for example, Chinese chives, spinach, baby leaves, etc.). In this case, it is necessary to change the parameters appropriately according to the vegetable to be predicted.
[0081] In addition, the vegetables to be predicted may be vegetables that are not regenerated but are planted, such as head vegetables such as cabbage, lettuce, and Chinese cabbage, and flower vegetables such as broccoli and cauliflower.
[0082] <In the case of flower vegetables> First, I will explain about flower vegetables such as broccoli.
[0083] (Growth model for flower vegetables) FIG. 33 shows a flower vegetable growth model created by the present inventor.
[0084] Hereinafter, an overview of the growth model in Fig. 33 will be described. Note that the growth model in Fig. 33 is held by the prediction unit 22 in Fig. 2(b), and the prediction unit 22 predicts the growth state of the flower vegetable based on the growth model.
[0085] When calculating the fresh weight as the growth state on a certain day (a day to be predicted) using the growth model of FIG. 33, the prediction unit 22 first calculates the leaf area (m 2 / stock) and the daily accumulated solar radiation (MJ / m 2 ) and the external input condition planting density (plants / m 2 ) and calculates the daily accumulated solar radiation shading amount (MJ / plant). If it is immediately after planting, the user may manually input the initial value of the leaf area, or a value determined in advance as the initial value of the leaf area may be used. Instead of manually inputting the initial value of the leaf area, the user may manually input the outer leaf fresh weight. In this case, the prediction unit 22 calculates the leaf area by multiplying the manually input outer leaf fresh weight by a predetermined coefficient.
[0086] Next, in step S32, the prediction unit 22 calculates the daily dry matter production (g / stock) on the predicted day from the calculated daily integrated solar radiation shading amount (MJ / stock). In calculating this daily dry matter production, the solar radiation use efficiency (g / MJ) is used.
[0087] Next, in step S34, the prediction unit 22 calculates the dry matter weight of the plant (g / plant) by adding the daily dry matter production amount (g / plant) calculated in step S32 to the dry matter weight up to the previous day.
[0088] Next, in step S36, the prediction unit 22 calculates the outer leaf dry matter weight (g / plant) and the flower bud dry matter weight (g / plant) using the plant dry matter weight (g / plant) and the flower bud dry matter distribution rate (%).
[0089] Next, in step S38, the prediction unit 22 calculates the outer leaf fresh weight (g / plant) based on the outer leaf dry weight (g / plant) and the outer leaf dry matter rate (%) calculated in step S36. Also, in step S40, the prediction unit 22 calculates the flower bud fresh weight (g / plant) based on the flower bud dry matter weight (g / plant) and the flower bud dry matter rate (%) calculated in step S36.
[0090] In step S44, the prediction unit 22 multiplies the ratio of outer leaf area / fresh weight by the outer leaf fresh weight (g / plant) to obtain a leaf area (m 2 / Stock) to update.
[0091] Thereafter, by repeating the process of FIG. 33, it is possible to predict the change in the growth state of the flowering vegetable (change in fresh weight) for a predetermined period of time.
[0092] (Growth stages of flower vegetables) Flower vegetables have growth stages as shown in Fig. 34(a). More specifically, the growth stages of flower vegetables are divided into an "early growth stage (rooting stage)", an "outer leaf development stage", and a "flower bud enlargement stage".
[0093] In this case, as with vegetables that can be grown by planting or regenerated after planting, the growth state can be predicted with high accuracy by setting different parameters for each growth stage, as shown in Figure 34(b). As with green onions, the parameters used at each stage are set based on the results of a cultivation test (crop shift test) conducted in advance. Note that in the table of Figure 34(b), since flower buds do not exist during the early growth stage and the outer leaf expansion stage, a parameter for the flower bud dry matter percentage is not set.
[0094] (Regarding the crop season shift test) As an example of flower vegetables, broccoli was cultivated at fixed planting dates shown in Figure 35(a) as a test of shifting the crop season. Each crop was cultivated with two different planting densities (dense and sparse), and the effects of light conditions in the same crop season were also examined.
[0095] During the cultivation period, multiple plants were collected several times as survey subjects. As shown in the photograph in Figure 35(b), the above-ground parts of the collected plants were divided into the expanded leaves including the petioles (defined here as the outer leaves) and the flower buds including the main stems (defined here as the flower buds), and the fresh weight and dry weight of each were obtained.
[0096] ((1) Growth characteristics and modeling) Figure 36(a) is a graph showing the growth of plants in each growing season (change in above-ground dry weight (g / plant)). Figure 36(a) shows that the rate of increase in above-ground dry weight differs depending on the growing season.
[0097] ((2) Amount of dry matter increase per unit of solar radiation received (solar radiation efficiency) Figure 36(b) shows the relationship between the aboveground dry weight and the cumulative amount of solar radiation received. The cumulative amount of solar radiation received by broccoli was estimated by creating a canopy solar radiation shading rate curve in the same way as for green onions, and calculating the amount of solar radiation received each day.
[0098] A linear relationship is observed between aboveground dry matter weight and the amount of accumulated solar radiation received for all crop seasons and planting densities. The slope (solar radiation utilization efficiency) was roughly the same for all crop seasons and planting densities, but it was found to differ depending on the crop season. In other words, Figure 36(b) suggests that the solar radiation utilization efficiency is likely to be affected by temperature.
[0099] ((3) Relationship between solar radiation efficiency and temperature) From the results of Figures 36(a) and 36(b), in order to analyze the influence of temperature on the solar radiation use efficiency, the relationship between the solar radiation use efficiency and temperature in each cropping period was confirmed. As a result, as shown in Figure 37, the relationship between different curves was recognized in the early growth stage, the outer leaf expansion stage, and the flower bud expansion stage. Therefore, the influence of temperature corresponding to each of the early growth stage, the outer leaf expansion stage, and the flower bud expansion stage was incorporated into the solar radiation use efficiency, and the curve shown by the dashed line in Figure 37 was set as the parameter α used as the solar radiation use efficiency in the early growth stage, the curve shown by the dotted line was set as the parameter β used as the solar radiation use efficiency in the outer leaf expansion stage, and the curve shown by the solid line was set as the parameter γ used as the solar radiation use efficiency in the flower bud expansion stage (see Figure 34(b)).
[0100] ((4) Relationship between aboveground dry weight and days after planting) Figure 38 shows the results of plotting the relationship between the dry weight of the aboveground parts and the number of days after planting. The aboveground parts are divided into the outer leaves and the flower buds, with the upper row showing the dry weight of the outer leaves and the lower row showing the dry weight of the flower buds.
[0101] In broccoli, the dry weight of the outer leaves increases relatively slowly until it reaches about 5g, after which it increases rapidly once the seedlings have taken root. Furthermore, after a certain period of time has passed since planting, the dry weight of the flower buds begins to increase, and at the same time, the increase in the dry weight of the outer leaves slows down or stops. It was also found that the rate at which each dry weight increases differs depending on the cultivation season and planting density.
[0102] ((5) Relationship between flower bud dry matter distribution rate and accumulated temperature (index value) during the cultivation period) Figure 39 is a plot of the relationship between the flower bud dry matter partitioning rate and the accumulated temperature (index value) during the cultivation period. Figure 39 shows that the flower bud dry matter partitioning rate of broccoli increases rapidly when the accumulated temperature reaches a certain value, regardless of the cultivation season or planting density.
[0103] From Figures 38 and 39, it was found that in broccoli, the "early growth" stage in Figure 33(a) can be defined as the period when the increase in dry weight of the outer leaves is gradual after planting until the seedlings take root, the "outer leaf expansion" stage is the period when the increase in dry weight of the outer leaves is vigorous, and the "flower bud enlargement" stage is the period when the increase in dry weight of the flower buds begins. It was also found that the "early growth" stage and the "outer leaf expansion" stage can be separated using the dry weight as an index, and the "outer leaf expansion" stage and the "flower bud enlargement" stage can be separated using the accumulated temperature as an index.
[0104] In addition, from Figure 39, we decided to set the parameter δ for the dry matter partitioning rate of the flower bud at the “early growth stage” and “outer leaf expansion stage” stages, and to set the parameter ε at the “flower bud enlargement stage” stage (see Figure 34(b)).
[0105] ((6) Characteristics of outer leaf dry matter percentage Figure 40(a) shows the plot of the relationship between outer leaf dry matter weight (g / plant) and outer leaf dry matter percentage (%). The outer leaf dry matter percentage tended to be almost constant or slightly decreasing relative to the outer leaf dry matter weight, and the relationship between the outer leaf dry matter weight and the outer leaf dry matter percentage varied depending on the cropping season.
[0106] When the relationship between the outer leaf dry matter rate and the temperature at the time of sampling was examined, as shown in Figure 40(b), different relationships between the outer leaf dry matter rate and the temperature were found in the early growth stage, the outer leaf expansion stage, and the flower bud expansion stage. Therefore, it was decided to incorporate the influence of temperature into the outer leaf dry matter rate in separate equations for the early growth stage, the outer leaf expansion stage, and the flower bud expansion stage. Note that the curve shown by the solid line in Figure 40(b) is the parameter ζ used as the outer leaf dry matter rate in the early growth stage, the curve shown by the dotted line is the parameter η used as the outer leaf dry matter rate in the outer leaf expansion stage, and the curve shown by the dashed line is the parameter θ used as the outer leaf dry matter rate in the flower bud expansion stage (see Figure 34(b)).
[0107] Regarding the outer leaf area / fresh weight ratio, a similar relationship is observed between broccoli and the curve shown in Figure 17 for green onions, so we decided to incorporate the curve equation as the parameter ι for the outer leaf area / fresh weight ratio.
[0108] (7) Characteristics of dry matter content of flower buds Figure 41(a) shows the plot of the relationship between the flower bud dry matter weight (g / plant) and the flower bud dry matter percentage (%). The flower bud dry matter percentage tended to be almost constant or slightly decrease relative to the flower bud dry matter weight, and the relationship between the flower bud dry matter weight and the flower bud dry matter percentage varied depending on the cultivation season.
[0109] When we looked at the relationship between the flower bud dry matter rate and the air temperature at the time of sampling, we found that there was a relationship between the flower bud dry matter rate and the air temperature, as shown by the dashed curve in Figure 41(b), so this curve was used as the parameter κ of the flower bud dry matter rate (see Figure 34(b)).
[0110] <For head vegetables> Next, the case of head vegetables such as cabbage will be described.
[0111] (Head vegetable growth model) FIG. 42 shows a growth model of heading vegetables created by the present inventor.
[0112] Below, an overview of the growth model in Fig. 42 will be described. The growth model in Fig. 42 is held by the prediction unit 22 in Fig. 2(b), and the prediction unit 22 predicts the growth state of the heading vegetable based on the growth model.
[0113] When calculating the fresh weight as the growth state on a certain day (a day to be predicted) using the growth model of FIG. 42, the prediction unit 22 first calculates the (projected) leaf area (m 2 / stock) and the daily accumulated solar radiation (MJ / m 2 ) and the external input condition planting density (plants / m 2) and calculates the daily accumulated solar radiation shading amount (MJ / plant). If it is immediately after planting, the user may manually input the initial value of the (projected) leaf area, or a value that is determined in advance as the initial value of the (projected) leaf area may be used. Instead of manually inputting the initial value of the (projected) leaf area, the user may manually input the outer leaf dry weight. In this case, the prediction unit 22 calculates the (projected) leaf area by multiplying the manually input outer leaf dry weight by a predetermined coefficient.
[0114] Next, in step S52, the prediction unit 22 calculates the daily dry matter production (g / stock) on the predicted day from the calculated daily integrated solar radiation shading amount (MJ / stock). In calculating this daily dry matter production, the solar radiation use efficiency (g / MJ) is used.
[0115] Next, in step S54, the prediction unit 22 calculates the dry matter weight of the plant (g / plant) by adding the daily dry matter production amount (g / plant) calculated in step S52 to the dry matter weight up to the previous day.
[0116] Next, in step S56, the prediction unit 22 calculates the outer leaf dry matter weight (g / plant) and the head dry matter weight (g / plant) using the plant dry matter weight (g / plant) and the head dry matter distribution rate (%).
[0117] Next, in step S60, the prediction unit 22 calculates the head fresh weight (g / plant) based on the head dry matter weight (g / plant) and head dry matter rate (%) calculated in step S56.
[0118] In step S64, the prediction unit 22 multiplies the ratio of the projected leaf area to the outer leaf dry weight by the outer leaf dry weight (g / plant) to obtain the (projected) leaf area (m 2 / Stock) to update.
[0119] Thereafter, by repeating the process of FIG. 42, it is possible to predict the change in the growth state of the heading vegetable (change in fresh weight) for a predetermined period of time.
[0120] (Head vegetable growth stages) Head vegetables have growth stages as shown in Fig. 43(a). More specifically, the growth stages of head vegetables are divided into an "early growth (rooting)" stage, an "outer leaf development" stage, and a "head enlargement" stage.
[0121] In this case, as with vegetables that can be grown by planting or regenerated after planting, the growth state can be predicted with high accuracy by setting different parameters for each growth stage, as shown in Figure 43(b). As with green onions, the parameters used at each stage are set based on the results of a cultivation test (crop shift test) conducted in advance. Note that in the table of Figure 43(b), since there are no head leaves during the early growth period and the outer leaf development period, a parameter for the head dry matter percentage is not set.
[0122] (Regarding the crop season shift test) In a cropping season shift test for cabbage, an example of a heading vegetable, fixed-plant cultivation was carried out on the planting date shown in Figure 44(a). During the cultivation period, multiple plants were sampled several times as survey subjects. As shown in the photograph in Figure 44(b), the above-ground parts of the sampled plants were divided into expanded leaves (defined here as outer leaves) including the petiole and main stem, and head leaves (defined here as head part), and the fresh weight and dry weight of each were obtained.
[0123] (Measuring cabbage leaf area and solar radiation shielding) Cabbage is different from other vegetables such as green onions and broccoli in that its stems and petioles do not grow three-dimensionally, but grow flat. For this reason, the projected leaf area of cabbage was calculated, and the product of the projected leaf area and the daily accumulated solar radiation was used as the solar radiation shading amount for that day. Daily accumulated solar radiation shielding amount (MJ / plant) = Projected leaf area (m 2 / stock) x solar radiation (MJ / m 2 )
[0124] Fig. 45(a) is a diagram for explaining the calculation of the projected leaf area. As shown in the left diagram of Fig. 45(a), a cabbage stalk is photographed from above. Note that the object surrounded by a dotted line in the photograph on the left side of Fig. 45(a) is an indicator for area calculation.
[0125] Next, as shown in the right diagram of Fig. 45(a), a projection image of the cabbage plant is obtained from a photograph taken from above. In the projection image shown on the left diagram of Fig. 45(a), the area of the gray part is calculated based on the indicators and is set as the projected leaf area.
[0126] Figure 45(b) is a plot of the relationship between the number of days after planting and the projected leaf area. The projected leaf area increases with the number of days after planting, but as the cabbage grows, the leaves become denser and there are no more gaps between adjacent plants, at which point it stops increasing. Therefore, as shown in Figure 45(b), the projected leaf area of a cabbage becomes constant after a certain period of time.
[0127] ((1) Growth characteristics and modeling) Figure 46(a) is a graph showing the growth of plants in each growing season (change in above-ground dry weight (g / plant)). Figure 46(a) shows that the rate of increase in above-ground dry weight differs depending on the growing season.
[0128] ((2) Amount of dry matter increase per unit of solar radiation received (solar radiation efficiency) Figure 46(b) shows the relationship between aboveground dry weight and the cumulative amount of solar radiation received. Although a linear relationship is observed between aboveground dry weight and the cumulative amount of solar radiation received in every growing season, the slope (solar radiation use efficiency) was found to differ depending on the growing season. In other words, Figure 46(b) suggests that it is highly likely that solar radiation use efficiency is affected by temperature.
[0129] When the relationship between solar radiation use efficiency and temperature was checked for each growth stage, it was found that, as with broccoli, different curves were observed for the early growth stage, the outer leaf development stage, and the head development stage. Therefore, it was decided to incorporate temperature parameters appropriate for each growth stage into the solar radiation use efficiency. Specifically, the solar radiation use efficiency for the early growth stage was set as parameter α, the solar radiation use efficiency for the outer leaf development stage was set as parameter β, and the solar radiation use efficiency for the head development stage was set as parameter γ (see Figure 44(b)).
[0130] ((3) Relationship between aboveground dry weight and days after planting Figure 47 shows the results of plotting the relationship between the dry weight of the aboveground part and the number of days after planting. The aboveground part is divided into the outer leaves and the head part, with the upper row showing the dry weight of the outer leaves and the lower row showing the dry weight of the head part.
[0131] In cabbage, like broccoli, the dry weight of the outer leaves increases relatively slowly, regardless of the growing season, until it reaches about 5g, after which it increases rapidly once the seedlings have taken root. After a certain period of cultivation, the dry weight of the head begins to increase, and after a while the increase in the dry weight of the outer leaves stops. It was also found that the rate at which the dry weight increases varies depending on the growing season.
[0132] ((4) Relationship between the dry matter distribution rate of the head and the accumulated temperature (index value) during the cultivation period) Figure 48 is a plot of the relationship between the head dry matter partitioning rate and the accumulated temperature (index value) during the cultivation period. Figure 48 shows that the head dry matter partitioning rate increases rapidly when the accumulated temperature reaches a certain value, regardless of the cultivation season.
[0133] Figures 47 and 48 show that, in the case of cabbage, the "early growth" stage, in which growth is slow after planting until the seedlings take root, and the "outer leaf development" stage, in which growth is vigorous, can be distinguished using dry weight as an indicator, and that the "outer leaf development" stage can be distinguished from the "head enlargement" stage, in which the head enlarges, using accumulated temperature as an indicator.
[0134] Also, from Figure 48, the dry matter distribution rate of the head was parameter δ in the "early growth" and "outer leaf expansion" stages, and the dry matter distribution rate of the head was parameter ε in the "head enlargement" stage (see Figure 43(b)).
[0135] ((5) Characteristics of head dry matter percentage Figure 49 shows the plot of the relationship between head dry weight (g / plant) and head dry matter percentage (%). The relationship between head dry weight and head dry matter percentage varies depending on the growing season, suggesting that it may be affected by temperature.
[0136] In addition, as with broccoli, a gentle curved relationship was observed between the head dry matter percentage and the average temperature (not shown), and this was incorporated as a parameter for the head dry matter percentage. Specifically, the parameter for the head dry matter percentage was set as parameter κ (see Figure 43(b)).
[0137] ((6) Relationship between the projected leaf area / outer leaf dry weight ratio and outer leaf dry weight (index value) Figure 50 shows the cabbage projected leaf area / outer leaf dry matter weight ratio (cm 2 The relationship between the outer leaf dry matter weight (index value) and the outer leaf dry matter weight (index value) is shown. In the case of projected leaf area, as with green onions and broccoli, there is a relationship between the outer leaf dry matter weight ratio and a curve, so we decided to include it as a parameter ι to estimate the projected leaf area from the outer leaf dry matter weight (see Figure 43(b)).
[0138] In this example, the projected leaf area is estimated directly from the dry weight of the outer leaves, but as with green onions and broccoli, a more accurate estimation can be achieved by incorporating a temperature parameter (parameter θ) appropriate for each growth stage and converting the dry weight to fresh weight.
[0139] (Regarding the processing of terminal 70) FIG. 51 is a flowchart showing an example of a process executed by the terminal 70 when predicting the growth state of flower vegetables or heading vegetables for each day.
[0140] 51, first, in step S200, the stage determination unit 20 determines whether the accumulated temperature is equal to or lower than a predetermined value for dividing the growth stages. If the accumulated temperature is equal to or lower than the predetermined value for dividing the growth stages, the process proceeds to step S202.
[0141] In step S202, the stage determination unit 20 determines whether the fresh weight of the plant is equal to or less than a predetermined weight for dividing the growth stages. If the determination is positive, that is, if the fresh weight is equal to or less than the predetermined weight, the process proceeds to step S204.
[0142] When the process proceeds to step S204, the stage determination unit 20 determines that the growth stage of the flower vegetable or the head vegetable is the early growth stage, and sets parameters. Specifically, the stage determination unit 20 sets the parameters to be used by referring to the table of FIG. 34(b) or FIG. 43(b). Then, the process proceeds to step S210.
[0143] On the other hand, if the determination in step S202 is negative, that is, if the fresh weight is greater than the predetermined weight, the process proceeds to step S206, where the stage determination unit 20 determines that the growth stage is the outer leaf expansion stage, and sets parameters by referring to the table in Fig. 34(b) or Fig. 43(b). Then, the process proceeds to step S210.
[0144] On the other hand, if the determination in step S200 is negative, the process proceeds to step S208, where the stage determination unit 20 determines that the growth stage of the flower vegetable or head vegetable is the flower bud thickening stage or the head thickening stage, and sets parameters by referring to the table in Fig. 34(b) or Fig. 43(b). After that, the process proceeds to step S210.
[0145] When any one of steps S204, S206, and S208 is executed and the process proceeds to step S210, the prediction unit 22 predicts the growth state for one day from the prediction model using the set parameters, and stores the prediction state in the prediction DB 30. The growth state of flower vegetables or head vegetables for each day (crop state variables in Figs. 33 and 42) is stored in the prediction DB 30. Note that the prediction unit 22 can use the daily average temperature and daily accumulated solar radiation predicted from past data, or the daily average temperature and daily accumulated solar radiation predicted by the Japan Meteorological Agency, etc., as the environmental conditions (daily average temperature and daily accumulated solar radiation).
[0146] Next, in step S212, the display control unit 24 displays the predicted growth state of the flower vegetable or the heading vegetable. For example, the display control unit 24 displays on the display unit 193 information such as how many grams the fresh weight will be on how many days.
[0147] Next, in step S214, the prediction unit 22 judges whether or not the process is finished. For example, if the prediction of the entire period set in advance is finished, the judgment in step S214 is affirmative, and the entire process in FIG. 51 is finished. On the other hand, if the judgment in step S214 is negative, the process returns to step S200. If the process returns to step S200, the above-mentioned process is repeatedly executed. Then, if the judgment in step S214 is affirmative, the entire process in FIG. 51 is finished.
[0148] Figures 52(a) and 52(b) show the results of predicting the fresh weight of broccoli florets including the main stem for cultivation in three different cropping periods (predicted values) for each number of days elapsed since the planting date using the method of this embodiment with the planting date as the initial value and daily solar radiation and temperature input, as well as the actual measured values. In Figures 52(a) and 52(b), the predicted values are shown as solid or dashed lines, and the actual measured values are shown as circle or square plots. As shown in Figures 52(a) and 52(b), the fresh weight of broccoli florets can be predicted with high accuracy using the method of this embodiment.
[0149] Figures 53(a) and 53(b) show the results of predicting the fresh weight of cabbage heads for four different cropping periods using the method of this embodiment (predicted values) for each number of days elapsed since the planting date, with the planting date as the initial value and daily solar radiation and temperature input, as well as the actual measured values. In Figures 53(a) and 53(b), the predicted values are shown as solid or dashed lines, and the actual measured values are shown as circle or square plots. As shown in Figures 53(a) and 53(b), the method of this embodiment can accurately predict the fresh weight of cabbage heads.
[0150] The above-described embodiment is a preferred example of the present invention, but the present invention is not limited to this embodiment and can be modified in various ways without departing from the scope of the present invention. [Explanation of symbols]
[0151] 70 Terminal (information processing device) 20 Stage Judging Section (Judgment Section, Decision Section) 22 Prediction Department
Claims
1. A method for predicting the growth state of a vegetable that can be regenerated after planting, comprising: determining whether the vegetable to be predicted belongs to one of a plurality of stages included in the first period of the planting cultivation or a plurality of stages included in the second period of the regeneration cultivation; determining parameters of a model for predicting the growth state of the vegetable based on the temperature and the amount of solar radiation based on the determined stage; predicting a growth state of the vegetable to be predicted using the model in which the determined parameters are set; A method for predicting growth conditions, characterized in that processing is executed by a computer.
2. In the determination process, Acquire information on whether the vegetable to be predicted has been harvested; When the vegetable to be predicted has not been harvested, the vegetable to be predicted is determined to belong to either an early growth stage in the first period or a full growth stage in the first period based on the dry matter weight of the vegetable to be predicted; The growth state prediction method according to claim 1, characterized in that, when the vegetable to be predicted has been harvested, it is determined that the vegetable to be predicted belongs to any one of the stages: the internal translocation stage of the second period, the early growth stage of the second period, or the full growth stage of the second period, based on the dry weight of the vegetable to be predicted.
3. 3. The method for predicting a growth state according to claim 1, wherein the parameters are determined based on the results of a cultivation test carried out in advance.
4. A method for predicting the growth state of a vegetable that can be cultivated by fixed planting or can be regenerated after fixed planting and has a leaf blade and a leaf sheath, comprising: Determine which of a plurality of stages included in a cultivation period the vegetable to be predicted belongs to; determining parameters of a model for predicting the growth state of the vegetable based on the temperature and the amount of solar radiation based on the determined stage; predicting a growth state of the vegetable to be predicted using the model in which the determined parameters are set; The computer executes the process, The parameters include a dry matter distribution rate used when estimating the dry matter weight of the leaf blade and the dry matter weight of the leaf sheath from the dry matter weight predicted to be produced in the vegetable, a leaf blade dry matter rate used when estimating the fresh weight from the estimated dry matter weight of the leaf blade, and a leaf sheath dry matter rate used when estimating the fresh weight from the estimated dry matter weight of the leaf sheath. A method for predicting growth status.
5. A growth condition prediction method for predicting the growth condition of flower vegetables, comprising: Determine to which of a plurality of stages included in a cultivation period the flower vegetable to be predicted belongs; determining parameters of a model for predicting the growth state of the flower vegetable based on the temperature and the amount of solar radiation based on the determined stage; predicting a growth state of the flower vegetable to be predicted using the model in which the determined parameters are set; The computer executes the process, The parameters include a dry matter distribution rate used to estimate the dry matter weight of the flower bud and the dry matter weight of the outer leaf from the dry matter weight predicted to be produced in the flower vegetable, an outer leaf dry matter rate used to estimate the fresh weight from the estimated dry matter weight of the outer leaf, and a flower bud dry matter rate used to estimate the fresh weight from the estimated dry matter weight of the flower bud. A method for predicting growth status.
6. A growth condition prediction method for predicting the growth condition of head vegetables, comprising: determining to which of a plurality of stages included in a cultivation period the head vegetable to be predicted belongs; determining parameters of a model for predicting the growth state of the head vegetable based on the temperature and the amount of solar radiation based on the determined stage; predicting a growth state of the heading vegetable to be predicted using the model in which the determined parameters are set; The computer executes the process, The parameters include a dry matter distribution ratio used to estimate the dry matter weight of the head part and the dry matter weight of the outer leaf part from the dry matter weight predicted to be produced in the head vegetable, an outer leaf part dry matter ratio used to estimate the fresh weight from the estimated dry matter weight of the outer leaf part, and a head part dry matter ratio used to estimate the fresh weight from the estimated dry matter weight of the head part. A method for predicting growth status.
7. A growth condition prediction program for predicting the growth condition of a vegetable that can be regenerated after planting, comprising: determining whether the vegetable to be predicted belongs to one of a plurality of stages included in the first period of the planting cultivation or a plurality of stages included in the second period of the regeneration cultivation; determining parameters of a model for predicting the growth state of the vegetable based on the temperature and the amount of solar radiation based on the determined stage; predicting a growth state of the vegetable to be predicted using the model in which the determined parameters are set; A growth condition prediction program for causing a computer to execute the processing.
8. A growth state prediction program for predicting the growth state of a vegetable that can be cultivated by fixed planting or can be regenerated after fixed planting and has a leaf blade and a leaf sheath, Determine which of a plurality of stages included in a cultivation period the vegetable to be predicted belongs to; determining parameters of a model for predicting the growth state of the vegetable based on the temperature and the amount of solar radiation based on the determined stage; predicting a growth state of the vegetable to be predicted using the model in which the determined parameters are set; The process is executed by a computer, The parameters include a dry matter distribution rate used when estimating the dry matter weight of the leaf blade and the dry matter weight of the leaf sheath from the dry matter weight predicted to be produced in the vegetable, a leaf blade dry matter rate used when estimating the fresh weight from the estimated dry matter weight of the leaf blade, and a leaf sheath dry matter rate used when estimating the fresh weight from the estimated dry matter weight of the leaf sheath. A growth condition prediction program comprising:
9. A growth condition prediction program for predicting the growth condition of flower vegetables, comprising: Determine to which of a plurality of stages included in a cultivation period the flower vegetable to be predicted belongs; determining parameters of a model for predicting the growth state of the flower vegetable based on the temperature and the amount of solar radiation based on the determined stage; predicting a growth state of the flower vegetable to be predicted using the model in which the determined parameters are set; The process is executed by a computer, The parameters include a dry matter distribution rate used to estimate the dry matter weight of the flower bud and the dry matter weight of the outer leaf from the dry matter weight predicted to be produced in the flower vegetable, an outer leaf dry matter rate used to estimate the fresh weight from the estimated dry matter weight of the outer leaf, and a flower bud dry matter rate used to estimate the fresh weight from the estimated dry matter weight of the flower bud. A growth condition prediction program comprising:
10. A growth state prediction program for predicting the growth state of head vegetables, comprising: determining to which of a plurality of stages included in a cultivation period the head vegetable to be predicted belongs; determining parameters of a model for predicting the growth state of the head vegetable based on the temperature and the amount of solar radiation based on the determined stage; predicting a growth state of the heading vegetable to be predicted using the model in which the determined parameters are set; The process is executed by a computer, The parameters include a dry matter distribution ratio used to estimate the dry matter weight of the head part and the dry matter weight of the outer leaf part from the dry matter weight predicted to be produced in the head vegetable, an outer leaf part dry matter ratio used to estimate the fresh weight from the estimated dry matter weight of the outer leaf part, and a head part dry matter ratio used to estimate the fresh weight from the estimated dry matter weight of the head part. A growth condition prediction program comprising:
11. An information processing device for predicting the growth state of vegetables that can be regenerated after planting, comprising: A determination unit that determines whether a prediction target vegetable belongs to one of a plurality of stages included in the first period of the fixed planting cultivation and a plurality of stages included in the second period of the regeneration cultivation; A determination unit that determines parameters of a model for predicting the growth state of the vegetable based on the temperature and the amount of solar radiation based on the determined stage; A prediction unit that predicts a growth state of the vegetable to be predicted by using the model in which the determined parameters are set; An information processing device comprising:
12. An information processing device for predicting a growth state of a vegetable that can be cultivated by fixed planting or can be regenerated after fixed planting and has a leaf blade and a leaf sheath, a determination unit that determines to which of a plurality of stages included in a cultivation period a vegetable to be predicted belongs; A determination unit that determines parameters of a model for predicting the growth state of the vegetable based on the temperature and the amount of solar radiation based on the determined stage; a prediction unit that predicts a growth state of the vegetable to be predicted by using the model in which the determined parameters are set, The parameters include a dry matter distribution rate used when estimating the dry matter weight of the leaf blade and the dry matter weight of the leaf sheath from the dry matter weight predicted to be produced in the vegetable, a leaf blade dry matter rate used when estimating the fresh weight from the estimated dry matter weight of the leaf blade, and a leaf sheath dry matter rate used when estimating the fresh weight from the estimated dry matter weight of the leaf sheath.
23. An information processing apparatus comprising:
13. An information processing device for predicting the growth state of flower vegetables, A determination unit that determines to which of a plurality of stages included in a cultivation period a flower vegetable to be predicted belongs; A determination unit that determines parameters of a model for predicting the growth state of the flower vegetable based on the temperature and the amount of solar radiation based on the determined stage; A prediction unit that predicts the growth state of the flower vegetable to be predicted using the model in which the determined parameters are set, The parameters include a dry matter distribution rate used to estimate the dry matter weight of the flower bud and the dry matter weight of the outer leaf from the dry matter weight predicted to be produced in the flower vegetable, an outer leaf dry matter rate used to estimate the fresh weight from the estimated dry matter weight of the outer leaf, and a flower bud dry matter rate used to estimate the fresh weight from the estimated dry matter weight of the flower bud.
23. An information processing apparatus comprising:
14. An information processing device for predicting the growth state of head vegetables, comprising: a determination unit that determines to which of a plurality of stages included in a cultivation period a heading vegetable to be predicted belongs; A determination unit that determines parameters of a model for predicting the growth state of the head vegetable based on the temperature and the amount of solar radiation based on the stage determined; a prediction unit that predicts a growth state of the head vegetable to be predicted by using the model in which the determined parameters are set, The parameters include a dry matter distribution ratio used to estimate the dry matter weight of the head part and the dry matter weight of the outer leaf part from the dry matter weight predicted to be produced in the head vegetable, an outer leaf part dry matter ratio used to estimate the fresh weight from the estimated dry matter weight of the outer leaf part, and a head part dry matter ratio used to estimate the fresh weight from the estimated dry matter weight of the head part.
23. An information processing apparatus comprising:
Citation Information
Patent Citations
Information processing device, and information processing method, and program
JP2016101117A
Culture support device, culture support method, computer program and recording medium
JP2019030253A
Producing method of shochu pomace fermentation product using koji
JP2019083754A
Production management system, management method, and program
JP2020024703A
