Information processing program, information processing method, and information processing device

Abstract

To reduce a processing load.SOLUTION: An information processing device 100 generates a three-dimensional model 110 representing a geography of a first region on the basis of first geographical data 101 representing a geography before the occurrence of an event about each first section forming a first region. The information processing device 100 generates second geographical data 102 representing a geography after the occurrence of the event about each first section by applying numerical simulation using environmental data representing environment of each first section to the generated three-dimensional model 110. The information processing device 100 generates a conversion model 120 on the basis of each first geographical data 101 and each second geographical data 102. The information processing device 100 converts third geographical data 103 representing the geography before the occurrence of the event about each second section forming a second region into fourth geographical data 104 representing the geography after the occurrence of the vent about the second section by using the generated conversion model 120.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Conventionally, with climate change, heavy rain has triggered disasters such as landslides and debris flows, causing damage to residents and their homes, and it is therefore desirable to be able to predict where disasters will occur.

[0003] Prior art includes, for example, predicting the risk of landslides in a target area based on changes in the state of features in the target area. Other prior art includes, for example, determining whether a landslide will occur using analysis by a neural network trained on past weather and disaster data. Other prior art includes, for example, training a probabilistic downscaling mapping function. Other prior art includes, for example, using a hydrological model to calculate water inflow and outflow between cells in a geographic area based on a weather scenario, and using a hydraulic model to calculate the water depth of each cell based on the weather scenario and the water inflow and outflow between cells.

[0004] There is also a technology for assessing the risk of a slope based on an evaluation score for each item. There is also a technology for predicting slopes where landslides will occur by statistical processing. There is also a technology for learning image data representing topographical characteristics as training data by using a convolutional neural network (CNN). There is also a technology for predicting the location of a landslide by using numerical simulation. There is also a technology for generating a reduced order model by using a proper orthogonal decomposition (POD)-neural network (NN). [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent Publication No. 2021-174013 [Patent Document 2] Japanese Patent Application Laid-Open No. 2004-346653 [Patent Document 3] US Patent Application Publication No. 2019 / 0318440 [Patent Document 4] US Patent Application Publication No. 2021 / 0064802 [Non-patent literature]

[0006] [Non-Patent Document 1] Akamine, T. et al. "Case study of creating a landslide hazard map for steep slopes (part 1)." Technology e-Forum 2008 (2008). [Non-patent document 2] Sakane, K. "Evaluation methods for slopes in the Rokko Mountains." Report of the Ministry of Land, Infrastructure, Transport and Tourism's National Land Technology Research Council (Proceedings of the Ministry of Land, Infrastructure, Transport and Tourism's National Land Technology Research Council) 2008 (2008): 208-213. [Non-patent document 3] Wang, Yi, Zhice Fang, and Haoyuan Hong. “Comparison of convolutional neural networks for landslide susceptibility mapping in Yanshan County, China.” Science of the total environment 666 (2019): 975-993. [Non-patent document 4] Zhao, Yidong, and Jinhyun Choo. “Stabilized material point methods for coupled large deformation and fluid flow in porous materials.” Computer Methods in Applied Mechanics and Engineering 362 (2020): 112742. [Non-Patent Document 5] Hesthaven, Jan S., and Stefano Ubbiali. “Non-intrusive reduced order modeling of nonlinear problems using neural networks.” Journal of Computational Physics 363 (2018): 55-78. Summary of the Invention [Problem to be solved by the invention]

[0007] However, with conventional technology, it is difficult to predict where disasters will occur within a target area. For example, a method for predicting where landslides will occur within a target area using a numerical simulation based on mechanics is conceivable, but there is a problem in that the processing load and processing time required for the prediction tend to increase.

[0008] In one aspect, the present invention aims to reduce the processing load. [Means for solving the problem]

[0009] According to one embodiment, an information processing program, an information processing method, and an information processing device are proposed that obtain second terrain data representing the terrain after the occurrence of an event for each of a plurality of first compartments that form a first region, the second terrain data being generated by applying a numerical simulation using environmental data representing the environment of each of the first compartments to a three-dimensional model representing the terrain of the first region, the second terrain data being based on first terrain data representing the terrain before the occurrence of an event for each of the plurality of first compartments that form the first region and are each the same size as the first compartments; generate a conversion model based on each of the first terrain data and each of the second terrain data that enables the terrain data representing the terrain before the occurrence of the event for a certain compartment to be converted into terrain data representing the terrain after the occurrence of the event for the certain compartment; and convert third terrain data representing the terrain before the occurrence of the event for each of a plurality of second compartments that form a second region and are each the same size as the first compartments into fourth terrain data representing the terrain after the occurrence of the event for the certain compartment using the generated conversion model, and output the converted data. [Effects of the Invention]

[0010] According to one aspect, it is possible to reduce the processing load. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is an explanatory diagram illustrating an example of an information processing method according to an embodiment. [Figure 2] FIG. 2 is an explanatory diagram illustrating an example of an information processing system 200. As shown in FIG. [Figure 3] FIG. 3 is a block diagram showing an example of the hardware configuration of the information processing device 100. As shown in FIG. [Figure 4] FIG. 4 is a block diagram showing an example of the functional configuration of the information processing device 100. As shown in FIG. [Figure 5] FIG. 5 is an explanatory diagram (part 1) showing the flow of operations of the information processing device 100. [Figure 6] FIG. 6 is an explanatory diagram (part 2) showing the flow of operations of the information processing device 100. [Figure 7] FIG. 7 is an explanatory diagram showing an example of generating digital elevation data 702 after a disaster occurs. [Figure 8] FIG. 8 is an explanatory diagram showing an example of generating a proxy model 800. [Figure 9] FIG. 9 is an explanatory diagram showing an example of dividing the target area 900. In FIG. [Figure 10] FIG. 10 is an explanatory diagram showing an example of application of the proxy model 800. [Figure 11] FIG. 11 is an explanatory diagram showing an example of overlapping risk areas. [Figure 12] FIG. 12 is a flowchart illustrating an example of a generation process procedure. [Figure 13] FIG. 13 is a flowchart illustrating an example of an application processing procedure. DETAILED DESCRIPTION OF THE INVENTION

[0012] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, an information processing program, an information processing method, and an information processing device according to embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0013] (An example of an information processing method according to an embodiment) 1 is an explanatory diagram illustrating an example of an information processing method according to an embodiment. The information processing device 100 is a computer for reducing the processing load and processing time required when predicting the location where a predetermined event will occur. The information processing device 100 is, for example, a server or a PC (Personal Computer).

[0014] The predetermined event is, for example, a disaster. Specific examples of the predetermined event include landslides, debris flows, floods, and inundation. Due to climate change, heavy rains can trigger disasters, causing damage to residents and homes, so it is desirable to predict where disasters will occur. However, it is difficult to predict where disasters will occur.

[0015] For example, a method can be considered for predicting slopes where landslides will occur by assessing the risk of a slope based on the evaluation scores of each of a plurality of items. The plurality of items may include, for example, items related to the height, angle, soil quality, and vegetation of the slope. The plurality of items may include, for example, items related to the condition of the slope, such as cracks, loose rocks, or spring water. The plurality of items may include, for example, an item related to rainfall. For information on this method, see, for example, Non-Patent Document 1 mentioned above. However, this method has the problem of making it difficult to accurately predict where a disaster will occur.

[0016] Another possible method is to predict slopes where landslides will occur in the future by statistical processing based on information about slopes where landslides have occurred in the past. Specifically, one possible method is to refer to the results of a slope stability survey, compare them with the causes of collapse of slopes where landslides have occurred in the past, and evaluate the risk of the slope to predict slopes where landslides will occur. For details about this method, see, for example, Non-Patent Document 2 mentioned above. However, this method has the problem of making it difficult to accurately predict the location of a disaster. For example, it is not possible to accurately predict the location of a disaster in an area where no disaster has occurred before.

[0017] Another possible method is to use machine learning to predict slopes where landslides will occur. Specifically, a CNN can be used to learn image data representing topographical features as training data, and predict slopes where landslides will occur. For details on this method, see, for example, Non-Patent Document 3 mentioned above. With this method, unless appropriate training data can be prepared, it is not possible to accurately predict the location of a disaster.

[0018] Another possible method is to use numerical simulation to predict where landslides will occur in a target area. For example, it is possible to predict where landslides will occur using arc slide analysis, the finite element method, or the particle method. For details on this method, see, for example, Non-Patent Document 4 mentioned above. However, this method has the problem that the processing load and processing time required for prediction tend to increase. Therefore, the larger the target area, the more difficult it becomes to put this method into practical use.

[0019] Therefore, in this embodiment, an information processing method will be described that makes it easier to accurately predict the location where an event will occur and that can reduce the processing load and processing time required for the prediction.

[0020] In FIG. 1, there is a first region. The first region is set, for example, as a rectangular region on a two-dimensional plane of latitude and longitude axes. The first region is a region for which an attempt is made to predict the topography after an event occurs. The event is, for example, a disaster. Specifically, the event is a landslide. The first region is formed by a plurality of first divisions. The first divisions are set, for example, as rectangular regions on a two-dimensional plane of latitude and longitude axes. Each of the plurality of first divisions is the same size.

[0021] There is also a second region. The second region may be, for example, the same region as the first region. The second region is a region for which the topography after the occurrence of an event is to be predicted. The second region is formed by a plurality of second divisions. The second divisions are set, for example, as rectangular regions on a two-dimensional plane of latitude and longitude axes. The plurality of second divisions are each the same size. The second divisions are the same size as the first division.

[0022] (1-1) The information processing device 100 acquires first topographical data 101 representing the topography of each first section forming a first region before the occurrence of an event. The first topographical data 101 indicates, for example, the elevation of the topography. Specifically, the first topographical data 101 is image-format data that indicates the elevation of the topography with color. The information processing device 100 generates a three-dimensional model 110 representing the topography of the first region based on the first topographical data 101. The three-dimensional model 110 corresponds to the topography of the first region before the occurrence of the event.

[0023] (1-2) The information processing device 100 applies a numerical simulation using environmental data representing the environment of each first section to the generated three-dimensional model 110. As a result, the information processing device 100 generates second terrain data 102 representing the terrain of each first section after the occurrence of the event. The environment is, for example, rainfall.

[0024] The information processing device 100 generates a 3D model 110 corresponding to a state after the occurrence of an event by, for example, applying a particle method to the generated 3D model 110 using environmental data representing the amount of rainfall in each first section. The information processing device 100 generates second terrain data 102 representing the terrain after the occurrence of the event for each first section, for example, based on the 3D model 110 after the occurrence of the event. The second terrain data 102 indicates, for example, the elevation of the terrain. Specifically, the second terrain data 102 is image data that indicates the elevation of the terrain with color.

[0025] This allows the information processing device 100 to prepare appropriate training data for generating the conversion model 120 that enables conversion of topographical data representing the topography before an event occurs into topographical data representing the topography after the event occurs. This allows the information processing device 100 to generate the conversion model 120 with high accuracy.

[0026] (1-3) The information processing device 100 generates a conversion model 120 based on each of the first terrain data 101 and each of the second terrain data 102. The conversion model 120 is a model that enables conversion of terrain data representing the terrain of a certain section before an event occurs into terrain data representing the terrain of the certain section after the event occurs. The conversion model 120 is, for example, a model that converts image format data. Specifically, the conversion model 120 is a CGAN (Conditional Generative Adversarial Network). The CGAN is defined by, for example, pix2pix. This enables the information processing device 100 to generate terrain data representing the terrain of a section after an event occurs without relying on numerical simulation.

[0027] (1-4) The information processing device 100 converts the third topographical data 103, which represents the topography of each of the second sections forming the second region before the occurrence of an event, into fourth topographical data 104, which represents the topography of the second section after the occurrence of the event, using the generated conversion model 120. This allows the information processing device 100 to generate the fourth topographical data 104, which represents the topography of the second section after the occurrence of an event, and which is useful for predicting the location in the second region where the event will occur. Because the information processing device 100 can generate the fourth topographical data 104 without relying on numerical simulation, it is possible to reduce the processing load and processing time required when predicting the location in the second region where the event will occur.

[0028] (1-5) The information processing device 100 outputs the converted fourth topographical data 104. The information processing device 100 outputs the converted fourth topographical data 104 to an analysis unit that predicts the location of an event in the second region. The analysis unit is, for example, a functional unit included in the information processing device 100. The analysis unit may be, for example, another computer.

[0029] The information processing device 100 may output the results of the analysis unit's prediction of the location in the second region where the event will occur. The output format may be, for example, display on a display, printout on a printer, transmission to another computer, or storage in a memory area. For example, the information processing device 100 displays the results of the analysis unit's prediction of the location in the second region where the event will occur on a display so that the user can refer to them. This allows the information processing device 100 to predict the location in the second region where the event will occur. The information processing device 100 can reduce the workload and work time imposed on the user.

[0030] The information processing device 100 may, for example, display the converted fourth topographical data 104 on a display so that the user can refer to it. This allows the information processing device 100 to make it easier for the user to predict the location in the second region where an event will occur.

[0031] Here, the case where the information processing device 100 operates independently has been described, but the present invention is not limited to this case, and the information processing device 100 may also operate in cooperation with another computer.

[0032] For example, another computer may generate the second topographical data 102 for each of the first sections. In this case, the other computer acquires the first topographical data 101 for each of the first sections forming the first region, and generates a 3D model 110 representing the topography of the first region based on the acquired first topographical data 101. The other computer then generates the second topographical data 102 for each of the first sections by applying a numerical simulation to the generated 3D model 110. Furthermore, the information processing device 100 acquires the second topographical data 102 for each of the first sections by receiving it from the other computer.

[0033] For example, there may be cases where another computer predicts the location in the second region where an event will occur. In this case, the information processing device 100 transmits the converted fourth topographical data 104 to the other computer. Then, the other computer predicts the location in the second region where the event will occur based on the received fourth topographical data 104. For an example of such a case, specifically, the information processing system 200 shown in FIG. 2 can be referred to.

[0034] (An example of the information processing system 200) Next, an example of an information processing system 200 to which the information processing device 100 shown in FIG. 1 is applied will be described with reference to FIG.

[0035] 2 is an explanatory diagram showing an example of an information processing system 200. In FIG. 2, the information processing system 200 includes an information processing device 100, a numerical analysis device 201, and a client device 202.

[0036] In the information processing system 200, the information processing device 100 and the numerical analysis device 201 are connected via a wired or wireless network 210. The network 210 is, for example, a local area network (LAN), a wide area network (WAN), the Internet, etc. In the information processing system 200, the information processing device 100 and the client device 202 are connected via the wired or wireless network 210.

[0037] The information processing device 100 is a computer used by a system administrator of the information processing system 200. The information processing device 100 generates a surrogate model. The surrogate model is a model that enables digital elevation data of a certain section before a disaster occurs to be converted into digital elevation data of the certain section after the disaster occurs. The digital elevation data of a certain section is, for example, image format data in which the latitudinal and longitudinal lengths of the certain section correspond to the vertical and horizontal lengths of an image, and the elevation of each point of the certain section is expressed by the color of each pixel of the image. The surrogate model corresponds to the conversion model shown in FIG. 1.

[0038] Specifically, the surrogate model is generated based on training data for each of a plurality of test sections divided into the test area. The training data for a test section is a combination of pre-disaster digital elevation data for the test section, which serves as an input sample for the surrogate model, and post-disaster digital elevation data for the test section, which serves as an output sample for the surrogate model.

[0039] The digital elevation data of a test section after a disaster occurs, which serves as an output sample of the surrogate model, is prepared by the numerical analysis device 201. Specifically, the digital elevation data of a test section after a disaster occurs, which serves as an output sample of the surrogate model, is generated by the numerical analysis device 201 by performing a numerical simulation based on the digital elevation data before the disaster occurs, which serves as an input sample of the surrogate model. The digital elevation data of a test section before a disaster occurs, which serves as an input sample, corresponds to the first topographical data shown in FIG. 1. The digital elevation data of a test section after a disaster occurs, which serves as an output sample, corresponds to the second topographical data shown in FIG. 1.

[0040] Specifically, the information processing device 100 receives training data for each test section from the numerical analysis device 201. Specifically, the information processing device 100 generates a surrogate model based on the received plurality of training data. More specifically, the information processing device 100 generates a CGAN that serves as a surrogate model such that an output sample included in the training data is output from the surrogate model in response to an input sample included in the training data being input to the surrogate model.

[0041] The information processing device 100 receives pre-disaster digital elevation data for a target area to be processed from the client device 202. The digital elevation data for the target area is, for example, image-format data in which the latitude and longitude lengths of the target area correspond to the vertical and horizontal lengths of the image, and the elevation of each point in the target area is expressed by the color of each pixel in the image. The information processing device 100 divides the target area into multiple target sections of the same size and generates pre-disaster digital elevation data for each of the multiple target sections. The sections may partially overlap. The pre-disaster digital elevation data for the target section corresponds to the third topographical data shown in Figure 1.

[0042] The information processing device 100 uses a proxy model to generate post-disaster digital elevation data for each target area based on the pre-disaster digital elevation data for that area. The post-disaster digital elevation data for the target area corresponds to the fourth topographical data shown in FIG. 1 . The information processing device 100 identifies hazardous areas within the target area that are determined to have a relatively high level of risk based on the generated post-disaster digital elevation data for each target area. The level of risk represents the probability of a disaster occurring, or the probability of personal or property damage due to a disaster. The information processing device 100 transmits area information that identifiably indicates the identified hazardous areas to the client device 202. The information processing device 100 is, for example, a server or a PC.

[0043] The numerical analysis device 201 is a computer used by a system administrator of the information processing system 200. For each test section, the numerical analysis device 201 generates training data by combining pre-disaster digital elevation data, which serves as an input sample for the proxy model, and post-disaster digital elevation data, which serves as an output sample for the proxy model.

[0044] The numerical analysis device 201 acquires pre-disaster digital elevation data for each test section, which serves as an input sample for the proxy model, based on, for example, an operational input from a system administrator. The numerical analysis device 201 performs a numerical simulation based on, for example, the pre-disaster digital elevation data for each test section, which serves as an input sample for the proxy model. As a result, the numerical analysis device 201 generates post-disaster digital elevation data for each test section, which serves as an output sample for the proxy model.

[0045] Specifically, the numerical analysis device 201 generates a 3D model that simulates the topography of the test area before the disaster, based on the pre-disaster digital elevation data of each test section, which serves as an input sample for the surrogate model. Specifically, the numerical analysis device 201 generates a 3D model that simulates the topography of the test area after the disaster, by applying a numerical simulation to the 3D model that simulates the topography of the test area before the disaster. Specifically, the numerical analysis device 201 generates post-disaster digital elevation data of each test section, which serves as an output sample for the surrogate model, based on the 3D model that simulates the topography of the test area after the disaster.

[0046] The numerical analysis device 201 transmits training data, which is a combination of the regional elevation data before the disaster and the regional elevation data after the disaster, for each test section to the information processing device 100. The numerical analysis device 201 is, for example, a server or a PC.

[0047] The client device 202 is a computer used by a system user of the information processing system 200. The client device 202 generates pre-disaster digital elevation data for the target area based on operational input from the system user and transmits it to the information processing device 100. The client device 202 receives area information from the information processing device 100 that identifies risk areas within the target area. The client device 202 outputs the area information so that it can be referenced by the system user. The client device 202 is, for example, a PC, a tablet terminal, or a smartphone.

[0048] Here, the case where the information processing device 100 is a computer different from the numerical analysis device 201 has been described, but this is not limiting. For example, the information processing device 100 may have the functions of the numerical analysis device 201 and operate as the numerical analysis device 201. Similarly, the case where the information processing device 100 is a computer different from the client device 202 has been described, but this is not limiting. For example, the information processing device 100 may have the functions of the client device 202 and operate as the client device 202. The following mainly describes the case where the information processing device 100 operates independently.

[0049] (Example of hardware configuration of information processing device 100) Next, an example of the hardware configuration of the information processing device 100 will be described with reference to FIG.

[0050] Fig. 3 is a block diagram showing an example of the hardware configuration of the information processing device 100. In Fig. 3, the information processing device 100 has a CPU (Central Processing Unit) 301, a memory 302, a network I / F (Interface) 303, a recording medium I / F 304, and a recording medium 305. Furthermore, each component is connected to each other by a bus 300.

[0051] Here, CPU 301 is responsible for overall control of information processing device 100. Memory 302 includes, for example, a read-only memory (ROM), a random access memory (RAM), and a flash ROM. Specifically, for example, the flash ROM or ROM stores various programs, and RAM is used as a work area for CPU 301. The programs stored in memory 302 are loaded into CPU 301, causing CPU 301 to execute coded processes.

[0052] The network I / F 303 is connected to the network 210 via a communication line, and is connected to other computers via the network 210. The network I / F 303 manages the internal interface with the network 210 and controls the input and output of data from other computers. The network I / F 303 is, for example, a modem or a LAN adapter.

[0053] The recording medium I / F 304 controls reading and writing of data from and to the recording medium 305 under the control of the CPU 301. The recording medium I / F 304 is, for example, a disk drive, a solid state drive (SSD), or a universal serial bus (USB) port. The recording medium 305 is a non-volatile memory that stores data written under the control of the recording medium I / F 304. The recording medium 305 is, for example, a disk, a semiconductor memory, or a USB memory. The recording medium 305 may be detachable from the information processing device 100.

[0054] In addition to the components described above, the information processing device 100 may also include, for example, a keyboard, a mouse, a display, a printer, a scanner, a microphone, a speaker, etc. The information processing device 100 may also include a plurality of recording medium I / Fs 304 and recording media 305. The information processing device 100 may also not include the recording medium I / Fs 304 and recording media 305.

[0055] (Example of hardware configuration of the numerical analysis device 201) A specific example of the hardware configuration of the numerical analysis device 201 is similar to the example of the hardware configuration of the information processing device 100 shown in FIG. 3, and therefore a description thereof will be omitted.

[0056] (Example of hardware configuration of client device 202) A specific example of the hardware configuration of the client device 202 is similar to the example of the hardware configuration of the information processing device 100 shown in FIG. 3, and therefore a description thereof will be omitted.

[0057] (Example of functional configuration of information processing device 100) Next, an example of the functional configuration of the information processing device 100 will be described with reference to FIG.

[0058] 4 is a block diagram showing an example of the functional configuration of the information processing device 100. The information processing device 100 includes a storage unit 401, an acquisition unit 402, an analysis unit 403, a generation unit 404, a conversion unit 405, an identification unit 406, and an output unit 407.

[0059] The storage unit 401 is realized by, for example, a storage area such as the memory 302 or the recording medium 305 shown in Fig. 3. In the following, a case where the storage unit 401 is included in the information processing device 100 will be described, but this is not limiting. For example, the storage unit 401 may be included in a device different from the information processing device 100, and the stored contents of the storage unit 401 may be accessible from the information processing device 100.

[0060] The acquiring unit 402 to the output unit 407 function as an example of a control unit. Specifically, the acquiring unit 402 to the output unit 407 realize their functions by causing the CPU 301 to execute a program stored in a storage area such as the memory 302 or the recording medium 305 shown in Fig. 3, or by the network I / F 303. The processing results of each functional unit are stored in a storage area such as the memory 302 or the recording medium 305 shown in Fig. 3, for example.

[0061] The storage unit 401 stores various types of information that are referenced or updated in the processing of each functional unit. The storage unit 401 stores topography data that represents the topography of a certain section. An event may be, for example, a disaster. An event may be, for example, a landslide. An event may specifically be a landslide, a debris flow, a flood, or inundation. The topography data may be, for example, image-format data that indicates the elevation of the topography of a certain section using color. The topography data may also be, for example, table-format data that associates the coordinates of each point in a certain section with the elevation of that point.

[0062] The storage unit 401 stores, for example, first topographical data representing the topography of a first section before an event occurs. The first section is a section included in a first region. The first region is a test region where changes in topography before and after a disaster occur are known. The first region is, for example, a test region where changes in elevation before and after a disaster occur are known. The first topographical data is acquired, for example, by the acquisition unit 402.

[0063] The storage unit 401 stores, for example, second topographical data representing the topography of the first section after the occurrence of the event. The second topographical data is acquired, for example, by the acquisition unit 402. The second topographical data may be generated, for example, by the analysis unit 403.

[0064] The storage unit 401 stores, for example, third topographical data representing the topography of the second section before the occurrence of an event. The second section is a section included in the second region. The second region may be the same region as the first region. The second region is a target region that is a processing target for which it is desired to predict changes in topography before and after the occurrence of a disaster. The second region is, for example, a target region that is a processing target for which it is desired to predict changes in elevation before and after the occurrence of a disaster. The third topographical data is acquired, for example, by the acquisition unit 402.

[0065] The storage unit 401 stores, for example, fourth terrain data representing the terrain of the second section after the occurrence of the event. The fourth terrain data is generated by the conversion unit 405, for example.

[0066] The storage unit 401 stores, for example, fifth terrain data representing the terrain of a third section before the occurrence of an event. The third section is a section included in the first region. The third section has a different size from the first section. The fifth terrain data is acquired by, for example, the acquisition unit 402.

[0067] The storage unit 401 stores, for example, sixth topographical data representing the topography of the third section after the occurrence of the event. The sixth topographical data is acquired, for example, by the acquisition unit 402. The sixth topographical data may be generated, for example, by the analysis unit 403.

[0068] The storage unit 401 stores, for example, seventh terrain data representing the terrain of the fourth section before the occurrence of the event. The fourth section is a section included in the second area. The fourth section has a different size from the second section. The seventh terrain data is acquired by, for example, the acquisition unit 402.

[0069] The storage unit 401 stores, for example, eighth terrain data representing the terrain after the occurrence of the event for the fourth section. The eighth terrain data is generated by the conversion unit 405, for example.

[0070] The storage unit 401 stores a three-dimensional model. The three-dimensional model is a model that imitates a topography. The storage unit 401 stores, for example, a three-dimensional model that represents the topography of a first region. The three-dimensional model is generated by the analysis unit 403, for example.

[0071] The memory unit 401 stores environmental data representing the environment of a certain section. The environment is, for example, the rainfall conditions. Specifically, the environment is the amount of rainfall. The environment may be temperature, air pressure, humidity, or the like. The memory unit 401 stores, for example, environmental data representing the environment of a first section. The memory unit 401 stores, for example, environmental data representing the environment of a second section. The memory unit 401 stores, for example, environmental data representing the environment of a third section. The memory unit 401 stores, for example, environmental data representing the environment of a fourth section. The environmental data is acquired, for example, by the acquisition unit 402.

[0072] The acquisition unit 402 acquires various types of information used in processing by each functional unit. The acquisition unit 402 stores the acquired various types of information in the storage unit 401 or outputs it to each functional unit. The acquisition unit 402 may also output the various types of information stored in the storage unit 401 to each functional unit. The acquisition unit 402 acquires various types of information based on, for example, a user's operation input. The acquisition unit 402 may receive various types of information from, for example, a device different from the information processing device 100.

[0073] The acquisition unit 402 acquires topographical data. For example, the acquisition unit 402 acquires first topographical data representing the topography before the occurrence of an event for each of a plurality of first sections that are the same size and form a first region. Specifically, the acquisition unit 402 may acquire first overall topographical data representing the topography of the first region before the occurrence of an event. Specifically, the acquisition unit 402 divides the acquired first overall topographical data to acquire first topographical data representing the topography before the occurrence of an event for each of the plurality of first sections. In this way, the acquisition unit 402 can obtain information that serves as the basis for generating second topographical data in the analysis unit 403.

[0074] The acquisition unit 402 may acquire the second topographical data, for example, when the analysis unit 403 does not generate the second topographical data. Specifically, the acquisition unit 402 acquires second topographical data representing the topography after the occurrence of an event for each first section. More specifically, the acquisition unit 402 may acquire second overall topographical data representing the topography of the first region after the occurrence of an event. Specifically, the acquisition unit 402 divides the acquired second overall topographical data to acquire second topographical data representing the topography after the occurrence of an event for each first section of the multiple first sections. This allows the acquisition unit 402 to enable the generation unit 404 to generate a conversion model.

[0075] The acquisition unit 402 acquires, for example, third terrain data representing the terrain before the occurrence of an event for each of a plurality of second sections that form the second region and that are each the same size as the first section. Specifically, the acquisition unit 402 may acquire third overall terrain data representing the terrain of the second region before the occurrence of an event. Specifically, the acquisition unit 402 divides the third overall terrain data to acquire the third terrain data representing the terrain before the occurrence of an event for each of the plurality of second sections. This allows the acquisition unit 402 to obtain information that serves as the basis for generating the fourth terrain data in the conversion unit 405.

[0076] Specifically, the acquisition unit 402 may detect an area in the second region that satisfies an occurrence condition related to the event. The occurrence condition may be, for example, the presence of a ridge. Specifically, the acquisition unit 402 sets a plurality of second divisions that form the second region, each including at least a portion of the detected area. Specifically, the acquisition unit 402 divides the third overall topographical data to acquire third topographical data representing the topography before the occurrence of the event for each of the set plurality of second divisions. This allows the acquisition unit 402 to obtain information that serves as the basis for generating fourth topographical data in the conversion unit 405. The acquisition unit 402 can narrow down the third topographical data it acquires to areas that are likely to become areas where events occur, thereby reducing the processing load.

[0077] Specifically, the acquiring unit 402 may set a plurality of second sections such that each second section overlaps with another second section among the plurality of second sections, thereby enabling the acquiring unit 402 to easily identify the area in which the event occurred using the identifying unit 406.

[0078] The acquisition unit 402, for example, acquires fifth terrain data representing the terrain before the occurrence of an event for each of a plurality of third sections that form the first region and that are the same size but different from the first sections. Specifically, the acquisition unit 402 may acquire first overall terrain data representing the terrain of the first region before the occurrence of an event. Specifically, the acquisition unit 402 divides the first overall terrain data to acquire fifth terrain data representing the terrain before the occurrence of an event for each of the plurality of third sections. In this way, the acquisition unit 402 can obtain information that serves as the basis for generating sixth terrain data in the analysis unit 403.

[0079] The acquisition unit 402 may acquire the sixth topographical data, for example, when the analysis unit 403 does not generate the sixth topographical data. Specifically, the acquisition unit 402 acquires sixth topographical data representing the topography after the occurrence of an event for each of the third sections. More specifically, the acquisition unit 402 may acquire second overall topographical data representing the topography after the occurrence of an event in the first region. Specifically, the acquisition unit 402 divides the acquired second overall topographical data to acquire sixth topographical data representing the topography after the occurrence of an event for each of the multiple third sections. This allows the acquisition unit 402 to enable the generation unit 404 to generate a conversion model.

[0080] The acquisition unit 402 acquires, for example, seventh terrain data representing the terrain before the occurrence of an event for each of a plurality of fourth sections that form the second region and that are the same size as the third sections. Specifically, the acquisition unit 402 may acquire second overall terrain data representing the terrain of the second region before the occurrence of an event. Specifically, the acquisition unit 402 divides the second overall terrain data to acquire seventh terrain data representing the terrain before the occurrence of an event for each of the plurality of fourth sections. This allows the acquisition unit 402 to obtain information that serves as the basis for generating the eighth terrain data in the conversion unit 405.

[0081] Specifically, the acquisition unit 402 may detect an area in the second region that satisfies an occurrence condition related to the event. Specifically, the acquisition unit 402 sets a plurality of fourth divisions that form the second region, each including at least a portion of the detected area. Specifically, the acquisition unit 402 divides the third overall terrain data to acquire seventh terrain data representing the terrain before the occurrence of the event for each of the set plurality of fourth divisions. This allows the acquisition unit 402 to obtain information that serves as the basis for generating the eighth terrain data in the conversion unit 405. The acquisition unit 402 can narrow down the acquired seventh terrain data to areas that are likely to become areas where the event occurs, thereby reducing the processing load.

[0082] Specifically, the acquiring unit 402 may set a plurality of fourth sections such that each fourth section overlaps with another fourth section among the plurality of fourth sections, thereby enabling the acquiring unit 402 to easily identify the area in which the event occurred using the identifying unit 406.

[0083] The acquisition unit 402 acquires environmental data. For example, the acquisition unit 402 acquires environmental data representing the environment of a first section. For example, the acquisition unit 402 acquires environmental data representing the environment of a second section. For example, the acquisition unit 402 acquires environmental data representing the environment of a third section. For example, the acquisition unit 402 acquires environmental data representing the environment of a fourth section.

[0084] The acquisition unit 402 may receive a start trigger that starts processing of one of the functional units. The start trigger may be, for example, a predetermined operational input by a user. The start trigger may be, for example, reception of predetermined information from another computer. The start trigger may be, for example, output of predetermined information by one of the functional units.

[0085] The acquisition unit 402 may, for example, receive the acquisition of the first topographical data as a start trigger for starting the processing of the analysis unit 403. The acquisition unit 402 may, for example, receive the acquisition of the second topographical data as a start trigger for starting the processing of the generation unit 404. The acquisition unit 402 may, for example, receive the acquisition of the third topographical data as a start trigger for starting the processing of the conversion unit 405.

[0086] The acquisition unit 402 may, for example, accept the acquisition of the fifth topographical data as a start trigger for starting the processing of the analysis unit 403. The acquisition unit 402 may, for example, accept the acquisition of the sixth topographical data as a start trigger for starting the processing of the generation unit 404. The acquisition unit 402 may, for example, accept the acquisition of the seventh topographical data as a start trigger for starting the processing of the conversion unit 405.

[0087] The analysis unit 403 generates a 3D model that imitates the terrain. The analysis unit 403 generates a 3D model for a plurality of first sections based on, for example, the first terrain data. The analysis unit 403 may generate a 3D model for a plurality of first sections based on, for example, first overall terrain data that represents the terrain of the first region before the occurrence of the event. This enables the analysis unit 403 to generate second terrain data.

[0088] The analysis unit 403 generates a 3D model for the plurality of third sections based on, for example, the fifth topographical data. The analysis unit 403 may generate a 3D model for the plurality of third sections based on, for example, first overall topographical data representing the topography of the first region before the occurrence of the event. The 3D model for the plurality of third sections may be the same 3D model as the 3D model for the plurality of first sections. This enables the analysis unit 403 to generate sixth topographical data.

[0089] The analysis unit 403 generates second topographical data for each of the first parcels using the generated 3D models for the multiple first parcels. The analysis unit 403 generates the second topographical data for each of the first parcels, for example, by applying a numerical simulation to the generated 3D models for the multiple first parcels using environmental data representing the environment of each of the first parcels. Specifically, the analysis unit 403 updates the 3D models for the multiple first parcels to a state after the occurrence of the event through the numerical simulation. Specifically, the analysis unit 403 generates second topographical data for each of the first parcels based on the updated 3D models for the multiple first parcels. This allows the analysis unit 403 to enable the generation unit 404 to generate a conversion model corresponding to the size of the first parcel.

[0090] The analysis unit 403 generates sixth topographical data for each of the third sections using the generated three-dimensional models for the multiple third sections. The analysis unit 403 generates the sixth topographical data for each of the third sections, for example, by applying a numerical simulation to the generated three-dimensional models for the multiple third sections using environmental data representing the environment of each of the third sections. Specifically, the analysis unit 403 updates the three-dimensional models for the multiple third sections to a state after the occurrence of the event through the numerical simulation. Specifically, the analysis unit 403 generates the sixth topographical data for each of the third sections based on the updated three-dimensional models for the multiple third sections. This allows the analysis unit 403 to enable the generation unit 404 to generate a conversion model corresponding to the size of the third section.

[0091] The generation unit 404 generates a conversion model that enables conversion of terrain data representing the terrain before an event occurs for a certain section into terrain data representing the terrain after the event occurs for that section. The conversion model is, for example, a CGAN. The conversion model is, for example, a neural network. The generation unit 404 generates a conversion model that corresponds to the size of the first section, for example, based on each piece of first terrain data and each piece of second terrain data. This enables the generation unit 404 to convert terrain data representing the terrain before an event occurs for other sections that are the same size as the first section into terrain data representing the terrain after the event occurs.

[0092] The generating unit 404 generates a conversion model corresponding to the size of the third section based on, for example, each of the fifth topographical data and each of the sixth topographical data, thereby enabling the generating unit 404 to convert topographical data representing the topography before the occurrence of an event into topographical data representing the topography after the occurrence of the event for other sections that are the same size as the third section.

[0093] The conversion unit 405 converts the third terrain data representing the terrain before the occurrence of an event for each of the plurality of second sections into fourth terrain data representing the terrain after the occurrence of the event for that second section, using a conversion model corresponding to the size of the generated first section. This allows the conversion unit 405 to reduce the processing load and processing time required when generating the fourth terrain data representing the terrain after the occurrence of an event for each of the second sections.

[0094] The conversion unit 405 converts the seventh terrain data representing the terrain before the occurrence of an event for each of the multiple fourth sections into eighth terrain data representing the terrain after the occurrence of the event for that fourth section, using a conversion model corresponding to the size of the generated third section. This allows the conversion unit 405 to reduce the processing load and processing time required when generating the eighth terrain data representing the terrain after the occurrence of an event for each of the fourth sections.

[0095] The identification unit 406 identifies an event occurrence area in the second region based on a pair of each piece of third topographical data and fourth topographical data obtained by converting each piece of third topographical data. The occurrence area is an area determined to have a relatively high probability of an event occurring. The occurrence area is, for example, an area determined to have a relatively high level of danger. For example, based on a pair of each piece of third topographical data and fourth topographical data obtained by converting each piece of third topographical data, the identification unit 406 identifies an area in the second region where the change in elevation before and after the event occurrence is equal to or greater than a threshold as a partial area that forms the event occurrence area. For example, the identification unit 406 identifies the entire area obtained by overlapping the identified partial areas as the event occurrence area. This allows the identification unit 406 to reduce the workload on the user when identifying the event occurrence area.

[0096] The identification unit 406 identifies an area in the second region where an event has occurred, based on a pair of each of the third topographical data and the fourth topographical data obtained by converting each of the third topographical data, and a pair of each of the seventh topographical data and the eighth topographical data obtained by converting each of the seventh topographical data. For example, based on a pair of each of the third topographical data and the fourth topographical data obtained by converting each of the third topographical data, the identification unit 406 identifies an area in the second region where the amount of change in elevation before and after the event has occurred is equal to or greater than a threshold, as a partial area forming the area where the event has occurred.

[0097] The identification unit 406, for example, based on a pair of each of the seventh topographical data and eighth topographical data obtained by converting each of the seventh topographical data, identifies, within the second region, an area in which the change in elevation before and after the occurrence of the event is equal to or greater than a threshold, as a partial area forming the area where the event occurred. For example, the identification unit 406 identifies, as the area where the event occurred, the entire area obtained by overlapping the identified partial areas. This allows the identification unit 406 to reduce the workload on the user when identifying the area where the event occurred.

[0098] The output unit 407 outputs the processing result of at least one of the functional units. The output format is, for example, display on a display, printout to a printer, transmission to an external device via the network I / F 303, or storage in a storage area such as the memory 302 or the recording medium 305. In this way, the output unit 407 can notify the user of the processing result of at least one of the functional units, thereby improving the convenience of the information processing device 100.

[0099] The output unit 407 outputs, for example, fourth terrain data representing the terrain after the occurrence of an event for each of the plurality of second sections forming the second region. Specifically, the output unit 407 outputs the fourth terrain data so that the user can refer to it. This allows the output unit 407 to use the fourth terrain data to make it easier to identify the area where the event occurred. Therefore, the output unit 407 can, for example, reduce the workload on the user.

[0100] The output unit 407 outputs, for example, eighth terrain data representing the terrain after the occurrence of an event for each of the multiple fourth sections forming the second region. Specifically, the output unit 407 outputs the eighth terrain data so that the user can refer to it. This allows the output unit 407 to use the eighth terrain data to make it easier to identify the area where the event occurred. Therefore, the output unit 407 can, for example, reduce the workload on the user.

[0101] The output unit 407 outputs, for example, the occurrence area of ​​the identified event. Specifically, the output unit 407 outputs the occurrence area of ​​the identified event so that the user can refer to it. In this way, the output unit 407 can enable the user to grasp the occurrence area of ​​the event. The output unit 407 can reduce the workload imposed on the user when identifying the occurrence area of ​​the event.

[0102] (Operation flow of information processing device 100) Next, the flow of operations of the information processing device 100 will be described with reference to FIGS.

[0103] 5 and 6 are explanatory diagrams showing the flow of operation of the information processing device 100. In FIG. 5, the information processing device 100 acquires pre-disaster digital elevation data 501 for each of a plurality of test sections into which a test area is divided, based on operational input from a user. There may be a plurality of test areas. The digital elevation data 501 is image-format data. For example, the digital elevation data 501 corresponds the latitude and longitude lengths of the test section to the vertical and horizontal lengths of the image, and expresses the elevation of each point in the test section by the color of each pixel in the image.

[0104] The information processing device 100 acquires environmental information 510 including geological information about the test area and rainfall information about the test area. The geological information includes, for example, soil thickness and ground strength. The soil thickness and ground strength are set by, for example, a user. The soil thickness and ground strength may be predicted from, for example, the shape of the ground surface. The shape of the ground surface may be identified by, for example, digital elevation data 501. The rainfall information includes, for example, the amount of rainfall. The amount of rainfall in the test plot may be set to, for example, the amount of rainfall in the test area.

[0105] The information processing device 100 generates a three-dimensional model 520 that imitates the topography of the test area before the disaster, based on the digital elevation data 501 of each test section before the disaster. Specifically, the information processing device 100 applies a numerical simulation using a particle method to the three-dimensional model 520 based on the acquired environmental information 510, thereby generating a three-dimensional model 521 that imitates the topography of the test area after the disaster. For details about the particle method, see Non-Patent Document 4 mentioned above.

[0106] As a result, the information processing device 100 can accurately simulate the behavior of a disaster such as a landslide by applying a particle-based numerical simulation that can model in detail the topography and ground characteristics, external factors, etc., to the three-dimensional model 520. As a result, the information processing device 100 can generate a three-dimensional model 521 that accurately simulates the topography of the test area after a disaster occurs.

[0107] The information processing device 100 generates digital elevation data 502 for each test section after the occurrence of a disaster, based on the generated three-dimensional model 521. The information processing device 100 may also generate deposition state data 503 indicating the deposition state of sediment flow in each test section after the occurrence of a disaster, based on the generated three-dimensional model 521.

[0108] This enables the information processing device 100 to generate the surrogate model 600 shown in Fig. 6. The information processing device 100 can generate, for example, digital elevation data 501 of the test section before the disaster occurs, which serves as an input sample for the surrogate model 600 shown in Fig. 6, and digital elevation data 502 of the test section after the disaster occurs, which serves as an output sample for the surrogate model 600 shown in Fig. 6. If there are multiple test areas, the information processing device 100 can generate the surrogate model 600 shown in Fig. 6 so as to be able to deal with various areas, taking into account different topography or different ground characteristics, etc. Next, we will move on to an explanation of Fig. 6.

[0109] 6, for example, the information processing device 100 sets, for each test plot, digital elevation data 501 of the test plot before the disaster occurred and environmental information 510 as input samples of the proxy model 600. For example, the information processing device 100 sets, for each test plot, digital elevation data 502 of the test plot after the disaster occurred as output samples of the proxy model 600. For example, the information processing device 100 may further set, for each test plot, deposition state data 503 indicating the deposition state of flow sediment in the test plot after the disaster occurred as output samples of the proxy model 600.

[0110] For example, the information processing device 100 sets a combination of the input sample and output sample set for each test section as training data. The information processing device 100 generates a surrogate model 600 based on the training data through machine learning. The surrogate model 600 has a function that enables conversion of digital elevation data for a certain section before a disaster occurs into digital elevation data for the certain section after the disaster occurs. For example, the surrogate model 600 has a function that outputs digital elevation data for the certain section after a disaster occurs in response to input of digital elevation data for the certain section before a disaster occurs and environmental information 510 for the certain section.

[0111] For example, the surrogate model 600 may have a function of outputting deposition state data in addition to digital elevation data of a certain section after a disaster occurs, in response to input of the digital elevation data of the certain section before a disaster occurs and the environmental information 510 of the certain section. The surrogate model 600 is a model that makes it possible to generate digital elevation data of a certain section after a disaster occurs and to predict the topographical condition of a certain section after a disaster occurs, without performing a numerical simulation.

[0112] The information processing device 100 generates the proxy model 600 so that the proxy model 600 outputs the digital elevation data 502 included in the training data in accordance with the digital elevation data 501 included in the training data and the environmental information 510. For details of the generation, see Non-Patent Document 6 below.

[0113] Non-Patent Document 6: Isola, Phillip, et al. “Image-to-image translation with conditional adversarial networks.” Proceedings of the IEEE conference on computer vision and pattern recognition. 2017.

[0114] For example, the information processing device 100 may generate the proxy model 600 so that the proxy model 600 outputs the digital elevation data 502 and the deposition state data 503 included in the training data in accordance with the digital elevation data 501 and the environmental information 510 included in the training data. This enables the information processing device 100 to generate digital elevation data for a certain section after a disaster occurs and to predict the topographical condition of a certain section after a disaster occurs, without performing a numerical simulation.

[0115] Based on user input, the information processing device 100 acquires pre-disaster digital elevation data 601 for each of a plurality of target sections divided into a target area for which a disaster occurrence situation is desired to be predicted. The digital elevation data 601 is image data. For example, the digital elevation data 601 corresponds the latitudinal and longitudinal lengths of the target section to the vertical and horizontal lengths of the image, and expresses the elevation of each point in the target section by the color of each pixel in the image. The information processing device 100 acquires environmental information 610 including geological information about the target area and rainfall information about the target area.

[0116] For each target section, the information processing device 100 inputs pre-disaster digital elevation data 601 for the target section and environmental information 610 into the generated proxy model 600. For each target section, the information processing device 100 acquires post-disaster digital elevation data 602 for the target section, which is output by the proxy model 600 in response to the input. The information processing device 100 may also acquire deposition state data 603 for each target section, which is output by the proxy model 600 in response to the input and indicates the deposition state of sediment flow in the target section after the disaster occurs.

[0117] This allows the information processing device 100 to suppress increases in the processing load and processing time required when acquiring post-disaster digital elevation data 602 for each target section of a target area. For example, the information processing device 100 can avoid having to perform a numerical simulation when acquiring post-disaster digital elevation data 602 for each target section of a target area. Therefore, the information processing device 100 can reduce the workload on the user.

[0118] The information processing device 100 may identify, within the target area, a risk area that is determined to have a relatively high probability of a disaster occurring, based on the post-disaster digital elevation data 602 of each target section. The information processing device 100, for example, calculates the amount of change in elevation of each point in each target section, based on the pre-disaster digital elevation data 601 of the target section and the post-disaster digital elevation data 602. The information processing device 100, for example, identifies, within each target section, an area represented by a point cloud where the calculated amount of change in elevation is equal to or greater than a threshold, as part of the risk area.

[0119] The information processing device 100 overlaps the identified portions of each target section to identify a risk area within the target area. The information processing device 100 outputs the identified risk area so that the user can refer to it. This allows the information processing device 100 to reduce the workload imposed on the user when identifying a risk area. The information processing device 100 makes it easier for the user to identify a risk area.

[0120] In this way, the information processing device 100 can avoid performing a numerical simulation even if the target section is relatively large, thereby reducing the processing load and processing time. Similarly, the information processing device 100 can avoid performing a numerical simulation even if there are multiple target sections, thereby reducing the processing load and processing time. Therefore, the information processing device 100 can easily realize the process of identifying a dangerous area even when the target section is relatively large or when there are multiple target sections. The information processing device 100 can accurately identify a dangerous area regardless of whether a disaster has occurred in the target section in the past.

[0121] (An example of the operation of the information processing device 100) Next, an example of the operation of the information processing device 100 will be described with reference to Figures 7 to 11. First, with reference to Figure 7, an example will be described in which the information processing device 100 performs a numerical simulation based on digital elevation data 701 before a disaster occurs, and generates digital elevation data 702 after a disaster occurs.

[0122] FIG. 7 is an explanatory diagram showing an example of generating digital elevation data 702 after a disaster occurs. In FIG. 7, the information processing device 100 divides the area α into a plurality of large patches A, each of which is at a first scale. The area α is a rectangular region. The large patches A correspond to the rectangular sections that make up the area α. The information processing device 100 divides the area α into a plurality of small patches a, each of which is at a second scale. The second scale indicates a size smaller than the first scale. The small patches a correspond to the rectangular sections that make up the area α.

[0123] The information processing device 100 acquires pre-disaster digital elevation data 701 for each large patch A. Based on the pre-disaster digital elevation data 701 for each large patch A, the information processing device 100 generates a three-dimensional model 710 that imitates the topography of the area α before the disaster.

[0124] The information processing device 100 generates a 3D model 711 that simulates the topography of the area α after the occurrence of a disaster, by applying a numerical simulation using a particle method, taking into account the amount of rainfall, to the generated 3D model 710. The information processing device 100 generates digital elevation data 702 for each large patch A after the occurrence of a disaster, based on the generated 3D model 711.

[0125] Similarly, the information processing device 100 acquires pre-disaster digital elevation data 701 for each small patch a. Based on the pre-disaster digital elevation data 701 for each small patch a, the information processing device 100 generates a three-dimensional model 710 that imitates the topography of area α before the disaster.

[0126] The information processing device 100 generates a 3D model 711 that mimics the topography of area a after a disaster occurs by applying a numerical simulation using a particle method to the generated 3D model 710, taking into account the amount of rainfall. The information processing device 100 generates digital elevation data 702 after a disaster occurs for each small patch a, based on the generated 3D model 711. Next, an example of the information processing device 100 generating a proxy model 800 will be described with reference to FIG. 8.

[0127] Fig. 8 is an explanatory diagram showing an example of generating a proxy model 800. In Fig. 8, the information processing device 100 generates, by machine learning, the proxy model 800 corresponding to the first scale based on the digital elevation data 701 of each large patch A before the occurrence of the disaster and the digital elevation data 702 of each large patch A after the occurrence of the disaster.

[0128] Similarly, the information processing device 100 generates, by machine learning, a proxy model 800 corresponding to the second scale based on the pre-disaster digital elevation data 701 of each small patch a and the post-disaster digital elevation data 702 of each small patch a. Next, an example will be described with reference to Fig. 9 in which the information processing device 100 divides a specified target area 900 in response to receiving designation of the target area 900.

[0129] Fig. 9 is an explanatory diagram showing an example of dividing a target area 900. In Fig. 9, the information processing device 100 accepts the designation of the target area 900. The information processing device 100 identifies a ridge topography 901 in the target area 900. The information processing device 100 identifies a line 902 that represents the ridge topography 901.

[0130] As indicated by the reference numeral 910, the information processing device 100 sets a plurality of overlapping large patches 911, 912 in the target area 900, each of which is at a first scale and includes at least a portion of the line 902. The information processing device 100 acquires digital elevation data of the large patches 911, 912 before the occurrence of the disaster.

[0131] Similarly, as indicated by the reference numeral 920, the information processing device 100 sets a plurality of overlapping small patches 921-923 in the target area 900, each of which is at the second scale and includes at least a portion of the line 902. The information processing device 100 acquires digital elevation data of the small patches 921-923 before the disaster occurred.

[0132] As a result, the information processing device 100 can reduce the number of large patches to be subsequently processed and the number of small patches to be subsequently processed, thereby reducing the processing load and processing time. Next, an example in which the information processing device 100 applies the proxy model 800 will be described with reference to FIG.

[0133] Fig. 10 is an explanatory diagram showing an example of application of a proxy model 800. In Fig. 10, the information processing device 100 inputs pre-disaster digital elevation data 1000 of the small patch 921 to the proxy model 800 corresponding to the second scale, taking into account the amount of rainfall. In response to the input, the information processing device 100 acquires post-disaster digital elevation data 1001 of the small patch 921 output from the proxy model 800 corresponding to the second scale.

[0134] The information processing device 100 identifies a partial region of the risk area included in the small patch 921 based on the digital elevation data 1000 and the digital elevation data 1001. For example, the information processing device 100 identifies, as a partial region of the risk area, a region of the small patch 921 where the absolute value of the difference in elevation before and after the occurrence of a disaster is equal to or greater than a threshold value, based on the digital elevation data 1000 and the digital elevation data 1001. Specifically, as shown in the X-X' cross section 1010 corresponding to the digital elevation data 1000 and the X-X' cross section 1011 corresponding to the digital elevation data 1001, the region where the absolute value of the difference in elevation before and after the occurrence of a disaster is equal to or greater than a threshold value is the partial region of the risk area.

[0135] 10, the information processing device 100 specifically identifies a partial area 1021 of the landslide risk area that is included in the small patch 921. Similarly, the information processing device 100 identifies a partial area 1122 of the landslide risk area that is included in the small patch 922 and will be described later in FIG. 11. Similarly, the information processing device 100 identifies a partial area 1123 of the landslide risk area that is included in the small patch 923 and will be described later in FIG. 11.

[0136] Similarly, the information processing device 100 identifies a partial area 1111 of the landslide risk area, which is included in the large patch 911 and will be described later in Fig. 11. Similarly, the information processing device 100 identifies a partial area 1112 of the landslide risk area, which is included in the large patch 912 and will be described later in Fig. 11. Next, an example in which the information processing device 100 superimposes risk areas will be described with reference to Fig. 11.

[0137] Fig. 11 is an explanatory diagram showing an example of superimposing risk areas. In Fig. 11, the information processing device 100 superimposes identified partial areas to identify a risk area included in the target area 900. In the example of Fig. 11, the information processing device 100 superimposes partial areas 1021, 1111, 1112, 1122, and 1123 to identify a risk area included in the target area 900.

[0138] This allows the information processing device 100 to reduce the processing load and processing time required to identify a risk area. Because the information processing device 100 sets small patches to overlap, it can easily prevent failure to identify a risk area that exists near the boundary between small patches. Similarly, because the information processing device 100 sets large patches to overlap, it can easily prevent failure to identify a risk area that exists near the boundary between large patches.

[0139] Here, the case where the information processing device 100 sets two types of patches, a large patch of a first scale and a small patch of a second scale, has been described, but the present invention is not limited to this. For example, the information processing device 100 may set three or more types of patches.

[0140] (Generation process procedure) Next, an example of a generation process procedure executed by the information processing device 100 will be described with reference to Fig. 12. The generation process is realized by, for example, the CPU 301, storage areas such as the memory 302 and the recording medium 305, and the network I / F 303 shown in Fig. 3.

[0141] Fig. 12 is a flowchart showing an example of a generation process procedure. In Fig. 12, the information processing device 100 acquires elevation image data before the occurrence of a disaster corresponding to each of a plurality of first patches, each of which is a first scale obtained by dividing the test area (step S1201). The information processing device 100 also acquires elevation image data before the occurrence of a disaster corresponding to each of a plurality of second patches, each of which is a second scale obtained by dividing the test area (step S1202).

[0142] Next, the information processing device 100 performs a numerical simulation based on the pre-disaster elevation image data corresponding to each of the first patches, and generates post-disaster elevation image data corresponding to each of the first patches (step S1203).Furthermore, the information processing device 100 performs a numerical simulation based on the pre-disaster elevation image data corresponding to each of the second patches, and generates post-disaster elevation image data corresponding to each of the second patches (step S1204).

[0143] Then, the information processing device 100 generates a first proxy model corresponding to the first scale based on the elevation image data before the disaster and the elevation image data after the disaster corresponding to each first patch (step S1205). Furthermore, the information processing device 100 generates a second proxy model corresponding to the second scale based on the elevation image data before the disaster and the elevation image data after the disaster corresponding to each second patch (step S1206). Then, the information processing device 100 ends the generation process. This allows the information processing device 100 to identify dangerous areas.

[0144] (Application procedure) Next, an example of an application processing procedure executed by the information processing device 100 will be described with reference to Fig. 13. The application processing is realized by, for example, the CPU 301, storage areas such as the memory 302 and the recording medium 305, and the network I / F 303 shown in Fig. 3.

[0145] 13 is a flowchart showing an example of an application process procedure, in which the information processing device 100 acquires elevation image data before the occurrence of a disaster that corresponds to the application area (step S1301).

[0146] Next, the information processing device 100 divides the application area into a plurality of first patches, each of which has a first scale (step S1302), and further divides the application area into a plurality of second patches, each of which has a second scale (step S1303).

[0147] Next, the information processing device 100 identifies a target area corresponding to the ridge in the application area (step S1304). Then, the information processing device 100 identifies a first patch that includes at least a part of the identified target area from among the multiple first patches (step S1305). Furthermore, the information processing device 100 identifies a second patch that includes at least a part of the identified target area from among the multiple second patches (step S1306).

[0148] Next, the information processing device 100 generates pre-disaster elevation image data corresponding to each of the identified first patches based on the pre-disaster elevation image data corresponding to the application area (step S1307).Furthermore, the information processing device 100 generates pre-disaster elevation image data corresponding to each of the identified second patches based on the pre-disaster elevation image data corresponding to the application area (step S1308).

[0149] Then, the information processing device 100 applies a first proxy model corresponding to the first scale to the pre-disaster elevation image data corresponding to each identified first patch, thereby generating post-disaster elevation image data corresponding to the first patch (step S1309).Furthermore, the information processing device 100 applies a second proxy model corresponding to the second scale to the pre-disaster elevation image data corresponding to each identified second patch, thereby generating post-disaster elevation image data corresponding to the second patch (step S1310).

[0150] Next, the information processing device 100 identifies a danger area in each of the generated first patches based on the post-disaster elevation image data corresponding to the first patches (step S1311).Furthermore, the information processing device 100 identifies a danger area in each of the generated second patches based on the post-disaster elevation image data corresponding to the second patches (step S1312).

[0151] Then, the information processing apparatus 100 identifies risk areas in the application area based on the identified risk areas in each of the first patches and the identified risk areas in each of the second patches (step S1313).

[0152] Next, the information processing device 100 outputs the risk area in the identified application area so that it can be referenced by the user (step S1314). Then, the information processing device 100 ends the application process. This allows the information processing device 100 to identify the risk area. The information processing device 100 can reduce the processing load and processing time required to identify the risk area.

[0153] Here, the information processing device 100 may change the order of the processes of some of the steps in the flowcharts of Figures 12 and 13. For example, the order of the processes of steps S1201 and S1202 can be changed. Furthermore, the information processing device 100 may omit some of the processes of some of the steps in the flowcharts of Figures 12 and 13. For example, the processes of steps S1313 and S1314 can be omitted.

[0154] As described above, the information processing device 100 can acquire second terrain data representing the terrain after the occurrence of an event for each first section. The information processing device 100 can generate a conversion model based on each of the first terrain data and each of the second terrain data. The information processing device 100 can convert third terrain data representing the terrain before the occurrence of an event for each second section into fourth terrain data representing the terrain after the occurrence of the event for the second section using the generated conversion model, and output the fourth terrain data. This allows the information processing device 100 to reduce the processing load and processing time required when generating the fourth terrain data.

[0155] The information processing device 100 can generate a three-dimensional model based on the first topographical data. The information processing device 100 can generate second topographical data for each of the first parcels by applying a numerical simulation to the generated three-dimensional model using environmental data that represents the environment of each of the first parcels. This enables the information processing device 100 to generate a conversion model.

[0156] According to the information processing device 100, it is possible to identify and output an area in the second region where an event has occurred, based on a set of each piece of third topographical data and fourth topographical data obtained by converting each piece of third topographical data. This allows the information processing device 100 to make the area where the event has occurred referable. The information processing device 100 can reduce the workload imposed on the user when identifying the area where the event has occurred.

[0157] The information processing device 100 can acquire sixth topographical data representing the topography of each third section after the occurrence of an event. The information processing device 100 can generate other conversion models based on the fifth topographical data and the sixth topographical data. The information processing device 100 can convert seventh topographical data representing the topography of each fourth section before the occurrence of an event into eighth topographical data representing the topography of the fourth section after the occurrence of an event, using the generated other conversion model. The information processing device 100 can identify and output an area in the second region where an event has occurred based on a pair of each third topographical data and each fourth topographical data, and a pair of each seventh topographical data and each eighth topographical data. This allows the information processing device 100 to make the area in which an event has occurred referable. The information processing device 100 can reduce the workload imposed on the user when identifying the area in which an event has occurred.

[0158] According to the information processing device 100, it is possible to generate another three-dimensional model based on the fifth topographical data. According to the information processing device 100, it is possible to generate sixth topographical data for each of the third sections by applying a numerical simulation to the generated other three-dimensional model using environmental data that represents the environment of each of the third sections. This enables the information processing device 100 to generate another conversion model.

[0159] The information processing device 100 can detect an area in the second region that satisfies an occurrence condition related to an event. The information processing device 100 can set a plurality of second sections that form the second region, each including at least a portion of the detected area. The information processing device 100 can set a plurality of fourth sections that form the second region, each including at least a portion of the detected area. This allows the information processing device 100 to reduce the processing load and processing time required when identifying the area where the event occurs.

[0160] According to the information processing device 100, a plurality of second sections can be set so that each second section overlaps with another second section among the plurality of second sections. According to the information processing device 100, a plurality of fourth sections can be set so that each fourth section overlaps with another fourth section among the plurality of fourth sections. This makes it easier for the information processing device 100 to accurately identify the area where an event has occurred.

[0161] According to the information processing device 100, it is possible to adopt a landslide as the event. According to the information processing device 100, it is possible to adopt, as the first topographical data, image format data that indicates, by color, the elevation of the topography of the first section before the occurrence of an event. According to the information processing device 100, it is possible to adopt, as the environment, rainfall conditions. According to the information processing device 100, it is possible to adopt, as the second topographical data, image format data that indicates, by color, the elevation of the topography of the first section after the occurrence of an event. According to the information processing device 100, it is possible to adopt, as the third topographical data, image format data that indicates, by color, the elevation of the topography of the second section before the occurrence of an event. According to the information processing device 100, it is possible to adopt, as the fourth topographical data, image format data that indicates, by color, the elevation of the topography of the second section after the occurrence of an event. This makes it possible for the information processing device 100 to be applied to the field of landslide disasters.

[0162] The information processing method described in this embodiment can be realized by executing a prepared program on a computer such as a PC or a workstation. The information processing program described in this embodiment is recorded on a computer-readable recording medium and executed by being read from the recording medium by the computer. The recording medium may be a hard disk, a flexible disk, a CD (Compact Disc)-ROM, an MO (Magneto Optical disc), a DVD (Digital Versatile Disc), or the like. The information processing program described in this embodiment may also be distributed via a network such as the Internet.

[0163] The following additional notes are provided regarding the above-described embodiment.

[0164] (Supplementary Note 1) Acquire second topographical data representing the topography of each of a plurality of first sections, each of which is the same size and forms a first region, after the occurrence of the event, the second topographical data being generated by applying a numerical simulation using environmental data representing the environment of each of the first sections to a three-dimensional model representing the topography of the first region, the three-dimensional model being based on first topographical data representing the topography of each of the first sections before the occurrence of the event; generating a conversion model that enables conversion of terrain data representing a terrain before the occurrence of the event for a certain section into terrain data representing a terrain after the occurrence of the event for the certain section, based on each of the first terrain data and each of the second terrain data; converting third topography data representing the topography before the occurrence of the event for each of a plurality of second sections, each of which is the same size as the first section and forms a second region, into fourth topography data representing the topography after the occurrence of the event for each of the second sections using the generated conversion model, and outputting the fourth topography data; An information processing program that causes a computer to execute a process.

[0165] (Supplementary Note 2) The three-dimensional model is generated based on the first topographical data. causing the computer to execute a process; The process of acquiring the second topographical data includes: An information processing program as described in Appendix 1, characterized in that the second topographical data is generated for each of the first sections by applying a numerical simulation to the generated three-dimensional model using environmental data representing the environment of each of the first sections.

[0166] (Supplementary Note 3) Based on a pair of each of the third topographical data and the fourth topographical data obtained by converting each of the third topographical data, an occurrence area of ​​the event in the second region is identified and output. 3. The information processing program according to claim 1 or 2, which causes the computer to execute the processing.

[0167] (Supplementary Note 4) acquiring sixth topographical data representing the topography of each of a plurality of third sections that form the first area, each of which has a size different from that of the first section but is the same size as the first section, generated by applying a numerical simulation using environmental data representing the environment of each of the third sections to another three-dimensional model that represents the topography of the first area, the sixth topographical data representing the topography of each of the third sections after the occurrence of the event; generating another conversion model that enables conversion of terrain data representing a terrain before the occurrence of the event for a certain section into terrain data representing a terrain after the occurrence of the event for the certain section, based on each of the fifth terrain data and each of the sixth terrain data; converting seventh topographical data representing the topography before the occurrence of the event for each of a plurality of fourth sections, each of which is the same size as the third section and which form the second region, into eighth topographical data representing the topography after the occurrence of the event for the fourth section, using the other conversion model that has been generated; causing the computer to execute a process; The output process includes: The information processing program according to claim 3, characterized in that the area in which the event occurred within the second region is identified and output based on a pair of each of the third topographical data and the fourth topographical data obtained by converting each of the third topographical data, and a pair of each of the seventh topographical data and the eighth topographical data obtained by converting each of the seventh topographical data.

[0168] (Appendix 5) The other three-dimensional model is generated based on the fifth topographical data. causing the computer to execute a process; The process of acquiring the sixth topographical data includes: An information processing program as described in Appendix 4, characterized in that the sixth topographical data is generated for each of the third sections by applying a numerical simulation using environmental data representing the environment of each of the third sections to the generated other three-dimensional models.

[0169] (Appendix 6) Detecting an area in the second region that satisfies the occurrence condition for the event; setting the plurality of second sections, each including at least a portion of the detected area, to form the second region; setting the plurality of fourth sections, each including at least a portion of the detected area, to form the second region; 6. The information processing program according to claim 4 or 5, which causes the computer to execute the processing.

[0170] (Supplementary Note 7) The plurality of second sections are set so that each of the second sections overlaps with another second section among the plurality of second sections; setting the plurality of fourth sections so that each of the fourth sections overlaps with another fourth section among the plurality of fourth sections; 7. The information processing program according to any one of claims 4 to 6, which causes the computer to execute the process.

[0171] (Appendix 8) The event is a sediment flow, the first topographical data is image data that indicates, by color, the elevation of the topography of the first section before the occurrence of the event; the environment is a rainy condition, the second topographical data is image data that indicates, by color, the elevation of the topography of the first section after the occurrence of the event; the third topographical data is image data that indicates, by color, the elevation of the topography of the second section before the occurrence of the event; The information processing program according to any one of appendices 1 to 7, wherein the fourth terrain data is image format data that indicates the elevation of the terrain of the second section after the occurrence of the event using color.

[0172] (Supplementary Note 9) Acquire second topographical data representing the topography of each of a plurality of first sections, each of which is the same size and forms a first region, after the occurrence of the event, the second topographical data being generated by applying a numerical simulation using environmental data representing the environment of each of the first sections to a three-dimensional model representing the topography of the first region, the three-dimensional model being based on first topographical data representing the topography of each of the first sections before the occurrence of the event; generating a conversion model that enables conversion of terrain data representing a terrain before the occurrence of the event for a certain section into terrain data representing a terrain after the occurrence of the event for the certain section, based on each of the first terrain data and each of the second terrain data; converting third topography data representing the topography before the occurrence of the event for each of a plurality of second sections, each of which is the same size as the first section and forms a second region, into fourth topography data representing the topography after the occurrence of the event for each of the second sections using the generated conversion model, and outputting the fourth topography data; An information processing method characterized in that the processing is executed by a computer.

[0173] (Supplementary Note 10) Acquire second topographical data representing the topography of each of a plurality of first sections, each of which is the same size and forms a first region, after the occurrence of the event, the second topographical data being generated by applying a numerical simulation using environmental data representing the environment of each of the first sections to a three-dimensional model representing the topography of the first region, the three-dimensional model being based on first topographical data representing the topography of each of the first sections before the occurrence of the event; generating a conversion model that enables conversion of terrain data representing a terrain before the occurrence of the event for a certain section into terrain data representing a terrain after the occurrence of the event for the certain section, based on each of the first terrain data and each of the second terrain data; converting third topography data representing the topography before the occurrence of the event for each of a plurality of second sections, each of which is the same size as the first section and forms a second region, into fourth topography data representing the topography after the occurrence of the event for each of the second sections using the generated conversion model, and outputting the fourth topography data; An information processing device comprising a control unit. [Explanation of symbols]

[0174] 100 Information processing device 101 First Topographic Data 102 Second Topographic Data 103 Third Topographic Data 104 4th Topographic Data 110,520,521,710,711 3D models 120 conversion model 200 Information Processing Systems 201 Numerical Analysis Equipment 202 Client device 210 Network 300 Bus 301 CPU 302 memory 303 Network I / F 304 Recording Media I / F 305 Recording Media 401 Storage section 402 Acquisition Department 403 Analysis Department 404 Generator 405 Conversion Unit 406 Specific part 407 Output Section 501,502,601,602,701,702,1000,1001 Digital elevation data 503,603 Sedimentary state data 510,610 Environmental information 600,800 Substitute Model 900 Target Areas 901 Ridge terrain 902 line 910,920 code 911,912 Large Patch 921~923 Small Patch 1010,1011 cross section 1021,1111,1112,1122,1123 partial area

Claims

1. acquiring second topographical data representing the topography of each of a plurality of first sections, each of which is the same size and forms a first area, after the occurrence of the event, the second topographical data being generated by applying a numerical simulation using environmental data representing the environment of each of the first sections to a three-dimensional model representing the topography of the first area, the three-dimensional model being based on first topographical data representing the topography of each of the first sections before the occurrence of the event; generating a conversion model that can convert topographical data representing the topography of a certain section before the occurrence of the event into topographical data representing the topography of the certain section after the occurrence of the event without using environmental data representing the environment of the certain section, by training the conversion model so that each of the first topographical data is converted into each of the second topographical data in response to an input of each of the first topographical data; converting third topography data representing the topography before the occurrence of the event for each of a plurality of second sections, each of which is the same size as the first section and which form a second region, into fourth topography data representing the topography after the occurrence of the event for each of the second sections using the generated conversion model, and outputting the fourth topography data; An information processing program that causes a computer to execute a process.

2. generating the three-dimensional model based on the first topographical data; causing the computer to execute a process; The process of acquiring the second topographical data includes: The information processing program according to claim 1, characterized in that the second topographical data is generated for each of the first sections by applying a numerical simulation to the generated three-dimensional model using environmental data representing the environment of each of the first sections.

3. identifying and outputting an occurrence area of ​​the event in the second region based on a pair of each of the third topographical data and the fourth topographical data obtained by converting each of the third topographical data; 3. The information processing program according to claim 1, wherein the information processing program causes the computer to execute processing.

4. acquiring sixth topographical data representing the topography of each of a plurality of third sections that form the first area, each of which has a size different from that of the first section but is the same size as the first section, after the occurrence of the event, the sixth topographical data being generated by applying a numerical simulation using environmental data representing the environment of each of the third sections to another three-dimensional model that represents the topography of the first area, the fifth topographical data representing the topography of each of the third sections before the occurrence of the event; generating another conversion model that can convert topographical data representing the topography of a certain section before the occurrence of the event into topographical data representing the topography of the certain section after the occurrence of the event without using environmental data representing the environment of the certain section, by training the model so that each of the fifth topographical data is converted into each of the sixth topographical data in response to an input of each of the fifth topographical data; converting seventh topographical data representing the topography before the occurrence of the event for each of a plurality of fourth sections, each of which is the same size as the third section and which form the second area, into eighth topographical data representing the topography after the occurrence of the event for the fourth section, using the other conversion model that has been generated; causing the computer to execute a process; The output process includes:

4. The information processing program according to claim 3, wherein an area in which the event occurs within the second region is identified and output based on a pair of each of the third topographical data and the fourth topographical data obtained by converting each of the third topographical data, and a pair of each of the seventh topographical data and the eighth topographical data obtained by converting each of the seventh topographical data.

5. generating the other three-dimensional model based on the fifth topographical data; causing the computer to execute a process; The process of acquiring the sixth topographical data includes: The information processing program according to claim 4, characterized in that the sixth topographical data is generated for each of the third sections by applying a numerical simulation to the generated other three-dimensional model using environmental data representing the environment of each of the third sections.

6. detecting an area in the second region that satisfies an occurrence condition related to the event; setting the plurality of second sections that form the second region and each include at least a portion of the detected area; setting the plurality of fourth sections, each including at least a portion of the detected area, to form the second region; 6. The information processing program according to claim 4, wherein the program causes the computer to execute processing.

7. setting the plurality of second sections such that each of the second sections overlaps with another of the plurality of second sections; setting the plurality of fourth sections such that each of the fourth sections overlaps with another fourth section among the plurality of fourth sections; 6. The information processing program according to claim 4, wherein the program causes the computer to execute processing.

8. acquiring second topographical data representing the topography of each of a plurality of first sections, each of which is the same size and forms a first area, after the occurrence of the event, the second topographical data being generated by applying a numerical simulation using environmental data representing the environment of each of the first sections to a three-dimensional model representing the topography of the first area, the three-dimensional model being based on first topographical data representing the topography of each of the first sections before the occurrence of the event; generating a conversion model that can convert topographical data representing the topography of a certain section before the occurrence of the event into topographical data representing the topography of the certain section after the occurrence of the event without using environmental data representing the environment of the certain section, by training the conversion model so that each of the first topographical data is converted into each of the second topographical data in response to an input of each of the first topographical data; converting third topography data representing the topography before the occurrence of the event for each of a plurality of second sections, each of which is the same size as the first section and which form a second region, into fourth topography data representing the topography after the occurrence of the event for each of the second sections using the generated conversion model, and outputting the fourth topography data; An information processing method characterized in that the processing is executed by a computer.

9. acquiring second topographical data representing the topography of each of a plurality of first sections, each of which is the same size and forms a first area, after the occurrence of the event, the second topographical data being generated by applying a numerical simulation using environmental data representing the environment of each of the first sections to a three-dimensional model representing the topography of the first area, the three-dimensional model being based on first topographical data representing the topography of each of the first sections before the occurrence of the event; generating a conversion model that can convert topographical data representing the topography of a certain section before the occurrence of the event into topographical data representing the topography of the certain section after the occurrence of the event without using environmental data representing the environment of the certain section, by training the conversion model so that each of the first topographical data is converted into each of the second topographical data in response to an input of each of the first topographical data; converting third topography data representing the topography before the occurrence of the event for each of a plurality of second sections, each of which is the same size as the first section and which form a second region, into fourth topography data representing the topography after the occurrence of the event for each of the second sections using the generated conversion model, and outputting the fourth topography data; An information processing device comprising a control unit.

Images