Information processing device, information processing method, and program

Abstract

The present invention achieves efficient utilization of water resources and reduction of environmental load by supporting appropriate water level management of paddy fields. A simulation unit 51 of a server 1 calculates a time-series change in water level of a predetermined paddy field using a simulation model in which a physical phenomenon related to water balance of the paddy field is modeled. An observation data acquisition unit 52 acquires remote sensing observation data in which a region including the predetermined paddy field is observed by remote sensing, and direct observation data in which the predetermined paddy field is directly observed by one or more sensors. A water level calculation unit 53 corrects calculation results of the simulation model on the basis of the remote sensing observation data and the direct observation data of the predetermined paddy field, and calculates an estimated value and a predicted value of the water level of the predetermined paddy field on the basis of the corrected results. A management information generation unit 54 generates management information regarding the predetermined paddy field on the basis of at least a part of the estimated value and the predicted value of the water level of the predetermined paddy field.

Description

Information processing device, information processing method, and program

[0001] The present invention relates to an information processing device, an information processing method, and a program.

[0002] Conventionally, water level management in rice paddies has been carried out by manually measuring water levels or by point observation using IoT sensors. There is also agricultural observation technology using remote sensing technology using satellites (see, for example, Patent Document 1).

[0003] JP 2018-46787 A

[0004] However, in recent years, there has been a demand for supporting appropriate water level management in rice paddies, achieving efficient water resource utilization, and reducing environmental impact, but conventional technologies, including the technology of Patent Document 1, are unable to adequately meet such demands.

[0005] The present invention was made in consideration of these circumstances, and aims to support appropriate water level management in rice paddies, thereby achieving efficient use of water resources and reducing environmental impact.

[0006] In order to achieve the above-mentioned object, one embodiment of the information processing device of the present invention is an information processing device for management based on the water level of paddy fields, comprising: a simulation means for calculating time-series changes in the water level of a specified paddy field using a simulation model in which physical phenomena related to the water balance of the paddy field are modeled; an observation data acquisition means for acquiring remote sensing observation data obtained as a result of remotely observing an area including the specified paddy field and direct observation data obtained as a result of directly observing the specified paddy field using one or more sensors; a water level calculation means for correcting the calculation results of the simulation model based on the remote sensing observation data and the direct observation data of the specified paddy field, and calculating estimated and predicted values ​​of the water level of the specified paddy field based on the corrected results; and a management information generation means for generating management information for the specified paddy field based on at least a portion of the estimated and predicted values ​​of the water level of the specified paddy field.

[0007] An information processing method and a program according to one aspect of the present invention are a method and a program corresponding to an information processing device according to one aspect of the present invention.

[0008] According to the present invention, it is possible to support appropriate water level management in rice paddies, thereby realizing efficient use of water resources and reducing environmental load.

[0009] 1 is a diagram showing an overview of the present service that can be realized by an information processing system to which a server according to an embodiment of the information processing device of the present invention is applied. It is a diagram showing an example of the configuration of an information processing system to which a server according to an embodiment of the information processing device of the present invention is applied. It is a block diagram showing an example of the hardware configuration of the server in the information processing system of FIG. 2. It is a functional block diagram showing an example of the functional configuration of the server of FIG. 3 that constitutes the information processing system of FIG. 2. It is a diagram showing a water level calculation method by the simulation unit and the water level calculation unit of FIG. 4. It is a diagram showing a water level calculation method and prediction accuracy by the water level calculation unit of FIG. 4. It is a diagram showing a calculation model of water levels that should be artificially controlled in the simulation unit of FIG. 4. It is a diagram showing a mechanism for improving the water level calculation model in the water level calculation unit of FIG. 4. It is a diagram showing a water level display screen on the user terminal of FIG. 2. It is a diagram showing a field details screen on the user terminal of FIG. 2. It is a diagram showing a management recommendation screen on the user terminal of FIG. 2. It is a diagram showing a regional water demand forecast by the water demand forecast unit of FIG. 4. It is a diagram showing calculation of the optimal irrigation water amount in the field by the irrigation optimization unit of FIG. 4. It is a diagram showing support for field leveling work by the management information generation unit of FIG. 4. Fig. 5 is a diagram showing a method for identifying an irrigated paddy field by the irrigation paddy field identifying unit of Fig. 4. Fig. 6 is a diagram showing a method for calculating a mid-drought period by the management information generating unit of Fig. 4. Fig. 7 is a diagram showing an internal algorithm configuration in the server functional configuration of Fig. 4. Fig. 8 is a diagram showing the processing flow of the entire information processing system of Fig. 2. Fig. 9 is a diagram showing a database structure inside the storage unit of Fig. 4.

[0010] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0011] First, an overview of a service (hereinafter referred to as "this service") that can be realized by an information processing system (see FIG. 2 described later) to which a server according to an embodiment of the information processing device of the present invention is applied will be described with reference to Fig. 1. Fig. 1 is a diagram showing an overview of this service that can be realized by an information processing system to which a server according to an embodiment of the information processing device of the present invention is applied.

[0012] This service supports appropriate water level management in rice paddies, achieving efficient water resource utilization and reducing environmental impact.

[0013] Specifically, for example, Figure 1 shows remote sensing observations being carried out in a designated rice paddy using SAR satellites, optical satellites, etc., and direct observations being carried out from IoT sensors such as IoT automatic water level gauges and soil moisture sensors installed in the designated rice paddy.

[0014] As shown in Figure 1, the server 1 uses these satellite data, which are capable of wide-area observation, to grasp surface water level and growth information for the entire field, which is not possible with conventional point observations, and at the same time calibrates and verifies the model using highly accurate ground measurement data.

[0015] The server 1 calculates the time-series changes in the water level of a given paddy field using a simulation model that inputs meteorological data, soil property data, and crop data, which are all major factors that affect the water balance of the paddy field.

[0016] Then, using a data assimilation technique, remote sensing data and direct observation data are combined to correct the results of the simulation model, and highly accurate water level estimates and forecasts are calculated.

[0017] Based on these results, as shown in Figure 1, a variety of management information is generated, such as irrigation timing according to the rice growth stage, water discharge timing to suppress methane emissions, calculation of inter-drought periods, instructions for soil movement to level the field, optimization of the amount of irrigation water within the field based on water level information for each pixel observed by satellite, identification of irrigated paddy fields where water is supplied by irrigation independent of precipitation, and calculation of the demand and supply period for irrigation water for the entire area including multiple specified paddy fields, and is provided to the paddy field manager via user terminal 2.

[0018] In this way, by using data assimilation techniques to combine a process-based model that performs physical simulations with actual observation data, it is possible to generate highly accurate water level information and provide comprehensive support for rice paddy management that was difficult to achieve with conventional technology.

[0019] Here, we explain the differences between this service and conventional technologies. Conventional technologies can be divided into three main categories. First, typical agricultural remote sensing technologies analyze crop vigor (NDVI, etc.) from optical images (images similar to those seen by the human eye) taken by satellites or drones and identify areas of poor growth. In contrast, this service not only uses optical images but also data from SAR (synthetic aperture radar) satellites, which can penetrate clouds and directly detect water surfaces. This allows for accurate determination of the presence or absence of water, essential for rice growth, regardless of weather. Furthermore, while conventional technologies are limited to "visualizing the current situation," this service differs crucially in that it uses observation data as "input to correct predictive models," not simply looking at the current situation but more accurately predicting the future.

[0020] Second, point-based observation technology using in-field IoT sensors typically involves installing IoT water level gauges or other sensors in designated paddy fields to measure water levels at those locations in real time and sending the results to smartphones or other devices. In contrast, this service solves the problem of only being able to obtain "point" information from the IoT sensors. While water levels are uneven within a single field due to differences in elevation, satellites can capture the water level distribution across the entire field as a "surface." Furthermore, while installing IoT sensors in multiple fields is costly, this service uses satellites that can observe a wide area at once, allowing for widespread deployment at low cost. Furthermore, rather than eliminating IoT sensors, this service incorporates them as valuable "ground data" for verifying the accuracy of models. By combining the two, a more accurate system can be built.

[0021] Third, cultivation support technologies that use simulation alone mainly simulate crop growth and water needs based on weather and soil data. In contrast, this service solves the problem of model errors accumulating over time, causing predictions to deviate significantly from reality, by using a "data assimilation" technique to correct the model's predicted trajectory using regularly obtained satellite observation data. This "closed-loop control" mechanism allows the reliability of the simulation to be continuously maintained, giving it an absolute advantage over conventional "open-loop" simulation technology.

[0022] Thus, the uniqueness of this service lies in the fact that it is not an extension of any one of the three technical fields mentioned above, but rather is the first to organically combine them. In other words, it is a system based on a new concept in which a "physical model (simulation)" is continuously corrected and optimized using the technological keystone known as "data assimilation" using real-world data of different natures - "area observations by remote sensing" and "point observations by IoT sensors."

[0023] In this service, as shown in FIG. 1, wide-area and continuous surface observation may be realized by remote sensing observation including satellite data.

[0024] In other words, server 1 can utilize SAR satellites, which can observe the presence or absence of water in rice paddies and the soil moisture content without being affected by clouds, and optical satellites, which can grasp the growth status of crops such as rice, classify the crops being grown, and observe the cultivation period.

[0025] This will enable more comprehensive rice paddy management.

[0026] This service may include data acquired by IoT sensors installed in designated rice paddies, as shown in Figure 1.

[0027] In other words, the server 1 can calibrate (adjust) a process-based model that enables water level prediction during periods when satellite data is unavailable, using data measured directly by farmers and ground devices such as IoT automatic water level gauges, fixed-point observation cameras, and soil moisture sensors, and can also verify the accuracy of the remote sensing data and the model itself.

[0028] This makes it possible to achieve extremely high estimation accuracy that would be difficult to achieve using remote sensing data alone.

[0029] In this service, as shown in FIG. 1, management information including irrigation timing according to the growth stage of rice in a specified paddy field may be generated.

[0030] That is, the server 1 can generate recommended irrigation timings that are beneficial to producers from the results of the predictive analysis.

[0031] This will go beyond simply providing water level information and provide specific management guidelines that are directly useful to farmers, making it possible to realize practical use of highly accurate water level predictions in agricultural fields.

[0032] In this service, as shown in FIG. 1, management information including the timing of water discharge for suppressing methane emissions in a specified rice paddy may be generated.

[0033] In other words, the server 1 can propose water management methods (such as when to drain water from rice paddies and when to fill them) for reducing methane emissions from rice paddies objectively without human intervention for a large number of fields over a wide area.

[0034] This will make it extremely valuable in the MRV (measurement, reporting, and verification) of the carbon credit system, and will enable it to contribute to creating environmental value and decarbonizing agriculture.

[0035] In this service, as shown in FIG. 1, management information including the mid-drainage period for a specific rice paddy may be generated.

[0036] In other words, the server 1 can comprehensively and objectively calculate the number of dry days over a large area, which is important for reducing methane emissions from rice cultivation.

[0037] This will automate and objectively determine the number of dry days, which previously required manual work, and enable comprehensive quantitative evaluation of the methane reduction effect over large areas, making it possible to achieve accurate MRV under the carbon credit system.

[0038] In this service, as shown in FIG. 1, management information may be generated that includes instructions for moving soil for field leveling based on the difference in soil surface elevation in a given rice paddy.

[0039] That is, the server 1 can conversely estimate the difference in soil surface elevation from the spatial distribution data of water levels and support field leveling work.

[0040] This will enable efficient support for field leveling work without relying on conventional surveying by estimating soil elevation differences through reverse calculations from water level information, contributing to improved field productivity.

[0041] In this service, as shown in Figure 1, the optimal irrigation water volume for the entire specified rice field may be calculated based on water level information for each satellite observation pixel contained in the remote sensing observation data, and management information based on the optimal irrigation water volume for the entire specified rice field may be generated.

[0042] That is, the server 1 can grasp the water level distribution in the field in units of satellite pixels and calculate the minimum amount of irrigation water required for the entire field.

[0043] This will enable precise water management that takes into account the unevenness of water level distribution within the field, making it possible to achieve efficient use of water resources and optimization within the field, something that cannot be achieved with conventional uniform irrigation.

[0044] In this service, as shown in Figure 1, for a given rice paddy, it is possible to determine whether it is an irrigated rice paddy, which receives water through irrigation independent of precipitation, based on remote sensing observation data, meteorological data, and vegetation index data, and to generate management information based on information on whether the given rice paddy is an irrigated rice paddy.

[0045] That is, the server 1 can identify paddy fields that are only irrigated and do not depend on precipitation, out of the three patterns of origin of water used in paddy fields: precipitation, irrigation, and precipitation and irrigation.

[0046] This will enable classification of rice paddies by water source, making it possible to objectively assess the degree of dependence on irrigation and optimize water resource management, and to accurately calculate methane emissions from irrigation under the carbon credit system.

[0047] In this service, as shown in Figure 1, for an area including multiple specified rice paddies, the demand for irrigation water and the supply period for the entire area are calculated based on the estimated or predicted water levels of each area, and management information based on the demand for irrigation water and the supply period for the entire area including multiple specified rice paddies may be generated.

[0048] In other words, the server 1 can calculate the amount of water and timing for irrigating the local rice fields from the water level calculation results, and can save water usage at the water source by supplying the necessary water to the waterways connecting the water source to the rice fields.

[0049] This will enable the integration of water level predictions for individual fields at a regional level, thereby optimizing water resource management over a wide area, which was previously difficult, and making it possible to use water sources more efficiently and refine supply plans.

[0050] Next, the configuration of an information processing system that realizes the provision of the above-described service, i.e., an information processing system to which a server according to an embodiment of the information processing device of the present invention is applied, will be described with reference to Fig. 2. Fig. 2 is a diagram showing an example of the configuration of an information processing system to which a server according to an embodiment of the information processing device of the present invention is applied.

[0051] 2 is configured to include a server 1, a user terminal 2, a weather data server 3, a satellite data server 4, and an IoT sensor terminal 5. The server 1, the user terminal 2, the weather data server 3, the satellite data server 4, and the IoT sensor terminal 5 are connected to each other via a network N such as the Internet.

[0052] The server 1 is an information processing device managed by the service provider of this service (Fig. 1). The server 1 executes various processes to realize this service while appropriately communicating with the user terminal 2, the weather data server 3, the satellite data server 4, and the IoT sensor terminal 5.

[0053] The user terminal 2 is an information processing device operated by the paddy field manager, and is composed of a smartphone, tablet, personal computer, etc.

[0054] The weather data server 3 is an information processing device that provides weather data such as precipitation, solar radiation, temperature, and humidity, and is configured by a smartphone, tablet, personal computer, or the like.

[0055] The satellite data server 4 is an information processing device that provides remote sensing data from SAR satellites and optical satellites, and is configured with a smartphone, tablet, personal computer, or the like.

[0056] The IoT sensor terminal 5 is an information processing device that provides ground observation data from IoT water level meters, soil sensors, etc. installed in a specified rice field, and is composed of a smartphone, tablet, personal computer, etc.

[0057] FIG. 3 is a block diagram showing an example of a hardware configuration of a server in the information processing system shown in FIG.

[0058] The server 1 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a bus 14, an input / output interface 15, an input unit 16, an output unit 17, a memory unit 18, a communication unit 19, and a drive 20.

[0059] The CPU 11 executes various processes according to programs recorded in the ROM 12 or programs loaded from the storage unit 18 into the RAM 13. The RAM 13 also stores data and the like necessary for the CPU 11 to execute various processes.

[0060] The CPU 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output interface 15 is also connected to this bus 14. An input unit 16, an output unit 17, a storage unit 18, a communication unit 19, and a drive 20 are connected to the input / output interface 15.

[0061] The input unit 16 is configured with, for example, a keyboard and is used to input various types of information. The output unit 17 is configured with, for example, a display such as an LCD, a speaker, and the like and outputs various types of information as images and sounds. The storage unit 18 is configured with, for example, a DRAM (Dynamic Random Access Memory) and is used to store various types of data. The communication unit 19 communicates with other devices (for example, the user terminal 2, weather data server 3, satellite data server 4, and IoT sensor terminal 5 in FIG. 2 ) via a network N including the Internet.

[0062] Removable media 21, such as a magnetic disk, optical disk, magneto-optical disk, or semiconductor memory, is appropriately attached to the drive 20. Programs read from the removable media 21 by the drive 20 are installed in the storage unit 18 as needed. The removable media 21 can also store various data stored in the storage unit 18 in the same way as the storage unit 18.

[0063] Although not shown, the user terminal 2, weather data server 3, satellite data server 4, and IoT sensor terminal 5 in Fig. 2 can also have basically the same hardware configuration as that shown in Fig. 3. Therefore, a description of the hardware configuration of the user terminal 2, weather data server 3, satellite data server 4, and IoT sensor terminal 5 will be omitted.

[0064] The various hardware and software components constituting the information processing system of FIG. 2, including the server 1 of FIG. 3, work together to execute various processes for providing the present service of FIG.

[0065] FIG. 4 is a functional block diagram showing an example of the functional configuration of the server of FIG. 3 in the information processing system of FIG.

[0066] 4, the CPU 11 of the server 1 functions as a simulation unit 51, an observation data acquisition unit 52, a water level calculation unit 53, a management information generation unit 54, an irrigation optimization unit 55, an irrigated paddy field identification unit 56, and a water demand prediction unit 57. In addition, one area of ​​the storage unit 18 of the server 1 is provided with a paddy field information DB 71, a weather data DB 72, a satellite data DB 73, a sensor data DB 74, a soil characteristics DB 75, a crop data DB 76, a water level history DB 77, a management information DB 78, a prediction model DB 79, and a user information DB 80.

[0067] The simulation unit 51 calculates the time-series change in water level of a specific paddy field (for example, the specific paddy field in FIG. 1) using a simulation model in which physical phenomena related to the water balance of paddy fields are modeled.

[0068] The simulation unit 51 extracts meteorological data such as precipitation, solar radiation, temperature, and humidity from the meteorological data DB 72, soil property data such as permeability to the ground from the soil property DB 75, and crop data such as water absorption according to the rice growth stage from the crop data DB 76, and executes a physical simulation using these as inputs. The calculated time-series change data is stored in the prediction model DB 79.

[0069] This allows for the physical consideration of all major factors that affect the water balance in rice paddies, making it possible to make highly accurate predictions of water level fluctuations based on scientific evidence, which is not possible using empirical methods.

[0070] The observation data acquisition unit 52 acquires remote sensing observation data obtained as a result of remote sensing observation of an area including the specified rice paddy, and direct observation data obtained as a result of direct observation of the specified rice paddy using one or more sensors.

[0071] The observation data acquisition unit 52 acquires remote sensing observation data from SAR satellites and optical satellites from the satellite data server 4, direct observation data from IoT automatic water level gauges, soil moisture sensors, etc. from the IoT sensor terminal 5, and direct measurement data by farmers from the user terminal 2, and stores these in the satellite data DB 73 and sensor data DB 74.

[0072] This will enable satellite data, which is capable of wide-area observation, to grasp surface-level water levels and growth information for the entire field, which was not possible with conventional point observations, and will enable more comprehensive rice paddy management.

[0073] The water level calculation unit 53 corrects the calculation results of the simulation model based on the remote sensing observation data and the direct observation data of the specified rice field, and calculates estimated and predicted values ​​of the water level of the specified rice field based on the corrected results.

[0074] The water level calculation unit 53 extracts data from the satellite data DB 73 and the sensor data DB 74, corrects the simulation results of the prediction model DB 79 using a data assimilation technique, calculates highly accurate water level estimates and predictions, and stores them in the water level history DB 77.

[0075] This will enable the generation of highly accurate water level information by combining a process-based model that performs physical simulations with actual measured observation data using data assimilation techniques, thereby enabling comprehensive support for rice paddy management that was difficult to achieve with conventional technology.

[0076] The management information generation unit 54 generates management information for the specified paddy field based on at least a part of the estimated value and the predicted value of the water level of the specified paddy field.

[0077] The management information generation unit 54 extracts water level information from the water level history DB 77, generates management information such as irrigation timing according to the rice growth stage, water discharge timing to suppress methane emissions, irrigation periods, and soil movement instructions for field leveling, and stores this information in the management information DB 78.

[0078] This will go beyond simply providing water level information and provide specific management guidelines that are directly useful to farmers, thereby enabling the practical use of highly accurate water level predictions in agricultural fields.

[0079] The irrigation optimization unit 55 calculates the optimal amount of irrigation water for the entire specified rice field based on water level information for each satellite observation pixel contained in the remote sensing observation data.

[0080] The irrigation optimization unit 55 extracts water level data in pixel units from the satellite data DB 73 , calculates the optimal amount of irrigation water taking into account the water level distribution in the field, and stores the calculated amount in the management information DB 78 .

[0081] This allows for precise water management that takes into account the unevenness of water level distribution within the field, resulting in efficient use of water resources and optimization within the field, which is not possible with conventional uniform irrigation.

[0082] The irrigated paddy field identification unit 56 identifies whether the specified paddy field is an irrigated paddy field that receives water through irrigation independently of precipitation, based on the remote sensing observation data, meteorological data, and vegetation index data.

[0083] The irrigated paddy field identification unit 56 extracts data from the satellite data DB 73 and meteorological data DB 72 , analyzes the relationship between precipitation, water level, and vegetation index, identifies irrigation-dependent paddy fields, and stores the data in the paddy field information DB 71 .

[0084] This will enable classification of rice paddies by water source, making it possible to objectively assess the degree of dependence on irrigation and optimize water resource management, and will have the effect of enabling accurate calculation of irrigation-related methane emissions under the carbon credit system.

[0085] The water demand prediction unit 57 calculates the demand and supply period for irrigation water for the entire area including a plurality of the specified rice paddies based on the estimated or predicted values ​​of the water levels of each area.

[0086] The water demand forecasting unit 57 extracts water level data for multiple fields from the water level history DB 77 , and comprehensively forecasts water demand at the regional level, and stores the forecast in the management information DB 78 .

[0087] This will enable the integration of water level predictions for individual fields at a regional level, thereby enabling the optimization of wide-area water resource management, which has previously been difficult, and will enable the efficient use of water sources and more precise supply plans.

[0088] Next, specific processing and display in the server 1 and the user terminal 2 will be described in detail with reference to FIGS.

[0089] FIG. 5 illustrates the water level calculation method used by the simulation unit 51 and water level calculation unit 53 in FIG. 4 . As shown in FIG. 5 , the simulation unit 51 calculates the water level change over a 15-day period in a time series. The water level calculation unit 53 calculates a highly accurate prediction portion through data assimilation using the estimated water level obtained by remote sensing, such as satellite data, from the satellite data server 4 and the field feedback water level from the user terminal 2. This is a specific example of water level information generation using the process-based model and data assimilation combination shown in FIG. 17 . This enables continuous water level monitoring and prediction for a specific paddy field plot. As shown in FIG. 5 , the water level calculation unit 53 can also perform water level estimation through machine learning using inputs such as remote sensing data from satellites, meteorological data, soil property data, water level data measured by humans or devices, and rice growth data. Also, as shown in FIG. 5 , the management information generation unit 54 can estimate methane production through machine learning using the water level estimation results calculated by the water level calculation unit 53, meteorological data, and methane data measured by humans or devices. This is a specific example of generating water level information by combining the process-based model and data assimilation shown in Figure 17. This enables continuous water level monitoring and prediction in a given paddy field section.

[0090] Figure 6 is a diagram showing the water level calculation method and prediction accuracy by the water level calculation unit 53 of Figure 4. As shown in Figure 6, the water level calculation unit 53 adds prediction accuracy to a 15-day graph, color-coding it with green (high), yellow (medium), and red (low), and displays the ideal water level and the route of water levels that should be avoided. This prediction accuracy information is stored in the water level history DB 77 and is used for display on the user terminal 2 of Figure 9. This allows the reliability of water level predictions to be visually grasped, supporting appropriate management decisions.

[0091] Fig. 7 is a diagram showing a calculation model for the water level to be artificially controlled in the simulation unit 51 of Fig. 4. As shown in Fig. 7, the simulation unit 51 calculates the water level to be controlled using a calculation formula that subtracts the water level that would occur if there was no artificial control from the ideal water level. This calculation uses meteorological data such as precipitation, temperature, and humidity from the meteorological data server 3, internal data from the soil property DB 75 and crop data DB 76, and observation data from the satellite data server 4 and IoT sensor terminal 5. This corresponds to the input data of the process-based model of Fig. 17.

[0092] Figure 8 is a diagram showing a mechanism for improving the water level calculation model in the water level calculation unit 53 in Figure 4. As shown in Figure 8, producers report actual water levels as numerical data and image data via the user terminal 2, and the IoT sensor terminal 5 automatically transmits the water level data, which the observation data acquisition unit 52 stores in the sensor data DB 74, and the calculation model in the water level calculation unit 53 is continuously improved. This corresponds to the use of observation data in data assimilation in Figure 17.

[0093] Figure 9 is a diagram showing the water level display screen on the user terminal 2 of Figure 2. As shown in Figure 9, the user terminal 2 displays the information generated by the management information generation unit 54 of Figure 4 and stored in the management information DB 78, and can switch between map display and list display, and displays the water level, number of irrigation days, and prediction accuracy for each paddy field area. The prediction accuracy is calculated using the information calculated in Figure 6. This allows the status of multiple specified paddy fields to be grasped at a glance.

[0094] Figure 10 is a diagram showing the field details screen on the user terminal 2 of Figure 2. As shown in Figure 10, the user terminal 2 displays a 15-day water level time series graph (estimated water level, measured water level, predicted water level, and ideal water level) calculated in Figures 5 and 6, as well as a growth status map, and provides a function for correcting water level values ​​and a function for sending feedback to the server 1. The corrected data is used in the improvement mechanism of Figure 8. This makes it possible to check and correct detailed information about individual specified rice paddies.

[0095] Fig. 11 is a diagram showing a management recommendation screen on the user terminal 2 of Fig. 2. As shown in Fig. 11, the user terminal 2 displays each recommendation generated by the management information generation unit 54, irrigation optimization unit 55, etc. of Fig. 4, such as irrigation recommendations (optimum water volume and timing), leveling work support (soil elevation difference map and movement instructions), and automatic sluice gate linkage (remote control), and provides an execution button. This allows the management information generated by the server 1 to be provided in a practical form.

[0096] Figure 12 is a diagram showing a regional water demand forecast by the water demand forecasting unit 57 in Figure 4. As shown in Figure 12, the water demand forecasting unit 57 analyzes the water level and number of irrigation days for each paddy field in regions A and B from the water level history DB 77, calculates a water supply plan for the entire region, such as "supply X kL in 5-7 days" or "supply Y kL in 1-2 days," and stores the plan in the management information DB 78. This enables efficient water resource management over a wide area.

[0097] Figure 13 is a diagram showing the calculation of the optimal irrigation water amount within a field by the irrigation optimization unit 55 of Figure 4. As shown in Figure 13, the irrigation optimization unit 55 acquires water level observation results (blue = flooded, yellow = not flooded) using pixel data in the satellite data DB 73 from the satellite data server 4, calculates the amount of water required for each pixel (dark red = large amount of water, light red = small amount of water), calculates the optimal amount of water required for one field, W = Σwi, and stores this in the management information DB 78. This corresponds to a specific implementation of the optimization of irrigation water amount within a field in Figure 1.

[0098] Figure 14 is a diagram showing the field leveling support provided by the management information generation unit 54 in Figure 4. As shown in Figure 14, the management information generation unit 54 estimates elevation differences (high soil surface = x cm, low soil surface = 0 cm) by remote sensing using observation data in the satellite data DB 73 from the satellite data server 4, and generates soil movement instructions indicating the post-leveling soil surface elevation difference (location to lower = x cm, location to raise = y cm) and the highest and lowest points, and stores these in the management information DB 78. This corresponds to a specific implementation of the field leveling support in Figure 1.

[0099] Figure 15 is a diagram showing a method for identifying irrigated paddy fields by the irrigation paddy field identification unit 56 in Figure 4. As shown in Figure 15, the irrigation paddy field identification unit 56 acquires precipitation data (0 = no precipitation, 1 = precipitation) from the weather data server 3, water level data (0 = no water level, 1 = water level) from the satellite data server 4, and a vegetation index (0 = no vegetation, 1 = vegetation) from the weather data DB 72 and satellite data DB 73, and calculates the results (0 and 1 = other than the above, 2 = paddy fields that are only irrigated) using four grid diagrams and stores them in the paddy field information DB 71. This corresponds to a specific implementation of identifying irrigated paddy fields in Figure 1.

[0100] Figure 16 is a diagram showing the method for calculating the inter-drought period by the management information generation unit 54 of Figure 4. As shown in Figure 16, the management information generation unit 54 acquires observation data from the satellite data server 4 and IoT sensor terminal 5 from the satellite data DB 73 and sensor data DB 74, monitors water level fluctuations in one plot (observation dates 11-13, water level prediction dates) and the relationship between the soil surface and the water surface, counts the number of inter-drought days on a grid diagram of the entire area A (1st day → 2nd day → 3rd day → xth day), calculates the maximum number of inter-drought days for each plot, and stores the calculated values ​​in the management information DB 78. This corresponds to the specific implementation of the inter-drought period calculation of Figure 1.

[0101] Fig. 17 is a diagram showing the internal algorithm configuration in the functional configuration of the server 1 in Fig. 4. As shown in Fig. 17, in the process-based model (physical simulation) at the top, a simulation unit 51 inputs weather data from the weather data server 3 and internal data from the soil property DB 75 and crop data DB 76, and outputs time-series changes in water level prediction, while in the data assimilation (combination of model and observation data) at the bottom, a water level calculation unit 53 inputs remote sensing data from the satellite data server 4 and ground IoT sensor data from the IoT sensor terminal 5, executes a correction and update process, and combines both to generate highly accurate water level information.

[0102] Figure 18 is a diagram showing the overall processing flow of the information processing system shown in Figure 2. As shown in Figure 18, data flows from the data acquisition sources on the left (satellite data server 4 for SAR satellites and optical satellites, IoT sensor terminal 5 for IoT devices, user terminal 2 for direct farmer measurement, and weather data server 3) to the central server 1 (observation data acquisition unit 52 for data acquisition and management function, simulation unit 51 and water level calculation unit 53 for prediction analysis function, management information generation unit 54 for management information generation function, etc.), and information is provided to user terminal 2 on the right (information display function, feedback function).

[0103] FIG. 19 is a diagram showing the database structure within the storage unit 18 of FIG. 4 . As shown in FIG. 19 , within the storage unit 18, the upper field table (including basic information such as field ID, polygon data as location information, and soil type and permeability used in the process-based model as soil properties) corresponds to the paddy field information DB 71. The lower time-series data table (including data ID, field ID, observed or estimated date and time, data type information such as "water level" and "soil moisture," specific data values, and data source information such as "SAR satellite," "IoT sensor," and "model estimate") corresponds to the weather data DB 72, satellite data DB 73, sensor data DB 74, and water level history DB 77. The two tables are connected by a link via the field ID, allowing each time-series data item to be associated with a specific field. This allows for accurate management of the type of data, the date, and the field.

[0104] Although one embodiment of the present invention has been described above, the present invention is not limited to the above-described embodiment, and modifications, improvements, etc. within the scope of achieving the object of the present invention are considered to be included in the present invention.

[0105] Furthermore, the system configuration shown in FIG. 2 and the hardware configuration of the server 1 shown in FIG. 3 are merely examples for achieving the object of the present invention, and are not particularly limited.

[0106] Furthermore, the functional block diagram shown in Fig. 4 is merely an example and is not particularly limited. That is, it is sufficient if the information processing system in Fig. 2 is provided with a function that can execute the various processes described above as a whole, and the functional blocks and databases used to realize this function are not particularly limited to the example in Fig. 4.

[0107] Furthermore, the locations of the functional blocks and databases are not limited to those shown in Fig. 4 and may be arbitrary. For example, at least some of the functional blocks and databases arranged on the server 1 side may be provided on the user terminal 2 side, the weather data server 3 side, the satellite data server 4 side, the IoT sensor terminal 5 side, or another information processing device not shown.

[0108] The above-described series of processes can be executed by hardware or software, and each functional block can be configured by hardware alone, software alone, or a combination of both.

[0109] When a series of processes is executed by software, the programs constituting the software are installed onto a computer or the like from a network or a recording medium. The computer may be a computer incorporated into dedicated hardware. The computer may also be a computer capable of executing various functions by installing various programs, such as a server, a general-purpose smartphone, or a personal computer.

[0110] The recording medium containing such a program may be composed of not only a removable medium (not shown) that is distributed separately from the device main body in order to provide the program to the user, but also a recording medium that is provided to the user in a state that it is pre-installed in the device main body.

[0111] In this specification, the steps describing the program to be recorded on the recording medium include not only processes that are performed chronologically in accordance with the order, but also processes that are not necessarily performed chronologically but are performed in parallel or individually.

[0112] To sum up, the information processing device to which the present invention is applied is sufficient as long as it has the following configuration, and can take on a variety of different embodiments. That is, an information processing device to which the present invention is applied (for example, the server 1 in FIGS. 2 to 4) is an information processing device for managing paddy fields based on the water level, comprising: simulation means (for example, the simulation unit 51 in FIG. 4 and the calculation model in FIG. 7) for calculating time-series changes in the water level of a specified paddy field (for example, the specified paddy field in FIG. 1 or the paddy field plot in FIG. 5) using a simulation model (for example, the prediction model DB 79 in FIG. 4 or the process-based model in FIG. 17) in which physical phenomena related to the water balance of the paddy field are modeled; observation data acquisition means (for example, the observation data acquisition unit 52 in FIG. 4 and the data acquisition and management function in FIG. 18) for acquiring remote sensing observation data obtained as a result of remote sensing observation of an area including the specified paddy field (for example, the satellite data DB 73 in FIG. 4, the satellite estimated water level in FIG. 5, the satellite pixel data in FIG. 13) and direct observation data obtained as a result of direct observation of the specified paddy field by one or more sensors (for example, the sensor data DB 74 in FIG. 4, the field feedback water level in FIG. 5, the IoT sensor data in FIG. 8); It is sufficient to have a water level calculation means (e.g., water level calculation unit 53 in Figure 4, prediction accuracy calculation in Figure 6, calculation model improvement in Figure 8, data assimilation in Figure 17) that corrects the calculation results of the simulation model based on the remote sensing observation data and the direct observation data of the specified paddy field, and calculates estimated and predicted values ​​of the water level of the specified paddy field based on the correction results, and a management information generation means (e.g., management information generation unit 54 in Figure 4, management recommendation screen in Figure 11, field leveling support in Figure 14, calculation of mid-drought period in Figure 16) that generates management information for the specified paddy field based on at least a part of the estimated and predicted values ​​of the water level of the specified paddy field.

[0113] In this way, it will be possible to support appropriate water level management in rice paddies, achieve efficient water resource utilization, and reduce environmental impact.

[0114] Furthermore, the remote sensing observation data can include data acquired by satellites (e.g., data from SAR satellites and optical satellites in Figure 1, satellite-estimated water levels in Figure 5, satellite observation results in Figure 13, and satellite water level and vegetation index data in Figure 15).

[0115] This will enable more comprehensive rice paddy management by using satellite data capable of wide-area observation to grasp surface-level water levels and growth information for the entire field, which was not possible with conventional point observations.

[0116] Furthermore, the direct observation data may include data acquired by IoT sensors installed in the specified rice paddy field (e.g., the IoT automatic water level meter and soil moisture sensor in Figure 1, the IoT sensor data in Figure 8, and the ground IoT sensor observation in Figure 16).

[0117] This makes it possible to calibrate and verify the model using highly accurate ground measurement data, achieving extremely high estimation accuracy that would be difficult to achieve using remote sensing data alone.

[0118] Furthermore, the simulation model can be a model that inputs meteorological data (e.g., meteorological data DB 72 in FIG. 4, meteorological data input in FIG. 7, precipitation data in FIG. 15, meteorological data input in FIG. 17), soil property data (e.g., soil property DB 75 in FIG. 4, soil property / crop data in FIG. 7, soil property data in FIG. 17), and crop data (e.g., crop data DB 76 in FIG. 4, soil property / crop data in FIG. 7, crop data in FIG. 17).

[0119] This physically takes into account all the major factors that affect the water balance in rice paddies, making it possible to predict water level fluctuations with high accuracy based on scientific evidence, something that is not possible using empirical methods.

[0120] Furthermore, the management information may include irrigation timing according to the growth stage of rice in the specified paddy field (for example, irrigation timing information in Figure 1, irrigation days display in Figure 9, and irrigation recommendations in Figure 11).

[0121] This will go beyond simply providing water level information and provide specific management guidelines that are directly useful to farmers, making it possible to realize practical use of highly accurate water level predictions in agricultural fields.

[0122] Furthermore, the management information may include the timing of water discharge for suppressing methane emissions in the specified rice paddy (for example, the methane emission suppression information in FIG. 1, and methane reduction management based on calculation of mid-drainage periods in FIG. 16).

[0123] This will enable objective methane reduction management, which has been difficult to achieve in the past, and will contribute to the creation of environmental value and the decarbonization of agriculture by complying with the MRV of the carbon credit system.

[0124] Furthermore, the management information may include the dry-up period in the specified paddy field (for example, the dry-up period information in FIG. 1 and the dry-up day count / calculation results in FIG. 16).

[0125] This will automate and objectively determine the number of dry days, which previously required manual work, and enable comprehensive quantitative evaluation of methane reduction effects over large areas, thereby realizing accurate MRV under the carbon credit system.

[0126] Furthermore, the management information may include soil movement instructions for field leveling based on the elevation difference of the soil surface of the specified rice paddy (e.g., the field leveling support information in Figure 1, the leveling work support in Figure 11, and the soil movement instructions / elevation difference map in Figure 14).

[0127] This will enable efficient support for field leveling work without relying on conventional surveying by estimating soil elevation differences through reverse calculations from water level information, contributing to improved field productivity.

[0128] Furthermore, the system may further include an irrigation optimization means (e.g., the irrigation optimization unit 55 in Figure 4, the in-field optimal irrigation water amount calculation unit in Figure 13, and the recommended optimal irrigation water amount in Figure 11) that calculates the optimal irrigation water amount for the entire specified paddy field based on water level information for each satellite observation pixel included in the remote sensing observation data, and the management information generation means (e.g., the management information generation unit 54 in Figure 4) can generate the management information based on the optimal irrigation water amount for the entire specified paddy field.

[0129] This allows for precise water management that takes into account the unevenness of water level distribution within the field, making it possible to achieve efficient use of water resources and optimization within the field, something that cannot be achieved with conventional uniform irrigation.

[0130] Furthermore, the system may further include an irrigated paddy field identification means (e.g., the irrigated paddy field identification unit 56 in FIG. 4 and the irrigated paddy field identification method / grid diagram discrimination in FIG. 15) that identifies whether or not the specified paddy field is an irrigated paddy field to which water is supplied by irrigation independent of precipitation, based on the remote sensing observation data, meteorological data, and vegetation index data, and the management information generation means (e.g., the management information generation unit 54 in FIG. 4) can generate the management information based on information as to whether or not the specified paddy field is an irrigated paddy field.

[0131] This will enable classification of rice paddies by water source, enabling an objective assessment of irrigation dependency and optimization of water resource management, and enabling accurate calculation of irrigation-related methane emissions under the carbon credit system.

[0132] Furthermore, the system may further include a water demand prediction means (e.g., the water demand prediction unit 57 in Figure 4 or the regional water demand prediction / water supply plan calculation unit in Figure 12) that calculates the demand and supply period for irrigation water for the entire region including a plurality of the specified rice fields based on the estimated or predicted values ​​of each water level, and the management information generation means (e.g., the management information generation unit 54 in Figure 4) can generate the management information based on the demand and supply period for irrigation water for the entire region including the plurality of specified rice fields.

[0133] This will enable the integration of water level predictions for individual fields at a regional level, thereby optimizing water resource management over a wide area, which was previously difficult, and making it possible to use water sources efficiently and refine supply plans.

[0134] 1...Server, 2...User terminal, 3...Weather data server, 4...Satellite data server, 5...IoT sensor terminal, 11...CPU, 12...ROM, 13...RAM, 14...Bus, 15...Input / output interface, 16...Input unit, 17...Output unit, 18...Memory unit, 19...Communication unit, 20...Drive, 21...Removable media, 51...Simulation unit, 52...Observation data acquisition unit, 53...Water level calculation unit, 54...Management information generation unit, 55...Irrigation optimization unit, 56...Irrigated paddy field identification unit, 57...Water demand forecasting unit, 71...Paddy field information DB, 72...Weather data DB, 73...Satellite data DB, 74...Sensor data DB, 75...Soil characteristics DB, 76...Crop data DB, 77...Water level history DB, 78...Management information DB, 79...Prediction model DB, 80...User information DB

Claims

1. In an information processing device that manages paddy fields based on water levels, A simulation means for calculating the time-series change in the water level of a given paddy field using a simulation model that models the physical phenomena related to the water balance of a paddy field, An observation data acquisition means that acquires remote sensing observation data obtained as a result of remote sensing of the area including the predetermined paddy field, and direct observation data obtained as a result of direct observation of the predetermined paddy field by one or more sensors, A water level calculation means that corrects the calculation results of the simulation model based on the remote sensing observation data and direct observation data of the predetermined paddy field, calculates estimated and predicted values ​​of the water level of the predetermined paddy field based on the correction results, calculates an index indicating uncertainty related to the predicted value, and outputs it. A management information generation means that generates management information for the predetermined paddy field based on at least a portion of the estimated and predicted values ​​of the water level of the predetermined paddy field, An information processing device equipped with the following features.

2. The water level calculation means outputs the indicator showing uncertainty in multiple stages, The information processing apparatus according to claim 1.

3. The water level calculation means outputs the indicator showing the uncertainty as a continuous value. The information processing apparatus according to claim 1.

4. The aforementioned remote sensing observation data includes data acquired by satellites. The information processing apparatus according to claim 1.

5. The aforementioned direct observation data includes data acquired by IoT sensors installed in the designated paddy field. The information processing apparatus according to claim 1.

6. The aforementioned simulation model is a model that takes weather data, soil characteristics data, and crop data as input. The information processing apparatus according to claim 1.

7. The aforementioned management information includes irrigation timing according to the growth stage of the rice in the designated paddy field. The information processing apparatus according to claim 1.

8. The management information includes the timing of water discharge for methane emission suppression in the designated paddy field. The information processing apparatus according to claim 1.

9. The aforementioned management information includes the mid-season drainage period in the designated paddy field. The information processing apparatus according to claim 1.

10. The management information includes instructions for soil movement for field leveling based on the elevation difference of the soil surface of the designated paddy field. The information processing apparatus according to claim 1.

11. The system further includes an irrigation optimization means that calculates the optimal amount of irrigation water for the entire predetermined paddy field based on water level information for each satellite observation pixel included in the remote sensing observation data, The management information generation means generates the management information based on the optimal irrigation water volume for the entire predetermined paddy field. The information processing apparatus according to claim 1.

12. The system further includes an irrigated paddy field identification means that identifies whether or not the designated paddy field is an irrigated paddy field that is supplied with water by irrigation independently of precipitation, based on the remote sensing observation data, meteorological data, and vegetation index data. The management information generation means generates the management information based on information as to whether or not the predetermined paddy field is an irrigated paddy field. The information processing apparatus according to claim 1.

13. The system further comprises a water demand forecasting means for calculating the total demand and supply timing of irrigation water for an area including multiple predetermined paddy fields, based on the estimated or predicted values ​​of the water levels for each of the paddy fields. The management information generation means generates the management information based on the demand and supply timing of irrigation water for the entire region, including the plurality of predetermined paddy fields. The information processing apparatus according to claim 1.

14. In an information processing method executed by an information processing device that manages paddy fields based on water levels, A simulation step to calculate the time-series change in the water level of a given paddy field using a simulation model that models the physical phenomena related to the water balance of a paddy field, Observation data acquisition step: Obtaining remote sensing observation data obtained as a result of remote sensing of the area including the predetermined paddy field, and direct observation data obtained as a result of direct observation of the predetermined paddy field by one or more sensors. A water level calculation step which involves correcting the calculation results of the simulation model based on the remote sensing observation data and direct observation data of the predetermined paddy field, calculating estimated and predicted values ​​of the water level of the predetermined paddy field based on the correction results, calculating an index indicating uncertainty related to the predicted value, and outputting it, A management information generation step that generates management information for the predetermined paddy field based on at least a portion of the estimated and predicted values ​​of the water level of the predetermined paddy field, Information processing methods including

15. A computer that manages rice paddies based on water levels, A simulation step to calculate the time-series change in the water level of a given paddy field using a simulation model that models the physical phenomena related to the water balance of a paddy field, Observation data acquisition step: Obtaining remote sensing observation data obtained as a result of remote sensing of the area including the predetermined paddy field, and direct observation data obtained as a result of direct observation of the predetermined paddy field by one or more sensors. A water level calculation step which involves correcting the calculation results of the simulation model based on the remote sensing observation data and direct observation data of the predetermined paddy field, calculating estimated and predicted values ​​of the water level of the predetermined paddy field based on the correction results, calculating an index indicating uncertainty related to the predicted value, and outputting it, A management information generation step that generates management information for the predetermined paddy field based on at least a portion of the estimated and predicted values ​​of the water level of the predetermined paddy field, A program that executes control processes, including those mentioned above.