Additional fertilization amount output program, additional fertilization amount output method and additional fertilization amount output device

Abstract

To output a proper additional fertilization amount.SOLUTION: A computer generates a prediction model which includes, as explanatory variables, meteorological data on a field acquired in a first period after rice planting, vegetation index data on paddy rice obtained in the field at predetermined timing after the first period, an additional fertilization amount, and meteorological information predicted in the field in a second period including a ripening period of paddy rice after the first period, and further includes the yield and quality of paddy rice in the field as objective variables. Once receiving input of the meteorological data on the first field in the first period, the vegetation index data on paddy rice obtained in the first field at the predetermined timing, the meteorological information predicted in the first field in the second period, and target values for values representing the yield and quality of the first field, the computer calculates a necessary additional fertilization amount for making the yield and quality of the first field closer to the target values by use of the prediction model, and then outputs the calculated additional fertilization amount.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present invention relates to a top dressing amount output program, a top dressing amount output method, and a top dressing amount output device. [Background technology]

[0002] In paddy rice cultivation, top dressing is an important factor that influences the quality and yield of the rice. Traditionally, rice farmers would measure the height, number of stalks, leaf color, etc. of the rice plants and compare the results with predetermined indicators to determine the amount of top dressing to apply.

[0003] However, this method requires a great deal of effort for the actual measurement work, so the number of survey points cannot be increased unnecessarily. Also, because the number of survey points within a field is limited, it is not possible to adjust the amount of top dressing to correspond to uneven growth occurring within the field.

[0004] In response to this, in recent years, advances in drone technology have made it possible to quickly and extensively obtain vegetation indices (e.g., NDVI values ​​(Normalized Difference Vegetation Index)), which are data indicating growth rates. Furthermore, technology is known that uses vegetation indices as an indicator of top dressing (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent Publication No. 2021-108650 Summary of the Invention [Problem to be solved by the invention]

[0006] However, there is room for improvement in the technology of Patent Document 1, and it may be possible to output a more appropriate value for the amount of top dressing by taking into account information other than the vegetation index. Also, in light of the recent rise in fertilizer prices, it is preferable to determine the amount of top dressing by taking into account the profitability of producers.

[0007] An object of the present invention is to provide a top dressing amount output program, a top dressing amount output method, and a top dressing amount output device that are capable of outputting an appropriate top dressing amount.

[0008] Another object of the present invention is to provide a top dressing amount output program, a top dressing amount output method, and a top dressing amount output device that are capable of outputting an appropriate top dressing amount taking profitability into consideration. [Means for solving the problem]

[0009] The top dressing amount output program of the present invention uses meteorological data of a field acquired during a first period after rice planting, vegetation index data of paddy rice obtained in the field at a predetermined timing after the first period, the amount of top dressing in the field, and meteorological information predicted in the field during a second period after the first period including the ripening period of paddy rice, as explanatory variables, and generates a prediction model using values ​​representing the yield and quality of paddy rice in the field as objective variables, and generates a prediction model using meteorological data of the first field acquired during the first period and vegetation index data of paddy rice obtained in the field at a predetermined timing after the first period, the amount of top dressing in the field, and meteorological information predicted in the field during a second period including the ripening period of paddy rice after the first period as objective variables. and upon receiving input of vegetation index data for rice obtained at the specified timing, weather information predicted for the first field during the second period, and a target value for the yield of rice in the first field and / or a target value for a value representing the quality of rice in the first field, the program uses the prediction model to calculate the amount of top dressing required to bring the value representing the yield and / or quality of rice in the first field closer to the target value, and outputs the calculated amount of top dressing.

[0010] In addition, the top dressing amount output program of the present invention is a program that causes a computer to execute the following process: it generates a prediction model using field weather data acquired during a specified period after rice planting, rice vegetation index data acquired in the field at a specified time after the specified period, and the amount of top dressing in the field as explanatory variables, and the rice yield in the field as the target variable; when it receives input of a first field weather data acquired during the specified period and rice vegetation index data acquired in the first field at the specified time, it uses the prediction model to calculate the rice yield in the first field for each of multiple top dressing amounts; and it identifies and outputs the top dressing amount among the multiple top dressing amounts that maximizes the difference between the profit based on the increased yield due to top dressing and the cost required for top dressing. [Effects of the Invention]

[0011] The top dressing amount output program, the top dressing amount output method, and the top dressing amount output device of the present invention have the effect of being able to output an appropriate top dressing amount.

[0012] The top dressing amount output program, the top dressing amount output method, and the top dressing amount output device of the present invention have the effect of being able to provide an appropriate top dressing amount that takes profitability into consideration. [Brief explanation of the drawings]

[0013] [Figure 1] FIG. 1 is a diagram showing the configuration of a top dressing amount output system according to the first embodiment. [Figure 2] FIG. 2(a) is a diagram showing the hardware configuration of a server, and FIG. 2(b) is a diagram showing the hardware configuration of a user terminal. [Figure 3] FIG. 3 is a functional block diagram of the server. [Figure 4] 4(a) is a diagram showing a prediction model 1, FIG. 4(b) is a diagram showing a prediction model 2, and FIG. 4(c) is a diagram showing a prediction model 3. As shown in FIG. [Figure 5] FIG. 5 is a diagram showing a prediction result table. [Figure 6]Figure 6(a) is a diagram illustrating the relationship between the NDVI value, the amount of top dressing, and the predicted yield, and Figure 6(b) is a diagram illustrating the relationship between the NDVI value, the amount of top dressing, and the predicted protein content. [Figure 7] FIG. 7 is a diagram illustrating the relationship between the NDVI value, the amount of top dressing, and the predicted value of the ratio of uniform grains. [Figure 8] Figures 8(a) to 8(d) show the effects of changes in weather conditions on rice during the period from transplanting to the young panicle formation stage until it can be confirmed that the average young panicle length has reached 1 to 2 mm. [Figure 9] FIG. 9 is a table summarizing the yield, protein content, and whole grain ratio in relation to whether or not top dressing was applied when growth at the young panicle formation stage was sufficient, and the weather conditions during the ripening stage. [Figure 10] FIG. 10 is a flowchart illustrating an example of the prediction model generation process. [Figure 11] FIG. 11 is a flowchart showing an example of the top dressing amount output process. [Figure 12] FIG. 12 is a diagram showing a prediction result table 40' according to the second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0014] First Embodiment The first embodiment will be described below with reference to Figs. 1 to 11. Fig. 1 is a diagram schematically showing the configuration of a top dressing amount output system 100 according to the first embodiment. As shown in Fig. 1, the top dressing amount output system 100 includes a server 10 as a top dressing amount output device, and a user terminal 70. The server 10 and the user terminal 70 are connected via a network 80 such as the Internet.

[0015] The server 10 is an information processing device that calculates the amount of fertilizer to be applied at the time of top dressing in a field (top dressing amount) based on information input from the user terminal 70, outputs the calculated amount to the user terminal 70, and provides it to a user (e.g., a farmer) using the user terminal 70. When applying top dressing, the user determines the amount of fertilizer to actually apply, referring to the amount of top dressing provided by the server 10. The amount of top dressing is expressed as the amount of fertilizer per unit area (for example, in units of "kg / 10a").

[0016] For ease of explanation, it is assumed below that the server 10 calculates the amount of top dressing for one field. The server 10 also regards the field as a surface, calculates the amount of top dressing for each point within the surface, and generates map information (top dressing amount map information) that displays the calculated amount of top dressing for each point. The server 10 may calculate the amount of top dressing for multiple fields, or may calculate the amount of top dressing for a portion of the field.

[0017] Generally, after rice is transplanted from the nursery to the field, it grows through the following stages in one season: tillering stage → panicle formation stage → heading stage → flowering and pollination stage → full heading stage → ripening stage → maturity stage. The panicle formation stage is the period when growth switches from the establishment of tillers (branches) (vegetative growth) to the formation of panicles (reproductive growth). This is the period when the panicles that will become panicles are formed and the average panicle length reaches 1-2 mm. Typically, when transplanting from the nursery to the field, nitrogen-based slow-release fertilizer is applied (called initial fertilization). Furthermore, the period around the panicle formation stage, starting about two weeks after the panicle formation stage, is the period for top dressing, during which fertilizer (called panicle fertilization) is added (top dressing) to increase the number of grains that form in the panicles and the amount of starch packed into the grains.

[0018] FIG. 2(a) shows a schematic diagram of the hardware configuration of the server 10. As shown in FIG. 2(a), the server 10 includes a central processing unit (CPU) 90, a read-only memory (ROM) 92, a random access memory (RAM) 94, storage (such as a hard disk drive (HDD) or a solid state drive (SSD)) 96, a network interface 97, and a portable storage medium drive 99. These components of the server 10 are connected to a bus 98. In the server 10, the CPU 90 executes a program (including a top dressing amount output program) stored in the ROM 92 or the storage 96, or a program read from the portable storage medium 91 by the portable storage medium drive 99, thereby realizing the functions of the components shown in FIG. 3. The functions of the components shown in FIG. 3 may be realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA).

[0019] Returning to FIG. 1, the user terminal 70 is an information processing device such as a PC (Personal Computer) or smartphone used by a user. FIG. 2(b) shows a schematic diagram of the hardware configuration of the user terminal 70. As shown in FIG. 2(b), the user terminal 70 includes a CPU 190, a ROM 192, a RAM 194, a storage 196, a network interface 197, a display unit 193, an input unit 195, and the like. These components of the user terminal 70 are connected to a bus 198. The display unit 193 includes a liquid crystal display, etc., and the input unit 195 includes a keyboard, a mouse, a touch panel, etc.

[0020] (About Server 10 functions) Fig. 3 shows a functional block diagram of the server 10. In the server 10, a CPU 90 executes a program to realize functions as a learning data collection unit 30, a prediction model generation unit 32, an information acquisition unit 34, a prediction unit 36, and an output unit 38, as shown in Fig. 3. Note that Fig. 3 also shows a prediction result table 40 stored in a storage 96 or the like.

[0021] The learning data collection unit 30 collects a large amount of data obtained in past rice cultivation as learning data. In the first embodiment, the learning data collection unit 30 acquires the following data obtained in past rice cultivation as learning data.

[0022] (A): The period from rice planting to the young panicle formation stage until it can be confirmed that the average young panicle length has reached 1-2 mm (the first period) is divided into the first half and the second half, and the weather data for each period (weather data are (1) accumulated solar radiation, (2) accumulated temperature) (B): Ground-resolution vegetation index data (NDVI: Normalized Difference Vegetation Index) for up to 14 days after the average young panicle length reaches 1-2 mm, which is the appropriate time for top dressing. (C): Amount of top dressing applied to the field after the panicle formation stage (D): Weather information (at least one of temperature and solar radiation) for a second period after the first period (the ripening period (after rice heading is confirmed)), (E): Yield at harvest (brown rice weight) (F): Protein content, an index of rice quality at harvest. (G): The ratio of whole grains (whole grain percentage), which is an index of the quality of rice at harvest.

[0023] Regarding (A), the period from rice planting to the young panicle formation stage until it can be confirmed that the average young panicle length has reached 1 to 2 mm can be divided simply into an equal number of days into the first and second halves, or into the first and second halves at a predetermined ratio. The accumulated solar radiation is the sum of the average daily solar radiation for each day of each period, and the accumulated temperature is the sum of the average daily temperature for each day of each period. Each meteorological data is obtained by the user terminal 70 aggregating data obtained from sensors installed in the field. However, this is not limiting, and each meteorological data may also be input by the user into the user terminal 70.

[0024] The NDVI value (B) is obtained by the user terminal 70 analyzing the analytical image data. The analytical image data is image data generated by photographing the rice colony in the field from above using a multispectral sensor mounted on an aircraft such as a drone at a predetermined timing before top dressing (e.g., immediately before top dressing or several weeks before heading). The user terminal 70 analyzes the analytical image data using a well-known method to obtain the NDVI value of each point in the field. Note that the analytical image data does not have to be image data taken from an aircraft such as a drone. For example, the analytical image data may be a satellite photograph, or may be image data taken by a device installed at the top of a tower or a device operated by a person standing on a stepladder. Note that the analysis image data does not have to be analyzed by the user terminal 70. For example, the server 10 may obtain the analytical image data from the user terminal 70 or the like, and analyze the obtained analytical image data. The data for analysis does not have to be images; it can be point data acquired using a device that can acquire a range of NDVI values ​​by holding it over the surveyed location. An example of such a device is the Smart Agriculture Sensing Meter (https: / / www.nikon-trimble.co.jp / products / product_detail.html?tid=428). Furthermore, the image data does not have to be generated by a multispectral sensor. For example, the image data for analysis can be data generated by infrared thermography.

[0025] The amount of top dressing in (C) is expressed in units of "kg / 10a." It is the amount of top dressing actually applied by the user at each point in the field, and is assumed to be a value input by the user to the user terminal 70.

[0026] The weather information (at least one of temperature and solar radiation) for the second period (ripening period) in (D) may be actual data on temperature and solar radiation obtained in the past during the ripening period, or may be data on a medium- to long-term forecast obtained before the ripening period. Note that the second period does not necessarily have to coincide with the ripening period, and may be a period that includes the ripening period.

[0027] The yield at harvest in (E) is expressed in units of "kg / 10a." It is the yield of paddy rice actually harvested by the user at each point in the field, and is assumed to be a value input by the user to the user terminal 70.

[0028] The protein content in (F) indicates the percentage of protein contained in the rice, and is expressed in percentages. Generally, when the protein content exceeds 7%, the texture becomes hard and the taste deteriorates due to the influence of amylose. For this reason, the protein content tends to be more important for rice intended for home use, which has a higher trading price. On the other hand, for commercial rice intended for ready-meals and restaurants, yield tends to be more important than protein content.

[0029] The (G) whole grain ratio (whole grain percentage) is the percentage of whole grains that are of good quality out of the total brown rice, and is expressed in percentages. The importance of the whole grain ratio varies depending on the use; for example, it is not important when used as feed rice.

[0030] The prediction model generation unit 32 generates a prediction model using the training data collected by the training data collection unit 30. Specifically, as shown in FIG. 4(a), the prediction model generation unit 32 generates a prediction model 1 in which the weather data for the first period, NDVI, top dressing amount, and weather information predicted for the second period (ripening period) are explanatory variables, and the yield at harvest is the dependent variable. Furthermore, as shown in FIG. 4(b), the prediction model generation unit 32 generates a prediction model 2 in which the weather data for the first period, NDVI, top dressing amount, and weather information predicted for the second period (ripening period) are explanatory variables, and the protein content at harvest is the dependent variable. Furthermore, as shown in FIG. 4(c), the prediction model generation unit 32 generates a prediction model 3 in which the weather data for the first period, NDVI, top dressing amount, and weather information predicted for the second period (ripening period) are explanatory variables, and the whole grain size ratio at harvest is the dependent variable.

[0031] Here, the prediction model generation unit 32 generates prediction models 1 to 3 using training data obtained from fields located in a predetermined region where the same variety of paddy rice is cultivated. Prediction models 1 to 3 generated in this manner are prediction models that can be used to predict the yield, protein content, and whole grain ratio when paddy rice that exhibits similar growth characteristics is cultivated in that region (including not only paddy rice of the same variety, but also paddy rice of varieties that exhibit the same growth tendency, such as parent-child varieties).

[0032] The information acquisition unit 34 acquires information necessary for calculating the amount of top dressing from the user terminal 70. The information acquired by the information acquisition unit 34 includes meteorological data ((1) accumulated solar radiation, (2) accumulated temperature) for each period (first period) divided into two halves, the first period being the period from rice planting to the young panicle formation stage until it is confirmed that the average young panicle length has reached 1 to 2 mm in the field to be top dressed as the first field (hereinafter referred to as the "target field"), NDVI data obtained in the target field for up to 14 days after the average young panicle length reaches 1 to 2 mm, which is suitable for top dressing, and medium- to long-term forecast data for at least one of temperature and solar radiation for the second period (ripening period). The medium- to long-term forecast data for the ripening period is assumed to be data provided by the Japan Meteorological Agency or mesh agricultural meteorological data provided by the National Agriculture and Food Research Organization, a National Research and Development Agency. In addition, the information acquired by the information acquisition unit 34 includes at least one target value of yield, protein content, and granularity ratio input by the user to the user terminal 70, as well as information on which of yield and protein content is to be prioritized.

[0033] When a user wants to know the amount of top dressing for a target field, the user specifies the location of the target field and the variety of rice being cultivated, and inputs a request to output the amount of top dressing into the user terminal 70, along with inputting at least one target value for yield, protein content, and whole grain ratio. The user also inputs information on which of yield and protein content is to be prioritized. When the user inputs a request to output the amount of top dressing, the user terminal 70 transmits the information input by the user to the information acquisition unit 34, along with weather data and NDVI data for the target field.

[0034] The information acquisition unit 34 transmits the acquired information, including weather data for the first period of the target field, NDVI data, and weather information predicted for the second period (ripening period), to the prediction unit 36, and transmits the other information to the output unit 38.

[0035] The prediction unit 36 ​​identifies the range of NDVI values ​​in the target field acquired from the information acquisition unit 34, and identifies multiple values ​​included in the range. If the NDVI range in the target field is 0.65 to 0.95, the prediction unit 36 ​​identifies multiple NDVI values, for example, 0.650, 0.655, 0.660, ..., 0.945, and 0.0950, at intervals of 0.005.

[0036] The prediction unit 36 ​​also specifies a plurality of values ​​as the amount of top dressing. For example, the prediction unit 36 ​​specifies 0 kg / 10 a, 1 kg / 10 a, and 2 kg / 10 a as the amount of top dressing. The value of the amount of top dressing specified by the prediction unit 36 ​​is set in advance.

[0037] The prediction unit 36 ​​then inputs all combinations of the identified NDVI values ​​(0.650, 0.655, 0.660, ..., 0.945, 0.0950) and the amounts of top dressing (0, 1, 2), the weather data for the first period, and the weather information predicted for the ripening period into prediction models 1 to 3, thereby predicting the yield, protein content, and whole grain ratio corresponding to each combination. The prediction unit 36 ​​stores the prediction results in a prediction result table 40.

[0038] The prediction result table 40 is a table (list) as shown in Fig. 5. Specifically, the prediction result table 40 stores predicted values ​​of the yield, protein content, and whole grain ratio predicted using each combination of NDVI and top dressing amount, weather data for the first period, and weather information predicted for the second period (ripening period).

[0039] The output unit 38 refers to the target values ​​entered by the user for at least one of yield, protein content, and whole grain ratio, as well as information on which of yield and protein content is to be prioritized, and determines the amount of top dressing to be applied at each point in the target field based on the prediction result table 40, and outputs the amount to the user terminal 70.

[0040] For example, when the predicted yield values ​​in Figure 5 are plotted on a graph with the NDVI value on the horizontal axis and the yield on the vertical axis, the result is as shown in Figure 6(a). Also, when the predicted protein content values ​​are plotted on a graph with the NDVI value on the horizontal axis and the protein content on the vertical axis, the result is as shown in Figure 6(b). Also, when the predicted whole grain ratio values ​​are plotted on a graph with the NDVI value on the horizontal axis and the whole grain ratio on the vertical axis, the result is as shown in Figure 7.

[0041] For example, as shown in Figure 6(a), yields tend to increase with increases in the NDVI value, an index of crop growth, and the amount of top dressing. Therefore, while increasing the amount of top dressing can increase yields, applying top dressing too much can cause the ears of rice to become too heavy, causing the rice plants to fall over before harvest (lodging), increasing the amount of work required for harvesting and, in some cases, making harvesting impossible.

[0042] On the other hand, as shown in Figure 6(b), the protein content tends to decrease as the NDVI value decreases and the amount of top dressing is reduced. Although a high protein content tends to worsen the taste, conversely, when the protein content falls below 6%, the nutrients stored in the rice grains become insufficient, resulting in an increase in the occurrence of immature grains that turn cloudy white in the brown rice, and a decrease in the whole grain ratio (whole grain percentage), which is an indicator of quality.

[0043] In consideration of these, the output unit 38 of the first embodiment determines the amount of top dressing according to the following cases.

[0044] (1) Cases where yield is prioritized Basically, it is sufficient to increase the amount of top dressing, but if it is increased too much, the appropriate yield may be exceeded and the rice may fall over, so the amount of top dressing is controlled according to the NDVI value and the predicted yield.

[0045] (2) When protein content is a priority When producing rice for home consumption, it is necessary to control the protein content, so the amount of top dressing is determined based on the target value entered by the user (approximately 6.50%).

[0046] (3) Size size ratio After setting target values ​​for yield and protein content, if there is room for adjustment in the amount of top dressing, determine the amount of top dressing so that the proportion of uniform grains increases.

[0047] For example, suppose that the user prioritizes yield and inputs a target value of 550 (kg / 10a) to prevent lodging. In this case, the output unit 38 determines the amount of top dressing to be 0 (kg / 10a) for points where the NDVI value exceeds 0.87, as shown in FIG. 6(a), and outputs this to the user terminal 70. Furthermore, for points where the NDVI value is 0.87 or less, the amount of top dressing is likely to be less than 550 (kg / 10a) even if the amount of top dressing is increased, so the amount of top dressing is determined to be 2 (kg / 10a) to maximize the yield, and outputs this to the user terminal 70.

[0048] Similarly, suppose that the user prioritizes protein content and inputs 6.50% as the target value for protein content. In this case, the output unit 38 determines the amount of top dressing to be 0 (kg / 10a) for points where the NDVI value exceeds 0.86, as shown in FIG. 6(b), and outputs this to the user terminal 70. Furthermore, for points where the NDVI value is 0.86 or less, the output unit 38 determines the amount of top dressing to be 2 (kg / 10a) so that the protein content is maximized, and outputs this to the user terminal 70.

[0049] Furthermore, in the process of determining the amount of top dressing as described above, if the predicted values ​​of yield and protein content do not change significantly whether the amount of top dressing is 2 (kg / 10a) or 1 (kg / 10a), the value with the refined grain ratio closest to the target value is determined as the amount of top dressing as shown in Figure 7 and output to the user terminal 70.

[0050] In the first embodiment, the weather data for the first period used to generate prediction models 1 to 3 and the weather data for the first period input as explanatory variables to prediction models 1 to 3 are weather data for the first and second periods from rice planting to the young panicle formation stage until it is confirmed that the average young panicle length has reached 1 to 2 mm. The reason for this will be explained in detail with reference to Figures 8(a) to 8(d). Figures 8(a) to 8(d) are diagrams showing the effects on paddy rice of changes in weather conditions from rice planting to the young panicle formation stage until it is confirmed that the average young panicle length has reached 1 to 2 mm.

[0051] Although it varies by region, after rice is transplanted in mid-May, it goes through the period of taking root in the field (establishment period) and then the tillering period, during which the number of stems increases, until around the time of young panicle formation in early-to-mid-July. During this tillering period, the important stems that produce panicles appear especially during the "productive tillering period" (the first half of the tillering period) until around mid-June. If low temperatures and insufficient sunlight continue during this period (bad weather), the number of productive tillers will be low and the number of panicles will be low (see dashed circle A in Figure 8(c) and Figure 8(d)). On the other hand, if the weather is warm and there is a lot of sunlight (good weather) during the productive tillering period, there will be many productive tillers and a large number of panicles (number of stems) (see dashed circle B in Figure 8(a) and Figure 8(b)).

[0052] On the other hand, if weather conditions are poor during the productive tillering stage (the first half of the tillering stage) but become favorable from late June onwards, a compensatory effect occurs in which the number of rice grains per ear increases to make up for the small number of ears (stalks) (see dashed circle C in Figure 8(c)). Conversely, if weather conditions are poor from late June onwards, the number of rice grains decreases (see dashed circle D in Figure 8(b) and Figure 8(d)).

[0053] Although it is not possible to fully explain yield and quality based on weather conditions until the rice growth stage transitions to the young panicle formation stage, it is known that at least the number of panicles (number of stems) x number of grains, which is a component of yield, fluctuates depending on weather conditions in the first and second half of the period from planting to the young panicle formation stage until it can be confirmed that the average young panicle length has reached 1-2 mm. Therefore, it can be said that it is effective to use weather data from the first half of the period from planting to the young panicle formation stage until it can be confirmed that the average young panicle length has reached 1-2 mm separately from weather data from the second half of the period as weather data for the first period for determining the amount of top dressing.

[0054] Below is an example of a report on the rice crop condition for each fiscal year (crop condition index: indicates the percentage of the yield for a given year, assuming the average yield is 100) that was given at the committee on rice crop conditions held by the Statistics Department of the Ministry of Agriculture, Forestry and Fisheries. (1) An example of a case where weather conditions were good throughout the panicle formation stage (such as in Figure 8(a)) is the Hokkaido rice harvest in 2019. The crop condition index at this time was 104. In this example, the weather was generally good from the rice planting stage onwards, so the total number of grains was "slightly high." (2) The Tohoku region in FY2018 is an example of a case where weather conditions worsened before the panicle formation stage (as in Figure 8(b)). The crop condition index at this time was 99. In Aomori, Miyagi, and Fukushima prefectures, the total number of unhulled grains was "slightly higher," and in Iwate and Yamagata prefectures, the total number of unhulled grains was "average," but in Akita prefecture, the number was "slightly lower" due to the effects of low temperatures and lack of sunlight in mid-June. (3) An example of a case where weather conditions were poor after rice planting and then improved (such as in Figure 8(c)) is the Hokkaido rice harvest in FY2022. The crop condition index at this time was 106. Although the low temperatures in early June immediately after the rice planting period (late May) inhibited tillering, the total number of unhulled grains was "slightly high" because temperatures were generally high from late June until the heading period (late July) and there was plenty of sunshine in early and late July, ensuring a sufficient number of unhulled grains per ear. (4) An example of a case where weather conditions were generally poor (such as in Figure 8(d)) is the 2018 harvest in Hokkaido. The crop condition index at that time was 90. From mid-June to mid-July, the weather was generally low temperature and insufficient sunlight, which inhibited tillers and reduced the number of ears, resulting in a "low" total number of grains.

[0055] In the first embodiment, data on temperature and solar radiation amount during the ripening period (actual data, mid- to long-term forecast data) are used as weather information during the ripening period used when generating the prediction models 1 to 3, and as weather information predicted during the ripening period to be input as explanatory variables into the prediction models 1 to 3. The reason for this will be explained with reference to Fig. 9.

[0056] Recent reports on high-temperature damage in summer have shown that high temperatures during the ripening period are the main cause of the occurrence of white immature grains, and that low nitrogen concentrations in the rice plant contribute to this. Figure 9 shows a table summarizing the yield, protein content, and whole grain ratio in relation to whether or not top dressing was applied when growth at the young panicle formation stage was sufficient, and the weather conditions during the ripening period.

[0057] Nos. 1 to 3 in Figure 9 show examples where top dressing was refrained because growth was sufficient during the young panicle formation stage. Of these, No. 2 is an example where the temperature and solar radiation thereafter remained at average levels, resulting in roughly normal yields, protein content, and whole grain ratios. On the other hand, No. 1 shows an example where the temperature during the ripening period was high and the solar radiation was high. In this case, growth became more vigorous, resulting in a slight deficiency in nitrogen concentration, a low protein content, a low yield, and a slightly poor whole grain ratio. Furthermore, No. 3 shows an example where the temperature during the ripening period was low and the solar radiation was low. In this case, the yield was normal, the protein content was slightly high, and the whole grain ratio was normal. As such, it can be seen that when top dressing is refrained, changes in rice growth can be seen depending on the temperature and solar radiation during the ripening period.

[0058] Nos. 4 to 6 in Figure 9 show examples where growth was sufficient at the panicle formation stage, but top dressing was applied. Nos. 4 to 6 show that when top dressing is applied, the nitrogen concentration becomes sufficient, so although the protein content increases slightly, the decrease in yield is suppressed. In this way, when top dressing is applied, it is possible to reduce changes in rice growth caused by temperature and solar radiation during the ripening period.

[0059] As described above, it is clear that there is a relationship between the amount of top dressing and meteorological information during the ripening period (at least one of temperature and solar radiation) and the yield, protein content, and proportion of whole grains. Therefore, in the first embodiment, an appropriate amount of top dressing can be determined by using meteorological information during the ripening period (at least one of temperature and solar radiation) as an explanatory variable for prediction models 1 to 3.

[0060] (Regarding Server 10 processing) The processing of the server 10 will be described in detail below with reference to the flowcharts of FIGS.

[0061] (Prediction model generation process) 10 is a flowchart showing the prediction model generation process by the prediction model generation unit 32. The process in FIG. 10 is executed when the learning data collection unit 30 has collected a large amount of learning data from the user terminal 70, for example.

[0062] When the process of FIG. 10 starts, first, in step S10, the prediction model generation unit 32 acquires training data from the training data collection unit 30. The training data is a dataset of meteorological data, NDVI values, top dressing amounts, meteorological information, yield, protein content, and proportion of whole grains for a first period obtained at each location where rice was actually cultivated. The meteorological data for the first period is meteorological data ((1) accumulated solar radiation, (2) accumulated temperature) for each period when the period from rice planting to the young panicle formation stage until it can be confirmed that the average young panicle length has reached 1 to 2 mm is divided into two parts. The NDVI values ​​are values ​​obtained up to 14 days after the average young panicle length has reached 1 to 2 mm, which is the time suitable for top dressing. The meteorological information for the second period is, for example, information on at least one of the temperature and solar radiation during the ripening stage. The yield, protein content, and proportion of whole grains are values ​​related to actually harvested rice.

[0063] Next, in step S12, the prediction model generation unit 32 generates a prediction model 1 using the weather data for the first period, the NDVI value, the amount of top dressing, and the weather information predicted for the second period (ripening period) as explanatory variables, and the yield as the objective variable. The prediction model generation unit 32 generates the prediction model 1 (see FIG. 4(a)) by machine learning or the like. The prediction model generation unit 32 generates one prediction model 1 using data obtained when paddy rice of the same variety is cultivated in the same predetermined region. In other words, a prediction model 1 is generated for each region and each variety.

[0064] Next, in step S14, the prediction model generation unit 32 generates a prediction model 2 (see FIG. 4(b)) using the weather data for the first period, the NDVI value, the amount of top dressing, and the weather information predicted for the second period (ripening period) as explanatory variables, and the protein content as the objective variable. The prediction model generation unit 32 generates the prediction model 2 by machine learning or the like. The prediction model generation unit 32 generates one prediction model 2 using data obtained when the same variety of paddy rice is cultivated in the same predetermined region. In other words, a prediction model 2 is generated for each region and each variety.

[0065] Next, in step S16, the prediction model generation unit 32 generates a prediction model 3 (see FIG. 4(c)) using the weather data for the first period, the NDVI value, the amount of top dressing, and the weather information predicted for the second period (ripening period) as explanatory variables, and the proportion of uniform grains as the objective variable. The prediction model generation unit 32 generates the prediction model 3 by machine learning or the like. The prediction model generation unit 32 generates one prediction model 3 using data obtained when paddy rice of the same variety is cultivated in the same predetermined region. In other words, a prediction model 3 is generated for each region and each variety.

[0066] This completes the entire process in Figure 10. The process in Figure 10 may be repeated each time a predetermined number of new training data items are acquired. In this case, for example, old training data that has been acquired for a certain period of time or more may not be used in generating prediction models 1 to 3.

[0067] (Top dressing amount output processing) Fig. 11 is a flowchart showing the top dressing amount output process executed by the server 10. The process in Fig. 11 is started when the user inputs a request to output the top dressing amount by specifying the location of the target field and the variety of paddy rice being cultivated on the user terminal 70, and the information acquisition unit 34 receives the input.

[0068] 11 starts, first, in step S30, the information acquisition unit 34 acquires meteorological data for a first period of the target field, an NDVI value, and meteorological information predicted for the target field in the ripening period (medium- to long-term forecast data for at least one of temperature and solar radiation). The information acquisition unit 34 transmits the acquired information to the prediction unit 36.

[0069] Next, in step S32, the information acquisition unit 34 acquires at least one target value of the yield, protein content, and size distribution ratio, as well as information on the priority item. The information acquisition unit 34 transmits the acquired information to the output unit 38. The priority item information is either the yield or the protein content selected by the user. Note that if the user has input a target value for only one of the yield and the protein content, the item for which the target value was input becomes the priority item.

[0070] Next, in step S34, the prediction unit 36 ​​identifies the range of NDVI values ​​in the target field and identifies multiple NDVI values ​​within the range. For example, assume that the range of NDVI values ​​measured in the target field is 0.65 to 0.95. In this case, using a predetermined interval (e.g., 0.005), the prediction unit 36 ​​identifies multiple NDVI values ​​as 0.650, 0.655, 0.660, ..., 0.945, and 0.0950.

[0071] Next, in step S36, the prediction unit 36 ​​determines prediction models 1 to 3 to be used based on the location of the target field and the variety cultivated in the target field. In other words, prediction models 1 to 3 that are suitable for the target field are determined.

[0072] Next, in step S38, the prediction unit 36 ​​inputs the acquired weather data for the first period, the weather information predicted for the ripening period, and the identified combinations of NDVI values ​​and top dressing amounts into the determined prediction models 1 to 3, predicts the yield, protein content, and whole grain ratio for each combination, and stores the results in a prediction result table 40. For example, the prediction unit 36 ​​identifies multiple values ​​(e.g., 0 kg / 10a, 1 kg / 10a, 2 kg / 10a) as the top dressing amount, and predicts the yield, protein content, and whole grain ratio for all combinations with the identified NDVI values ​​(0.650, 0.655, 0.660, ..., 0.945, 0.0950). The prediction unit 36 ​​then stores the prediction results in a prediction result table 40.

[0073] Next, in step S40, the output unit 38 refers to the prediction result table 40 and determines the amount of top dressing at each point in the target field from the acquired target values ​​and information on the priority items.

[0074] For example, in the examples of Figures 6(a) to 7, "yield" is the priority item, the target value of yield is 550 (kg / 10a), the target value of protein content is 6.50 (%), the larger the whole grain ratio, the better, and the NDVI value is 0.8. In this case, (1) The output unit 38 first considers the amount of top dressing to bring the priority item "yield" closer to its target value of 550. With reference to FIG. 6(a), the output unit 38 determines that if the NDVI value (horizontal axis) is 0.8, the amount of top dressing should be 2 (kg / 10a) or 1 (kg / 10a). (2) Next, the output unit 38, referring to Figure 6(b), determines that when the NDVI value (horizontal axis) = 0.8, in order to bring the protein content closer to the target value = 6.50, it is best to set the amount of top dressing to 2 (kg / 10a). (3) Furthermore, with reference to FIG. 7, the output unit 38 determines that the amount of top dressing does not have much effect on the uniform grain size ratio when the NDVI value (horizontal axis) is 0.8. (4) Then, the output unit 38 comprehensively considers the results of the above determinations (1) to (3) and determines the amount of top dressing at the point where the NDVI value is 0.8 to be 2 (kg / 10a).

[0075] On the other hand, in the examples of Figures 6(a) to 7, the protein content (taste) is the priority item, the target value of the protein content is 6.50 (%), the target value of the yield is 550 (kg / 10a), the larger the ratio of whole grains is the better, and the NDVI value is 0.9. In this case, (1) First, in order to bring the priority item “protein content” closer to the target value of 6.50, the output unit 38 refers to FIG. 6(b) and determines that if the NDVI value (horizontal axis) is 0.9, the amount of top dressing should be set to 0 (kg / 10a). (2) Next, the output unit 38, referring to Figure 6(a), determines that when the NDVI value (horizontal axis) = 0.9, in order to bring the yield closer to the target value = 550, it is best to set the amount of top dressing to 0 (kg / 10a). (3) Furthermore, the output unit 38, referring to FIG. 7, determines that if the NDVI value (horizontal axis) is 0.9, it is better to set the amount of top dressing to 0 (kg / 10a) in order to maximize the ratio of uniform grains. (4) Then, the output unit 38 comprehensively considers the results of the above determinations (1) to (3) and determines the amount of top dressing at the point where the NDVI value is 0.9 to be 0 (kg / 10a).

[0076] In addition, if only some of the target values ​​for yield, protein content, and whole grain ratio are input, the output unit 38 can make a judgment similar to that described above using only the input target values ​​and determine the amount of top dressing.

[0077] Returning to FIG. 11 , in the next step S42, the output unit 38 outputs the determined amount of top-dressing fertilizer to the user terminal 70. In this case, the output unit 38 regards the target field as a surface and determines the amount of top-dressing fertilizer for each point using the NDVI value of each point within the surface. The output unit 38 then generates the determined amount of top-dressing fertilizer for each point (top-dressing fertilizer amount map information) and outputs it to the user terminal 70. The user can operate a top-dressing fertilizer device based on the top-dressing fertilizer amount map information to apply top-dressing fertilizer to the target field. The user terminal 70 may also provide the top-dressing fertilizer amount map information to a mobile object (e.g., a drone or a riding implement for cultivation management) equipped with a fertilizer spreader that can automatically control the amount of spread. The mobile object monitors its current location while moving, and adjusts the amount of top-dressing fertilizer to be applied for each position based on its current location and the top-dressing fertilizer amount map information. This makes it possible to easily apply an appropriate amount of top-dressing fertilizer to the target field. In addition, if the mobile object is capable of measuring the NDVI value, the mobile object may measure the NDVI value while moving, and top dressing may be performed based on the amount of top dressing calculated based on the measurement results.

[0078] As can be seen from the explanation so far, in this first embodiment, the prediction unit 36 ​​and the output unit 38 realize the function of a processing unit that determines the amount of top dressing required to bring values ​​representing yield and quality in the target field (protein content and whole grain ratio) closer to target values, and outputs the result to the user terminal 70.

[0079] As explained in detail above, according to the first embodiment, the prediction model generation unit 32 generates prediction models 1 to 3 using as explanatory variables field weather data acquired during the first period after rice planting (the period from rice planting to the young panicle formation period until it can be confirmed that the average young panicle length has reached 1 to 2 mm), the NDVI value for the next 14 days after the average young panicle length has reached 1 to 2 mm, which is suitable for top dressing, the amount of top dressing, and weather information (at least one of temperature and solar radiation) predicted in the field during the second period after the first period (ripening period), and values ​​representing yield and quality (protein content and whole grain ratio) as target variables. Furthermore, the prediction unit 36 ​​and the output unit 38 determine the amount of top dressing required to bring the values ​​representing the yield and quality (protein content and proportion of whole grains) in the target field closer to the target values, based on meteorological data for the target field over a predetermined period, NDVI values ​​obtained in the target field up to 14 days after the average young panicle length reaches 1 to 2 mm, which is the time when top dressing is appropriate, meteorological information (at least one of temperature and solar radiation) predicted for the field during the second period (ripening period), and target values ​​for values ​​representing yield and quality (protein content and proportion of whole grains).The output unit 38 then outputs the determined amount of top dressing to the user terminal 70.As a result, in the first embodiment, the amount of top dressing can be accurately determined based on the NDVI values ​​obtained in the target field, meteorological data for the first period, forecast information for the second period (ripening period) (at least one of temperature and solar radiation), and target values ​​for yield and quality, and can be provided to the user of the user terminal 70. In this case, by using the NDVI value, it is not necessary to actually measure the dimensions of the rice plant, etc., which reduces the workload. In addition, by using the NDVI value, it is possible to grasp the field as a surface and determine the amount of top dressing for each position within the surface, so it is possible to generate and provide users with top dressing amount map information that shows the amount (distribution) of top dressing within the field in detail.

[0080] Furthermore, in the first embodiment, the prediction unit 36 ​​uses prediction models 1 to 3 to predict values ​​representing yield and quality (protein content and proportion of well-formed grains) for each combination of multiple NDVI values ​​and multiple values ​​of top dressing amounts, and stores the results in a prediction result table 40. The output unit 38 then determines and outputs the amount of top dressing corresponding to the target values ​​of yield and quality input by the user from the prediction result table 40. This makes it possible to determine an appropriate amount of top dressing through simple processing and provide it to the user.

[0081] Furthermore, in the first embodiment, the output unit 38 determines the amount of top dressing in consideration of the priority item (yield or protein content) designated by the user. This allows a more appropriate value to be determined as the amount of top dressing.

[0082] Furthermore, in this first embodiment, as the meteorological data for the first period, meteorological data (accumulated solar radiation and accumulated temperature) for the period (first half and second half) divided into two equal parts from rice planting to the young panicle formation stage until it can be confirmed that the average young panicle length has reached 1 to 2 mm is used.Therefore, as explained using Figures 8(a) to 8(d), it is possible to generate an accurate prediction model that reflects the impact on rice plants of the meteorological conditions in the first and second half of the period from rice planting to the young panicle formation stage until it can be confirmed that the average young panicle length has reached 1 to 2 mm.

[0083] Second Embodiment The second embodiment will be described below with reference to Fig. 12. The configuration of the top dressing amount output system of the second embodiment is the same as that of Fig. 1, the configuration of the server 10 is the same as that of Fig. 2(a), and the functional block of the server 10 is the same as that of Fig. 3.

[0084] Therefore, similar to the first embodiment, the prediction unit 36 ​​of the server 10 of this second embodiment inputs all combinations of multiple NDVI values ​​(0.650, 0.655, 0.660, ..., 0.945, 0.0950) and multiple top dressing amounts (0, 1, 2), weather data for the first period, and weather information predicted for the ripening period into prediction models 1 to 3, thereby predicting the yield, protein content, and whole grain ratio corresponding to each combination, and storing the predicted results in the prediction result table 40 shown in Figure 4.

[0085] Thereafter, the prediction unit 36 ​​of the second embodiment generates a prediction result table 40' as shown in Fig. 12 based on the prediction result table 40 of Fig. 4. The prediction result table 40' of Fig. 12 has a column for cost-effectiveness in addition to the prediction result table 40 of Fig. 4. The cost-effectiveness can be calculated by the following formula (1). Cost-effectiveness = {Yield increase due to top dressing (predicted value) x trading price} - {amount of top dressing x fertilizer unit price} …(1)

[0086] Note that "yield increase due to top dressing" refers to the yield increase when top dressing is applied compared to when the NDVI is the same and the amount of top dressing is 0, and {yield increase due to top dressing (predicted value) × transaction price} refers to the increased profit due to top dressing. {amount of top dressing × unit price of fertilizer} refers to the cost required for top dressing. For example, looking at the row where NDVI = 0.650 in Figure 12, when the standard amount of top dressing = 0 (kg / 10a), the amount of yield increase is (x1 - x1) (kg / 10a) = 0. Therefore, the cost-effectiveness is 0. On the other hand, in the row where the amount of top dressing = 1 (kg / 10a), the amount of yield increase is (x2 - x1) (kg / 10a). Therefore, if the transaction price is a (yen / kg) and the unit price of fertilizer is b (yen / kg), the cost-effectiveness v2 of top dressing can be calculated from the above formula (1) as follows: v2={(x2-x1)×a}-(1×b) It can be found that:

[0087] In addition, in the case of the row where the amount of top dressing = 2 (kg / 10a), the yield increase is (x3-x1) (kg / 10a). Therefore, the cost-effectiveness of top dressing v3 is calculated from the above formula (1): v3={(x3-x1)×a}-(2×b) It can be found that:

[0088] In this second embodiment, the user is assumed to have input in advance which of the following is a priority: yield, protein content, whole grain ratio, or cost-effectiveness. The output unit 38 then references the priority items input by the user and determines the amount of top dressing for each location in the target field based on the prediction result table 40, and outputs the result to the user terminal 70. For example, if cost-effectiveness is input as a priority item, the output unit 38 outputs the amount of top dressing that maximizes cost-effectiveness for rows with the same NDVI value. That is, if the NDVI value is 0.650, the cost-effectiveness values ​​(0, v2, v3) are compared and the amount of top dressing that maximizes cost-effectiveness (either 0, 1, or 2) is output. Note that if the protein content or whole grain ratio affects the transaction price a, the transaction price a used in the above formula (1) may be corrected using the protein content or whole grain ratio.

[0089] In the second embodiment, the weather information for the second period (ripening period) is used when generating Models 1 to 3, and the weather information predicted for the second period (ripening period) is input as the explanatory variables for Models 1 to 3. However, the present invention is not limited to this. That is, the weather information for the second period (ripening period) does not need to be used when generating Models 1 to 3, and the weather information predicted for the second period (ripening period) does not need to be input as the explanatory variables for Models 1 to 3.

[0090] In the above embodiments, the NDVI value is used as the vegetation index data, but the present invention is not limited to this. For example, the SPAD value, which can be used as an index for measuring the vigor of rice plants based on leaf color, like the NDVI, may be used.

[0091] In the above embodiments, the period from rice planting to the young panicle formation stage until it can be confirmed that the average young panicle length has reached 1 to 2 mm is divided into two parts (first half and second half), and meteorological data (accumulated solar radiation and accumulated temperature) for the first and second halves are used for prediction. However, this is not limited to this, and the period from rice planting to the young panicle formation stage until it can be confirmed that the average young panicle length has reached 1 to 2 mm may be divided into three or more parts, and meteorological data for each part may be used for prediction.

[0092] The above processing functions can be realized by a computer. In this case, a program is provided that describes the processing contents of the functions that the processing device should have. By executing the program on a computer, the above processing functions are realized on the computer. The program that describes the processing contents can be recorded on a computer-readable storage medium (excluding carrier waves).

[0093] When distributing a program, it is sold in the form of a portable storage medium on which the program is recorded, such as a DVD (Digital Versatile Disc) or a CD-ROM (Compact Disc Read Only Memory).The program can also be stored in the storage device of a server computer and transferred from the server computer to other computers via a network.

[0094] A computer that executes a program stores, for example, a program recorded on a portable storage medium or a program transferred from a server computer in its own storage device. The computer then reads the program from its own storage device and executes processing in accordance with the program. Note that the computer can also read the program directly from a portable storage medium and execute processing in accordance with that program. The computer can also execute processing in accordance with the program received each time a program is transferred from the server computer.

[0095] The above-described embodiment is a preferred example of the present invention, but the present invention is not limited to this and can be modified in various ways without departing from the spirit of the present invention. [Explanation of symbols]

[0096] 10 Server (top dressing amount output device) 30 Learning Data Collection Unit 32 Prediction model generation unit 34 Information Acquisition Department 36 Prediction unit (part of the processing unit) 38 Output unit (part of the processing unit) 40 Prediction result table (list)

Claims

1. a prediction model is generated using, as explanatory variables, meteorological data for the field acquired during a first period after rice planting, vegetation index data for the paddy rice obtained in the field at a predetermined timing after the first period, the amount of top dressing in the field, and meteorological information predicted for the field during a second period after the first period, including the ripening period of the paddy rice; and a value representing the yield and quality of the paddy rice in the field as objective variables; When receiving input of weather data for the first field acquired during the first period, vegetation index data for paddy rice obtained at the predetermined timing in the first field, weather information predicted for the first field during the second period, and a target value for the yield of paddy rice in the first field and / or a target value for a value representing the quality of paddy rice in the first field, the prediction model is used to calculate an amount of top dressing required to bring the value representing the yield and / or the quality of paddy rice in the first field closer to the target value, Output the calculated amount of top dressing. A top dressing amount output program characterized by causing a computer to execute processing.

2. In the calculation process, inputting the weather data of the first field acquired during the first period, the weather information predicted for the first field during the second period, and combinations of a plurality of vegetation index data values ​​and a plurality of top dressing amount values ​​into the prediction model, thereby obtaining values ​​representing the yield and quality of paddy rice for each combination of the vegetation index data value and the top dressing amount value, and compiling the values ​​into a list; extracting from the list a value of a top dressing amount corresponding to the input vegetation index data of paddy rice obtained at the predetermined timing in the first field and the target value; 2. The top dressing amount output program according to claim 1 .

3. In the calculation process, Accepting input of information on items to be prioritized among the values ​​representing the yield and quality; 2. The top dressing amount output program according to claim 1, wherein the top dressing amount is calculated based on information on the items to be prioritized.

4. The top dressing amount output program described in claim 1, characterized in that the weather data for the first period is weather data for multiple periods divided into periods from rice planting to the young panicle formation period until it can be confirmed that the average young panicle length has reached 1 to 2 mm.

5. The top dressing amount output program described in claim 4, characterized in that the weather data for the first period is weather data for two periods equally divided by the number of days from rice planting to the young panicle formation period until it can be confirmed that the average young panicle length has reached 1 to 2 mm.

6. 2. The top dressing amount output program according to claim 1, wherein the meteorological data is data on accumulated solar radiation and accumulated temperature.

7. 2. The top dressing amount output program according to claim 1, wherein the value representing the quality is at least one of a protein content rate and a ratio of uniform grain size.

8. 2. The top dressing amount output program according to claim 1, wherein the meteorological information is information on at least one of temperature and solar radiation.

9. A prediction model is generated using meteorological data of the field acquired during a predetermined period after rice planting, vegetation index data of paddy rice obtained in the field at a predetermined timing after the predetermined period, and the amount of top dressing applied to the field as explanatory variables, and using the yield of paddy rice in the field as a target variable; when receiving input of weather data for the first field acquired during the predetermined period and vegetation index data for paddy rice obtained at the predetermined timing in the first field, calculating a yield of paddy rice in the first field according to each of a plurality of amounts of top dressing using the prediction model; Among the plurality of amounts of top dressing, the amount of top dressing that maximizes the difference between the profit based on the amount of increase in yield due to the top dressing and the cost required for the top dressing is identified and output. A top dressing amount output program characterized by causing a computer to execute processing.

10. The explanatory variables include meteorological information predicted in the field for a period including a ripening period of the rice plant; the calculating process receives input of weather data for the first field acquired during the predetermined period, vegetation index data for paddy rice obtained at the predetermined timing in the first field, and weather information predicted for the first field during a period including the ripening period, and calculates the yield of paddy rice in the first field according to each of the plurality of amounts of top dressing using the prediction model; 10. The top dressing amount output program according to claim 9.

11. a prediction model is generated using, as explanatory variables, meteorological data for the field acquired during a first period after rice planting, vegetation index data for the paddy rice obtained in the field at a predetermined timing after the first period, the amount of top dressing in the field, and meteorological information predicted for the field during a second period after the first period, including the ripening period of the paddy rice; and a value representing the yield and quality of the paddy rice in the field as objective variables; When receiving input of weather data for the first field acquired during the first period, vegetation index data for paddy rice obtained at the predetermined timing in the first field, weather information predicted for the first field during the second period, and a target value for the yield of paddy rice in the first field and / or a target value for a value representing the quality of paddy rice in the first field, the prediction model is used to calculate an amount of top dressing required to bring the value representing the yield and / or the quality of paddy rice in the first field closer to the target value, Output the calculated amount of top dressing. A method for outputting a top dressing amount, characterized in that the processing is performed by a computer.

12. A prediction model is generated using meteorological data of the field acquired during a predetermined period after rice planting, vegetation index data of paddy rice obtained in the field at a predetermined timing after the predetermined period, and the amount of top dressing applied to the field as explanatory variables, and using the yield of paddy rice in the field as a target variable; when receiving input of weather data for the first field acquired during the predetermined period and vegetation index data for paddy rice obtained at the predetermined timing in the first field, calculating a yield of paddy rice in the first field according to each of a plurality of amounts of top dressing using the prediction model; Among the plurality of amounts of top dressing, the amount of top dressing that maximizes the difference between the profit based on the amount of increase in yield due to the top dressing and the cost required for the top dressing is identified and output. A method for outputting a top dressing amount, characterized in that the processing is performed by a computer.

13. a prediction model generation unit that generates a prediction model using, as explanatory variables, meteorological data of the field acquired during a first period after rice planting, vegetation index data of the paddy rice obtained in the field at a predetermined timing after the first period, the amount of top dressing in the field, and meteorological information predicted in the field during a second period including the ripening period of the paddy rice after the first period, and values ​​representing the yield and quality of the paddy rice in the field as objective variables; a processing unit that, upon receiving input of weather data for the first field acquired during the first period, vegetation index data for paddy rice obtained at the predetermined timing in the first field, weather information predicted for the first field during the second period, and a target value for the yield of paddy rice in the first field and / or a target value for a value representing the quality of paddy rice in the first field, calculates an amount of top dressing required to bring the value representing the yield and / or the quality of paddy rice in the first field close to the target value using the prediction model, and outputs the calculated amount of top dressing; A top dressing amount output device equipped with:

14. a prediction model generation unit that generates a prediction model using meteorological data of the field acquired during a predetermined period after rice planting, vegetation index data of the paddy rice obtained in the field at a predetermined timing after the predetermined period, and the amount of top dressing in the field as explanatory variables, and using the yield of the paddy rice in the field as a response variable; a processing unit that, upon receiving input of weather data for the first field acquired during the specified period and vegetation index data for paddy rice obtained at the specified timing in the first field, calculates the yield of paddy rice in the first field according to each of a plurality of top dressing amounts using the prediction model, identifies and outputs the top dressing amount among the plurality of top dressing amounts that maximizes the difference between the profit based on the increase in yield due to the top dressing and the cost required for the top dressing; A top dressing amount output device equipped with:

Images