Method for constructing a water level prediction model, program for constructing a water level prediction model, method for outputting water level prediction data, program for outputting water level prediction data, method for interpolating test data, and method for calculating the accuracy of water level predictions.

Abstract

This disclosure aims to improve the accuracy of water level prediction in the downstream area of ​​a dam to the same level as in general river areas, using a water level prediction model. [Solution] In this disclosure, the training data extraction unit 2 extracts, as training data necessary for learning the water level at a water level prediction point downstream of the dam, at least one of the water level data WL and rainfall data RD, and dam discharge data DD indicating the discharge amount at the dam at that time, in the past before that time, and in the future before that time. The water level prediction model construction unit 3 then constructs a water level prediction model M for predicting the water level at a water level prediction point downstream of the dam using at least one of the water level data WL and rainfall data RD and the dam discharge data DD.

Description

[Technical Field]

[0001] This disclosure relates to a technology for learning and predicting water levels at water level prediction points in the downstream area of ​​a dam. [Background technology]

[0002] A technique for learning and predicting water levels at water level prediction points in a river area using machine learning models such as neural networks is disclosed in Patent Document 1, etc.

[0003] First, a water level prediction model is constructed using training data. Specifically, as training data necessary to learn the water level at a given time at a water level prediction point, at least one of the following is extracted: (1) water level data showing the water level at the time and at least one of the past time at at least one of the water level prediction point and upstream of the water level prediction point; and (2) rainfall data showing the rainfall at the time, at least one of the past time and at least one of the future time at at least one of the water level prediction point and upstream of the water level prediction point. Then, a water level prediction model is constructed to predict the water level at the water level prediction point using at least one of the water level data and rainfall data.

[0004] Next, the water level at the prediction point is predicted using the water level prediction model constructed with training data. Specifically, as test data necessary to predict the water level at a given time at the prediction point, at least one of the following is input into the water level prediction model: (1) water level data showing the water level at the time and at least one of the past times at at least one of the prediction point and upstream of the prediction point, and (2) rainfall data showing the rainfall at the time, at least one of the past times and at least one of the future times at at least one of the prediction point and upstream of the prediction point. The water level prediction model then outputs the predicted water level data for that time at the prediction point. [Prior art documents] [Patent Documents]

[0005] [Patent Document 1] Japanese Patent Publication No. 2019-095240 [Overview of the project] [Problems that the invention aims to solve]

[0006] Figure 1 illustrates the challenges of conventional water level prediction processing. The upper part of Figure 1 shows the temporal changes in water level (indicated by the left arrow) and rainfall (indicated by the right arrow) in the downstream area of ​​the dam. It can be seen that the water level in the downstream area of ​​the dam changes over time with low correlation to the rainfall in the downstream area. The lower part of Figure 1 shows the temporal changes in water level (indicated by the left arrow) and dam discharge (indicated by the right arrow) in the downstream area of ​​the dam. It can be seen that the water level in the downstream area of ​​the dam changes over time with high correlation to the dam discharge (the longer the distance from the dam, the greater the delay in water level change).

[0007] Therefore, unlike in general river areas, in the downstream area of ​​a dam, even if the water level prediction model for general river areas described in Patent Document 1 is used, it is not possible to improve the accuracy of water level prediction.

[0008] Therefore, in order to solve the aforementioned problems, this disclosure aims to improve the accuracy of water level prediction in the downstream area of ​​a dam to the same level as in general river areas, using a water level prediction model. [Means for solving the problem]

[0009] To solve the aforementioned problem, training data necessary for learning the water level at a water level prediction point downstream of the dam is extracted, which includes at least one of the water level data and rainfall data, and dam discharge data showing the discharge amount at the dam at that time, in the past, and in the future. Then, a water level prediction model is constructed to predict the water level at the water level prediction point downstream of the dam using at least one of the water level data and rainfall data, and the dam discharge data.

[0010] Specifically, the present disclosure is a method for constructing a water level prediction model, comprising, in order, a training data extraction step of extracting (1) water level data showing at least one of the water levels at the water level prediction point and

[0011] With this configuration, it is possible to construct a water level prediction model in the downstream area of ​​the dam that improves the accuracy of water level prediction to the same level as in general river areas, by also using dam discharge data.

[0012] Furthermore, this disclosure provides a method for constructing a water level prediction model, characterized in that the training data extraction step extracts dam upstream rainfall data as rainfall data, which shows at least one of the rainfall amounts for the time, past the time, and future the time, in the watershed upstream of the dam.

[0013] This configuration allows for the construction of a water level prediction model that improves the accuracy of water level predictions by using not only dam discharge data but also rainfall data from upstream of the dam.

[0014] Furthermore, this disclosure is a method for constructing a water level prediction model, characterized in that the training data extraction step extracts at least one of the following as upstream rainfall data for the dam: (1) instantaneous rainfall data showing the amount of rain at any instant among the time, the time in the past, and the time in the future in the basin upstream of the dam; (2) total rainfall data showing the total amount of rain from the start of rainfall to at least one of the time, the time in the past, and the time in the future in the basin upstream of the dam (however, it is reset to 0 when a predetermined time has elapsed from the time when no rain started); and (3) average rainfall data showing the average amount of rain within a predetermined average period up to at least one of the time, the time in the past, and the time in the future in the basin upstream of the dam.

[0015] With this configuration, using total rainfall data as upstream rainfall data, a water level prediction model can be constructed that improves the accuracy of water level prediction by considering the time required from rainfall in the upstream area of ​​the dam to inflow into the upstream area of ​​the dam. Furthermore, using average rainfall data as upstream rainfall data, a water level prediction model can be constructed that improves the accuracy of water level prediction without abruptly resetting the data to zero, unlike with total rainfall data.

[0016] Furthermore, this disclosure provides a method for constructing a water level prediction model, characterized in that it further includes a water level prediction model selection step after the water level prediction model construction step, in which verification data for verifying the water level prediction model is input into multiple types of the water level prediction models constructed using multiple types of the training data, and a water level prediction model is selected that performs water level predictions that better meet the issuance criteria.

[0017] This configuration allows for the selection of the optimal water level prediction model from multiple water level prediction models constructed using multiple types of training data, such that the generalization performance is high near the water level peak (especially near the water level peak that serves as the basis for issuing evacuation advisories, etc.).

[0018] In addition, the present disclosure is a water level prediction model construction program for causing a computer to execute each processing step included in the water level prediction model construction method described above in order.

[0019] According to this configuration, a program having the effects described above can be provided.

[0020] In addition, when predicting the water level at the water level prediction point downstream of the dam using the water level prediction model constructed by the water level prediction model construction method described above, as test data necessary for predicting the water level at a certain time at the water level prediction point, at least any one of the water level data and the rainfall data, and the dam discharge data are input into the water level prediction model, and water level prediction data indicating the predicted water level at that time at the water level prediction point is output from the water level prediction model, and a water level prediction data output method is characterized by including this.

[0021] According to this configuration, in the downstream area of the dam, the prediction accuracy of the water level can be improved in the same manner as in the general river area by using the water level prediction model constructed using the dam discharge data as well.

[0022] In addition, the present disclosure is a water level prediction data output program for causing a computer to execute the water level prediction data output step included in the water level prediction data output method described above.

[0023] According to this configuration, a program having the effects described above can be provided.

[0024] In order to solve further problems, when interpolating the water level data at the time of missing measurement in the downstream area of the dam as test data, when reflecting the dam discharge, rainfall, and actual water level situation at a prediction time arbitrarily before the time of missing measurement, interpolation is performed using the water level prediction data at the time of missing measurement arbitrarily after the prediction time in the downstream area of the dam that is output.

[0025] Specifically, the present disclosure is a test data interpolation method characterized in that, when the water level data at the water level prediction point is missing in the test data extracted by the water level prediction data output method described above, the water level data interpolation step comprises a test data interpolation step which interpolates the water level data at the time of the missing data at the water level prediction point using the water level prediction data output by the water level prediction data output at a prediction time arbitrarily prior to the time of the missing data, and at a time of the missing data that is arbitrarily later than the prediction time at the water level prediction point.

[0026] With this configuration, even when water level test data is missing in the downstream area of ​​the dam, the accuracy of water level prediction in the downstream area of ​​the dam can be improved by reflecting dam discharge, rainfall, and actual water level conditions, and then interpolating the water level test data from the downstream area of ​​the dam.

[0027] To address further challenges, water level data, historical rainfall data, future rainfall forecast data, and dam discharge data are extracted as verification data. The percentage of water level prediction data that falls within the error range surrounding the water level observation data is calculated as the water level prediction accuracy rate.

[0028] Specifically, this disclosure is a method for calculating the accuracy of a water level prediction, comprising, in order: a verification data extraction step of extracting, as verification data for verifying the water level prediction model constructed by the water level prediction model construction method described above, the water level data, past observed rainfall data and future forecast rainfall data as rainfall data, and the dam discharge data; a water level prediction data output step of inputting, as verification data, the water level data, past observed rainfall data, future forecast rainfall data, and dam discharge data for verifying the water level at multiple times at the water level prediction point, into the water level prediction model, and outputting water level prediction data from the water level prediction model that shows the predicted water level at those multiple times at the water level prediction point; and a water level prediction accuracy calculation step of calculating, as the accuracy of the prediction of the water level at the water level prediction point, the proportion of the water level prediction data at those multiple times at the water level prediction point that falls within the error range around the water level observation data at those multiple times at the water level prediction point.

[0029] With this configuration, since future observed rainfall data cannot be extracted as test data during the prediction phase, even when future forecast rainfall data is extracted, the reliability of the water level prediction data can be visualized by calculating the water level prediction accuracy rate during the verification phase.

[0030] Furthermore, the inventions disclosed above can be combined as much as possible. [Effects of the Invention]

[0031] Thus, this disclosure demonstrates that, in the downstream area of ​​a dam, the water level prediction accuracy can be improved to the same level as in general river areas by using a water level prediction model. [Brief explanation of the drawing]

[0032] [Figure 1] This figure shows the challenges of conventional water level prediction processing techniques. [Figure 2] This figure shows the configuration of the water level prediction device disclosed herein. [Figure 3] This figure shows the procedure for water level prediction processing in this disclosure. [Figure 4] This figure shows the dam discharge data and upstream rainfall data of the dam as disclosed herein. [Figure 5] This figure shows the total rainfall data and average rainfall data disclosed herein. [Figure 6] This figure shows examples of prior art and the water level prediction process described herein. [Figure 7] This figure shows the configuration of the water level prediction device disclosed herein. [Figure 8] This diagram shows the procedure for selecting a water level prediction model in this disclosure. [Figure 9] This figure shows a specific example of the synthesis process of training data as described in this disclosure. [Figure 10] This figure shows a specific example of the selection process for the water level prediction model disclosed herein. [Figure 11] This figure shows the configuration of the water level prediction device disclosed herein. [Figure 12] This figure shows the procedure for the test data interpolation process described herein. [Figure 13] This figure shows a specific example of the water level test data interpolation process described herein. [Figure 14] This figure shows a specific example of the rainfall test data interpolation process described herein. [Figure 15] This figure shows the configuration of the water level prediction device disclosed herein. [Figure 16] This diagram shows the procedure for calculating the accuracy rate of water level predictions as disclosed herein. [Figure 17] This figure shows a specific example of the water level prediction error range setting process disclosed herein. [Figure 18] This figure shows a specific example of the water level prediction accuracy calculation process disclosed herein. [Modes for carrying out the invention]

[0033] Embodiments of the present disclosure will be described with reference to the attached drawings. The embodiments described below are examples of the implementation of the present disclosure, and the present disclosure is not limited to these embodiments.

[0034] (Procedure for water level prediction processing in this disclosure) Figure 2 shows the configuration of the water level prediction device disclosed in this disclosure. Figure 3 shows the procedure for the water level prediction process disclosed in this disclosure. A technology for learning and predicting water levels at water level prediction points in the downstream area of ​​a dam using machine learning models such as neural networks is disclosed in the following description of this disclosure.

[0035] The water level prediction device W is equipped with a dam upstream rainfall data conversion unit 1, a training data extraction unit 2, and a water level prediction model construction unit 3 to execute the water level prediction model construction method (steps S1 to S3). It constructs a water level prediction model M and can be realized by installing the water level prediction model construction program (steps S1 to S3) shown in Figure 3 onto a computer.

[0036] The water level prediction device W is equipped with a dam upstream rainfall data conversion unit 1, a test data extraction unit 4, and a water level prediction data output unit 5 to execute the water level prediction data output method (steps S4 to S6). It can be realized by applying the water level prediction model M and installing the water level prediction data output program (steps S4 to S6) shown in Figure 3 onto a computer.

[0037] In the following, we will first describe the training phase processing (steps S1-S3) of the water level prediction model M disclosed herein, then describe the prediction phase processing (steps S4-S6) of the water level prediction model M disclosed herein, and finally describe examples of the prior art and the water level prediction processing disclosed herein.

[0038] The training data extraction unit 2 extracts the following as training data necessary for learning the water level at a water level prediction point downstream of the dam at a given time: (1) water level data WL showing the water level at the time and at least one of the past water levels at at least one of the water level prediction point and at a point upstream of the water level prediction point; (2) rainfall data RD showing the rainfall at the time, at least one of the past water levels and at least one of the future rainfall at at least one of the water level prediction point and the upstream water basin; and (3) dam discharge data DD showing the discharge amount at the time, at least one of the past water levels and at least one of the future rainfall at the dam (step S2). Here, for the rainfall data RD, "upstream water basin" may also include "upstream point only". And for the dam discharge data DD, "past and present observation data" and "future planned data" are included.

[0039] Here, the training data extraction unit 2 preferably extracts rainfall and water level data from periods with a high correlation to the water level during floods at the water level prediction points downstream of the dam, and preferably discards rainfall and water level data from periods with a low correlation.

[0040] For example, the training data extraction unit 2 may, as training data, (1) set a water level peak discrimination threshold that rejects periods of no water level fluctuation and then select a period for extracting water level data; (2) set a water level peak extraction width that rejects periods of no water level fluctuation and then select a period for extracting water level data; (3) set a predetermined water level period for extracting periods of rising and falling water levels and then select a period for extracting water level data; (4) set a predetermined rainfall period that takes into account the time it takes for rainfall to reach the water level prediction point and then select a period for extracting rainfall data; or (5) set a predetermined cumulative period that takes into account the time it takes for rainfall to flow from the soil or reservoir into the river and then select a period for extracting rainfall data (see Patent Document 1).

[0041] The water level prediction model construction unit 3 constructs a water level prediction model M for predicting the water level at a water level prediction point downstream of the dam, using at least one of the water level data WL and rainfall data RD, and dam discharge data DD (step S3).

[0042] In this way, by using dam discharge data DD in the downstream area of ​​the dam, it is possible to construct a water level prediction model M that improves the accuracy of water level prediction to the same level as in general river areas.

[0043] The test data extraction unit 4 extracts the following test data necessary for predicting the water level at a water level prediction point downstream of the dam at a given time: (1) water level data WL showing the water level at the time and at least one of the past times at at least one of the water level prediction point and at least one of the points upstream of the water level prediction point; (2) rainfall data RD showing the rainfall at the time, at least one of the past times and at least one of the future times at at least one of the water level prediction point and the water basin upstream of the water level prediction point; and (3) dam discharge data DD showing the discharge amount at the time, at least one of the past times and at least one of the future times at the dam (step S5). Here, for the rainfall data RD, "upstream water basin" may also include "upstream points only". And for the dam discharge data DD, "past and present observation data" and "future planned data" are included.

[0044] The water level prediction data output unit 5 inputs at least one of the water level data WL and rainfall data RD, along with dam discharge data DD, as test data to the water level prediction model M (step S5), and outputs water level prediction data P from the water level prediction model M, which shows the predicted water level at that time at a water level prediction point downstream of the dam (step S6).

[0045] In this way, in the downstream area of ​​the dam, the water level prediction accuracy can be improved to the same level as in general river areas by using the water level prediction model M constructed using dam discharge data DD.

[0046] The dam discharge data and dam upstream rainfall data disclosed herein are shown in Figure 4. The dam upstream rainfall data conversion unit 1 generates dam upstream rainfall data RD, which shows at least one of the rainfall amounts in the basin upstream of the dam at the current time, in the past, or in the future (steps S1, S4). The training data extraction unit 2 and the test data extraction unit 4 extract the dam upstream rainfall data as rainfall data RD (steps S2, S5). Here, for the dam upstream rainfall data, "upstream basin" may also include "upstream points only".

[0047] In Figure 4, in order to predict the water level at the water level prediction point WP in the downstream area DS of the dam, not only is the dam discharge data DD from the dam D and the rainfall data RD from the non-dam upstream area US3 extracted, but the upstream rainfall data from the dam upstream areas US1 and US2 is also extracted.

[0048] Thus, by using not only dam discharge data DD but also upstream dam rainfall data, it is possible to construct a water level prediction model M with improved accuracy. However, there may also be cases where a water level prediction model M with improved accuracy can be constructed using only dam discharge data DD and without using upstream dam rainfall data (see Figure 9).

[0049] The total rainfall data and average rainfall data of this disclosure are shown in Figure 5. The dam upstream rainfall data conversion unit 1 generates at least one of the following as dam upstream rainfall data: (1) instantaneous rainfall data showing the amount of rain at any instantaneously from the time in question, before that time, and in the future from that time, in the basin upstream of the dam; (2) total rainfall data showing the total amount of rain from the start of rainfall to at least one of the time in question, before that time, and in the future from that time (however, it is reset to 0 when a predetermined time has elapsed from the start of no rainfall); and (3) average rainfall data showing the average amount of rain within a predetermined average period from the time in question, before that time, and in the future from that time, in the basin upstream of the dam (steps S1, S4). The training data extraction unit 2 and the test data extraction unit 4 extract at least one of the instantaneous rainfall data, total rainfall data, and average rainfall data as dam upstream rainfall data (steps S2, S5). Here, the instantaneous rainfall data, total rainfall data, and average rainfall data may be either the "spatial average value for the entire upstream basin" or the "spatial sum for the entire upstream basin."

[0050] In the upper part of Figure 5, total rainfall data is extracted, showing the total rainfall from the start of rainfall to the time of concern (instantaneous rainfall data is indicated by a left arrow, and total rainfall data is indicated by a right arrow). However, the total rainfall data is reset to 0 after a predetermined time has elapsed from the start of no rainfall. Here, the "predetermined elapsed time" should be set to construct a water level prediction model M with improved water level prediction accuracy. In the lower part of Figure 5, average rainfall data is extracted, showing the average rainfall within a predetermined averaging period up to the time of concern (instantaneous rainfall data is indicated by a left arrow, and average rainfall data is indicated by a right arrow). Here, the "predetermined averaging period" should be set to construct a water level prediction model M with improved water level prediction accuracy. Note that since the total rainfall data is greater than the average rainfall data, it is desirable to standardize either the total rainfall data or the average rainfall data so that the water level prediction data P based on the total rainfall data is approximately equal to the water level prediction data P based on the average rainfall data.

[0051] Thus, by using total rainfall data as upstream rainfall data for the dam, a water level prediction model M can be constructed that improves the accuracy of water level prediction by considering the time required from rainfall in the upstream area of ​​the dam to inflow into the upstream area of ​​the dam. Furthermore, by using average rainfall data as upstream rainfall data for the dam, a water level prediction model M can be constructed that improves the accuracy of water level prediction without abruptly resetting the data to zero, unlike with total rainfall data. However, there may also be cases where a water level prediction model M that improves the accuracy of water level prediction can be constructed using only dam discharge data DD, without using upstream rainfall data (at least one of instantaneous rainfall data, total rainfall data, and average rainfall data) (see Figure 9).

[0052] Figure 6 shows examples of the conventional technology and the water level prediction processing described herein. In the conventional technology, a water level prediction model M is constructed using only water level data WL and rainfall data RD. In this disclosure, a water level prediction model M is constructed using not only water level data WL and rainfall data RD, but also dam discharge data DD, and more preferably, upstream dam rainfall data (at least one of instantaneous rainfall data, total rainfall data, and average rainfall data).

[0053] Figure 6 shows the temporal changes in actual water level data (indicated by the left arrow), predicted water level data P (predicted water level 6 hours later, indicated by the left arrow), and upstream dam rainfall data (indicated by the right arrow) during rainfall. It can be seen that, with conventional technology, the predicted water level data P differs significantly from the actual water level data (because the rainfall is not initially stored in the dam but immediately flows downstream, the predicted water level greatly exceeds the actual water level immediately after rainfall), and unlike the actual water level data, it does not reach the flood warning level. On the other hand, in this disclosure, the predicted water level data P is in close agreement with the actual water level data (because the rainfall is initially stored in the dam and then flows downstream, the predicted water level is almost equal to the actual water level immediately after rainfall), and compared to the actual water level data, it reaches the evacuation decision level, making it possible to issue evacuation guidance orders.

[0054] (Procedure for selecting a water level prediction model in this disclosure) The configuration of the water level prediction device disclosed herein (in particular, the water level prediction model selection process) is also shown in Figure 7. The procedure for the water level prediction model selection process disclosed herein is shown in Figure 8. The water level prediction device W also includes a verification data extraction unit 6 and a water level prediction model selection unit 7, and the water level prediction model selection program shown in Figure 8 can also be realized by installing it on a computer.

[0055] The training data extraction unit 2 extracts multiple types of training data (step S11, see Figure 9). The water level prediction model construction unit 3 constructs multiple types of water level prediction models M1, ..., Mn using the multiple types of training data (step S11).

[0056] The verification data extraction unit 6 extracts the following data as verification data necessary to verify the water level at a water level prediction point downstream of the dam at a given time: (1) water level data WL showing the water level at the time and at least one of the past times at at least one of the water level prediction point and at least one of the points upstream of the water level prediction point; (2) rainfall data RD showing the rainfall at the time, at least one of the past times and at least one of the future times at at least one of the water level prediction point and the upstream water basin; and (3) dam discharge data DD showing the discharge amount at the time, at least one of the past times and at least one of the future times at the dam (step S12). Here, for the rainfall data RD, "upstream water basin" may also include "upstream points only". And for the dam discharge data DD, "past and present observation data" and "future planned data" are included. Furthermore, the extraction period for the verification data is the same as that for the training data.

[0057] The water level prediction model selection unit 7 inputs verification data for verifying the water level prediction model M into multiple types of water level prediction models M1, ..., Mn, which are constructed using multiple types of training data (step S12), and selects a water level prediction model (for example, M1) that better satisfies the issuance criteria (i.e., has a smaller prediction error near the water level peak) (step S13).

[0058] A specific example of the data synthesis process for training data in this disclosure is shown in Figure 9. The training data extraction unit 2 (and the verification data extraction unit 6) extracts water level data WL and dam discharge data DD as mandatory data, and arbitrarily extracts dam upstream rainfall data (at least one of instantaneous rainfall data, total rainfall data, and average rainfall data) as rainfall data RD.

[0059] In the upper left column of Figure 9, only the dam discharge data DD from time t1 to time t2 is extracted as the first training data, and the upstream rainfall data of the dam is not extracted. In the lower left column of Figure 9, the dam discharge data DD and instantaneous rainfall data from time t1 to time t2 are extracted as the second training data. In the upper middle column of Figure 9, the dam discharge data DD and total rainfall data from time t1 to time t2 are extracted as the third training data. In the lower middle column of Figure 9, the dam discharge data DD, instantaneous rainfall data and total rainfall data from time t1 to time t2 are extracted as the fourth training data. In the upper right column of Figure 9, the dam discharge data DD and average rainfall data from time t1 to time t2 are extracted as the fifth training data. In the lower right column of Figure 9, the dam discharge data DD, instantaneous rainfall data and average rainfall data from time t1 to time t2 are extracted as the sixth training data.

[0060] A specific example of the water level prediction model selection process in this disclosure is shown in the left column of Figure 10. The water level prediction model selection unit 7 should select a water level prediction model (e.g., M1) when the predicted time of the water level rise period near the water level peak is the same as the actual time of the water level rise period. Even if the predicted time of the water level rise period near the water level peak is not the same as the actual time of the water level rise period, a water level prediction model (e.g., M1) should be selected according to the following policy.

[0061] In other words, as in Model B, the water level prediction model is considered superior when the predicted time of the water level rise period is earlier than the actual time of the water level rise period. On the other hand, as in Model A, the water level prediction model is considered inferior when the predicted time of the water level rise period is later than the actual time of the water level rise period. In this way, the possibility of delays in issuing evacuation advisories and other warnings is reduced.

[0062] A specific example of the water level prediction model selection process in this disclosure is also shown in the right column of Figure 10. The water level prediction model selection unit 7 should select a water level prediction model (e.g., M1) when the predicted water level near the water level peak (peak water level, etc.) is the same as the actual water level near the water level peak. Even if the predicted water level near the water level peak (peak water level, etc.) is not the same as the actual water level near the water level peak, a water level prediction model (e.g., M1) should be selected according to the following policy.

[0063] In other words, as in Model B, the water level prediction model is considered superior when the predicted water level near the peak is higher than the actual water level near the peak. On the other hand, as in Model A, the water level prediction model is considered inferior when the predicted water level near the peak is lower than the actual water level near the peak. In this way, the possibility of the criteria for issuing evacuation advisories not being met is reduced.

[0064] In this way, from multiple types of water level prediction models M1, ..., Mn constructed using multiple types of training data, the optimal water level prediction model M can be selected so as to enhance generalization performance near the water level peak (especially near the water level peak that serves as the basis for issuing evacuation advisories, etc.).

[0065] (Procedure for test data interpolation processing in this disclosure) The configuration of the water level prediction device of this disclosure (particularly the test data interpolation process) is also shown in Figure 11. The procedure for the test data interpolation process of this disclosure is shown in Figure 12. A specific example of the water level test data interpolation process of this disclosure is shown in Figure 13. A specific example of the rainfall test data interpolation process of this disclosure is shown in Figure 14. The water level prediction device W also includes a test data interpolation unit 8, and the test data interpolation program shown in Figure 12 can also be realized by installing it on a computer.

[0066] The test data interpolation unit 8 interpolates the water level data WL at the time of the missing data at the water level prediction point when the water level data WL at the water level prediction point is missing (step S21) (step S22). Here, the test data interpolation unit 8 interpolates using the water level prediction data P at the time of the missing data, which was output by the water level prediction data output unit 5 at a prediction time arbitrarily before the time of the missing data, and which occurred at a time arbitrarily after the prediction time at the water level prediction point (step S22). The test data extraction unit 4 inputs the test data (including the water level data WL at the time of the missing data interpolated by the test data interpolation unit 8, and the rainfall data RD at the time of the missing data will be described later) into the water level prediction model M (step S22).

[0067] Furthermore, if water level data WL is missing at the upstream location, even if water level data WL is available at the water level prediction location, the water level prediction data P at the water level prediction location cannot be output. Therefore, the water level data WL at the time of the missing data at the upstream location is interpolated using the water level prediction data P at the upstream location.

[0068] Furthermore, the arbitrary time set by the test data interpolation unit 8 is equal to the time interval at which the water level prediction data output unit 5 outputs the water level prediction data P. In other words, the rainfall forecast for a short period of time is highly accurate, and the arbitrary time set by the test data interpolation unit 8 is short.

[0069] In the first section of Figure 13, in order to predict the water level at 12:30 (30 minutes from the current time), the following test data are extracted: water level data of 3.0m at 11:00 (1 hour prior to the current time), water level data of 4.0m at 11:30 (30 minutes prior to the current time), and water level data of 5.0m at 12:00 (the current time). In sections 3-5 of Figure 13, some water level data is missing as test data.

[0070] In the second section of Figure 13, the predicted water level 30 minutes from the current time is output as follows: predicted water level data of 2.9m for 11:00 (one hour prior to the current time), predicted water level data of 3.9m for 11:30 (30 minutes prior to the current time), and predicted water level data of 4.8m for 12:00 (the current time). In the second section of Figure 13, the arbitrary time set by the test data interpolation unit 8 is 30 minutes.

[0071] In the third panel of Figure 13, the water level data for 11:00 (3.0m) and 11:30 (4.0m) are missing. Therefore, these are interpolated using the predicted water level data for 11:00 (2.9m) and 11:30 (3.9m). In the fourth panel of Figure 13, the water level data for 11:30 (4.0m) and 12:00 (5.0m) are missing. Therefore, these are interpolated using the predicted water level data for 11:30 (3.9m) and 12:00 (4.8m). In the fifth panel of Figure 13, the water level data for 11:30 (4.0m) is missing. Therefore, this is interpolated using the predicted water level data for 11:30 (3.9m).

[0072] In this way, even when water level test data is missing in the downstream area of ​​the dam, the accuracy of water level prediction in the downstream area can be improved by reflecting dam discharge, rainfall, and actual water level conditions, and then interpolating the water level test data from the downstream area.

[0073] Then, the missing data can be interpolated using water level prediction data P, which is output at a prediction time shortly before the missing data time (the time interval for water level prediction), reflecting dam discharge, rainfall, and actual water level conditions, and then output at the prediction time shortly after the prediction time (the time interval for water level prediction) in the downstream area of ​​the dam.

[0074] When rainfall data RD is missing at a water level prediction point (step S23), the test data interpolation unit 8 interpolates the rainfall data RD for the missing time at the water level prediction point (step S24). Here, the test data interpolation unit 8 interpolates using the forecast rainfall data RF for the missing time at the water level prediction point (step S24). The test data extraction unit 4 inputs the test data (including the rainfall data RD for the missing time interpolated by the test data interpolation unit 8, and the water level data WL for the missing time as described above) into the water level prediction model M (step S24).

[0075] Furthermore, if rainfall data RD is missing in the upstream basin, even if rainfall data RD is available at the water level prediction point, the water level prediction data P at the water level prediction point cannot be output. Therefore, the rainfall data RD for the missing time in the upstream basin is interpolated using the forecast rainfall data RF from the upstream basin.

[0076] In the first section of Figure 14, in order to predict the water level at 12:30 (30 minutes from the current time), rainfall data of 30 mm at 11:00 (1 hour prior to the current time), rainfall data of 40 mm at 11:30 (30 minutes prior to the current time), and rainfall data of 50 mm at 12:00 (the current time) are extracted as test data. In sections 3-5 of Figure 14, some rainfall data is missing as test data.

[0077] In the second row of Figure 14, the forecast rainfall data RF (short-term precipitation forecast) is entered as follows: forecast rainfall data of 29 mm for 11:00 (one hour before the current time), forecast rainfall data of 39 mm for 11:30 (30 minutes before the current time), and forecast rainfall data of 48 mm for 12:00 (the current time).

[0078] In the third row of Figure 14, the rainfall data for 11:00 (30 mm) and 11:30 (40 mm) are missing. Therefore, these are interpolated using the forecast rainfall data for 11:00 (29 mm) and 11:30 (39 mm). In the fourth row of Figure 14, the rainfall data for 11:30 (40 mm) and 12:00 (50 mm) are missing. Therefore, these are interpolated using the forecast rainfall data for 11:30 (39 mm) and 12:00 (48 mm). In the fifth row of Figure 14, the rainfall data for 11:30 (40 mm) is missing. Therefore, this is interpolated using the forecast rainfall data for 11:30 (39 mm).

[0079] In this way, even when rainfall test data is missing in the upstream area of ​​the dam, the accuracy of water level prediction in the downstream area of ​​the dam can be improved by incorporating forecast rainfall data (RF) from the upstream area of ​​the dam and then interpolating the rainfall test data from the upstream area.

[0080] (Procedure for calculating the accuracy rate of water level predictions in this disclosure) The configuration of the water level prediction device disclosed herein (particularly the water level prediction accuracy calculation process) is also shown in Figure 15. The procedure for calculating the water level prediction accuracy of the disclosed water level prediction is shown in Figure 16. The water level prediction device W also includes a water level prediction error range setting unit 9 and a water level prediction accuracy calculation unit 10, and the water level prediction accuracy calculation program shown in Figure 16 can also be realized by installing it on a computer.

[0081] The training data extraction unit 2 extracts, as training data necessary for learning the water level at a given time at a water level prediction point, past observed rainfall data RO for at least one of the water level prediction point and at least one of the upstream watersheds from the water level prediction point, and rainfall data RO for "future observations" from that time onward.

[0082] The test data extraction unit 4 extracts, as test data necessary for predicting the water level at a given time at a water level prediction point, the following: past observed rainfall data RO at the water level prediction point and at least one of the upstream areas of the water basin from the water level prediction point, at the time in question and at least one of the past areas prior to that time; and "future forecast" rainfall data RF from that time onward.

[0083] However, because the "future forecast" rainfall data RF is less accurate than the "future observation" rainfall data RO, the water level "prediction" data P can deviate significantly from the water level "observation" data. Therefore, this disclosure visualizes the reliability of the water level "prediction" data P.

[0084] Here, the training data is known data for water level learning and cannot be applied to the calculation of the water level prediction accuracy rate H, as it is set to approximately 100%. The test data is unknown data for water level prediction, but it is data specific to a particular rainfall situation and therefore cannot be applied to the calculation of the water level prediction accuracy rate H. On the other hand, the validation data is unknown data for validating the water level prediction model M and is not data specific to a particular rainfall situation, so it can be applied to the calculation of the water level prediction accuracy rate H.

[0085] A specific example of the water level prediction error range setting process in this disclosure is shown in Figure 17. The verification data extraction unit 6 extracts water level data WL, past observed rainfall data RO, future observed rainfall data RO, and dam discharge data DD as verification data for verifying the water level prediction model M (step S31), but does not extract future forecast rainfall data RF.

[0086] The verification data extraction unit 6 inputs water level data WL, past observed rainfall data RO, future observed rainfall data RO, and dam discharge data DD as verification data to the water level prediction model M for verifying water levels at multiple times at the water level prediction point (step S32). The water level prediction error width setting unit 9 obtains water level prediction data P, which shows the predicted water levels at the water level prediction point for those multiple times, from the water level prediction model M (step S32).

[0087] The water level prediction error range setting unit 9 calculates the prediction error probability distribution E for the water level at the water level prediction point and sets the error range of the water level prediction data P with respect to the water level observation data in the water level prediction accuracy calculation step S35 (step S33). Here, the water level prediction error range setting unit 9 calculates the prediction error probability distribution E for each issuance criterion for water level warning at the water level prediction point, and / or for each period length from the prediction output time in the water level prediction data output step S32 to each prediction target time, and sets the error range of the water level prediction data P (step S33).

[0088] In the "Prediction Error After Each N Hours" column of Figure 17, the prediction error probability distribution E for the water level at the water level prediction point is calculated for observed water levels of 0m or more but less than the warning threshold water level A, observed water levels of warning threshold water level A or more but less than the warning threshold water level B, and observed water levels of warning threshold water level B or higher. In the "Error Range After Each N Hours" column of Figure 17, the prediction error probability distribution E is calculated for observed water levels of 0m or more but less than the warning threshold water level A or more but less than the warning threshold water level B, and observed water levels of warning threshold water level B or higher. lоw-min That's all for now. lоw-max The following and e mid-min That's all for now. mid-max The following and e high-min That's all for now. high-maxThe error range of the water level prediction data P with respect to the water level observation data is set so that the following and are within the error range. Here, with the minimum value and the maximum value of the prediction error probability distribution E being 0% and 100%, 0.1% ≦ e high-min ≦ e mid-min ≦ e lоw-min ≦ 20%, and 80% ≦ e lоw-max ≦ e mid-max ≦ e high-max ≦ 99.9% are satisfied. That is, the error range of the water level prediction data P is set wider for higher water levels, narrower for lower water levels, and in the middle for middle water levels. The upward and downward swing ranges of the error range of the water level prediction data P may be equal or different according to the distribution shape of the prediction error probability distribution E.

[0089] In this way, when predicting the water level in the downstream area of the dam using machine learning, in the verification stage, the prediction error probability distribution E of the water level can be calculated, the error range of the water level prediction data P with respect to the water level observation data can be set, and the water level prediction median rate H can be prepared for calculation.

[0090] And in the prediction stage, since the future observed rainfall data RO cannot be extracted as test data, even when extracting the future forecast rainfall data RF, by preparing the calculation of the water level prediction median rate H in the verification stage, it is possible to prepare for assisting in the determination of reaching each issuance criterion.

[0091] A specific example of the water level prediction median rate calculation process of the present disclosure is shown in FIG. 18. The verification data extraction unit 6 extracts the water level data WL, the past observed rainfall data RO, the future forecast rainfall data RF, and the dam discharge data DD as verification data for verifying the water level prediction model M (step S31), but does not extract the future observed rainfall data RO.

[0092] The verification data extraction unit 6 inputs water level data WL, past observed rainfall data RO, future forecast rainfall data RF, and dam discharge data DD as verification data to the water level prediction model M for verifying water levels at multiple times at the water level prediction point (step S34). The water level prediction data output unit 5 outputs water level prediction data P, which shows the predicted water levels at the water level prediction point for those multiple times, from the water level prediction model M (step S34).

[0093] The water level prediction accuracy calculation unit 10 calculates the water level prediction accuracy rate H at the water level prediction point as the proportion of the water level prediction data P at the water level prediction point at the water level prediction point at the water level prediction point at the water level prediction point at the water level prediction point at the water level prediction point at the water level prediction point at the water level prediction point at the water level prediction point at the water level prediction point at the water level prediction point at the water level prediction point at the water level prediction point at the water level prediction point at the water level prediction point (step S35).

[0094] In the "Predicted Data for Each N Hours Later" column of Figure 18, water level prediction data P for multiple time points at the water level prediction point is output for observed water levels of 0m or more but less than the warning threshold water level A, observed water levels of warning threshold water level A or more but less than the warning threshold water level B, and observed water levels of warning threshold water level B or higher. For observed water levels of 0m or more but less than the warning threshold water level A, there are 80 data points that fall within the error range, 10 data points that are below the error range, and 10 data points that are above the error range. For observed water levels of warning threshold water level A or more but less than the warning threshold water level B, there are 30 data points that fall within the error range, 15 data points that are below the error range, and 15 data points that are above the error range. For observed water levels of warning threshold water level B or higher, there are 10 data points that fall within the error range, 10 data points that are below the error range, and 10 data points that are above the error range.

[0095] In the "Accuracy of Prediction After Each N Hours" column of Figure 18, the accuracy of water level prediction H at the water level prediction point is calculated for observed water levels of 0m or more but less than the warning threshold water level A, observed water levels of warning threshold water level A or more but less than the warning threshold water level B, and observed water levels of warning threshold water level B or higher. For observed water levels of 0m or more but less than the warning threshold water level A, the accuracy of water level prediction is 80 / (80+10+10)×100=80%. For observed water levels of warning threshold water level A or more but less than the warning threshold water level B, the accuracy of water level prediction is 30 / (30+15+15)×100=50%. For observed water levels of warning threshold water level B or higher, the accuracy of water level prediction is 10 / (10+10+10)×100=33%.

[0096] Thus, since future observed rainfall data RO cannot be extracted as test data during the prediction stage, even when extracting future forecast rainfall data RF, the reliability of the water level prediction data P can be visualized by calculating the water level prediction accuracy rate H during the verification stage.

[0097] Furthermore, since future observed rainfall data RO cannot be extracted as test data during the prediction phase, even when extracting future forecasted rainfall data RF, the water level prediction accuracy rate H can be calculated during the verification phase to support the determination of whether each issuance criterion has been reached. [Industrial applicability]

[0098] The water level prediction model construction method, water level prediction model construction program, water level prediction data output method, and water level prediction data output program disclosed herein can improve the accuracy of water level prediction in the downstream area of ​​a dam to the same level as in general river areas, using the water level prediction model.

[0099] The test data interpolation method disclosed herein can improve the accuracy of water level predictions in the downstream area of ​​a dam, even when water level test data in that area is missing. The water level prediction accuracy calculation method disclosed herein can visualize the reliability of water level prediction data by calculating the water level prediction accuracy rate. [Explanation of Symbols]

[0100] W: Water level prediction device M, M1, Mn: Water level prediction model 1: Dam upstream rainfall data conversion unit 2: Training data extraction unit 3: Water Level Prediction Model Construction Department 4: Test data extraction unit 5: Water level prediction data output unit 6: Data extraction unit for verification 7: Water Level Prediction Model Selection Section 8: Test data interpolation section 9: Water level prediction error range setting section 10: Water level prediction accuracy calculation unit WL: Water level data RD: Rainfall data DD: Dam discharge data P: Water level prediction data RO: Observed rainfall data RF: Predicted rainfall data E: Prediction error probability distribution H: Water level prediction accuracy rate V: Verification data D: Dam US1, US2: Upstream area of ​​the dam US3: Non-dam upstream area DS: Downstream area of ​​the dam WP: Water level prediction point

Claims

1. A training data extraction step to extract the following as training data necessary for learning the water level at a water level prediction point downstream of the dam: (1) water level data showing the water level at at least one of the water level at the water level prediction point and at least one of the water level in the past at the time in question and at least one of the water level in the past at the time in question and at least one of the water level in the past at the time in question and at least one of the rainfall at at least one of the water level prediction point and at least one of the water basin upstream of the water level prediction point; (2) rainfall data showing the rainfall at the time in question, at least one of the rainfall in the past at the time in question and at least one of the rainfall in the future at the time in question and at least one of the rainfall in the future; A water level prediction model construction step involves constructing a water level prediction model for predicting the water level at the water level prediction point downstream of the dam, using at least one of the water level data and the rainfall data, and the dam discharge data. A method for constructing a water level prediction model, characterized by comprising the following elements in order.

2. The training data extraction step extracts dam upstream rainfall data as rainfall data, which shows at least one of the following rainfall amounts in the basin upstream of the dam: at the time in question, in the past, and in the future. A method for constructing a water level prediction model according to claim 1, characterized in that...

3. The training data extraction step extracts at least one of the following as upstream rainfall data for the dam: (1) instantaneous rainfall data showing the amount of rain at any instant among the time, the time in the past, and the time in the future in the basin upstream of the dam; (2) total rainfall data showing the total amount of rain from the start of rainfall to at least one of the time, the time in the past, and the time in the future in the basin upstream of the dam (however, it is reset to 0 when a predetermined time has elapsed from the time when no rain started); and (3) average rainfall data showing the average amount of rain within a predetermined average period up to at least one of the time, the time in the past, and the time in the future in the basin upstream of the dam. A method for constructing a water level prediction model according to claim 2, characterized in that...

4. A water level prediction model selection step involves inputting verification data for verifying the water level prediction model into multiple types of water level prediction models constructed using multiple types of training data, and selecting the water level prediction model that best fulfills the issuance criteria. A method for constructing a water level prediction model according to any one of claims 1 to 3, further comprising the step of constructing the water level prediction model after the step of constructing the water level prediction model.

5. A water level prediction model construction program for causing a computer to sequentially execute each processing step of the water level prediction model construction method described in claim 1.

6. In order to predict the water level at the water level prediction point downstream of the dam using the water level prediction model constructed by the water level prediction model construction method according to any one of claims 1 to 3, the water level prediction data output step involves inputting at least one of the water level data and the rainfall data, and the dam discharge data, as test data necessary for predicting the water level at a certain time at the water level prediction point, into the water level prediction model, and outputting water level prediction data from the water level prediction model that shows the predicted water level at that time at the water level prediction point. A method for outputting water level prediction data, characterized by comprising the following features.

7. A water level prediction data output program for causing a computer to perform the water level prediction data output step included in the water level prediction data output method according to claim 6.

8. In the test data extracted by the water level prediction data output method according to claim 6, when the water level data at the water level prediction point is missing, the water level data for the time of the missing data at the water level prediction point is interpolated using the water level prediction data output at the prediction time, which is output at an arbitrary time before the time of the missing data, and is interpolated using the water level prediction data for the time of the missing data after the arbitrary time after the prediction time at the water level prediction point. A test data interpolation method characterized by comprising the following:

9. A water level prediction model construction method according to any one of claims 1 to 3 includes a verification data extraction step of extracting the following as verification data for verifying the constructed water level prediction model: water level data, past observed rainfall data and future forecast rainfall data as rainfall data, and dam discharge data. The verification data includes inputting the water level data, past observed rainfall data, future forecast rainfall data, and dam discharge data for verifying the water level at multiple times at the water level prediction point into the water level prediction model, and outputting water level prediction data from the water level prediction model that shows the predicted water level at the water level prediction point for those multiple times. A water level prediction accuracy calculation step, in which the proportion of the water level prediction data for multiple time points at the water level prediction point that falls within the error range around the water level observation data for multiple time points at the water level prediction point is calculated as the water level prediction accuracy at the water level prediction point, A method for calculating the accuracy rate of water level prediction, characterized by comprising the following in order.

Images