Seismic ground motion evaluation model generation method, seismic ground motion evaluation model generation device, seismic ground motion evaluation method, and seismic ground motion evaluation device

The seismic motion evaluation model uses machine learning and cluster analysis to generate a model that accurately predicts seismic motion indicators by incorporating interrelationships among multiple seismic motion characteristic parameters, addressing the limitations of conventional prediction formulas.

JP2024162658APending Publication Date: 2024-11-21SHIMIZU CORP

Patent Information

Application Number
JP2023078392
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-05-11
Publication Date
2024-11-21

AI Technical Summary

Technical Problem

Conventional earthquake motion prediction formulas fail to adequately incorporate interrelationships among various seismic motion characteristic parameters, including seismic source, propagation, site, and azimuth characteristics, leading to dispersion in prediction results.

Method used

A seismic motion evaluation model is generated through machine learning using a database of seismic motion data, performing cluster analysis to assign cluster identification parameters and learning correlations between feature amounts and objective variables, reflecting interrelationships among multiple seismic motion characteristic parameters.

Benefits of technology

This approach allows for high-accuracy evaluation and prediction of seismic motion indicators by easily and appropriately considering the interrelationships among various seismic motion characteristic parameters.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2024162658000001_ABST
    Figure 2024162658000001_ABST
Patent Text Reader

Abstract

To provide a seismic ground motion evaluation model generation method that makes it possible to evaluate and predict a seismic ground motion index with high accuracy by enabling the interrelationship between a plurality of seismic ground motion characteristics parameters to be easily and appropriately reflected.SOLUTION: A seismic ground motion evaluation model generation method includes: a cluster analysis step in which cluster analysis of seismic ground motion data is carried out on the basis of a first seismic ground motion characteristics parameter group included in seismic ground motion characteristics parameter groups and a cluster identification parameter is thereby assigned to each of a plurality of pieces of seismic ground motion data; an acquisition step in which training data composed of a feature amount and an objective variable are acquired in plurality, where a second seismic ground motion characteristics parameter group included in the seismic ground motion characteristics parameter groups and the cluster identification parameter are adopted as the feature amount, and a seismic ground motion index obtained from seismic ground motion waveforms is adopted as the objective variable; and a generation step in which a correlation relationship of the feature amount and the objective variable is learned by machine learning on the basis of the plurality of pieces of training data and a seismic ground motion evaluation model is generated as a machine learning trained model.SELECTED DRAWING: Figure 3
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to a method for generating an earthquake motion evaluation model, an apparatus for generating an earthquake motion evaluation model, an earthquake motion evaluation method, and an apparatus for evaluating earthquake motion. [Background technology]

[0002] Conventionally, as an example of a technique for evaluating and predicting seismic motion indexes such as the maximum amplitude of seismic motion (maximum acceleration, maximum velocity, maximum displacement), seismic motion prediction formulas created based on empirical knowledge obtained mainly from large earthquakes nationwide have been used (see, for example, Patent Document 1 and Non-Patent Document 1). In general, seismic motion prediction formulas use variables (seismic motion characteristic parameters) that are considered to have a large effect on seismic motion indexes, and are defined as formulas that are explained by about 4 to 6 variables, such as the magnitude of the earthquake, the epicenter distance, the epicenter depth, and the ground characteristics of the evaluation point. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2008-39446 A [Non-patent literature]

[0004] [Non-Patent Document 1] Nobuyuki Morikawa and Hiroyuki Fujiwara,A New Ground Motion Prediction Equation for Japan Applicable up to M9 Mega-Earthquake,Journal of Disaster Research,Vol.8,No.5,2013,p.878-888 Summary of the Invention [Problem to be solved by the invention]

[0005] Some of the existing earthquake motion prediction formulas have been proposed that categorize earthquakes according to the type of source fault (normal fault, reverse fault, strike-slip fault) and the type of earthquake (inland crustal earthquake, plate boundary earthquake, intraslab earthquake). However, there is a possibility that there are interrelationships between the various earthquake motion characteristic parameters that have not been sufficiently considered so far. In addition, the earthquake motion characteristic parameters include not only parameters related to source characteristics, but also parameters related to various characteristics such as propagation characteristics, site characteristics, and azimuth characteristics, and there is a possibility that there are interrelationships between the various earthquake motion characteristic parameters that have not been paid attention to so far. If such characteristics could be reflected in the evaluation and prediction of earthquake motion indices, there would be room to reduce the variance of the prediction results of earthquake motion indices, but there was a problem that it was difficult to incorporate them into the existing earthquake motion prediction formulas.

[0006] The present invention has been made in consideration of the above circumstances, and aims to provide a method and device for generating an earthquake motion evaluation model, a method and device for generating an earthquake motion evaluation model, which are capable of easily and appropriately reflecting the interrelationships between a plurality of earthquake motion characteristic parameters, and enabling evaluation and prediction of earthquake motion indices with high accuracy. [Means for solving the problem]

[0007] The present invention relates to a method for generating a seismic motion evaluation model, A method for generating a seismic motion evaluation model by machine learning using a computer, comprising: a cluster analysis step of referring to a database storing a plurality of pieces of earthquake motion data correlating earthquake motion waveforms caused by an earthquake with a group of earthquake motion characteristic parameters consisting of a plurality of types of earthquake motion characteristic parameters at the time when the earthquake motion waveforms were obtained, and performing a cluster analysis of the earthquake motion data based on a first group of earthquake motion characteristic parameters included in the group of earthquake motion characteristic parameters, thereby assigning cluster identification parameters to each of the plurality of pieces of earthquake motion data, and storing the data in the database; an acquisition step of acquiring, from the database, a second group of earthquake motion characteristic parameters included in the group of earthquake motion characteristic parameters and the cluster identification parameter as feature quantities, and an earthquake motion index obtained from the earthquake motion waveform as a response variable, a plurality of learning data sets configured with the feature quantities and the response variable; and a generation process of generating the seismic motion evaluation model as a trained model of the machine learning by learning the correlation between the feature values ​​and the objective variable through the machine learning based on the multiple learning data acquired in the acquisition process.

[0008] Moreover, the earthquake motion evaluation model generating device according to one embodiment of the present invention comprises: The computer includes a control unit that executes each step included in the method for generating a seismic motion evaluation model.

[0009] Further, a method for evaluating earthquake motion according to an embodiment of the present invention includes the steps of: A method for evaluating characteristics of the earthquake motion based on the earthquake motion evaluation model generated by the earthquake motion evaluation model generation method using a computer, comprising the steps of: a receiving step of receiving the group of earthquake motion characteristic parameters to be predicted; a cluster assignment step of assigning the cluster identification parameter based on the first group of earthquake motion characteristic parameters included in the group of earthquake motion characteristic parameters of the prediction target received in the receiving step; and a prediction process for predicting the seismic motion index corresponding to the seismic motion characteristic parameter group of the prediction target based on the objective variable output from the seismic motion evaluation model by inputting the second seismic motion characteristic parameter group included in the seismic motion characteristic parameter group of the prediction target received in the reception process and the cluster identification parameter assigned in the cluster assignment process into the seismic motion evaluation model as the feature amount.

[0010] Moreover, the earthquake motion evaluation device according to one embodiment of the present invention is The computer includes a control unit that executes each step included in the earthquake motion evaluation method. Effect of the Invention

[0011] According to the earthquake motion evaluation model generating method and earthquake motion evaluation model generating device according to an embodiment of the present invention, a cluster identification parameter assigned by performing cluster analysis of earthquake motion data based on a first earthquake motion characteristic parameter group included in the earthquake motion characteristic parameter group, and a second earthquake motion characteristic parameter group included in the earthquake motion characteristic parameter group are used as feature quantities, and a plurality of learning data are obtained that are configured with an earthquake motion index obtained from an earthquake motion waveform as a response variable. Then, based on the plurality of learning data, a correlation between the feature quantities and the response variable is learned by machine learning, and an earthquake motion evaluation model is generated as a machine learning trained model. Therefore, it is possible to generate an earthquake motion evaluation model that can easily and appropriately reflect the interrelationships between the plurality of earthquake motion characteristic parameters included in the first earthquake motion characteristic parameter group and can evaluate and predict the earthquake motion index with high accuracy.

[0012] According to the earthquake motion evaluation method and earthquake motion evaluation device of one embodiment of the present invention, by using the earthquake motion evaluation model generation device and the earthquake motion evaluation model generated by the earthquake motion evaluation model generation method, the cluster identification parameter assigned based on the first earthquake motion characteristic parameter group included in the earthquake motion characteristic parameter group of the prediction target and the second earthquake motion characteristic parameter group included in the earthquake motion characteristic parameter group of the prediction target are used as feature quantities to predict the earthquake motion index corresponding to the earthquake motion characteristic parameter group of the prediction target. Therefore, the interrelationships between the plurality of earthquake motion characteristic parameters included in the first earthquake motion characteristic parameter group are simply and appropriately reflected, and the earthquake motion index can be evaluated and predicted with high accuracy. [Brief description of the drawings]

[0013] [Figure 1] 1 is a schematic configuration diagram showing an example of a seismic motion evaluation system 1 according to an embodiment of the present invention. [Diagram 2] FIG. 1 is a block diagram showing an example of a seismic motion evaluation system 1 according to an embodiment of the present invention. [Diagram 3] FIG. 2 is a functional explanatory diagram showing an example of a seismic motion evaluation model generating device 3 and a seismic motion evaluation model generating method according to the embodiment of the present invention. [Figure 4] FIG. 2 is a data structure diagram showing an example of a database 10. [Diagram 5] FIG. 1 is a schematic diagram illustrating an example of cluster analysis. [Figure 6] FIG. 1 is a schematic diagram illustrating an example of a gradient boosting tree. [Figure 7] FIG. 2 is a functional explanatory diagram showing an example of a seismic motion evaluation device 4 and a seismic motion evaluation method according to the embodiment of the present invention. [Figure 8] FIG. 13 is a diagram showing the degree of influence of a group of earthquake motion characteristic parameters and a cluster identification parameter on the evaluation value of the earthquake motion index. [Figure 9] 1 is a scatter diagram showing the correlation between the “observed value” of the seismic motion index obtained from the seismic motion waveform and the “evaluated value” of the seismic motion index obtained by the seismic motion evaluation model 13. [Figure 10] FIG. 13 is a histogram showing the logarithmic value of “evaluation value / observation value” for each objective variable (seismic motion index). DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] Hereinafter, an embodiment of the present invention will be described with reference to the accompanying drawings.

[0015] Fig. 1 is a schematic configuration diagram showing an example of a seismic motion evaluation system 1 according to an embodiment of the present invention. Fig. 2 is a block diagram showing an example of the seismic motion evaluation system 1 according to an embodiment of the present invention.

[0016] The earthquake motion evaluation system 1 includes an observation data providing device 2A that collects earthquake motion waveforms as earthquake motion observation records obtained by observing earthquake motion caused by earthquakes at multiple observation points and provides the observation results to the outside, an analysis data providing device 2B that analyzes the epicenter and magnitude of the earthquake based on the earthquake motion waveforms and provides the analysis results to the outside, an underground structure data providing device 2C that provides to the outside underground structure parameters related to the underground structure used in evaluating and predicting earthquake motion, and an earthquake motion simulation data providing device 2D that executes an earthquake motion simulation according to a predetermined simulation method and provides to the outside the simulation conditions and simulation results at that time as simulation data.

[0017] The earthquake motion evaluation system 1 also includes an earthquake motion evaluation model generating device 3 that registers the data provided by the data providing devices 2A to 2D in a database 10 and generates an earthquake motion evaluation model 13 based on machine learning using the database 10, an earthquake motion evaluation device 4 that evaluates and predicts earthquake motion based on the earthquake motion evaluation model 13 generated by the earthquake motion evaluation model generating device 3, and a network 5 that connects each of the devices.

[0018] In this embodiment, the earthquake motion evaluation model 13 generated by the earthquake motion evaluation model generation device 3 is described as being used in the earthquake motion evaluation device 4, but it can be widely used in society, for example, from analysis and interpretation of earthquake motion characteristics to behavior prediction and structural design of buildings and structures, and even earthquake disaster prevention.

[0019] The observation data providing device 2A collects time history waveform data of three components in the north-south, east-west, and up-down directions measured by seismometers (not shown) installed at multiple observation points when an earthquake occurs, and provides observation data including the seismic waveform and additional information such as the observation point location indicating the location of the observation point to an external party. For example, data provided by the strong earthquake observation network K-NET of the National Research and Development Agency National Research Institute for Earth Science and Disaster Resilience (hereinafter referred to as "NIED") is used as the observation data. Note that in FIG. 1, 138 observation points (see FIG. 1) installed in one metropolis and six prefectures in the Kanto region (Tokyo, Kanagawa, Chiba, Saitama, Ibaraki, Tochigi, and Gunma) are shown as the observation points, but the locations and number of the observation points are not limited to these.

[0020] The analysis data providing device 2B analyzes the epicenter and scale of the earthquake based on the seismic motion waveform, and provides to the outside, as the analysis result, analysis data including, for example, moment magnitude, Japan Meteorological Agency magnitude, epicenter location, epicenter depth, earthquake type, fault type, and focal mechanism solution, etc. The analysis data used is, for example, data provided by the broadband earthquake observation network F-net of the National Research Institute for Earth Science and Disaster Prevention and the Japan Meteorological Agency.

[0021] The underground structure data providing device 2C externally provides underground structure data including, as underground structure parameters, for example, the depth of the seismic bedrock surface, the depth of the engineering bedrock surface, the layer thickness, the density, the seismic wave propagation velocity, the Q value, the attenuation constant, etc. As the underground structure data, for example, data provided by the earthquake hazard station J-SHIS of the National Research Institute for Earth Science and Disaster Prevention is used.

[0022] When an earthquake occurs, the observation data providing device 2A, the analysis data providing device 2B, and the underground structure data providing device 2C may provide data relating to the earthquake in real time to the earthquake motion evaluation model generating device 3, or when a data request is received from the earthquake motion evaluation model generating device 3, they may provide data relating to the request (which may be data relating to a plurality of earthquakes that have occurred in the past and meet a predetermined condition) to the earthquake motion evaluation model generating device 3. In the present embodiment, the data providing devices 2A to 2C are described as three separate devices, but this is not limiting and they may be configured as one device, or other data providing devices may be further added.

[0023] The earthquake motion simulation data providing device 2D analyzes earthquake motion caused by an earthquake according to a predetermined simulation method when an earthquake occurs or when a virtual earthquake is assumed to occur, and provides the simulation conditions and simulation results at that time to an external entity as simulation data. At that time, any method can be adopted as the predetermined simulation method, and multiple methods may be adopted. In addition, the earthquake motion simulation data providing device 2D may provide simulation data by executing an earthquake motion simulation in its own device, or may provide simulation data when an earthquake motion simulation is executed in another device.

[0024] In addition, when a new earthquake motion simulation is executed, the earthquake motion simulation data providing device 2D may provide simulation data related to the earthquake motion simulation to the earthquake motion evaluation model generation device 3 at any time, or when a data request is received from the earthquake motion evaluation model generation device 3, it may provide simulation data related to the request to the earthquake motion evaluation model generation device 3 (in the case where simulation conditions are received from the earthquake motion evaluation model generation device 3, simulation data including simulation results when an earthquake motion simulation is executed based on those simulation conditions) to the earthquake motion evaluation model generation device 3.

[0025] The network 5 communicates various data and signals by wireless or wired communication, and any communication standard is used.

[0026] (Configuration of the seismic motion evaluation model generation device 3 and the processes performed by each part) The earthquake motion evaluation model generation device 3 collects data (observation data, analysis data, underground structure data, simulation data) provided by the data providing devices 2A to 2D, and registers the data in a database 10. The earthquake motion evaluation model generation device 3 uses the database 10 to execute machine learning algorithms such as gradient boosting trees, random forests, neural networks, and convolutional neural networks (CNN), thereby generating an earthquake motion evaluation model 13 as a machine learning trained model.

[0027] The seismic motion evaluation model generation device 3 is composed of a general-purpose or dedicated computer, and as shown in Figure 2, is equipped with a storage unit 30 composed of a HDD, memory, etc., a control unit 31 composed of a processor such as a CPU, GPU, etc., a communication unit 32 which is a communication interface with the network 5, an input unit 33 composed of a keyboard, mouse, etc., and a display unit 34 composed of a display, touch panel, etc.

[0028] The storage unit 30 stores a database 10 in which data provided by the data providing devices 2A to 2D is registered and updated, a trained model, an earthquake motion evaluation model 13, and an earthquake motion evaluation model generation program 300 that realizes the earthquake motion evaluation model generation method by controlling the operation of the earthquake motion evaluation model generation device 3. The database 10 may be stored in an external storage device instead of the storage unit 30, and in that case, the earthquake motion evaluation model generation device 3 may access the database 10 by communicating with the external storage device via a network 5.

[0029] The control unit 31 executes the earthquake motion evaluation model generating program 300 to function as a DB management unit 310, a cluster analysis unit 311, an acquisition unit 312, and a generation unit 313. The functions of each unit will be described in detail later.

[0030] FIG. 3 is a functional explanatory diagram showing an example of the earthquake motion evaluation model generating device 3 and the earthquake motion evaluation model generating method according to the embodiment of the present invention.

[0031] (Regarding the database management process by the DB management unit 310) The DB management unit 310 collects seismic motion data 11 based on the provided data (observation data, analysis data, underground structure data, simulation data) provided by the data providing devices 2A to 2D, and registers the data in the database , thereby managing the database .

[0032] 4 is a data configuration diagram showing an example of the database 10. In the database 10, a plurality of pieces of earthquake motion data 11 are registered and stored, in which earthquake motion waveforms observed at observation points of earthquake motions due to earthquakes are associated with earthquake motion characteristic parameter groups consisting of a plurality of types of earthquake motion characteristic parameters at the time when the earthquake motion waveforms were observed. In the case where the simulation data includes simulation conditions and simulation results when earthquake motions due to an actual earthquake or a virtual earthquake are calculated by earthquake motion simulation, the simulation conditions are treated as a set of earthquake motion characteristic parameters, and the simulation results are treated as earthquake motion waveforms or earthquake motion indices, so that the simulation data is registered and stored in the database 10 as the earthquake motion data 11.

[0033] In addition, in the database 10, cluster identification parameters (Cluster) as analysis results when a cluster analysis (details will be described later) of the seismic motion data 11 is performed are registered and stored in association with the seismic motion data 11.

[0034] The earthquake motion characteristic parameter group is made up of various earthquake motion characteristic parameters that describe the characteristics of earthquake motion. The characteristics of earthquake motion include, for example, earthquake source characteristics and propagation characteristics of earthquake motion, and further include site characteristics, direction characteristics, earthquake motion observation characteristics, and earthquake motion prediction characteristics. In this embodiment, the earthquake motion characteristic parameters are data provided by the data providing devices 2A to 2D, which are classified and recorded according to the above-mentioned characteristics of earthquake motion. Below, the earthquake motion characteristic parameters include earthquake source characteristic parameters related to earthquake source characteristics, propagation characteristic parameters related to propagation characteristics, site characteristic parameters related to site characteristics, direction characteristic parameters related to direction characteristics, observation characteristic parameters related to earthquake motion observation characteristics, and prediction characteristic parameters related to earthquake motion prediction characteristics.

[0035] The source characteristic parameters related to the source characteristics include at least one of the following: magnitude (moment magnitude Mw, Japan Meteorological Agency magnitude MJ, etc.), focal depth H, focal location (latitude lat_eq, longitude lon_eq), earthquake type Type (inland crustal earthquake, plate boundary earthquake, intraslab earthquake), fault type Mech (normal fault, reverse fault, strike-slip fault), source mechanism solution (strike Strike1, dip angle dip1, slip angle rake1), conjugate solution of the source mechanism solution (strike Strike2, dip angle dip2, slip angle rake2), six moment tensors Mxx, Mxy, Mxz, Myy, Myz, Mzz, and the rupture propagation effect coefficient Dir of the source. In the example shown in Figure 4, the source characteristics are the moment magnitude Mw, the Japan Meteorological Agency magnitude MJ, the focal depth H, the latitude and longitude of the source, the source mechanism solution, the conjugate solution of the source mechanism solution, the moment tensor, and the rupture propagation effect coefficient of the source.

[0036] The propagation characteristic parameters related to the propagation characteristics are, for example, at least one of the epicenter distance Xmin, the shortest fault distance, and the epicenter distance. In the example of Fig. 4, the epicenter distance Xmin is illustrated as the propagation characteristic, and the epicenter distance Xmin is calculated as the distance between the observation point position and the epicenter position.

[0037] The site characteristic parameters are, for example, at least one of the following: observation point location (latitude lat_site, longitude lon_site), microtopographic classification JCODE, seismic bedrock depth, engineering bedrock depth, layer thickness, density, seismic wave propagation velocity, Q value, attenuation constant, and volcanic front passage judgment flag. In the example of Figure 4, the latitude and longitude of the observation point, the S-wave velocity of the top layer VS1, the average S-wave velocity in the surface layer 10 m AVS10, the average S-wave velocity in the surface layer 30 m AVS30, the seismic bedrock depth Dbase, and the volcanic front passage judgment flag Xvflg are illustrated as site characteristics. The seismic bedrock depth Dbase was set to the bottom depth of the 28th layer of the deep ground model of the mesh that includes the target observation point location, which is published by the earthquake hazard station J-SHIS of the National Research Institute for Earth Science and Disaster Prevention (equal to the top depth of the 29th layer with a P-wave velocity of 5000 m / s and an S-wave velocity of 2700 m / s, which corresponds to the seismic bedrock in the same model).

[0038] The azimuth characteristic parameters related to the azimuth characteristics are, for example, the epicenter azimuth Λ, which indicates the azimuth in which the epicenter is located with respect to the observation point. Therefore, the epicenter azimuth Λ is calculated as the azimuth in which the epicenter is located with respect to the observation point position. In this case, the epicenter azimuth Λ is defined clockwise with true north as 0°, and since it is a discontinuous quantity with true north as the boundary, the example in Figure 4 shows a case where a pair of sinΛ and cosΛ, which represent the epicenter azimuth Λ, is used as the azimuth characteristics.

[0039] The observation characteristic parameters related to the earthquake motion observation characteristics are, for example, the directional component Comp of the earthquake motion, which indicates that the data of the time history waveform recorded as the earthquake motion waveform is in either the north-south direction, the east-west direction, or the up-down direction. Note that in the example of Figure 4, the earthquake motion observation characteristics are omitted.

[0040] The prediction characteristic parameters related to the earthquake motion prediction characteristics are, for example, the prediction result MF13 of the earthquake motion index based on the existing earthquake motion evaluation formula f. In the example of Fig. 4, the prediction result MF13 of the earthquake motion index is illustrated, and the prediction result MF13 is calculated by substituting, for example, four types of the earthquake motion characteristic parameters, the moment magnitude Mw, the epicenter depth H, the epicenter distance X, and the earthquake type Type, into the earthquake motion evaluation formula f.

[0041] The earthquake motion waveform is, for example, a time history waveform of the three components of acceleration, velocity, and displacement in the north-south, east-west, and up-down directions. The earthquake motion waveform is evaluated and analyzed by a predetermined evaluation method to obtain various earthquake motion indices. The earthquake motion waveform according to this embodiment is a time history waveform of two horizontal components (north-south and east-west directions) observed at 138 observation points (see FIG. 1) installed in the Kanto region (Tokyo, Kanagawa, Chiba, Saitama, Ibaraki, Tochigi, and Gunma) of the K-NET strong earthquake observation network. Note that the locations and number of observation points are not limited to these.

[0042] The seismic motion index includes at least one of the amplitude characteristic, the period characteristic, and the time characteristic of the seismic motion.

[0043] The amplitude characteristic is at least one of the maximum acceleration PGA, maximum velocity, and maximum displacement of the earthquake motion obtained from the earthquake motion waveform (time history waveform of acceleration, velocity, and displacement). The amplitude characteristic according to this embodiment is the maximum acceleration PGA.

[0044] The periodic characteristic is a response value for at least one period in a response spectrum or Fourier spectrum obtained from a seismic motion waveform (time history waveforms of acceleration, velocity, and displacement). The response spectrum is, for example, an acceleration response spectrum, a pseudo velocity response spectrum pSv, a velocity response spectrum, and a displacement response spectrum for a predetermined damping constant (e.g., 5%). The Fourier spectrum is, for example, an acceleration Fourier spectrum, a velocity Fourier spectrum, and a displacement Fourier spectrum. The periodic characteristic according to this embodiment is five pseudo velocity response spectra pSv(0.1s), pSv(0.5s), pSv(1s), pSv(3s), and pSv(5s) with a damping constant of 5% in periods of 0.1 seconds, 0.5 seconds, 1 second, 3 seconds, and 5 seconds.

[0045] The time-dependent characteristic is, for example, a response duration for at least one period in a response duration spectrum obtained from a seismic motion waveform (time history waveforms of acceleration, velocity, and displacement). The response duration spectrum is, for example, an acceleration response duration spectrum, a velocity response duration spectrum TSv, and a displacement response duration spectrum for a predetermined damping constant (for example, 5%). The time-dependent characteristic according to this embodiment is five velocity response duration spectra TSv(0.1s), TSv(0.5s), TSv(1s), TSv(3s), and TSv(5s) with a damping constant of 5% in periods of 0.1 seconds, 0.5 seconds, 1 second, 3 seconds, and 5 seconds. The parameters that define the start and end of the response duration are p1=0.03 and p2=0.95.

[0046] (Regarding the cluster analysis process by the cluster analysis unit 311 and cluster identification parameters) The cluster analysis unit 311 refers to the database 10 and performs cluster analysis of the earthquake motion data 11 based on the first group of earthquake motion characteristic parameters included in the group of earthquake motion characteristic parameters, thereby assigning cluster identification parameters to each of the multiple earthquake motion data 11 and storing them in the database 10.

[0047] For example, the cluster analysis unit 311 standardizes or normalizes a first group of earthquake motion characteristic parameters in the plurality of earthquake motion data 11 for each of the earthquake motion characteristic parameters, and performs dimension reduction to two or three dimensions to obtain a group of feature parameters after dimension reduction, and assigns cluster identification parameters to each of the plurality of earthquake motion data 11. The cluster identification parameters are registered in the database 10 in a state associated with the earthquake motion data 11, respectively.

[0048] The cluster identification parameter is an identifier for identifying a cluster, and is a feature obtained from the first group of earthquake motion characteristic parameters by unsupervised learning. The cluster identification parameter can use any data format. For example, the cluster identification parameter may be specified by alphabets or numbers, or may be specified by two-dimensional coordinates or three-dimensional coordinates using a group of feature parameters after dimension reduction, which will be described later.

[0049] Fig. 5 is a schematic diagram showing an example of cluster analysis. In this embodiment, a case where 13 types of earthquake motion characteristic parameters (specifically, 13 types of earthquake source characteristic parameters) consisting of moment magnitude Mw, hypocenter depth H, hypocenter latitude lat_eq / longitude lon_eq, strike Strike1, dip angle Dip1, slip angle Rake1, and six moment tensors Mxx, Mxy, Mxz, Myy, Myz, and Mzz are adopted as the first earthquake motion characteristic parameter group will be described with reference to Fig. 5. Note that the types and numbers of earthquake motion characteristic parameters included in the first earthquake motion characteristic parameter group are not limited to the above example. Not limited to.

[0050] First, the cluster analysis unit 311 standardizes or normalizes the first group of earthquake motion characteristic parameters in the plurality of earthquake motion data 11 for each of the earthquake motion characteristic parameters. In this embodiment, since the first group of earthquake motion characteristic parameters is composed of 13 types of earthquake motion characteristic parameters as described above, each of the 13 types of earthquake motion characteristic parameters is standardized or normalized. Whether to standardize or normalize can be determined for each type of earthquake motion characteristic parameter.

[0051] Next, the standardized or normalized 13 types (13 dimensions) of earthquake motion characteristic parameters are compressed into a two- or three-dimensional feature parameter group by performing dimensionality reduction. Dimensionality reduction techniques that can be used include, for example, principal component analysis, t-distribution type stochastic neighbor embedding (t-SNE, etc.), and multidimensional scaling. The example in Figure 5 shows a case where the parameters are compressed into two dimensions.

[0052] Then, clustering is performed on the dimension-reduced feature parameter group, and cluster identification parameters are assigned to the seismic motion data 11 corresponding to the dimension-reduced feature parameter group. For example, a non-hierarchical method such as the k-means method or a hierarchical method such as a shortest distance method can be used as a clustering method. The cluster identification parameters assigned as a result of clustering are registered in the database 10 in a state associated with each of the seismic motion data 11. The example in FIG. 5 illustrates a case where the seismic motion data 11 is classified into nine clusters by the k-means method, and the letters A to I are assigned to each of the seismic motion data 11 as cluster identification parameters.

[0053] The cluster identification parameter is preferably assigned based on a plurality of earthquake motion characteristic parameters to be considered as a set of combinations having mutual correlation. The cluster identification parameter may be assigned based on a first earthquake motion characteristic parameter group including a combination such as strike Strike1, dip angle Dip1, and slip angle Rake1 constituting a focal mechanism solution, or may be assigned based on a first earthquake motion characteristic parameter group including a combination such as six moment tensors Mxx, Mxy, Mxz, Myy, Myz, and Mzz. In this case, the first earthquake motion characteristic parameter group may include a plurality of combinations as in this embodiment. The first earthquake motion characteristic parameter group may also include a plurality of earthquake motion characteristic parameters based on combinations other than those described above. Furthermore, the first earthquake motion characteristic parameter group may include a plurality of seismic source characteristic parameters (specifically, 13 types of seismic source characteristic parameters) as in this embodiment, or may include earthquake motion characteristic parameters related to other characteristics (specifically, propagation characteristic parameters, site characteristic parameters, orientation characteristic parameters, observation characteristic parameters, or prediction characteristic parameters). In this case, the first earthquake motion characteristic parameter group may be any combination of earthquake motion characteristic parameters related to a plurality of characteristics, such as, for example, seismic source characteristic parameters and site characteristic parameters.

[0054] Therefore, the cluster identification parameter can be regarded as a new earthquake motion characteristic parameter that integrates multiple earthquake motion characteristic parameters that should be considered as a set into a single parameter.

[0055] (Regarding the acquisition process by the acquisition unit 312 and the learning data 12) As shown in Fig. 3, the acquisition unit 312 acquires from the database 10 a plurality of pieces of learning data 12 consisting of feature quantities and objective variables, using a second group of earthquake motion characteristic parameters and a cluster identification parameter included in the group of earthquake motion characteristic parameters as feature quantities and an earthquake motion index obtained from an earthquake motion waveform as an objective variable. The learning data 12 is data used as learning data (training data), verification data, and test data in supervised learning. A collection of the learning data 12 consisting of a plurality of pieces of learning data 12 is called a learning dataset.

[0056] In this embodiment, as shown in Fig. 3, the learning data 12 is configured with a second set of earthquake motion characteristic parameters consisting of six types of earthquake motion characteristic parameters and a cluster identification parameter as feature quantities, and one type of earthquake motion index as a response variable. In particular, the second set of earthquake motion characteristic parameters as feature quantities of the learning data 12 are, but are not limited to, the Japan Meteorological Agency magnitude MJ, the epicenter depth H, the epicenter distance Xmin, the average S-wave velocity in the surface layer of 30 m AVS30, the depth of the top surface of the seismic bedrock Dbase, and the epicenter direction Λ (a pair of sinΛ and cosΛ). In addition, the earthquake motion evaluation index as a response variable of the learning data 12 is, but is not limited to, one type, the maximum acceleration PGA.

[0057] The features of the learning data 12 include not only a cluster identification parameter that can be regarded as a new group of earthquake motion characteristic parameters obtained by integrating the first group of earthquake motion characteristic parameters, but also a second group of earthquake motion characteristic parameters, so that the second group of earthquake motion characteristic parameters acts to complement the cluster identification parameters.

[0058] The first earthquake motion characteristic parameter group to be subjected to the cluster analysis and the second earthquake motion characteristic parameter group constituting the feature amount of the learning data 12 may include some overlapping earthquake motion characteristic parameters. In this embodiment, the first earthquake motion characteristic parameter group and the second earthquake motion characteristic parameter group include the focal depth H as an overlapping earthquake motion characteristic parameter. In this case, the influence of a specific earthquake motion characteristic parameter (the focal depth H in this embodiment) included in both the first earthquake motion characteristic parameter group and the second earthquake motion characteristic parameter group can be strongly reflected in the evaluation and prediction of the objective variable so as not to be buried in the cluster identification parameters.

[0059] Furthermore, the first group of earthquake motion characteristic parameters to be subjected to the cluster analysis and the second group of earthquake motion characteristic parameters constituting the feature quantities of the learning data 12 may not include overlapping earthquake motion characteristic parameters. In this case, the second group of earthquake motion characteristic parameters not included in the cluster identification parameters complement the cluster identification parameters, thereby further improving the evaluation and prediction accuracy of the objective variable.

[0060] (Regarding the generation process by the generation unit 313 and the earthquake motion evaluation model 13) 3, the generation unit 313 learns correlations between feature amounts and objective variables by machine learning based on the multiple pieces of learning data 12 acquired by the acquisition unit 312, thereby generating a seismic motion evaluation model 13 as a trained model, and stores the model in the storage unit 30. In this embodiment, a case will be described in which a Gradient Boosting Decision Tree is used as a machine learning algorithm in the machine learning.

[0061] FIG. 6 is a schematic diagram showing an example of a gradient boosting tree. A gradient boosting tree is a learning device that combines gradient boosting and a decision tree. Gradient boosting is a method for constructing a strong learner (a high-performance machine learning model) by combining multiple weak learners (low-performance machine learning models). A decision tree is a method for generating a machine learning model capable of classification and regression by performing conditional branching using the branching structure of a tree. A gradient boosting tree, which combines these two methods, is a method for combining multiple weak learners generated by a decision tree using gradient boosting.

[0062] Of the 11 types of seismic motion indices shown in Figure 4, the number of data for maximum acceleration PGA and pseudo velocity response spectrum pSv is thought to decrease rapidly as the amplitude increases. Therefore, in order to reduce the bias that occurs in the distribution diagram of the objective variables, common logarithms (log 10 PGA and log 10 As loss functions in the gradient boosting tree, it is preferable to apply the least squares method (normal distribution diagram) to the maximum acceleration PGA and the pseudo velocity response spectrum pSv, and to apply a Poisson distribution diagram to the velocity response duration spectrum TSv.

[0063] Furthermore, when the generating unit 313 generates the earthquake motion evaluation model 13 using the gradient boosting tree, if the eleven types of earthquake motion indexes shown in Fig. 4 are adopted as the objective variables, the earthquake motion evaluation model 13 may be generated for each objective variable. That is, the third earthquake motion evaluation model 13C to the eleventh earthquake motion evaluation model 13K may be generated, such as the first earthquake motion evaluation model 13A that learns the correlation between the feature amount and the objective variable (maximum acceleration PGA = first type of earthquake motion index), the second earthquake motion evaluation model 13B that learns the correlation between the feature amount and the objective variable (pseudo velocity response spectrum pSv (0.1s) = second type of earthquake motion index), and so on, so that a total of eleven earthquake motion evaluation models 13A to 13K may be generated.

[0064] In addition, in the database management process by the DB management unit 310, seismic motion data 11 is registered in the database 10 from time to time, and when a predetermined number of seismic motion data 11 are newly accumulated, the seismic motion evaluation model 13 may be updated by repeating the cluster analysis process by the cluster analysis unit 311, the acquisition process by the acquisition unit 312, and the generation process by the generation unit 313 for the multiple seismic motion data 11 including the new seismic motion data 11.

[0065] (Configuration of the earthquake motion evaluation device 4 and the process performed by each part) The earthquake motion evaluation device 4 evaluates and predicts earthquake motion based on the earthquake motion evaluation model 13 generated by the earthquake motion evaluation model generation device 3, and outputs the results to an output medium such as a display medium or a paper medium.

[0066] The seismic motion evaluation device 4, like the seismic motion evaluation model generation device 3, is composed of a general-purpose or dedicated computer, and as shown in Figure 2, is equipped with a storage unit 40 composed of a HDD, memory, etc., a control unit 41 composed of a processor such as a CPU, GPU, etc., a communication unit 42 which is a communication interface with the network 5, an input unit 43 composed of a keyboard, mouse, etc., and a display unit 44 composed of a display, touch panel, etc.

[0067] The memory unit 40 stores an earthquake motion evaluation model 13 provided as a trained model by the earthquake motion evaluation model generation device 3, and an earthquake motion evaluation program 400 that controls the operation of the earthquake motion evaluation device 4 to realize the earthquake motion evaluation method.

[0068] The control unit 41 executes the earthquake motion evaluation program 400 to function as a reception unit 410, a cluster assignment unit 411, a prediction unit 412, and an output processing unit 413. The functions of each unit will be described in detail later.

[0069] FIG. 7 is a functional explanatory diagram showing an example of the earthquake motion evaluation device 4 and the earthquake motion evaluation method according to the embodiment of the present invention.

[0070] (Regarding the reception process by the reception unit 410) The reception unit 410 receives a group of earthquake motion characteristic parameters of a prediction target. Specifically, the reception unit 410 receives, for example, a group of earthquake motion characteristic parameters of an earthquake (hereinafter referred to as an "anticipated earthquake") that is anticipated as a prediction target by the user of the earthquake motion evaluation device 4 via the input unit 33, and also receives, via the input unit 33, a prediction point position indicating a position of a prediction point at which it is desired to predict the degree of earthquake motion caused by the anticipated earthquake. The prediction point position may be any position, or may be the same as the observation point position. Furthermore, there may be multiple prediction point positions, and for example, they may be each lattice point at a predetermined lattice interval (for example, 5 km interval).

[0071] (Regarding the cluster assignment process by the cluster assignment unit 411) The cluster assignment unit 411 assigns cluster identification parameters based on a first group of earthquake motion characteristic parameters included in the group of earthquake motion characteristic parameters of the prediction target received by the reception unit 410. For example, the cluster assignment unit 411 assigns cluster identification parameters using a method similar to the dimensionality reduction method or clustering method used when the cluster analysis unit 311 performed cluster classification. At this time, it is preferable to assign the cluster identification parameters by inheriting the algorithm and parameters used by the cluster analysis unit 311.

[0072] (Regarding the prediction process by the prediction unit 412) The prediction unit 412 inputs the second group of earthquake motion characteristic parameters included in the group of earthquake motion characteristic parameters to be predicted received by the receiving unit 410 and the cluster identification parameter assigned by the cluster assignment unit 411 as features into an earthquake motion evaluation model 13 (in this embodiment, six types of earthquake motion characteristic parameters and the cluster identification parameter are used as features, and one type of earthquake motion index is used as an objective variable, and a trained model that has learned the correlation between the two) and predicts the earthquake motion index corresponding to the group of earthquake motion characteristic parameters to be predicted based on the objective variable output from the earthquake motion evaluation model 13.

[0073] In this case, when the receiving unit 410 receives multiple anticipated earthquakes or multiple prediction point positions, thereby receiving multiple groups of earthquake motion characteristic parameters as prediction targets, the prediction unit 412 predicts earthquake motion indices (predicted values) corresponding to each of the multiple groups of earthquake motion characteristic parameters.

[0074] In addition, when the earthquake motion evaluation model 13 includes a total of 11 earthquake motion evaluation models 13A to 13K generated for each objective variable (11 types of earthquake motion indices), the prediction unit 412 inputs the earthquake motion characteristic parameters to be predicted as features to each of the 11 earthquake motion evaluation models 13A to 13K, and predicts the earthquake motion index (predicted value) corresponding to the earthquake motion characteristic parameters to be predicted for each objective variable (11 types of earthquake motion indices) output from the 11 earthquake motion evaluation models 13A to 13K.

[0075] (Regarding the output processing step by the output processing unit 413) The output processing unit 413 outputs the predicted value of the seismic motion index predicted by the prediction unit 412 to a visually recognizable output medium. For example, when the output medium is a display medium such as the display unit 44, the output processing unit 413 generates display data (output data) for display on the display medium, and displays and outputs the data on the display medium. When the output medium is a paper medium, the output processing unit 413 generates print data (output data) for printing on the paper medium, and prints and outputs the data on the paper medium. The output processing unit 413 may communicate and output the output data to, for example, a seismic motion prediction map creation system or a hazard map creation system, or may communicate and output the output data to a disaster prevention system for a public facility, building, factory, or the like.

[0076] For example, when the group of earthquake motion characteristic parameters to be predicted received by the receiving unit 410 is a group of multiple earthquake motion characteristic parameters for one anticipated earthquake, for example, with each grid point serving as a prediction point position, the output processing unit 413 outputs the predicted values ​​of multiple earthquake motion indices at each prediction point position predicted by the prediction unit 412 based on the multiple groups of earthquake motion characteristic parameters to an output medium so as to be superimposed on a map, for example, as a contour diagram or a color-coded mesh diagram.

[0077] In addition, when the group of earthquake motion characteristic parameters to be predicted received by the receiving unit 410 is a group of earthquake motion characteristic parameters including a plurality of different directional characteristics centered on the prediction point position, the output processing unit 413 represents the predicted values ​​of a plurality of earthquake motion indices in each direction predicted by the prediction unit 412 based on the plurality of earthquake motion characteristic parameter groups as distances from a reference point on the output medium, and outputs a plurality of earthquake motion indices to the output medium by assigning a plurality of directional characteristics to each direction centered on the reference point.

[0078] Furthermore, when the group of earthquake motion characteristic parameters to be predicted received by the receiving unit 410 is a group of multiple earthquake motion characteristic parameters including different epicenter distances, the output processing unit 413 outputs a plurality of earthquake motion indices to an output medium by expressing the predicted values ​​of the plurality of earthquake motion indices predicted by the prediction unit 412 based on the plurality of earthquake motion characteristic parameter groups as distance attenuation characteristics.

[0079] As described above, according to the earthquake motion evaluation model generating device 3 and the earthquake motion evaluation model generating method of the present embodiment, a cluster identification parameter assigned by performing cluster analysis of the earthquake motion data 11 based on the first earthquake motion characteristic parameter group included in the earthquake motion characteristic parameter group, and a plurality of learning data 12 configured with the second earthquake motion characteristic parameter group included in the earthquake motion characteristic parameter group as feature quantities and the earthquake motion index obtained from the earthquake motion waveform as the objective variable are obtained. Then, based on the plurality of learning data 12, the correlation between the feature quantities and the objective variable is learned by machine learning, and the earthquake motion evaluation model 13 is generated as a machine learning trained model. Therefore, it is possible to generate the earthquake motion evaluation model 13 that can easily and appropriately reflect the interrelationships between the plurality of earthquake motion characteristic parameters included in the first earthquake motion characteristic parameter group and can evaluate and predict the earthquake motion index with high accuracy.

[0080] Moreover, according to the earthquake motion evaluation device 4 and earthquake motion evaluation method of this embodiment, by using the earthquake motion evaluation model generation device 3 and the earthquake motion evaluation model 13 generated by the earthquake motion evaluation model generation method, the earthquake motion index corresponding to the earthquake motion characteristic parameter group of the prediction target is predicted using the cluster identification parameter assigned based on the first earthquake motion characteristic parameter group included in the earthquake motion characteristic parameter group of the prediction target and the second earthquake motion characteristic parameter group included in the earthquake motion characteristic parameter group of the prediction target as feature quantities. Therefore, the interrelationships between the plurality of earthquake motion characteristic parameters included in the first earthquake motion characteristic parameter group are simply and appropriately reflected, and the earthquake motion index can be evaluated and predicted with high accuracy.

[0081] Figure 8 shows the degree of influence of the seismic motion characteristic parameters and the cluster identification parameters on the evaluation value of the seismic motion index. It was found that the influence of the cluster identification parameters (Cluster) is comparable to the feature quantities of the surface and deep ground.

[0082] FIG. 9 is a scatter plot showing the correlation between the "observed value" of the seismic motion index obtained from the seismic motion waveform and the "evaluated value" of the seismic motion index obtained by the seismic motion evaluation model 13. FIG. 10 is a histogram showing the logarithmic value of the "evaluated value / observed value" of each objective variable (seismic motion index). It was found that the common logarithmic standard deviation of the ratio of the evaluated value to the observed value was approximately 0.16, which is smaller than the approximately 0.2 to 0.4 of the conventional seismic motion prediction formula.

[0083] (Other embodiments) Although the embodiments of the present invention have been described above, the present invention is not limited to the above-described embodiments, and can be modified as appropriate without departing from the technical concept of the present invention.

[0084] For example, in each of the above embodiments, the area targeted by the earthquake motion evaluation model 13 may be changed as appropriate, for example, the range or shape of the area targeted may be changed arbitrarily. Furthermore, the earthquake motion evaluation model 13 may target not only an area, but also any point, or a point group in which a plurality of points are grouped according to a predetermined classification criterion.

[0085] In addition, in each of the above embodiments, the earthquake motion evaluation model generating program 300 and the earthquake motion evaluation program 400 have been described as being stored in the storage units 30 and 40, respectively, but they may be provided by being recorded in a computer-readable recording medium such as a CD-ROM, DVD, or USB memory as a file in an installable or executable format. Also, the earthquake motion evaluation model generating program 300 and the earthquake motion evaluation program 400 may be provided by being stored on a computer connected to a network such as the Internet and downloaded via the network. [Explanation of symbols]

[0086] 1: Earthquake motion evaluation system, 2A: Observation data providing device, 2B: Analysis data providing device, 2C: Underground structure data providing device, 2D: Earthquake motion simulation data provider, 3...Earthquake motion evaluation model generation device, 4...Earthquake motion evaluation device, 5...Network, 10...database, 11...earthquake motion data, 12...training data, 13…Earthquake motion evaluation model, 30: memory unit, 31: control unit, 32: communication unit, 33: input unit, 34: display unit, 40: memory unit, 41: control unit, 42: communication unit, 43: input unit, 44: display unit, 300: Earthquake motion evaluation model generation program, 310: DB management section, 311: cluster analysis unit; 312: acquisition unit; 313: generation unit; 400: earthquake motion evaluation program, 410: reception unit, 411: cluster assignment unit, 412: prediction unit; 413: output processing unit

Claims

1. A method for generating a seismic motion evaluation model by machine learning using a computer, comprising: a cluster analysis step of referring to a database storing a plurality of pieces of earthquake motion data correlating an earthquake motion waveform caused by an earthquake with a group of earthquake motion characteristic parameters consisting of a plurality of types of earthquake motion characteristic parameters at the time when the earthquake motion waveform was obtained, and performing a cluster analysis of the earthquake motion data based on a first group of earthquake motion characteristic parameters included in the group of earthquake motion characteristic parameters, thereby assigning cluster identification parameters to each of the plurality of pieces of earthquake motion data, and storing the data in the database; an acquisition step of acquiring, from the database, a second group of earthquake motion characteristic parameters included in the group of earthquake motion characteristic parameters and the cluster identification parameter as feature quantities, and an earthquake motion index obtained from the earthquake motion waveform as a response variable, a plurality of learning data sets configured with the feature quantities and the response variable; and a generating step of generating the seismic motion evaluation model as a trained model of the machine learning by learning a correlation between the feature amount and the objective variable by the machine learning based on the plurality of learning data acquired in the acquiring step. Method for generating earthquake motion evaluation models.

2. The cluster analysis step includes: standardizing or normalizing the first group of earthquake motion characteristic parameters in the plurality of earthquake motion data for each of the earthquake motion characteristic parameters, and performing dimension reduction to obtain a group of feature parameters after dimension reduction, and assigning the cluster identification parameters to each of the plurality of earthquake motion data. The method for generating a seismic motion evaluation model according to claim 1 .

3. the first group of earthquake motion characteristic parameters and the second group of earthquake motion characteristic parameters do not include earthquake motion characteristic parameters that overlap with each other; The method for generating a seismic motion evaluation model according to claim 1 .

4. The first group of earthquake motion characteristic parameters and the second group of earthquake motion characteristic parameters include some of the earthquake motion characteristic parameters that overlap with each other. The method for generating a seismic motion evaluation model according to claim 1 .

5. A method for evaluating characteristics of earthquake motion based on the earthquake motion evaluation model generated by the method for generating an earthquake motion evaluation model according to any one of claims 1 to 4, comprising the steps of: a receiving step of receiving the group of earthquake motion characteristic parameters to be predicted; a cluster assignment step of assigning the cluster identification parameter based on the first group of earthquake motion characteristic parameters included in the group of earthquake motion characteristic parameters of the prediction target received in the receiving step; a prediction step of predicting the seismic motion index corresponding to the seismic motion characteristic parameter group of the prediction target based on the objective variable output from the seismic motion evaluation model by inputting the second seismic motion characteristic parameter group included in the seismic motion characteristic parameter group of the prediction target received in the reception step and the cluster identification parameter assigned in the cluster assignment step as the feature amount into the seismic motion evaluation model, Earthquake motion assessment methods.

6. A computer comprising: A control unit that executes each step included in the method for generating a seismic motion evaluation model according to any one of claims 1 to 4. Earthquake motion evaluation model generator.

7. A computer comprising: A control unit that executes each step included in the earthquake motion evaluation method according to claim 5. Earthquake motion evaluation device.

Citation Information

Patent Citations

  • Earthquake damage evaluation program

    JP2008039446A

Cited By

  • Management system, management method, and management program

    JP7702766B1