JP2022053155A - Earthquake motion evaluation model generation method, earthquake motion evaluation model generation device, earthquake motion evaluation method, and earthquake motion evaluation device - Google Patents

Abstract

To provide an earthquake motion evaluation model generation method capable of utilizing detailed knowledge individually obtained by an earthquake motion simulation under a limited condition in a more generalized form.SOLUTION: An earthquake motion evaluation model generation method includes: an acquisition process for acquiring a plurality of learning data composed of a feature amount and an object variable with an earthquake motion characteristic parameter as the feature amount and with an earthquake motion index calculation result as the object variable from a database 10 for storing a plurality of pieces of earthquake motion data in which an earthquake motion characteristic parameter, and an earthquake motion index calculation result in execution of an earthquake motion simulation for calculating an earthquake motion index on the basis of the earthquake motion characteristic parameter are related; and a generation process for generating an earthquake motion evaluation model 13 as a model learned by machine learning by learning a correlation between the feature amount of the object variable by machine learning on the basis of the plurality of learning data.SELECTED DRAWING: Figure 3

Description

The present invention relates to a seismic motion evaluation model generation method, a seismic motion evaluation model generation device, a seismic motion evaluation method, and a seismic motion evaluation device.

Technology for evaluating and predicting the characteristics of earthquake motions that are expected to occur in the future based on various data obtained from past earthquakes (slip-breaking phenomenon of source faults) and earthquake motions (ground motion caused by earthquakes) Because of its usefulness, it is widely used in society, from characteristic analysis and interpretation of earthquake motion to behavior prediction and structural design of buildings and structures, and even earthquake disaster prevention.

The technology for evaluating and predicting the characteristics of seismic motion is generally the technology for collecting, organizing, evaluating and predicting a huge amount of seismic observation records obtained in the past, and the seismic motion developed based on the theory and experience of earthquakes and seismic motion. It is roughly divided into two technologies that evaluate and predict using simulation methods. In general, the former is a technology that deals with representative and basic indicators obtained for an unspecified number of earthquakes and seismic motions, and the latter is a technology that deals with the detailed characteristics of seismic motions caused by a specific assumed earthquake.

Regarding the former technology, after the data and information of the observed earthquakes and seismic motions selected by a very limited number of experts with their own judgment are analyzed by a professional method, the seismic motions of future earthquakes Evaluates and predicts the maximum amplitude (maximum acceleration, maximum speed, maximum displacement, etc.) and response spectrum (maximum response amplitude of the one-plate point system when seismic motion is input to a one-sided point system with a certain natural period and decay constant). Seismic motion evaluation formulas (sometimes referred to as distance damping formulas, seismic motion prediction formulas, etc.) have been developed and utilized (see, for example, Patent Document 1 and Non-Patent Document 1).

On the other hand, regarding the latter technology, we will use advanced methods developed by a limited number of experts against the background of the rapid increase in data and information in recent years and the advancement of computer performance, and will use the advanced method developed by a limited number of experts to reduce the seismic motion of future earthquakes. Broadband time history is evaluated and predicted in a face-to-face manner, and especially recently, these results have been widely published and utilized. In terms of surface, including rare large-scale earthquakes for which observation records have not been obtained but are feared to occur in the future, large-amplitude seismic motions near the fault pole, and seismic motions at points where seismic observations have not been made. Data and information on seismic motions that have been evaluated and predicted in a uniform and well-balanced manner are provided, and it is possible to utilize these.

Japanese Unexamined Patent Publication No. 2008-39446

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

The former technology based on the collection and organization of huge seismic records is evaluated and predicted because large earthquakes and large earthquake motions are rare (low frequency) events and the positions of seismic stations are limited. The data and information on earthquakes and ground motions, which are the basis of this, are not always obtained in a uniform and well-balanced manner.

On the other hand, as mentioned above, the technology based on the latter seismic motion simulation method may be able to eliminate the shortcomings of the former technology, but the seismic motion data and information provided as a result of the latter technology are available. It is an evaluation / prediction at a specific point group based on a limited assumed scenario, and it is not always sufficient as a basis for comprehensive judgment that society truly wants for various earthquakes that occur in the future.

The present invention has been made in consideration of such circumstances, and it is possible to utilize the detailed knowledge individually obtained by the seismic motion simulation under limited conditions in a more generalized form. It is an object of the present invention to provide a seismic motion evaluation model generation method, a seismic motion evaluation model generation device, a seismic motion evaluation method, and a seismic motion evaluation device.

The present invention solves the above-mentioned problems, and the seismic motion evaluation model generation method according to the embodiment of the present invention is
It is a seismic motion evaluation model generation method that generates a seismic motion evaluation model by machine learning using a computer.
The seismic motion characteristic parameters are characterized from a database that stores multiple seismic motion data associated with the seismic motion index calculation results when the seismic motion index is calculated based on the seismic motion characteristic parameters. An acquisition process for acquiring a plurality of learning data composed of the feature amount and the objective variable, using the seismic motion index calculation result as an amount and the objective variable.
The seismic motion evaluation model as a learned model of the machine learning by learning the correlation between the feature amount and the objective variable by the machine learning based on the plurality of learning data acquired in the acquisition step. Includes a generation process and.

Further, the seismic motion evaluation model generator according to the embodiment of the present invention is
It is a computer and includes a control unit that executes each process included in the above-mentioned seismic motion evaluation model generation method.

Further, the seismic motion evaluation method according to the embodiment of the present invention is
It is a seismic motion evaluation method that evaluates the characteristics of seismic motion based on the seismic motion evaluation model generated by the seismic motion evaluation model generation method using a computer.
The reception process that accepts the seismic motion characteristic parameters to be predicted,
The prediction target is based on the objective variable output from the seismic motion evaluation model by inputting the seismic motion characteristic parameters of the prediction target received in the reception step into the seismic motion evaluation model as the feature quantities. Includes a prediction step for predicting the seismic motion index corresponding to the seismic motion characteristic parameters.

Further, the seismic motion evaluation device according to the embodiment of the present invention is
It is a computer and includes a control unit that executes each process included in the above-mentioned seismic motion evaluation method.

According to the seismic motion evaluation model generator and the seismic motion model generator according to the embodiment of the present invention, the seismic motion characteristic parameters and the seismic motion index calculation results when the seismic motion simulation is executed are set as feature quantities and objective variables, respectively. Generate a seismic motion evaluation model based on the training data. Therefore, in the seismic motion evaluation model, the correlation between the seismic motion characteristic parameters and the seismic motion index calculation results when the seismic motion simulation is executed assuming various earthquakes that are expected to occur in the future is learned, and obtained from various seismic motion simulations. The findings are aggregated. Therefore, it is possible to provide a seismic motion evaluation model that makes it possible to utilize the detailed knowledge obtained individually in the seismic motion simulation under limited conditions in a more generalized form.

Further, according to the seismic motion evaluation method according to the embodiment of the present invention and the seismic motion evaluation device, the seismic motion evaluation model generated by the seismic motion evaluation model generation device and the seismic motion evaluation model generation method can be used for individual specialization. Since the knowledge obtained individually in the seismic motion simulation is provided in a generalized form without depending on the experience of the house, it is possible to evaluate and predict the characteristics of the seismic motion due to the earthquake that is expected to occur in the future with high accuracy. Can be done.

It is a schematic block diagram which shows an example of the seismic motion evaluation system 1 which concerns on 1st Embodiment of this invention. It is a block diagram which shows an example of the seismic motion evaluation system 1 which concerns on 1st Embodiment of this invention. It is a functional explanatory diagram which shows an example of the seismic motion evaluation model generation apparatus 3 and the seismic motion evaluation model generation method which concerns on 1st Embodiment of this invention. It is a data structure diagram which shows an example of the database 10 which concerns on 1st Embodiment of this invention. It is a schematic diagram which shows the outline of the gradient boosting tree. It is a functional explanatory diagram which shows an example of the seismic motion evaluation apparatus 4 and the seismic motion evaluation method which concerns on 1st Embodiment of this invention. It is a function explanatory drawing which shows an example of the seismic motion evaluation model generation apparatus 3 and the seismic motion evaluation model generation method which concerns on 2nd Embodiment of this invention. It is a data structure diagram which shows an example of the database 10 which concerns on 2nd Embodiment of this invention. It is a functional explanatory diagram which shows an example of the seismic motion evaluation apparatus 4 and the seismic motion evaluation method which concerns on 2nd Embodiment of this invention. It is a function explanatory drawing which shows an example of the seismic motion evaluation model generation apparatus 3 and the seismic motion evaluation model generation method which concerns on 3rd Embodiment of this invention. It is a data structure diagram which shows an example of the database 10 which concerns on 3rd Embodiment of this invention. It is a functional explanatory diagram which shows an example of the seismic motion evaluation apparatus 4 and the seismic motion evaluation method which concerns on 3rd Embodiment of this invention. It is a function explanatory drawing which shows an example of the seismic motion evaluation model generation apparatus 3 and the seismic motion evaluation model generation method which concerns on 4th Embodiment of this invention. It is a data structure diagram which shows an example of the database 10 which concerns on 4th Embodiment of this invention. It is a functional explanatory diagram which shows an example of the seismic motion evaluation apparatus 4 and the seismic motion evaluation method which concerns on 4th Embodiment of this invention. It is a function explanatory drawing which shows an example of the seismic motion evaluation model generation apparatus 3 and the seismic motion evaluation model generation method which concerns on 5th Embodiment of this invention. It is a data structure diagram which shows an example of the database 10 which concerns on 5th Embodiment of this invention. It is a function explanatory drawing which shows an example of the seismic motion evaluation apparatus 4 and the seismic motion evaluation method which concerns on 5th Embodiment of this invention.

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

(First Embodiment)
FIG. 1 is a schematic configuration diagram showing an example of a seismic motion evaluation system 1 according to the first embodiment of the present invention. FIG. 2 is a block diagram showing an example of the seismic motion evaluation system 1 according to the first embodiment of the present invention.

The seismic motion evaluation system 1 is provided by the seismic motion simulation data providing device 2 and the seismic motion simulation data providing device 2 that execute the seismic motion simulation according to a predetermined seismic motion simulation method and provide the simulation conditions and simulation results at that time to the outside as simulation data. The database 10 is updated based on the simulated simulation data, and the seismic motion evaluation model generation device 3 and the seismic motion evaluation model generation device 3 generate the seismic motion evaluation model 13 based on machine learning using the updated database 10. A seismic motion evaluation device 4 that evaluates and predicts seismic motion based on the seismic motion evaluation model 13 and a network 5 that connects the devices are provided.

The seismic motion evaluation model 13 provided to the seismic motion evaluation device 4 by the seismic motion evaluation model generation device 3 ranges from, for example, characteristic analysis / interpretation of seismic motion to behavior prediction / structural design of buildings / structures, and further to earthquake disaster prevention. It can be widely used in society.

The seismic motion simulation data providing device 2 analyzes the seismic motion caused by the earthquake when an earthquake occurs or when it is assumed that a virtual earthquake has occurred, according to a predetermined seismic motion simulation method, and the simulation at that time. Provide conditions and simulation results to the outside as simulation data. At that time, any method can be adopted, and a plurality of methods may be adopted.

The seismic motion simulation data providing device 2 may provide simulation data by executing the seismic motion simulation in its own device, or may provide simulation data when the seismic motion simulation is executed by another device. good. Further, the seismic motion simulation data providing device 2 may acquire various data necessary for executing the seismic motion simulation from another data providing device. For example, the Meteorological Agency, National Research Institute for Earth Science and Disaster Prevention (National Research Institute for Earth Science and Disaster Prevention). Data such as seismic motion observation records and underground structure data may be acquired from the strong motion observation network K-NET, the broadband seismic observation network F-NET, and the seismic hazard station J-SHIS (hereinafter referred to as "National Research Institute for Earth Science and Disaster Prevention"). ..

Further, the seismic motion simulation data providing device 2 may provide simulation data related to the seismic motion simulation to the seismic motion evaluation model generating device 3 at any time when a new seismic motion simulation is executed, or data from the seismic motion evaluation model generating device 3. When the request is received, the simulation data related to the request (when the simulation condition is received from the seismic motion evaluation model generator 3, the simulation data including the simulation result when the seismic motion simulation is executed based on the simulation condition is also available. Good) may be provided to the seismic motion evaluation model generator 3.

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

(Regarding the configuration of the seismic motion evaluation model generator 3 and the process by each part)
The seismic motion evaluation model generation device 3 is based on the simulation data provided by the seismic motion simulation data providing device 2, for example, a gradient boosting tree, a random forest, a neural network, a convolutional neural network (CNN), and a hostile generation network (GAN). ) And the like to generate a seismic motion evaluation model 13 as a trained model of machine learning.

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

The storage unit 30 controls the operations of the database 10 in which the simulation data provided by the seismic motion simulation data providing device 2 is registered and updated, the seismic motion evaluation model 13 which is a trained model, and the seismic motion evaluation model generation device 3. The seismic motion evaluation model generation program 300 that realizes the seismic motion evaluation model generation method is stored. The storage unit 30 may store data such as seismic motion observation records and underground structure data provided by another data providing device, and may be further registered as a part of the database 10. Further, the database 10 may be stored in an external storage device instead of the storage unit 30, and in that case, the seismic motion evaluation model generation device 3 communicates with the external storage device via the network 5. The database 10 may be accessed.

The control unit 31 functions as a DB management unit 310, an acquisition unit 311 and a generation unit 312 by executing the seismic motion evaluation model generation program 300. The details of the functions of each part will be described later.

FIG. 3 is a functional explanatory diagram showing an example of the seismic motion evaluation model generation device 3 and the seismic motion evaluation model generation method according to the first embodiment of the present invention.

(About the database management process by the DB management unit 310 and the database 10)
The DB management unit 310 manages the database 10 based on the simulation data provided by the seismic motion simulation data providing device 2. Specifically, each time the seismic motion simulation is executed by the seismic motion simulation data providing device 2 and new simulation data is provided, the DB management unit 310 sets the simulation conditions and simulation results included in the simulation data to the seismic motion. It is registered in the database 10 as various characteristic parameters and seismic motion index calculation results.

FIG. 4 is a data structure diagram showing an example of the database 10 according to the first embodiment of the present invention. In the database 10, a plurality of seismic motion data 11 associated with seismic motion characteristic parameters and seismic motion indexes when the seismic motion simulation is executed are registered and stored.

The seismic motion characteristic parameters are various parameters that describe the seismic motion characteristics, and the seismic motion characteristics include, for example, the source characteristic, the propagation characteristic, and the site characteristic of the seismic motion, and further include the orientation characteristic. The seismic motion characteristic parameters are those in which the simulation conditions when the seismic motion simulation data providing device 2 executes the seismic motion simulation are classified and recorded according to the above-mentioned seismic motion characteristics.

In the present embodiment, the seismic motion characteristic parameters constituting the seismic motion data 11 are the source characteristic, propagation characteristic, and azimuth characteristic of the seismic motion when the seismic motion index at a predetermined target point is calculated for the seismic motion caused by the predetermined earthquake by the seismic motion simulation. It is numerical data showing. The source characteristics, propagation characteristics, site characteristics, and directional characteristics of seismic motion will be described below.

The epicenter characteristics are, for example, magnitude (moment magnitude Mw, Meteorological Agency magnitude, etc.), seismic center position (latitude lat_eq, longitude long_eq), epicenter depth H, earthquake type Type (inland crustal earthquake, plate boundary earthquake, slab earthquake), Fault type Mech (normal fault / reverse fault / strike-slip fault), seismic source mechanism solution (strike 1, tilt angle dip1, slip angle lake1), and conjugate solution of seismic source mechanism solution (strike2, tilt angle dip2, slip angle racke2) Etc. at least one. The epicenter characteristics according to this embodiment are the moment magnitude Mw, the epicenter position (latitude lat_eq, longitude lon_eq), the epicenter depth H, the earthquake type Type, the fault type Mech, the epicenter mechanism solution (Strike1, dip1, rake1), and the epicenter. It is a conjugate solution of the mechanism solution (Strike2, dip2, lake2).

The propagation characteristic is, for example, at least one of the epicentral distance X, the shortest fault distance, and the epicenter distance. The propagation characteristic according to the present embodiment is the epicentral distance X, and is calculated as the distance between the target point position indicating the position of the target point and the epicenter position.

The site characteristic is, for example, at least one of the target point position (latitude lat_site, longitude long_site), seismic base plane depth, engineering base plane depth, layer thickness, density, seismic wave propagation velocity, Q value, and attenuation constant. Is. The site characteristics according to this embodiment are the target point position (latitude lat_site, longitude long_site), the top layer S wave velocity VS1, the surface layer 10 m average S wave velocity AVS10, the surface layer 30 m average S wave velocity AVS30, microtopography classification JCODE, S. Wave velocity 700m / s layer upper surface depth D7, S wave velocity 1400m / s layer upper surface depth D17, S wave velocity 2100m / s layer upper surface depth D24, and seismic basement surface depth D28 (= S wave velocity 2700m / s layer upper surface depth). If the surface layer 30 m average S wave velocity AVS30 cannot be obtained from the underground structure data of the target point, the surface layer 30 m average S wave velocity AVS30 of the 250 m mesh of the Earthquake Hazard Station J-SHIS of the Disaster Prevention Research Institute is used instead. When the 10 m average S wave velocity AVS10 cannot be obtained from the underground structure data of the target point, the surface layer 30 m average S wave velocity AVS30 is used instead. In addition, the seismic base surface depth D28 is the bottom depth of the 28th layer of the deep ground model of the mesh including the target point position published at the Seismic Hazard Station J-SHIS of the National Research Institute for Earth Science and Disaster Prevention (the same model is used for the seismic base). It is equal to the depth of the upper surface of the 29th layer having a corresponding P wave velocity of 5000 m / s and an S wave velocity of 2700 m / s).

The azimuth characteristic is, for example, the epicenter azimuth Λ indicating the azimuth in which the epicenter is located with respect to the target point. Therefore, the epicenter direction Λ is calculated as the direction in which the epicenter position exists with reference to the target point position. At that time, the epicenter direction Λ is determined clockwise with true north as 0 °, and the amount is discontinuous with true north as the boundary. Therefore, the directional characteristics according to the present embodiment are sin Λ and cos Λ representing the epicenter direction Λ. Use a pair.

The seismic motion index calculation result is various seismic motion indexes that describe the strength and shaking of the seismic motion, and includes at least one of the amplitude characteristic, the periodic characteristic, and the temporal characteristic of the seismic motion. The seismic motion index calculation result is a classification and recording of the simulation results when the seismic motion simulation data providing device 2 executes the seismic motion simulation according to the above seismic motion index.

In the present embodiment, the seismic motion index calculation result constituting the seismic motion data 11 is the seismic motion index at the target point when the seismic motion index at a predetermined target point is calculated based on the seismic motion characteristic parameters (numerical data) by the seismic motion simulation. It is the numerical data shown. The amplitude characteristics, periodic characteristics, and temporal characteristics of seismic motion will be described below.

The amplitude characteristic is at least one of the maximum acceleration PGA, the maximum velocity, and the maximum displacement of the seismic motion. The amplitude characteristic according to this embodiment is the maximum acceleration PGA.

The periodic characteristic is a response value for at least one period in a response spectrum or a Fourier spectrum obtained from seismic motion observation records (acceleration, velocity, and time history waveform of displacement). The response spectrum is, for example, an acceleration response spectrum with respect to a predetermined attenuation constant (for example, 5%), a pseudo velocity response spectrum pSv, a velocity response spectrum, a displacement response spectrum, and the like. The Fourier spectrum is, for example, an acceleration Fourier spectrum, a velocity Fourier spectrum, a displacement Fourier spectrum, or the like. The periodic characteristics according to the present embodiment are pseudo-velocity response spectra pSv (0.1s) and pSv (0) having an attenuation constant of 5% in each period of 0.1 second, 0.5 second, 1 second, 3 seconds, and 5 seconds. .5s), pSv (1s), pSv (3s), pSv (5s).

The temporal characteristic is, for example, the response duration for at least one period in the response duration spectrum obtained from the seismic motion observation record (acceleration, velocity, and displacement time history waveform). The response duration spectrum is, for example, an acceleration response duration spectrum, a velocity response duration spectrum TSv, a displacement response duration spectrum, or the like with respect to a predetermined attenuation constant (for example, 5%). The temporal characteristics according to the present embodiment are the velocity response duration spectrum TSv (0.1s), TSv ( 0.5s), TSv (1s), TSv (3s), and TSv (5s). The parameters that define the start and end of the response duration are p1 = 0.03 and p2 = 0.95.

When the seismic motion simulation provides surface simulation data by calculating the seismic motion index for a plurality of target points included in a predetermined target area instead of one target point, each of them. A plurality of seismic motion data 11 corresponding to the seismic motion index of the target point are registered in the database 10. For example, the seismic motion simulation targets the Kanto region's six prefectures (Tokyo, Kanagawa, Chiba, Saitama, Ibaraki, Tochigi, Gunma), and the observation points 138 of the strong motion observation network K-NET included in the target area. When executed as a plurality of target points, the seismic motion index at 138 points is calculated as a simulation result, so that 138 seismic motion data 11 are registered in the database 10.

(About the acquisition process by the acquisition unit 311 and the learning data 12)
As shown in FIG. 3, the acquisition unit 311 uses seismic motion characteristic parameters (numerical data) as feature quantities from a plurality of seismic motion data 11 registered in the database 10 and seismic motion index calculation results (numerical data) as objective variables. , A plurality of learning data 12 composed of feature quantities and objective variables are acquired. The learning data 12 is data used as learning data (training data), verification data, and test data in supervised learning. Further, a set of learning data 12 composed of a plurality of learning data 12 is called a learning data set.

In the present embodiment, the feature quantities constituting the learning data 12 are the moment magnitude Mw, the epicenter depth H, the epicentral distance X, and the epicenter direction Λ (sinΛ and cosΛ) among the 24 types of seismic motion characteristic parameters shown in FIG. Pair), surface layer 30m average S wave velocity AVS30, and seismic basement surface depth (S wave velocity 2700m / s layer top surface depth) D28, and the objective variables constituting the training data 12 are shown in FIG. It will be described as one of the maximum acceleration PGA among the 11 types of seismic motion indexes shown in 4. The feature amount is not limited to the above 6 types of seismic motion characteristic parameters, and any seismic motion characteristic parameter may be selected and combined from 24 types of seismic motion characteristic parameters, or 24 types of seismic motion characteristic parameters may be combined. Other seismic motion characteristic parameters other than the above may be further combined as feature quantities.

(About the generation process by the generation unit 312 and the seismic motion evaluation model 13)
As shown in FIG. 3, the generation unit 312 learns the correlation between the feature amount and the objective variable by machine learning based on the plurality of learning data 12 acquired by the acquisition unit 311. The seismic motion evaluation model 13 is generated and stored in the storage unit 30. In this embodiment, a case where a gradient boosting decision tree is used as a machine learning algorithm in machine learning will be described.

FIG. 5 is a schematic diagram showing an outline of a gradient boosting tree. The gradient boosting tree is a learning device that combines gradient boosting and a decision tree. Gradient boosting is a method of constructing a strong learner (high-performance machine learning model) by combining multiple weak learners (low-performance machine learning model). Decision trees are a method of generating machine learning models that can be classified and regressed by performing conditional branching using the branch structure of trees. A gradient boosting tree that combines these two methods is a method of combining a plurality of weak learners generated by a decision tree by gradient boosting.

Of the 11 types of seismic motion indexes shown in FIG. 4, it is considered that the number of data for the maximum acceleration PGA and the pseudo-velocity response spectrum pSv decreases sharply as the amplitude increases. Therefore, in order to reduce the bias generated in the distribution map of the objective variable, it is preferable to use the common logarithms (log ₁₀ PGA and log ₁₀ pSv) as the data of the objective variable for the maximum acceleration PGA and the pseudo-velocity response spectrum pSv, respectively. Further, as a loss function in the gradient boosting tree, the least squares method (normal distribution map) is applied to the maximum acceleration PGA and the pseudo velocity response spectrum pSv, and the Poisson distribution map is applied to the velocity response duration spectrum TSv. Is preferable.

Further, when the generation unit 312 adopts the 11 types of seismic motion indexes shown in FIG. 4 as the objective variable when generating the seismic motion evaluation model 13 using the gradient boosting tree, the seismic motion evaluation model 13 is used as the objective variable. It may be generated every time. That is, the first seismic motion evaluation model 13A in which the correlation between the feature amount and the objective variable (maximum acceleration PGA = first type seismic motion index) is learned, the feature amount and the objective variable (pseudo-velocity response spectrum pSv (0.1s)). ) = The second seismic motion evaluation model 13B trained to correlate with the second type of seismic motion index), and the third seismic motion evaluation model 13C to the eleventh seismic motion evaluation model 13K are generated and totaled. Eleven seismic motion evaluation models 13A to 13K may be generated.

(About the configuration of the seismic motion evaluation device 4 and the process by each part)
The seismic motion evaluation device 4 evaluates and predicts seismic motion based on the seismic motion evaluation model 13 generated by the seismic motion evaluation model generation device 3, and outputs the result to an output medium such as a display medium or a paper medium.

Like the seismic motion evaluation model generator 3, the seismic motion evaluation device 4 is composed of a general-purpose or dedicated computer, and as shown in FIG. 2, a storage unit 40 composed of an HDD, a memory, and the like, a CPU, and a GPU. A control unit 41 composed of a processor such as the above, a communication unit 42 which is a communication interface with the network 5, an input unit 43 composed of a keyboard, a mouse, etc., and a display unit 44 composed of a display, a touch panel, etc. To prepare for.

The storage unit 40 stores a seismic motion evaluation model 13 generated as a trained model by the seismic motion evaluation model generator 3 and a seismic motion evaluation program 400 that controls the operation of the seismic motion evaluation device 4 to realize a seismic motion evaluation method. There is. The storage unit 40 may store data such as seismic motion observation records and underground structure data provided by another data providing device.

By executing the seismic motion evaluation program 400, the control unit 41 functions as a reception unit 410, a prediction unit 411, and an output processing unit 412. The details of the functions of each part will be described later.

FIG. 6 is a functional explanatory diagram showing an example of the seismic motion evaluation device 4 and the seismic motion evaluation method according to the first embodiment of the present invention.

(Regarding the reception process by the reception department 410)
The reception unit 410 receives various seismic motion characteristic parameters to be predicted. Specifically, the reception unit 410 has, for example, the moment magnitude Mw, the epicenter position, and the epicenter depth H of the earthquake assumed as the prediction target by the user of the seismic motion evaluation device 4 (hereinafter referred to as “assumed earthquake”). Is received via the input unit 33, and the predicted point position indicating the position of the predicted point for which the seismic motion due to the assumed earthquake is to be predicted, the surface layer 30 m average S wave velocity AVS30 and the earthquake base at the predicted point position. The surface depth D28 is also received via the input unit 33. When the underground structure data is stored in the storage unit 40, the reception unit 410 refers to the underground structure data to obtain a surface layer 30 m average S wave velocity AVS30 and an earthquake basement surface depth D28 at the predicted point position. May be obtained. Further, the predicted point positions may be plural, and may be, for example, each grid point at a predetermined grid spacing (for example, 5 km spacing).

Then, the reception unit 410 calculates the epicentral distance X and the epicenter direction Λ based on the epicenter position of the assumed earthquake and the predicted point position of the seismic motion. As a result, the reception unit 410 can use the seismic motion characteristic parameters to be predicted (moment magnitude Mw of the assumed earthquake, epicenter depth H of the assumed earthquake, epicentral distance X between the epicenter of the assumed earthquake and the predicted point position, and predicted point position). The seismic center direction Λ indicating the direction in which the epicenter position of the assumed earthquake exists, the surface layer 30 m average S wave velocity AVS30 at the predicted point position, and the seismic base plane depth D28) at the predicted point position are accepted.

(About the prediction process by the prediction unit 411)
The prediction unit 411 uses the seismic motion characteristic parameters (numerical data) of the prediction target received by the reception unit 410 as feature quantities, and the seismic motion evaluation model 13 (in this embodiment, six types of seismic motion characteristic parameters as feature quantities). Based on the objective variable (numerical data) output from the seismic motion evaluation model 13 by inputting one type of seismic motion index into the learned model) that has learned the correlation between the two, the seismic motion to be predicted. Predict the seismic motion index (predicted value) corresponding to various characteristic parameters. At that time, when the reception unit 410 accepts a plurality of assumed earthquakes or a plurality of predicted point positions to receive a plurality of seismic motion characteristic parameters as prediction targets, the prediction unit 411 receives a plurality of seismic motions. By inputting each of the various characteristic parameters into the seismic motion evaluation model 13, the seismic motion index (predicted value) corresponding to each of the plurality of seismic motion characteristic parameters is predicted.

When the seismic motion evaluation model 13 includes a total of 11 seismic motion evaluation models 13A to 13K generated for each objective variable (11 types of seismic motion indexes), the prediction unit 411 uses the seismic motion characteristic parameters to be predicted. Is input to a total of 11 seismic motion evaluation models 13A to 13K as feature quantities, and for each objective variable (11 types of seismic motion indicators) output from the total of 11 seismic motion evaluation models 13A to 13K, the seismic motion to be predicted The seismic motion index (predicted value) corresponding to various characteristic parameters may be predicted.

(About the output processing process by the output processing unit 412)
The output processing unit 412 outputs the predicted value of the seismic motion index predicted by the prediction unit 411 to a visible output medium. For example, when the output medium is a display medium such as the display unit 44, the output processing unit 412 generates display data (output data) for display on the display medium and displays and outputs the display data on the display medium. When the output medium is a paper medium, the output processing unit 412 generates print data (output data) for printing on the paper medium and prints and outputs the print data on the paper medium. The output processing unit 412 may output the output data to, for example, a seismic motion prediction map creation system, a hazard map creation system, or the like, or may output the output data to a disaster prevention system such as a public facility, a building, or a factory. You may do so.

For example, in the output processing unit 412, a plurality of seismic motions such that the seismic motion characteristic parameters of the prediction target received by the reception unit 410 set each grid point as the predicted point position for one assumed earthquake, for example. When it is a characteristic parameter, for example, a contour diagram so that the predicted values of a plurality of seismic motion indexes at each predicted point position predicted by the prediction unit 411 based on the plurality of seismic motion characteristic parameters are superimposed on the map. Or, it is output to the output medium as a color-coded mesh diagram.

Further, when the seismic motion characteristic parameters of the prediction target received by the reception unit 410 are a plurality of seismic motion characteristic parameters including a plurality of different directional characteristics centered on the predicted point position, the output processing unit 412 has the plurality. The predicted values of multiple seismic motion indexes in each direction predicted by the prediction unit 411 based on the various seismic motion characteristic parameters of the above are expressed as distances from the reference point in the output medium, and the multiple direction characteristics are centered on the reference point. By assigning to each direction, a plurality of seismic motion indexes are output to the output medium.

Further, when the seismic motion characteristic parameters of the prediction target received by the reception unit 410 are a plurality of seismic motion characteristic parameters including different epicentral distances, the output processing unit 412 is based on the plurality of seismic motion characteristic parameters. By expressing the predicted values of the plurality of seismic motion indexes predicted by the prediction unit 411 as the distance attenuation characteristics, the plurality of seismic motion indexes are output to the output medium.

As described above, according to the seismic motion evaluation model generation device 3 and the seismic motion evaluation model generation method according to the present embodiment, the seismic motion characteristic parameters and the seismic motion index calculation results when the seismic motion simulation is executed are characteristic quantities and objective variables, respectively. The seismic motion evaluation model 13 is generated based on the training data 12. Therefore, in the seismic motion evaluation model 13, the correlation between the seismic motion characteristic parameters and the seismic motion index calculation results when the seismic motion simulation is executed assuming various earthquakes that are considered to occur in the future is learned, and from various seismic motion simulations. The obtained findings are aggregated. Therefore, it is possible to provide a seismic motion evaluation model 13 that makes it possible to utilize the detailed knowledge individually obtained by the seismic motion simulation under limited conditions in a more generalized form.

Further, according to the seismic motion evaluation device 4 and the seismic motion evaluation method according to the present embodiment, by using the seismic motion evaluation model generation device 3 and the seismic motion evaluation model 13 generated by the seismic motion evaluation model generation method, individual experts can use the seismic motion evaluation device 4. Since the knowledge obtained individually by the seismic motion simulation is provided in a generalized form without depending on experience, it is possible to evaluate and predict the characteristics of the seismic motion due to the earthquake that is expected to occur in the future with high accuracy. ..

(Second embodiment)
In the seismic motion evaluation system 1 according to the second embodiment, the objective variable of the seismic motion evaluation model 13 is not the numerical data as in the first embodiment, but the distribution map of the seismic motion index in the target region represented by the image data. It differs from the first embodiment in some respects. Since other basic configurations and operations are the same as those of the first embodiment, the differences between the two will be mainly described below.

(About seismic motion evaluation model generator 3)
FIG. 7 is a functional explanatory diagram showing an example of the seismic motion evaluation model generation device 3 and the seismic motion evaluation model generation method according to the second embodiment of the present invention. FIG. 8 is a data structure diagram showing an example of the database 10 according to the second embodiment of the present invention.

The seismic motion characteristic parameters constituting the seismic motion data 11 are numerical data indicating the source characteristics of the seismic motion when the seismic motion index in a predetermined target area is calculated for the seismic motion caused by the predetermined earthquake by the seismic motion simulation. Further, the seismic motion index calculation result constituting the seismic motion data 11 is a distribution map of the seismic motion index in the target area when the seismic motion index in a predetermined target area is calculated based on various seismic motion characteristic parameters (numerical data) by the seismic motion simulation. It is the image data shown.

As shown in FIG. 7, the acquisition unit 311 uses seismic motion characteristic parameters (numerical data) as feature quantities from a plurality of seismic motion data 11 registered in the database 10 and seismic motion index calculation results (image data) as objective variables. , A plurality of learning data 12 composed of feature quantities and objective variables are acquired. In the present embodiment, the feature amount is the numerical data of the moment magnitude Mw indicating the epicenter characteristic, the epicenter position lat_eq, lon_eq, and the epicenter depth H, and the objective variable is the image data showing the seismic intensity distribution map in the target region.

The generation unit 312 machine-learns the correlation between the feature amount and the objective variable based on the plurality of learning data 12 acquired by the acquisition unit 311 (for example, a neural network, a convolutional neural network, a hostile generation network, etc.). As a trained model, the seismic motion evaluation model 13 is generated and stored in the storage unit 30.

(About seismic motion evaluation device 4)
FIG. 9 is a functional explanatory diagram showing an example of the seismic motion evaluation device 4 and the seismic motion evaluation method according to the second embodiment of the present invention.

The reception unit 410 receives numerical data (moment magnitude Mw, epicenter position lat_eq, long_eq, epicenter depth H) indicating the epicenter characteristics as various seismic motion characteristic parameters to be predicted. The prediction unit 411 uses the seismic motion characteristic parameters (numerical data) of the prediction target received by the reception unit 410 as feature quantities and inputs them into the seismic motion evaluation model 13, and the objective variable (objective variable) output from the seismic motion evaluation model 13. Based on the image data), the distribution map of the seismic motion index corresponding to the seismic motion characteristic parameters to be predicted is predicted. The output processing unit 412 outputs the distribution map of the seismic motion index predicted by the prediction unit 411 to a visible output medium.

As described above, according to the seismic motion evaluation model generation device 3 and the seismic motion evaluation model generation method according to the present embodiment, various seismic motion characteristic parameters (numerical data) and seismic motion index calculation results (image data) when the seismic motion simulation is executed. The seismic motion evaluation model 13 is generated based on the training data 12 having the feature amount and the objective variable, respectively. Therefore, in the seismic motion evaluation model 13, the correlation between the seismic motion characteristic parameters and the seismic motion index calculation results when the seismic motion simulation is executed assuming various earthquakes that are considered to occur in the future is learned, and the seismic source characteristics of the seismic motion are obtained. Based on this, the knowledge for evaluating and predicting the distribution map of the seismic motion index will be collected.

(Third embodiment)
In the seismic motion evaluation system 1 according to the third embodiment, the feature amount of the seismic motion evaluation model 13 is not the numerical data as in the second embodiment, but the seismic motion characteristics represented by the combination of the numerical data and the image data. It differs from the second embodiment in that it is a parameter. Since other basic configurations and operations are the same as those of the second embodiment, the differences between the two will be mainly described below.

(About seismic motion evaluation model generator 3)
FIG. 10 is a functional explanatory diagram showing an example of the seismic motion evaluation model generation device 3 and the seismic motion evaluation model generation method according to the third embodiment of the present invention. FIG. 11 is a data structure diagram showing an example of the database 10 according to the third embodiment of the present invention.

The seismic motion characteristic parameters constituting the seismic motion data 11 are numerical data indicating the source characteristics of the seismic motion when the seismic motion index in the predetermined target area is calculated for the seismic motion caused by the predetermined earthquake by the seismic motion simulation, and the site characteristics in the target area. It is image data which shows a distribution map. Further, the seismic motion index calculation result constituting the seismic motion data 11 is the seismic motion index in the target area when the seismic motion index in a predetermined target area is calculated based on various seismic motion characteristic parameters (numerical data and image data) by the seismic motion simulation. It is image data which shows a distribution map.

As shown in FIG. 10, the acquisition unit 311 uses seismic motion characteristic parameters (numerical data and image data) as feature quantities from a plurality of seismic motion data 11 registered in the database 10 and obtains seismic motion index calculation results (image data). As the objective variable, a plurality of learning data 12 composed of the feature amount and the objective variable are acquired. In the present embodiment, the feature quantities are numerical data of moment magnitude Mw indicating the epicenter characteristics, epicenter position rat_eq, lon_eq, and epicenter depth H, and image data showing a distribution map of the epicenter surface depth D28, which are objective variables. Is image data showing a seismic intensity distribution map in the target area.

The generation unit 312 machine-learns the correlation between the feature amount and the objective variable based on the plurality of learning data 12 acquired by the acquisition unit 311 (for example, a neural network, a convolutional neural network, a hostile generation network, etc.). As a trained model, the seismic motion evaluation model 13 is generated and stored in the storage unit 30.

The image data showing the distribution map of the site characteristics as the feature quantity may represent the underground structure, topography, etc. as the site characteristics, and represents various seismic motion characteristic parameters other than the site characteristics shown in FIG. It may be a thing. Further, the image data as the feature amount may be image data showing a plurality of seismic motion characteristic parameters, and not only the distribution map of the seismic base surface depth D28 but also, for example, the distribution map of the surface layer 30 m average S wave velocity AVS30. It may be included.

(About seismic motion evaluation device 4)
FIG. 12 is a functional explanatory diagram showing an example of the seismic motion evaluation device 4 and the seismic motion evaluation method according to the third embodiment of the present invention.

The reception unit 410 contains numerical data showing the epicenter characteristics (moment magnitude Mw, epicenter position rat_eq, long_eq, epicenter depth H) as seismic motion characteristic parameters to be predicted, and a distribution map of site characteristics in the target area (earthquake infrastructure surface). Image data showing the distribution map of the depth D28) is accepted. The prediction unit 411 outputs from the seismic motion evaluation model 13 by inputting the seismic motion characteristic parameters (numerical data and image data) of the prediction target received by the reception unit 410 into the seismic motion evaluation model 13 as feature quantities. Based on the objective variable (image data), the distribution map of the seismic motion index corresponding to the seismic motion characteristic parameters to be predicted is predicted. The output processing unit 412 outputs the distribution map of the seismic motion index predicted by the prediction unit 411 to a visible output medium.

As described above, according to the seismic motion evaluation model generation device 3 and the seismic motion evaluation model generation method according to the present embodiment, various seismic motion characteristic parameters (numerical data and image data) and seismic motion index calculation results (numerical data and image data) when the seismic motion simulation is executed. The seismic motion evaluation model 13 is generated based on the training data 12 in which the image data) is used as the feature amount and the objective variable, respectively. Therefore, in the seismic motion evaluation model 13, the correlation between the seismic motion characteristic parameters and the seismic motion index calculation results when the seismic motion simulation is executed assuming various earthquakes that are considered to occur in the future is learned, and the distribution of the underground structure data is learned. Knowledge for evaluating and predicting the distribution map of seismic motion index is collected based on the figure.

(Fourth Embodiment)
In the seismic motion evaluation system 1 according to the fourth embodiment, the feature amount of the seismic motion evaluation model 13 is not the combination of the numerical data and the image data as in the third embodiment, but the image data in which the numerical data is embedded. It differs from the third embodiment in that it is a seismic motion characteristic parameter represented. Since other basic configurations and operations are the same as those of the third embodiment, the differences between the two will be mainly described below.

(About seismic motion evaluation model generator 3)
FIG. 13 is a functional explanatory diagram showing an example of the seismic motion evaluation model generation device 3 and the seismic motion evaluation model generation method according to the fourth embodiment of the present invention. FIG. 14 is a data structure diagram showing an example of the database 10 according to the fourth embodiment of the present invention.

The seismic motion characteristic parameters constituting the seismic motion data 11 are images in which numerical data indicating the source characteristics of the seismic motion is embedded when the seismic motion index in a predetermined target area is calculated for the seismic motion caused by the predetermined earthquake by the seismic motion simulation. , Image data showing a distribution map of site characteristics in the target area. Further, the seismic motion index calculation result constituting the seismic motion data 11 is obtained in the target area when the seismic motion index in a predetermined target area is calculated based on various seismic motion characteristic parameters (image data in which numerical data is embedded) by seismic motion simulation. It is image data which shows the distribution map of the seismic motion index.

As shown in FIG. 13, the acquisition unit 311 uses seismic motion characteristic parameters (image data in which numerical data is embedded) as feature quantities from a plurality of seismic motion data 11 registered in the database 10, and seismic motion index calculation results (images). Data) is used as the objective variable, and a plurality of learning data 12 composed of the feature amount and the objective variable are acquired. In the present embodiment, the feature amount is an image showing the distribution map of the seismic base plane depth D28 in which the moment magnitude Mw and the numerical data indicating the epicenter depth H are recorded with respect to the epicenter position lat_eq and lon_eq indicating the epicenter characteristics. It is data, and the objective variable is image data showing a seismic intensity distribution map in a target area.

The generation unit 312 machine-learns the correlation between the feature amount and the objective variable based on the plurality of learning data 12 acquired by the acquisition unit 311 (for example, a neural network, a convolutional neural network, a hostile generation network, etc.). As a trained model, the seismic motion evaluation model 13 is generated and stored in the storage unit 30.

(About seismic motion evaluation device 4)
FIG. 15 is a functional explanatory diagram showing an example of the seismic motion evaluation device 4 and the seismic motion evaluation method according to the fourth embodiment of the present invention.

The reception unit 410 is image data in which numerical data indicating the epicenter characteristics (moment magnitude Mw, epicenter position rat_eq, long_eq, epicenter depth H) is embedded as various seismic motion characteristic parameters to be predicted, and is a site in the target area. It accepts image data showing a distribution map of characteristics (distribution map of seismic base plane depth D28). The prediction unit 411 uses the seismic motion characteristic parameters (image data in which numerical data is embedded) of the prediction target received by the reception unit 410 as feature quantities and inputs them into the seismic motion evaluation model 13 from the seismic motion evaluation model 13. Based on the output objective variable (image data), the distribution map of the seismic motion index corresponding to the seismic motion characteristic parameters to be predicted is predicted. The output processing unit 412 outputs the distribution map of the seismic motion index predicted by the prediction unit 411 to a visible output medium.

As described above, according to the seismic motion evaluation model generation device 3 and the seismic motion evaluation model generation method according to the present embodiment, various seismic motion characteristic parameters (image data with embedded numerical data) and seismic motion index when the seismic motion simulation is executed. A seismic motion evaluation model 13 is generated based on the learning data 12 in which the calculation result (image data) is used as a feature amount and an objective variable, respectively. Therefore, in the seismic motion evaluation model 13, the correlation between the seismic motion characteristic parameters and the seismic motion index calculation results when the seismic motion simulation is executed assuming various earthquakes that are considered to occur in the future is learned, and the seismic source characteristics and the seismic motion index are learned. Knowledge for evaluating and predicting the distribution map of seismic motion index is collected based on the distribution map of underground structure data.

(Fifth Embodiment)
In the seismic motion evaluation system 1 according to the fifth embodiment, the objective variable of the seismic motion evaluation model 13 is not the numerical data as in the first embodiment, but the spectral diagram of the seismic motion index at the target point represented by the image data. It differs from the first embodiment in some respects. Since other basic configurations and operations are the same as those of the first embodiment, the differences between the two will be mainly described below.

(About seismic motion evaluation model generator 3)
FIG. 16 is a functional explanatory diagram showing an example of the seismic motion evaluation model generation device 3 and the seismic motion evaluation model generation method according to the fifth embodiment of the present invention. FIG. 17 is a data structure diagram showing an example of the database 10 according to the fifth embodiment of the present invention.

The seismic motion characteristic parameters constituting the seismic motion data 11 are numerical data indicating the source characteristics, propagation characteristics, and site characteristics of the seismic motion when the seismic motion index at a predetermined target point is calculated for the seismic motion caused by the predetermined earthquake by the seismic motion simulation. be. Further, the seismic motion index calculation result constituting the seismic motion data 11 is a spectral diagram of the seismic motion index at the target point when the seismic motion index at a predetermined target point is calculated based on various seismic motion characteristic parameters (numerical data) by the seismic motion simulation. It is the image data shown.

As shown in FIG. 16, the acquisition unit 311 uses seismic motion characteristic parameters (numerical data) as feature quantities from a plurality of seismic motion data 11 registered in the database 10, and seismic motion index calculation results (image data) as objective variables. , A plurality of learning data 12 composed of feature quantities and objective variables are acquired. In this embodiment, there are six types of feature quantities: moment magnitude Mw, epicenter depth H, epicentral distance X, epicenter direction Λ, surface layer 30 m average S wave velocity AVS30, and earthquake base surface depth D28 for learning. The objective variable constituting the data 12 is image data showing a spectral diagram of the pseudo-velocity response spectrum pSv.

The generation unit 312 machine-learns the correlation between the feature amount and the objective variable based on the plurality of learning data 12 acquired by the acquisition unit 311 (for example, a neural network, a convolutional neural network, a hostile generation network, etc.). As a trained model, the seismic motion evaluation model 13 is generated and stored in the storage unit 30.

The image data showing the spectrum diagram of the seismic motion index as the objective variable may be a color image or a gray scale image, and it is preferable that the unit and scale of the coordinate axes are standardized among a plurality of image data, but conversion is performed. If possible. Further, the image data may include one type of spectrum diagram or may include a plurality of types of spectrum diagrams.

(About seismic motion evaluation device 4)
FIG. 18 is a functional explanatory diagram showing an example of the seismic motion evaluation device 4 and the seismic motion evaluation method according to the fifth embodiment of the present invention.

The reception unit 410 has numerical data (moment magnitude Mw, epicenter depth H, epicentral distance X, epicenter direction Λ, surface layer 30 m average S wave velocity AVS30, earthquake) showing pseudo-velocity response spectrum pSv as various characteristic parameters of seismic motion to be predicted. Base surface depth D28) is accepted. The prediction unit 411 uses the seismic motion characteristic parameters (numerical data) of the prediction target received by the reception unit 410 as feature quantities and inputs them into the seismic motion evaluation model 13, and the objective variable (objective variable) output from the seismic motion evaluation model 13. Based on the image data), the spectral diagram of the seismic motion index corresponding to the seismic motion characteristic parameters to be predicted is predicted. The output processing unit 412 outputs the spectral diagram of the seismic motion index predicted by the prediction unit 411 to a visible output medium.

As described above, according to the seismic motion evaluation model generation device 3 and the seismic motion evaluation model generation method according to the present embodiment, various seismic motion characteristic parameters (numerical data) and seismic motion index calculation results (image data) when the seismic motion simulation is executed. The seismic motion evaluation model 13 is generated based on the training data 12 having the feature amount and the objective variable, respectively. Therefore, in the seismic motion evaluation model 13, the correlation between the seismic motion characteristic parameters and the seismic motion index calculation results when the seismic motion simulation is executed assuming various earthquakes that are considered to occur in the future is learned, and the seismic source characteristics and the seismic motion index are learned. Knowledge for evaluating and predicting the distribution map of seismic motion index is collected based on the distribution map of underground structure data.

(Other embodiments)
Although the embodiments of the present invention have been described above, the present invention is not limited to the above embodiments and can be appropriately modified without departing from the technical idea of the present invention.

For example, in the first embodiment described above, the area subject to the seismic motion evaluation model 13 has been described as being in the Kanto region, but the area subject to the seismic motion evaluation model 13 is not limited to this, and is also a target. The range and shape of the area may be changed arbitrarily. Further, the seismic motion evaluation model 13 may not only target an area but also an arbitrary point, or may target a point group in which a plurality of points are grouped according to a predetermined classification standard.

Further, in each of the above embodiments, the seismic motion evaluation model generation program 300 and the seismic motion evaluation program 400 have been described as being stored in the storage units 30 and 40, respectively, but the CD is in an installable format or an executable format. -It may be recorded and provided on a computer-readable recording medium such as a ROM, DVD, or USB memory. Further, the seismic motion evaluation model generation program 300 and the seismic motion evaluation program 400 may be provided by storing them on a computer connected to a network such as the Internet and downloading them via the network.

1 ... Seismic motion evaluation system, 2 ... Seismic motion simulation data providing device,
3 ... Seismic motion evaluation model generator, 4 ... Seismic motion evaluation device, 5 ... Network,
10 ... database, 11, 11A, 11B ... seismic motion data 12 ... learning data, 13, 13A to 13K ... seismic motion evaluation model,
30 ... storage unit, 31 ... control unit, 32 ... communication unit, 33 ... input unit, 34 ... display unit,
40 ... storage unit, 41 ... control unit, 42 ... communication unit, 43 ... input unit, 44 ... display unit,
300 ... Seismic motion evaluation model generation program,
310 ... DB management unit, 311 ... acquisition unit, 312 ... generation unit 400 ... seismic motion evaluation program,
410 ... Reception unit, 411 ... Prediction unit, 412 ... Output processing unit

Claims (9)

It is a seismic motion evaluation model generation method that generates a seismic motion evaluation model by machine learning using a computer.
The seismic motion characteristic parameters are characterized from a database that stores multiple seismic motion data associated with the seismic motion index calculation results when the seismic motion index is calculated based on the seismic motion characteristic parameters. An acquisition process for acquiring a plurality of learning data composed of the feature quantity and the objective variable, using the seismic motion index calculation result as an amount and the objective variable.
The seismic motion evaluation model as a learned model of the machine learning by learning the correlation between the feature amount and the objective variable by the machine learning based on the plurality of learning data acquired in the acquisition step. To produce a production process, including,
Seismic motion evaluation model generation method. The seismic motion characteristic parameters are
Numerical data showing the source characteristics, propagation characteristics, and site characteristics of the seismic motion when the seismic motion index at a predetermined target point is calculated for the seismic motion caused by the predetermined earthquake by the seismic motion simulation.
The seismic motion index calculation result is
Numerical data showing the seismic motion index at the target point.
The method for generating a seismic motion evaluation model according to claim 1. The seismic motion characteristic parameters are
It is numerical data showing the epicenter characteristic of the seismic motion when the seismic motion index in a predetermined target area is calculated for the seismic motion caused by the predetermined earthquake by the seismic motion simulation.
The seismic motion index calculation result is
Image data showing a distribution map of the seismic motion index in the target area.
The method for generating a seismic motion evaluation model according to claim 1. The seismic motion characteristic parameters are
Numerical data showing the source characteristics of the seismic motion and image data showing the distribution map of the site characteristics in the target region when the seismic motion index in the predetermined target area is calculated for the seismic motion caused by the predetermined earthquake by the seismic motion simulation. ,
The seismic motion index calculation result is
Image data showing a distribution map of the seismic motion index in the target area.
The method for generating a seismic motion evaluation model according to claim 1. The seismic motion characteristic parameters are
Image data in which numerical data indicating the source characteristics of the seismic motion is embedded when the seismic motion index in a predetermined target area is calculated for the seismic motion caused by the predetermined earthquake by the seismic motion simulation, and is the image data of the site characteristics in the target area. This is the image data showing the distribution map.
The seismic motion index calculation result is
Image data showing a distribution map of the seismic motion index in the target area.
The method for generating a seismic motion evaluation model according to claim 1. The seismic motion characteristic parameters are
Numerical data showing the source characteristics, propagation characteristics, and site characteristics of the seismic motion when the seismic motion index at a predetermined target point is calculated for the seismic motion caused by the predetermined earthquake by the seismic motion simulation.
The seismic motion index calculation result is
Image data showing a spectral diagram of the seismic motion index at the target point.
The method for generating a seismic motion evaluation model according to claim 1. A seismic motion evaluation method for evaluating the characteristics of seismic motion based on the seismic motion evaluation model generated by the seismic motion evaluation model generation method according to any one of claims 1 to 6, using a computer.
The reception process that accepts the seismic motion characteristic parameters to be predicted,
The prediction target is based on the objective variable output from the seismic motion evaluation model by inputting the seismic motion characteristic parameters of the prediction target received in the reception step into the seismic motion evaluation model as the feature quantities. A prediction step for predicting the seismic motion index corresponding to the seismic motion characteristic parameters, and the like.
Seismic motion evaluation method. It ’s a computer,
A control unit for executing each step included in the seismic motion evaluation model generation method according to any one of claims 1 to 6.
Seismic motion evaluation model generator. It ’s a computer,
A control unit for executing each step included in the seismic motion evaluation method according to claim 7 is provided.
Seismic motion evaluation device.

Images