Prediction device, prediction method, and program

Abstract

Predicts the occurrence of plant diseases and pests with high accuracy. [Solution] The prediction device (1) includes a calculation unit (12) that calculates the current rate of proliferation of plant diseases and pests by referring to at least one of the information indicating the temperature, humidity, and sunshine hours around the plant at the present time, and a prediction unit (13) that predicts the current amount of disease and pest occurrence using Bayesian modeling based on the cumulative value of the proliferation rate and the amount of disease and pest occurrence at a time prior to the present time.

Description

Technical Field

[0001] The present invention relates to a prediction device, a prediction method, and a program for predicting the occurrence amounts of plant diseases and pests.

Background Art

[0002] Techniques for predicting the occurrence of plant diseases and pests are known. In the present disclosure, "diseases and pests" are also referred to as "pest-diseases".

[0003] For example, Patent Document 1 discloses a pest-disease occurrence estimation device that estimates locations in a space where pest-diseases are likely to occur based on environmental factors at each location in the space. The pest-disease occurrence estimation device estimates locations where pest-diseases are likely to occur based on environmental factors at a certain measurement date and time.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] However, since the above-described pest-disease occurrence estimation device estimates locations where pest-diseases are likely to occur based on environmental factors at a certain measurement date and time, there is a problem that the accuracy of the estimation is low.

[0006] One aspect of the present invention aims to realize a technique for predicting the occurrence of plant pest-diseases with high accuracy.

Means for Solving the Problems

[0007] To solve the above problems, a prediction device according to one aspect of the present invention includes a calculation unit that calculates the current rate of proliferation of pests and diseases on the plant by referring to at least one of the information indicating the temperature around the plant at the present time, information indicating humidity, and information indicating the amount of sunlight; and a prediction unit that predicts the current amount of pests and diseases on the plant using Bayesian modeling based on the cumulative value of the proliferation rate and the amount of pests and diseases on the plant at a time prior to the present time.

[0008] To solve the above problems, a prediction method according to one aspect of the present invention includes a calculation process that calculates the current rate of proliferation of pests and diseases on the plant by referring to at least one of information indicating the temperature around the plant at the present time, information indicating humidity, and information indicating the amount of sunlight; and a prediction process that uses Bayesian modeling to predict the current amount of pests and diseases on the plant based on the cumulative value of the proliferation rate and the amount of pests and diseases on the plant at a time prior to the present time.

[0009] To solve the above problems, a program according to one aspect of the present invention is a program for causing a computer to function as a prediction device, wherein the computer functions as a calculation unit that calculates the current rate of proliferation of pests and diseases on the plant by referring to at least one of information indicating the temperature around the plant at the present time, information indicating humidity, and information indicating the amount of sunlight; and a prediction unit that predicts the current amount of pests and diseases on the plant using Bayesian modeling based on the cumulative value of the proliferation rate and the amount of pests and diseases on the plant at a time prior to the present time. [Effects of the Invention]

[0010] According to one aspect of the present invention, the occurrence of plant diseases and pests can be predicted with high accuracy. [Brief explanation of the drawing]

[0011] [Figure 1] This is a block diagram showing the configuration of a prediction device according to Embodiment 1 of the present invention. [Figure 2]This figure shows an overview of the method by which the prediction device according to Embodiment 1 of the present invention predicts the occurrence of plant diseases and pests. [Figure 3] This figure shows an example of a system using a prediction device according to Embodiment 1 of the present invention. [Figure 4] This is a flowchart showing the processing flow executed by the prediction device according to Embodiment 1 of the present invention. [Figure 5] This is a block diagram showing the configuration of a prediction device according to Embodiment 2 of the present invention. [Figure 6] This is a flowchart showing the processing flow executed by the prediction device according to Embodiment 2 of the present invention. [Figure 7] This is an example of a graph showing the diseased leaf rate and proliferation rate in Example 1 of the present invention. [Figure 8] This is another example of a graph showing the diseased leaf rate and proliferation rate in Example 1 of the present invention. [Figure 9] This is an example of a graph showing the diseased leaf rate and proliferation rate in Example 2 of the present invention. [Figure 10] This graph shows the relationship between temperature, humidity, and growth rate in Example 2 of the present invention. [Figure 11] This graph shows the relationship between temperature, sunshine duration, and growth rate in Example 2 of the present invention. [Modes for carrying out the invention]

[0012] [Embodiment 1] One embodiment of the present invention will be described in detail below.

[0013] (Overview of Prediction Device 1) The prediction device 1 according to this embodiment is a device for predicting the occurrence of plant diseases and pests. The plant diseases and pests in this disclosure are not particularly limited, but as an example, plant diseases are fungal diseases. Furthermore, the fungal diseases in this disclosure are not particularly limited, but as an example, fungal diseases are filamentous fungal diseases. Furthermore, the filamentous fungal diseases in this disclosure are not particularly limited, but as an example, filamentous fungal diseases are powdery mildew. Furthermore, the pests in this disclosure are not particularly limited, but as an example, pests are mites, aphids, or thrips.

[0014] The method by which the prediction device 1 predicts the occurrence of plant diseases and pests will be explained with reference to Figure 2. Figure 2 is a diagram illustrating the method by which the prediction device 1 according to this embodiment predicts the occurrence of plant diseases and pests.

[0015] Prediction device 1 predicts the occurrence of plant diseases and pests using a state-space model that takes time series into account.

[0016] For example, as shown in Figure 2, the prediction device 1 uses the amount of pests and diseases occurring in plants at time k-1 and environmental information such as the temperature and humidity around the plants at time k to predict the amount of pests and diseases occurring in plants at time k as the state at time k. "k" is not particularly limited, but as an example, it may be a day. That is, time k-1 may be day k-1, and time k may be day k.

[0017] Next, the prediction device 1 uses the amount of plant pests and diseases at time k and the environmental information surrounding the plant at time k+1 to predict the state at time k+1, specifically the amount of plant pests and diseases at time k+1.

[0018] In this way, the prediction device 1 uses a state-space model that takes time series into account to cumulatively predict the state at time t.

[0019] (Configuration of prediction device 1) The configuration of the prediction device 1 will be described with reference to Figure 1. Figure 1 is a block diagram showing the configuration of the prediction device 1 according to this embodiment. As shown in Figure 1, the prediction device 1 includes a control unit 10, a storage unit 20, a communication unit 30, and an input / output unit 40.

[0020] (Storage unit 20) The storage unit 20 stores data that the control unit 10 references. Examples of the storage unit 20 include, but are not limited to, flash memory, HDD (Hard Disk Drive), SSD (Solid State Drive), or a combination thereof.

[0021] Examples of data stored in the memory unit 20 include, but are not limited to, temperature information TI (information indicating temperature), humidity information HI (information indicating humidity), sunshine duration information SI (information indicating sunshine duration), proliferation rate information PRI (information indicating the proliferation rate of plant diseases and pests at the current time), and occurrence amount information DSI (information indicating the occurrence amount of plant diseases and pests).

[0022] (Communications Section 30) The communication unit 30 is an interface for sending and receiving data over a network. Examples of the communication unit 30 include, but are not limited to, communication chips in various communication standards such as Ethernet (registered trademark), Wi-Fi (Wireless Fidelity) (registered trademark), and wireless communication standards for mobile data communication networks.

[0023] As an example, the communication unit 30 supplies data output from other devices via the network to the control unit 10. As another example, the communication unit 30 outputs data supplied from the control unit 10 to other devices via the network.

[0024] (Input / output section 40) The input / output unit 40 is an interface for connecting an input device that receives data input from the user, or an output device that outputs data supplied from the control unit 10 to the user. Examples of input devices include, but are not limited to, a keyboard, mouse, and touchpad. Examples of output devices include, but are not limited to, a liquid crystal display and a speaker.

[0025] As an example, the input / output unit 40 supplies data indicating the input received via the input device to the control unit 10. As another example, the input / output unit 40 supplies data supplied from the control unit 10 to the output device.

[0026] (Control Unit 10) The control unit 10 controls each component of the prediction device 1. As shown in Figure 1, the control unit 10 also includes an acquisition unit 11, a calculation unit 12, a prediction unit 13, and an output unit 14.

[0027] (Acquisition part 11) The acquisition unit 11 acquires data output from the communication unit 30 or the input / output unit 40. The acquisition unit 11 stores the acquired data in the storage unit 20. As an example, the acquisition unit 11 acquires at least one of the following: temperature information TI, humidity information HI, and sunshine duration information SI.

[0028] (Calculation Unit 12) The calculation unit 12 calculates the proliferation rate of plant diseases and pests. The calculation unit 12 stores the proliferation rate information PRI, which indicates the calculated proliferation rate, in the storage unit 20. As an example, the calculation unit 12 calculates the current proliferation rate of plant diseases and pests by referring to at least one of the current temperature information TI, humidity information HI, and sunshine duration information SI around the plant.

[0029] For example, the calculation unit 12 uses the following formula (1) to calculate the proliferation rate at time t (the percentage of plant pests and diseases that have proliferated from time t-1 to time t). G t =a1(Temp t -a2) P1+a3(Humid t -a4) P2 +a5(Sun t -a6) P3 +a7···(1) G t : Growth rate at time t Temp t : Temperature around the plant at time t Humid t : Humidity around the plant at time t Sun t : Sunshine duration around the plant at time t a1, a2, a3, a4, a5, a6, a7, P1, P2, P3: Constants That is, the calculation unit 12 calculates the growth rate G using a growth rate model with at least one of the temperature Temp t , humidity Humid t , and sunshine duration Sun t around the plant at the current time point t as a variable. With this configuration, the calculation unit 12 can calculate the unmeasurable growth rate as a value. An example of the growth rate model used by the calculation unit 12 will be described later.

[0030] Also, a1, a2, a3, a4, a5, a6, a7, P1, P2, and P3 are appropriately set in advance by the administrator of the prediction device 1 by repeating the calculation of the growth rate Gt and the prediction of the occurrence amount S of pests and diseases described later. t

[0031] (Prediction unit 13) The prediction unit 13 predicts the occurrence amount of pests and diseases of the plant. The prediction unit 13 stores the occurrence amount information DSI indicating the predicted occurrence amount in the storage unit 20. As an example, the prediction unit 13 predicts the occurrence amount of pests and diseases of the plant at the current time point using Bayesian modeling based on the integrated value of the growth rate calculated by the calculation unit 12 and the occurrence amount of pests and diseases of the plant at a time point before the current time point.

[0032] ​​​For example, the prediction unit 13 predicts the amount of plant pests and diseases at time t using the state equations shown in equations (2) and (3) and the observation equation shown in equation (4) below. S1~Normal(0,1) ···(2) S t ~Normal(G t S t-1 Sigma s ) ···(3) R t ~Normal(S t Sigma r ) ···(4) S1: Initial value of pest and disease occurrence S t : Pest and disease occurrence at time t G t : Pest and disease proliferation rate at time t S t-1 : Pest and disease occurrence at time t-1 Sigma s : Error in condition R t : Observed values Sigma r : Observation error S t R indicates the amount of pest and disease outbreaks. t This shows the observed values ​​for the occurrence of pests and diseases.

[0033] In other words, the prediction unit 13 predicts the current amount of plant pests and diseases using Bayesian modeling based on a state equation that includes a term for the product of the growth rate and the amount of plant pests and diseases at a time point prior to the current time point (time point t) (time point t-1), and a term for state error, and an observation equation that includes a term for the amount of plant pests and diseases and a term for observation error.

[0034] More specifically, the amount of pests and diseases S at time t. t G is the growth rate at time t. t and the amount of pests and diseases at time t-1 S t-1 The product of these is the mean, and the standard deviation is Sigma. s It follows a probability distribution that is a normal distribution. Also, the observed value R at time t tS is the amount of pests and diseases occurring at time t. t The mean and standard deviation are Sigma. s It follows a probability distribution that is a normal distribution.

[0035] Here, the amount of plant pests and diseases at a previous time (time t-1) is calculated using the amount of plant pests and diseases at an even earlier time (time t-2). In this way, the prediction unit 13 predicts the amount of plant pests and diseases at the present time based on the cumulative value of the pest and disease outbreaks predicted so far. Therefore, the prediction unit 13 can predict the amount of plant pests and diseases with higher accuracy compared to predicting the amount of plant pests and diseases at the present time from a given time point.

[0036] Also, Sigma s and Sigma r The proliferation rate G t Calculation of the amount of disease and pest outbreaks S t By repeatedly making predictions, an appropriate value is pre-set by the administrator of prediction device 1.

[0037] (Output section 14) The output unit 14 outputs data via the communication unit 30 or the input / output unit 40. As an example, the output unit 14 outputs occurrence amount information DSI, which indicates the amount of pests and diseases predicted by the prediction unit 13. As another example, if the proliferation rate exceeds a predetermined value, the output unit 14 outputs information indicating that an increase in the amount of pests and diseases is predicted. The predetermined value is not particularly limited, but as an example, the predetermined value is 1. With this configuration, the output unit 14 can notify that the prediction device 1 has predicted an increase in the amount of pests and diseases.

[0038] (Example of a system using prediction device 1) An example of a system using the prediction device 1 will be described with reference to Figure 3. Figure 3 shows an example of a system using the prediction device 1 according to this embodiment.

[0039] As shown in Figure 3, the prediction device 1 acquires temperature information TI, humidity information HI, and sunshine duration information SI from the greenhouse where plants are being grown. Here, when the prediction device 1 predicts the daily occurrence of pests and diseases, the prediction device 1 may use the average daily temperature, humidity, and sunshine duration based on the acquired information.

[0040] Furthermore, as shown in Figure 3, the prediction device 1 outputs the predicted amount of pests and diseases to a terminal UE owned by the greenhouse user. Here, the prediction device 1 may also output information to the terminal UE indicating whether or not the amount of pests and diseases on plants in the greenhouse will increase. For example, as shown in Figure 3, the prediction device 1 may output to the terminal UE an image indicating that the amount of pests and diseases was predicted not to increase the day before yesterday, an image indicating that the amount of pests and diseases was predicted to increase slightly yesterday, and an image indicating that the amount of pests and diseases was predicted to increase today (information indicating that the amount of pests and diseases is predicted to increase).

[0041] (Process flow executed by prediction device 1) The processing flow performed by the prediction device 1 will be explained with reference to Figure 4. Figure 4 is a flowchart showing the processing flow performed by the prediction device 1 according to this embodiment.

[0042] (Step S11) In step S11, the acquisition unit 11 acquires at least one of the current ambient temperature information TI, humidity information HI, and sunshine duration information SI. The acquisition unit 11 stores the acquired data in the storage unit 20.

[0043] (Step S12) In step S12, the calculation unit 12 refers to at least one of the current ambient temperature information TI, humidity information HI, and sunshine duration information SI acquired by the acquisition unit 11, and calculates the current rate of proliferation of plant diseases and pests. The calculation unit 12 stores the calculated proliferation rate information PRI, which indicates the proliferation rate, in the storage unit 20.

[0044] (Step S13) In step S13, the prediction unit 13 predicts the current amount of plant pests and diseases based on the cumulative value of the proliferation rate calculated by the calculation unit 12 and the amount of plant pests and diseases at a time prior to the present time, using Bayesian modeling. The prediction unit 13 stores the predicted amount of pests and diseases, which is represented by the occurrence amount information DSI, in the storage unit 20.

[0045] (Step S14) In step S14, the output unit 14 outputs a DSI of occurrence amount information, which indicates the amount of pests and diseases predicted by the prediction unit 13.

[0046] (Example of a growth rate model) As described above, the calculation unit 12 calculates the proliferation rate at time t (the percentage of plant pests and diseases that have proliferated from time t-1 to time t) using the following formula (1). G t =a1(Temp t -a2) P1 +a3(Humid t -a4) P2 +a5( Sun t -a6) P3 +a7···(1) Here, a1-a7 and P1-P3 are pre-set to appropriate values ​​depending on the environment and pests.

[0047] For example, the calculation unit 12 calculates the rate of powdery mildew growth on plants in the greenhouse using, as an example, the following formula (5). G t =a1(Temp t -a2) 2 +a3Humid t +a4···(5) As another example, the calculation unit 12 calculates the rate of powdery mildew growth on plants outside the greenhouse using the following formula (6). G t =a1(Temp t -a2) 2 +a3Sun t +a4···(6) In other words, a1-a7 and P1-P3 are set according to the environmental conditions under which the pests and diseases proliferate. Examples of pests and diseases other than powdery mildew are shown in Table 1 below.

[0048] [Table 1]

[0049] The information on each pest and disease listed in Table 1 was obtained from the following sources. • Gray mold disease: Kochi Prefecture Agricultural Promotion Department, "Eggplant gray mold disease," [online], October 17, 2012, Internet. <url: https: www.nogyo.tosa.pref.kochi.lg.jp info dtl.php?id="3522"> • Bacterial spot disease: Manabu Umekawa and Yasumasa Watanabe, "Effects of temperature and humidity on the occurrence of bacterial spot disease in cucumbers in greenhouse cultivation," July 1982, The Plant Pathology Society of Japan. • Bacterial wilt: Kochi Prefecture Agricultural Promotion Department, "Eggplant Bacterial Wilt," [online], February 9, 2024, Internet <url: https: www.nogyo.tosa.pref.kochi.lg.jp info dtl.php?id="3516"> • Mosaic disease: Tsutomu Yamamoto, "The effect of temperature on the occurrence and damage of cucumber green spot mosaic disease," 1968, Shikoku Plant Protection Research, No. 3: 47-51. • Aphids: Shunichi Miyai, "Effects on Aphids and Others that Transmit Viral Diseases," July 2010, Japan Plant Protection Association, 64(7):448-452. Here, P1 to P3 represent the temperature, humidity, and daylight hours surrounding the plant at time t. A value of "1" indicates that the growth rate of the pest increases as the temperature, humidity, and daylight hours increase above a certain value. A value of "2" indicates that the growth rate is influenced more or less as the values ​​approach a certain value. A value of "0" indicates that the growth rate is not related to the values.

[0050] For example, in Table 1, if the pest is an aphid that transmits gray mold, bacterial leaf spot, or viral disease, the value of P1 will be "2". Also, if the pest is bacterial wilt or mosaic disease, the value of P1 will be "1". Furthermore, if it is gray mold, bacterial leaf spot, or bacterial wilt, the value of P2 will be "1".

[0051] Thus, the prediction device 1 can predict the occurrence of various plant diseases and pests.

[0052] (Effect of prediction device 1) Thus, the prediction device 1 comprises a calculation unit 12 that calculates the growth rate Gt using a growth rate model in which at least one of the ambient temperature Tempt, humidity Humidt, and sunshine duration Sunt at the current time t is a variable, and a prediction unit 13 that predicts the current amount of plant diseases and pests using Bayesian modeling based on a state equation that includes a term for the product of the growth rate and the amount of plant diseases and pests at a time earlier than the current time (time t) (time t-1), and a term for state error, and an observation equation that includes a term for the amount of disease and pests and a term for observation error.

[0053] In other words, the prediction device 1 predicts the current pest and disease outbreak amount (at time t) based on the cumulative value of the pest and disease outbreak amounts predicted up to a previous time point (time t-1). Therefore, the prediction device 1 can predict the pest and disease outbreak amount on plants with higher accuracy compared to predicting the pest and disease outbreak amount from a certain point in time to the present.

[0054] [Example 1] The prediction device 1 according to this modified example may be configured not to perform the process in step S13 described above if certain conditions are met. An example of a predetermined condition is when it is decided whether or not to perform the process in step S13 and it is decided not to perform the process in step S13. Another example of a predetermined condition is when the growth rate calculated in step S12 exceeds a predetermined value.

[0055] In this configuration, if it is decided not to perform the processing in step S13, the system may output information corresponding to the growth rate calculated in step S12 in step S14. For example, if the growth rate calculated in step S12 exceeds a predetermined value, the output unit 14 may output information in step S14 indicating that an increase in the occurrence of pests and diseases is predicted. For example, in step S14, the output unit 14 outputs a warning indicating that the occurrence of pests and diseases on plants will increase.

[0056] Alternatively, the prediction device 1 may be configured to output a warning indicating an increase in the occurrence of plant diseases and pests based on a graph showing the relationship between temperature, humidity, sunshine hours, and the growth rate. Examples of graphs showing the relationship between temperature, humidity, and sunshine hours (or at least one of temperature, humidity, and sunshine hours) and the growth rate are shown in Figures 10 and 11, which will be described later.

[0057] As an example of this configuration, if the growth rate value corresponding to the value indicated by at least one of the current temperature information TI, humidity information HI, and sunshine duration information SI obtained in step S11 exceeds a predetermined value on the graph, the output unit 14 outputs a warning indicating that the occurrence of plant diseases and pests will increase. The determination of whether or not the growth rate value corresponding to the value indicated by at least one of the current temperature information TI, humidity information HI, and sunshine duration information SI obtained in step S11 exceeds a predetermined value on the graph may be performed by the output unit 14, or the administrator of the prediction device 1 may visually check the graph.

[0058] With this configuration, the prediction device 1 can notify that the occurrence of plant diseases and pests is likely to increase, without having to predict the occurrence of plant diseases and pests using Bayesian modeling each time.

[0059] [Differentiation 2] The prediction device 1 according to this modified example may be configured to output a graph (for example, graphs 10 and 11 described later) showing the relationship between temperature, humidity, and sunshine duration (or at least one of temperature, humidity, and sunshine duration) and the growth rate to the terminal UE shown in Figure 3.

[0060] In this case, the processor in the terminal UE acquires the graph output from the prediction device 1. The processor also acquires at least one of the current temperature information TI, humidity information HI, and sunshine duration information SI around the plant. If the growth rate value corresponding to the value indicated by at least one of the acquired current temperature information TI, humidity information HI, and sunshine duration information SI exceeds a predetermined value on the graph, the output unit 14 outputs a warning indicating that the occurrence of plant diseases and pests will increase.

[0061] With this configuration, the terminal UE can notify that an increase in the occurrence of pests and diseases is predicted, even without obtaining information indicating the proliferation rate from the prediction device 1.

[0062] Alternatively, the processor may be configured to display the graph output from the prediction device 1. This configuration allows the terminal UE to understand what the estimated growth rate is based on the current temperature, humidity, and sunshine duration, even if it is unable to obtain information indicating the growth rate from the prediction device 1.

[0063] [Embodiment 2] Other embodiments of the present invention are described below. For the sake of clarity, components having the same function as those described in the above embodiments will be denoted by the same reference numerals, and their descriptions will not be repeated.

[0064] (Overview of Prediction Device 1A) The prediction device 1A according to this embodiment is a device for calculating the proliferation rate of plant diseases and pests. The method for calculating the occurrence amount and proliferation rate of diseases and pests is the same as in the embodiment described above.

[0065] Furthermore, the prediction device 1A outputs information based on the calculated proliferation rate. Examples of information output by the prediction device 1A include, but are not limited to, information indicating that an increase in the occurrence of pests and diseases is predicted, and information indicating the conditions under which an increase in the occurrence of pests and diseases is predicted.

[0066] (Configuration of prediction device 1A) The configuration of the prediction device 1A will be described with reference to Figure 5. Figure 5 is a block diagram showing the configuration of the prediction device 1A according to this embodiment. As shown in Figure 5, the prediction device 1A includes a control unit 10A, a storage unit 20A, a communication unit 30, and an input / output unit 40. The communication unit 30 and the input / output unit 40 are as described above.

[0067] (Storage unit 20A) The storage unit 20A stores data that the control unit 10A references, similar to the storage unit 20 described above. Examples of the storage unit 20A include, but are not limited to, flash memory, HDD, SSD, or a combination thereof.

[0068] Examples of data stored in the memory unit 20A include, but are not limited to, temperature information TI, humidity information HI, sunshine duration information SI, and growth rate information PRI, which indicates the current growth rate of plant diseases and pests, as shown in Figure 5.

[0069] (Control Unit 10A) The control unit 10A controls each component of the prediction device 1A, similar to the control unit 10 described above. In addition, as shown in Figure 5, the control unit 10A includes an acquisition unit 11A, a calculation unit 12A, and an output unit 14A.

[0070] (Acquisition part 11A) The acquisition unit 11A acquires data output from the communication unit 30 or input / output unit 40, similar to the acquisition unit 11 described above. The acquisition unit 11A stores the acquired data in the storage unit 20A. As an example, the acquisition unit 11A acquires at least one of the following: temperature information TI, humidity information HI, and sunshine duration information SI.

[0071] (Calculation part 12A) The calculation unit 12A calculates the proliferation rate of plant diseases and pests, similar to the calculation unit 12 described above. Specifically, the calculation unit 12A calculates the proliferation rate Gt using a proliferation rate model that uses at least one of the following variables: temperature Tempt, humidity Humidt, and sunshine duration Sunt, as well as the variables, as the calculation unit 12A calculates the proliferation rate Gt. The calculation unit 12A stores the proliferation rate information PRI, which indicates the calculated proliferation rate, in the storage unit 20A. An example of the proliferation rate model is also as described above.

[0072] (Output section 14A) The output unit 14A outputs data via the communication unit 30 or input / output unit 40, similar to the output unit 14 described above. As an example, the output unit 14 outputs information based on the proliferation rate calculated by the calculation unit 12A.

[0073] As an example, output unit 14A outputs information indicating that the amount of pests and diseases will increase if the proliferation rate exceeds a predetermined value. For example, if the proliferation rate two days ago was lower than a first predetermined value, output unit 14A outputs an image, as shown in Figure 3, indicating that it was predicted that the amount of pests and diseases would not increase two days ago. Also, if the proliferation rate yesterday was greater than or equal to the first predetermined value and lower than a second predetermined value which is greater than the first predetermined value, output unit 14A outputs an image indicating that it was predicted that the amount of pests and diseases would increase slightly yesterday. Furthermore, if the proliferation rate today is greater than or equal to the second predetermined value, output unit 14A outputs an image (information indicating that it was predicted that the amount of pests and diseases would increase) indicating that it was predicted that the amount of pests and diseases would increase today.

[0074] (Process flow executed by prediction device 1A) The processing flow performed by the prediction device 1A will be explained with reference to Figure 6. Figure 6 is a flowchart showing the processing flow performed by the prediction device 1A according to this embodiment.

[0075] (Step S21) In step S21, the acquisition unit 11A acquires at least one of the current temperature information TI, humidity information HI, and sunshine duration information SI around the plant. The acquisition unit 11A stores at least one of the acquired temperature information TI, humidity information HI, and sunshine duration information SI in the storage unit 20A.

[0076] (Step S22) In step S22, the calculation unit 12A refers to at least one of the current ambient temperature information TI, humidity information HI, and sunshine duration information SI acquired by the acquisition unit 11A, and calculates the current rate of plant pest and disease proliferation. The calculation unit 12 stores the proliferation rate information PRI, which indicates the calculated proliferation rate, in the storage unit 20A.

[0077] (Step S23) In step S23, the output unit 14A outputs information based on the growth rate calculated by the calculation unit 12A.

[0078] (Effect of prediction device 1A) Thus, the prediction device 1A uses a growth rate model in which at least one of the following variables—temperature Tempt, humidity Humidt, and sunshine duration Sunt—as variables, to predict the growth rate G t A calculation unit 12A calculates the growth rate G t It includes an output unit 14A that outputs information based on the above.

[0079] Therefore, the prediction device 1A can, for example, notify a terminal owned by a farmer of the possibility of future plant diseases and pests occurring in the plants that the farmer is cultivating.

[0080] [Difference 3] The prediction device 1A according to this modified example may also be configured to output a warning indicating an increase in the occurrence of plant diseases and pests, based on a graph (Figures 10 and 11 described later) showing the relationship between temperature, humidity, sunshine hours, and proliferation rate, similar to the prediction device 1 in the modified example 1 described above.

[0081] In this configuration as well, if the growth rate value corresponding to the value indicated by at least one of the current temperature information TI, humidity information HI, and sunshine duration information SI obtained in step S21 exceeds a predetermined value on the graph, the output unit 14 outputs a warning indicating that the occurrence of plant diseases and pests will increase. The determination of whether or not the growth rate value corresponding to the value indicated by at least one of the current temperature information TI, humidity information HI, and sunshine duration information SI obtained in step S21 exceeds a predetermined value on the graph may be performed by the output unit 14A, or the administrator of the prediction device 1 may visually check the graph.

[0082] [Example 1] One embodiment of the present invention is described below.

[0083] The incidence rate of powdery mildew in eggplant leaves (the proportion of diseased leaves relative to the number of leaves surveyed) was predicted under the following conditions. G t =a1(Temp t -a2) 2 +a3Humid t +a4 Temp t : Temperature inside the greenhouse at time t Humid t Humidity inside the greenhouse at time t The prediction results are shown in Figure 7. Figure 7 is an example of a graph showing the diseased leaf rate and proliferation rate in this embodiment.

[0084] The upper graph in Figure 7 shows diseased leaf rate on the vertical axis and days on the horizontal axis. In the upper graph of Figure 7, the line represents the predicted value, the gray area around the line represents the 95% confidence interval, and the dots represent the observed value. As shown in the upper graph of Figure 7, the observed value falls almost within the 95% confidence interval of the predicted value.

[0085] Furthermore, the graph at the bottom of Figure 7 shows the growth rate on the vertical axis and the number of days on the horizontal axis. In the graph at the bottom of Figure 7, if we define D1 as the day when the growth rate exceeded 1, we can see that the percentage of diseased leaves increased from D1 onwards.

[0086] Furthermore, the incidence rate of powdery mildew on eggplant leaves was predicted under similar conditions in other greenhouses. The prediction results are shown in Figure 8. Figure 8 is another example of a graph showing the incidence rate and proliferation rate in this embodiment.

[0087] The left side of Figure 8 shows a graph from a different greenhouse than the one shown in Figure 7. The right side of Figure 8 also shows a graph from a different greenhouse than those shown in Figures 7 and 8. In the graphs shown in Figure 8, the observed values ​​are almost within the 95% confidence interval of the predicted values. Furthermore, similar to Figure 7, Figure 8 shows that the diseased leaf rate increases after D1, when the proliferation rate exceeds 1.

[0088] [Example 2] Other embodiments of the present invention are described below.

[0089] The incidence of powdery mildew on eggplant leaves was predicted under the following conditions. In this example, the incidence of powdery mildew was predicted based on temperature and humidity at two locations outside the greenhouse. G t =a1(Temp t -a2) 2 +a3Humid t +a4 Temp t : Temperature outside the greenhouse at time t Humid t Humidity outside the greenhouse at time t The prediction results are shown in Figure 9. Figure 9 is an example of a graph showing the diseased leaf rate and proliferation rate in this embodiment.

[0090] As shown in the graph in Figure 9, the observed values ​​fall within approximately the 95% confidence interval of the predicted values ​​at all locations. Furthermore, the graph in Figure 9 also shows that the diseased leaf rate increases after D1, when the proliferation rate exceeds 1.

[0091] Furthermore, Figure 10 shows the relationship between the temperature and humidity outside the greenhouse and the growth rate. Figure 10 is a graph showing the relationship between temperature, humidity and growth rate in this embodiment.

[0092] In Figure 10, areas with high growth rates are shown in darker colors. As shown in Figure 10, the closer the temperature outside the greenhouse is to 18°C, the higher the growth rate. Also, the lower the humidity outside the greenhouse, the higher the growth rate. In other words, the growth rate model used to calculate the growth rate Gt was found to be appropriate.

[0093] Furthermore, Figure 11 shows the relationship between temperature outside the greenhouse, sunshine duration, and propagation rate. Figure 11 is a graph showing the relationship between temperature, sunshine duration, and propagation rate in this embodiment.

[0094] In Figure 11, areas with high growth rates are shown in darker colors. As shown in Figure 11, the closer the temperature outside the greenhouse is to 18°C, the higher the growth rate. Also, the longer the hours of sunlight outside the greenhouse, the higher the growth rate. In other words, it was found that the growth rate model used to calculate the growth rate Gt can also be calculated using temperature and sunlight hours as variables.

[0095] Furthermore, the output unit 14 or output unit 14A described above may be configured to output the graph shown in Figure 10 or Figure 11.

[0096] [Examples of implementation using software] The functions of the prediction devices 1 and 1A (hereinafter referred to as "devices") are programs that cause a computer to function as the device, and these programs can be realized by programs that cause a computer to function as each control block of the device (especially each part included in the control units 10 and 10A).

[0097] In this case, the device includes a computer having at least one control device (e.g., a processor) and at least one storage device (e.g., memory) as hardware for executing the program. By executing the program using this control device and storage device, the functions described in each of the embodiments are realized.

[0098] The above program may be recorded on one or more computer-readable recording media, not temporary ones. These recording media may or may not be provided by the above device. In the latter case, the program may be supplied to the above device via any wired or wireless transmission medium.

[0099] Furthermore, some or all of the functions of each of the above control blocks can also be realized by logic circuits. For example, an integrated circuit in which logic circuits functioning as each of the above control blocks are formed is also included in the scope of the present invention. In addition, it is also possible to realize the functions of each of the above control blocks by, for example, a quantum computer.

[0100] Furthermore, each process described in the above embodiments may be performed by AI (Artificial Intelligence). In this case, the AI ​​may operate on the control device described above, or it may operate on other devices (for example, an edge computer or a cloud server).

[0101] [summary] The prediction device according to embodiment 1 of this embodiment includes a calculation unit that calculates the current rate of proliferation of pests and diseases on the plant by referring to at least one of the information indicating the temperature around the plant at the present time, information indicating humidity, and information indicating the amount of sunlight; and a prediction unit that predicts the current amount of pests and diseases on the plant using Bayesian modeling based on the cumulative value of the proliferation rate and the amount of pests and diseases on the plant at a time prior to the present time.

[0102] The above configuration allows for highly accurate prediction of plant disease and pest outbreaks.

[0103] The prediction device according to embodiment 2 of this embodiment further comprises an output unit that outputs information indicating that an increase in the amount of the diseased pest is predicted when the proliferation rate exceeds a predetermined value, as described in embodiment 1 above.

[0104] The above configuration allows for notification that an increase in the occurrence of pests and diseases is predicted.

[0105] In the prediction device according to embodiment 3 of this embodiment, the calculation unit in embodiment 1 or 2 calculates the growth rate using a growth rate model in which at least one of the temperature, humidity, and sunshine duration around the plant at the present time is used as a variable.

[0106] With the above configuration, it is possible to calculate the growth rate, which cannot be measured directly, as a value.

[0107] In the prediction device according to embodiment 4 of this embodiment, the prediction unit in any of embodiments 1 to 3 predicts the amount of occurrence using Bayesian modeling based on a state equation that includes a term for the product of the growth rate and the amount of pests and diseases occurring on the plant at a time prior to the present time, and a term for state error, and an observation equation that includes a term for the amount of occurrence and a term for observation error.

[0108] With the above configuration, it is possible to predict the occurrence of plant diseases and pests with higher accuracy compared to predicting the occurrence of diseases and pests from a certain point in time to the present.

[0109] In the prediction device according to embodiment 5 of this embodiment, the plant disease in any of embodiments 1 to 4 is a fungal disease.

[0110] The above configuration allows for highly accurate prediction of the occurrence of fungal diseases.

[0111] In the prediction device according to embodiment 6 of this embodiment, the fungal disease in embodiment 5 is a disease caused by filamentous fungi.

[0112] The above configuration allows for highly accurate prediction of the occurrence of diseases caused by filamentous fungi.

[0113] In the prediction device according to embodiment 7 of this embodiment, the fungal disease in embodiment 6 is powdery mildew.

[0114] With the above configuration, the occurrence of powdery mildew can be predicted with high accuracy.

[0115] The prediction method according to aspect 8 of this embodiment includes a calculation process that calculates the current rate of proliferation of pests and diseases on the plant by referring to at least one of the information indicating the temperature around the plant at the present time, information indicating humidity, and information indicating the amount of sunlight; and a prediction process that uses Bayesian modeling to predict the current amount of pests and diseases on the plant based on the cumulative value of the proliferation rate and the amount of pests and diseases on the plant at a time prior to the present time.

[0116] The above configuration allows for highly accurate prediction of plant disease and pest outbreaks.

[0117] The program according to aspect 9 of this embodiment is a program for causing a computer to function as a prediction device, and the computer functions as a calculation unit that calculates the current rate of proliferation of pests and diseases on the plant by referring to at least one of the information indicating the temperature around the plant at the present time, information indicating humidity, and information indicating the amount of sunlight; and a prediction unit that predicts the current amount of pests and diseases on the plant using Bayesian modeling based on the cumulative value of the proliferation rate and the amount of pests and diseases on the plant at a time prior to the present time.

[0118] The present invention is not limited to the embodiments described above, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention. [Explanation of Symbols]

[0119] 1. 1A Prediction device 11, 11A Acquisition Department 12, 12A calculation section 13 Prediction Section 14, 14A output section TI temperature information HI humidity information SI Sunshine Hours Information PRI Growth Rate Information DSI generation information< / url:> < / url:>

Claims

1. A calculation unit that calculates the current rate of proliferation of pests and diseases in the plant by referring to at least one of the following: information indicating the temperature around the plant at the present time, information indicating humidity, and information indicating the amount of sunlight; A prediction unit that uses Bayesian modeling to predict the current amount of pests and diseases on the plant based on the cumulative value of the growth rate and the amount of pests and diseases on the plant at a time prior to the present time, A prediction device equipped with the following features.

2. The system further includes an output unit that outputs information indicating that an increase in the number of pests and diseases is predicted when the proliferation rate exceeds a predetermined value. The prediction device according to claim 1.

3. The calculation unit calculates the growth rate using a growth rate model in which at least one of the current ambient temperature, humidity, and sunshine duration of the plant is a variable. The prediction device according to claim 1 or 2.

4. The prediction unit, The equation of state includes a term representing the product of the growth rate and the amount of pests and diseases occurring in the plant at a time point prior to the present, and a term representing the error in the state, An observation equation including the term for the amount generated and the term for the error of observation, Using Bayesian modeling based on this, predict the amount of occurrence. The prediction device according to claim 1 or 2.

5. The aforementioned plant disease is a fungal disease. The prediction device according to claim 1 or 2.

6. The aforementioned fungal diseases are diseases caused by filamentous fungi. The prediction device according to claim 5.

7. The aforementioned fungal disease is powdery mildew. The prediction device according to claim 6.

8. A calculation process that calculates the current rate of proliferation of pests and diseases in the plant by referring to at least one of the following: information indicating the temperature around the plant at the present time, information indicating humidity, and information indicating the amount of sunlight. A prediction process that uses Bayesian modeling to predict the current amount of pests and diseases on the plant, based on the cumulative value of the growth rate and the amount of pests and diseases on the plant at a time prior to the present time, A prediction method that includes this.

9. A program that makes a computer function as a prediction device, The aforementioned computer, A calculation unit that calculates the current rate of proliferation of pests and diseases in the plant by referring to at least one of the following: information indicating the temperature around the plant at the present time, information indicating humidity, and information indicating the amount of sunlight; A prediction unit that uses Bayesian modeling to predict the current amount of pests and diseases on the plant based on the cumulative value of the growth rate and the amount of pests and diseases on the plant at a time prior to the present time, A program that makes it function as such.

Images