JP4414378B2 - River flow estimation system and method, river water level estimation system and method, and program - Google Patents

Description

  The present invention relates to a river flow rate / river water level estimation technique, and more particularly to a river flow rate / river water level estimation technique for estimating a river flow rate / river water level at a predetermined river observation point based on precipitation in the upstream area.

  When implementing a river project, it is important to accurately grasp the river flow rate and river water level. For example, in river environmental conservation projects, accurate river flow is required to manage river water pollution. In river flood control projects, it is necessary to estimate river increase due to rainfall in the river basin and to take appropriate measures and measures.

  When considering water circulation including rivers and sewers, the amount of water released into the river after flowing through the sewer can be measured at a sewage treatment plant, but the amount of water flowing directly into the river without passing through such facilities can be measured or It is difficult to calculate. Also, when actually measuring river flow rate, measure the river channel cross-section in advance and calculate the river flow rate from the relationship between the flow velocity obtained from the flow velocity distribution within a predetermined range and the river water level (for example, surface velocity flow measurement method) However, the error is large in large rivers. Moreover, it is necessary to actually measure the river water level and flow velocity, and it is not possible to estimate the river increase due to rainfall.

  Conventionally, a river flow estimation technique for estimating a river flow rate from precipitation in a river basin using an arbitrary estimation model has been proposed (see, for example, Non-Patent Documents 1 and 2). In such a river flow estimation technique, when estimating a river flow at an arbitrary river observation point, it is necessary to accurately specify a rainfall region that affects a desired estimated river flow, that is, a rainfall influence range. Many of the models used in conventional river flow estimation technology create rainwater lines for the river basin from the topographic elevation data of the river basin and determine the rain-affected area.

http://www.pwri.go.jp/team/suiri/yata-r/3-1.htm, “Introduction of WEP model (water cycle analysis tool)”, Public Works Research Institute http://www1.gsi.go.jp/geowww/globalmap-gsi/utilization/pamph-moc/j_comp_assess_4_2.html, "Institute of Industrial Science Distributed Hydrological Model (IISDHM)", Institute of Industrial Science, University of Tokyo

  However, in such conventional technology, rainwater flowing in via routes other than the ground surface is taken into consideration because the rainfall impact range is determined by creating the waterfall line of the river basin from the terrain elevation data of the river basin. It has not been. Therefore, there is a problem that the rainfall influence range cannot be determined accurately, and as a result, the river flow rate cannot be accurately estimated.

  River flow fluctuations are greatly affected by rainwater flowing in from small and medium-sized tributaries via the ground surface, so there is a large correlation between the topography of the river basin and the rain-affected area on a macro scale. However, the inflow route of rainwater is not only from the ground surface, but also from, for example, a route that flows into a tributary opposite to a mountain ridge via an underground water vein, a route that flows into a tributary via an underground rainwater pipe, or a sewer pipe In many cases, it passes through other inflow routes such as a route that flows into a branch river through a sewage treatment plant, and rainwater from such a complicated inflow route cannot be derived from topographic elevation data of the river basin. .

  The present invention is intended to solve such a problem, and a river flow estimation system, method, and program capable of accurately determining a rainfall influence range on a river flow at a river observation point and, as a result, accurately estimating a river flow. The purpose is to provide.

  In order to achieve such an object, the river flow estimation system according to the present invention is based on the precipitation data indicating the time series of precipitation in each area in the river basin and the time of the river flow at an arbitrary river observation point. Rainfall influence range having a pattern matching analysis section that performs pattern matching analysis on river flow data indicating series changes, and a rain influence range determination section that determines a rain influence range that affects river flow at a river observation point based on the analysis result Creating an estimation model that uses the determination device and historical data that includes precipitation data and river flow data at river observation points in any specific area within the rain influence range determined by the rain influence range determination device To estimate the estimated river discharge at the river observation point using the estimation model And a estimation device having an estimation unit.

  At this time, the pattern matching analysis unit calculates the correlation value between the precipitation data and river flow data for each district, and the rainfall influence range determination unit determines the district where the correlation value exceeds the threshold value. May be set as the rain influence range.

  In addition, the pattern matching analysis unit calculates, as precipitation data, accumulated precipitation data for each accumulation period, using precipitation accumulated retrospectively over an arbitrary accumulation period from each measurement time point as precipitation at each measurement time point, In the rainfall influence range determination unit, a district in which the correlation value in an arbitrary integration period is greater than or equal to a threshold value among the districts may be set as the rain influence range.

  In addition, the pattern matching analysis unit calculates the correlation value of both by sequentially shifting the time position of precipitation data and river flow data, and the maximum correlation value of these correlation values is used as the correlation value of both. Also good.

  In addition, the estimated model creation unit generates a plurality of historical data consisting of a set of model input data including precipitation in a specific area at a given point in time and model output data consisting of river flow at the river observation point at the corresponding point in time. A plurality of case data consisting of a set of input values and output values representing one or more of these historical data is generated, an estimation model is created from a case base using these case data, and the output estimation unit The case data having an input value that matches or is similar to the estimated condition data is searched from the case base of the estimated model, and the river flow corresponding to the estimated condition data is calculated based on the output value of the searched case data. Good.

  The output estimation unit divides the estimated river flow rate by the predetermined flow velocity at the river observation point to obtain the flow cross-sectional area corresponding to the estimated river flow rate, and from this flow cross-sectional area, the flow cross-sectional area and river water level at the river observation point are obtained. The river water level at the river observation point may be calculated based on the function indicating the relationship.

  Further, the river water level estimation system according to the present invention includes precipitation data indicating a time series change of precipitation in each region in the river basin, a river flow data indicating a time series change of a river flow at an arbitrary river observation point, and A rain impact range determination device having a pattern matching analysis unit for pattern matching analysis, a rain impact range determination unit for determining a rain impact range that affects the river flow rate at a river observation point based on the analysis result, and a rain impact range determination An estimation model creation unit that creates an estimation model using historical data including precipitation data and river water level data at river observation points in any specific area within the rain-affected area determined by the device, and a new model in the specific area A river water level having an output estimation unit for estimating an estimated river water level at a river observation point from an estimation condition data including precipitation using an estimation model And a constant unit.

  The river flow estimation method according to the present invention is a river flow estimation method used in a river flow estimation system for estimating an estimated river flow at a river observation point from arbitrary estimation condition data, and each region in a river basin Pattern matching analysis step for pattern matching analysis of precipitation data showing time series change of precipitation and river flow data showing time series change of river flow at any river observation point, and river observation based on this analysis result Estimated using historical data including rainfall impact range determination step to determine the rain impact range that affects the river flow at the point, and precipitation data in any specific area within the rain impact range and river flow data at the river observation point Estimated model creation step to create a model and estimated condition data including new precipitation in a specific area. The estimated river flow and an output estimation step of estimating for using the estimated model.

  At this time, the estimated river flow is divided by the predetermined flow velocity at the river observation point to obtain the flow cross-sectional area corresponding to the estimated river flow, and the relationship between the flow cross-sectional area at the river observation point and the river water level is shown from this flow cross-sectional area. You may further provide the step which calculates the river water level in a river observation point based on a function.

  The river water level estimation method according to the present invention is a river water level estimation method used in a river water level estimation system for estimating an estimated river water level at a river observation point from arbitrary estimation condition data. Pattern matching analysis step for pattern matching analysis of precipitation data showing time series change of precipitation and river flow data showing time series change of river flow at any river observation point, and river observation based on this analysis result Estimated using historical data including rainfall impact range determination step to determine the rain impact range that affects river flow at the point, and precipitation data in any specific area within the rain impact range and river water level data at the river observation point Estimated model creation step to create a model and estimated condition data including new precipitation in a specific area. The estimated river level and an output estimation step of estimating for using the estimated model.

  In addition, the program according to the present invention provides a computer of a river flow estimation system that estimates an estimated river flow at a river observation point from arbitrary estimation condition data, and shows precipitation time series changes in each area within the river basin. A pattern matching analysis step that performs pattern matching analysis on the river flow data indicating time series changes in river flow at any river observation point, and the rainfall impact range that affects the river flow at the river observation point based on this analysis result A step of determining a rain influence range for determining the estimation model, a step of creating an estimation model using a historical data including precipitation data and river flow data at a river observation point in any specific area within the rain influence range, Estimated river flow at a river observation point from estimation condition data including new precipitation in a specific area To execute and output estimating step of estimating with.

  At this time, the estimated river flow is divided by the predetermined flow velocity at the river observation point to obtain the flow cross-sectional area corresponding to the estimated river flow, and the relationship between the flow cross-sectional area at the river observation point and the river water level is shown from this flow cross-sectional area. The step of calculating the river water level at the river observation point based on the function may be further executed.

  In addition, another program according to the present invention provides a computer of a river water level estimation system that estimates an estimated river water level at a river observation point from arbitrary estimation condition data, and displays time-series changes in precipitation in each district within the river basin. A pattern matching analysis step that performs pattern matching analysis of the rainfall data shown and river flow data showing time-series changes in river flow at any river observation point, and rainfall that affects river flow at the river observation point based on the analysis result Rainfall impact range determination step for determining the impact range, and estimation model creation step for creating an estimation model using historical data including precipitation data and river level data at river observation points in any specific area within the rain impact range And the estimated river water level at the river observation point from the estimated condition data including new precipitation in the specific area. To execute and output estimating step of estimating with the Le.

  According to the present invention, the rainfall influence range determination device uses the rainfall data indicating the time series change of precipitation in each area in the river basin and the river flow data indicating the time series change of river flow at any river observation point. Pattern matching analysis is performed, and based on the analysis results, the rainfall influence range that affects the river flow at the river observation point is determined, and the estimation device uses the precipitation data and the river observation point in any specific area within the rainfall influence range. The historical model including the river flow data is used to create an estimation model, and the estimated river flow at the river observation point is estimated using the estimation model from the estimation condition data including new precipitation in a specific area.

  In addition, the estimation device creates an estimation model using the precipitation data in any specific area within the rain-affected area and the river water level data at the river observation point, and the estimation condition data including new precipitation in the specific area The estimated river water level at the river observation point is estimated using the estimation model.

Compared to the conventional case where the rainfall influence range is determined by creating the drainage line of the river basin from the topographic elevation data of the river basin and specifying the inflow route on the ground surface as in the past, In addition to the inflow route, it is possible to determine the rain influence range considering all inflow routes such as underground water veins and rainwater pipes, as well as inflow routes via sewage pipes and sewage treatment plants.
Therefore, it is possible to estimate the desired river flow rate and river water level using the amount of precipitation in a specific area that affects the river flow rate and river water level at the river observation point. Can be estimated.

Next, embodiments of the present invention will be described with reference to the drawings.
[First Embodiment]
First, a river flow rate estimation system according to a first embodiment of the present invention will be described with reference to FIG. FIG. 1 is a block diagram showing a configuration of a river flow rate estimation system according to the first embodiment of the present invention.
This river flow estimation system is a system that estimates a river flow at a river observation point in real time from precipitation in a river basin using a predetermined estimation model, and includes a rainfall influence range determination device 10 and an estimation device 20. Has been.

  The rainfall influence range determination device 10 as a whole is composed of an information processing device such as a personal computer that outputs desired information by performing arithmetic processing on input processing information, and the amount of precipitation in each district in the river basin. And the river flow rate at the river observation point, it has a function to determine the rain influence range that affects the estimated river flow rate at the river observation point.

  The estimation device 20 as a whole is composed of an information processing device such as a personal computer that outputs desired information by performing arithmetic processing on the input processing information, and the rainfall influence range determined by the rainfall influence range determination device. A function to create an estimation model using historical data including precipitation data showing the time series of precipitation in a specific area and river flow data showing the river flow at a river observation point, and a new It has a function to estimate the estimated river flow at the river observation point from the estimation condition data including the amount of precipitation using the estimation model.

  In the present embodiment, the rainfall influence range determination device 10 is used to determine the precipitation data indicating the time-series change of precipitation in each area in the river basin and the river flow indicating the time-series change of the river flow at an arbitrary river observation point. Pattern matching analysis is performed on the data, and based on the results of this analysis, the rainfall influence range that affects the river flow at the river observation point is determined.

  In the present invention, most of the river flow is regarded as rainwater. In addition, for groundwater that flows into the river after a long period of one month or more after the rain, the causal relationship with the rain cannot be specified, and it is determined that it is not necessary to handle it with an estimated span of about ten and several hours like the present invention. It was outside. In addition, the amount of evaporation from the river surface was excluded because it is very small and within the error range.

[Rainfall influence range determination device]
Next, with reference to FIG. 1, the structure of the rainfall influence range determination apparatus used with the river flow volume estimation system concerning the 1st Embodiment of this invention is demonstrated in detail.
The rainfall influence range determination apparatus 10 includes an input unit 11, a pattern matching analysis unit 12, and a rain influence range determination unit 13 as functional units.

  These functional units are realized by a dedicated circuit unit, an arithmetic processing unit, or a storage unit. Among these, the arithmetic processing unit has a microprocessor such as a CPU and a DSP and its peripheral circuits, and implements various functional units by reading and executing the program from the inside of the microprocessor or the memory or storage unit of the peripheral circuit. The storage unit includes a storage device such as a hard disk and a memory, and stores various processing information and programs used for processing operations in the dedicated circuit unit and the arithmetic processing unit.

The input unit 11 is composed of a dedicated interface circuit unit, and has a function of fetching processing information and other data used for the rainfall influence range process from an external device or recording medium, and a function of saving the fetched data in a storage unit (not shown) And have.
The main processing information captured by the input unit 11 includes history data 40 including precipitation data 41 and river flow data 42.

Precipitation data 41 is data indicating time-series changes in precipitation measured in each district in the river basin upstream of the river observation point 30. These districts are provided by dividing the candidate area set in the river basin into a mesh shape. The river flow data 42 is data indicating a time-series change of the river flow measured at the river observation point 30 of the river that is the target of the river flow estimation.
The precipitation data 41 for each area may be obtained from a provider that provides general weather data. For example, the precipitation data 41 is obtained from the Japan Meteorological Agency in one-hour cycles and from the River Information Center in ten-minute cycles. Each is provided. The river flow rate data 42 may be measured by a known measurement method such as a surface velocity type flow rate measurement method.

  The pattern matching analysis unit 12 includes an arithmetic processing unit, and calculates a correlation value between precipitation data and river flow data of each district captured by the input unit 11 to perform pattern matching analysis on both. When calculating the precipitation data for each accumulation period, the precipitation data collected from the measurement time points as the precipitation data, and the accumulated precipitation data for each accumulation period. It has a function of sequentially shifting the time position of the flow rate data to calculate the correlation values of both, and setting the maximum correlation value among these correlation values as the correlation value of both.

  The rain influence range determination unit 13 includes an arithmetic processing unit, and has a function of setting a district where the correlation value calculated by the pattern matching analysis unit 12 is equal to or greater than a threshold value in each district, Of these, the function of setting the area where the correlation value in an arbitrary integration period is equal to or greater than the threshold value as the rainfall influence range, and the identification information indicating each area constituting the determined rain influence range, that is, the specific area, are the rain influence range determination information 43. As an output function.

[Estimation device]
Next, the configuration of the estimation apparatus according to the first embodiment of the present invention will be described in detail with reference to FIG.
The estimation device 20 includes an input unit 21, an estimation model creation unit 23, an adaptive learning unit 25, and an output estimation unit 26.

  These functional units are realized by a dedicated circuit unit, an arithmetic processing unit, or a storage unit. Among these, the arithmetic processing unit has a microprocessor such as a CPU and a DSP and its peripheral circuits, and implements various functional units by reading and executing a program from the inside of the microprocessor or the memory or storage unit of the peripheral circuit. The storage unit includes a storage device such as a hard disk and a memory, and stores various processing information and programs used for processing operations in the dedicated circuit unit and the arithmetic processing unit.

The input unit 21 includes a dedicated interface circuit unit, and has a function of importing processing information and other data used for estimation model creation processing and river flow estimation processing from an external device or recording medium, and a storage unit (not shown). ).
The main processing information captured by the input unit 21 includes the rainfall influence range determination information 43 output from the rain influence range determination device 10, the history data 50 used for the estimation model creation process, and the estimation condition used for the river flow estimation process. There is data 60.

The history data 50 includes weather data 51, time data 52, and river flow data 53.
The meteorological data 51 is data indicating precipitation, temperature, weather, and the like measured in each district, and is used as model input data when an estimated model is created. The time data 52 is data indicating the time when the river flow data 53 is obtained, the day type (day of the week, holidays, etc.), the season, and the like, and is used as model input data when an estimated model is created. The river flow data 53 is data indicating a river flow time-series change measured at the river observation point 30 of the river that is the target of the river flow estimation, and is used as model output data when an estimated model is created.

The estimation condition data 60 is a variable value that defines the river flow rate estimated by the estimation device 20, and includes a weather parameter 61 and a time parameter 62.
The meteorological parameter 61 corresponds to the meteorological data 51 of the history data 50, and includes information relating to the meteorological environment such as precipitation, temperature, and weather measured or predicted in a specific area used for estimating the river flow rate. Used.
The time parameter 62 corresponds to the time data 52 of the history data 50, and indicates the type of day for estimating the river flow, for example, the day type indicating the day of the week, weekday, holiday, old previous day, national holiday, year-end and New Year holidays, working day, etc. In addition to information, time information such as time information and season information indicating the season to which the day belongs are used alone or in combination.

The estimation model creation unit 23 includes an arithmetic processing unit, and is a non-linear black for estimating the estimated river flow corresponding to the estimation condition data 60 based on the history data 22 captured by the input unit 21 and stored in the storage unit. It has a function of creating an estimation model 24 composed of a box estimation model and a function of saving the created estimation model 24 in a storage unit.
The nonlinear black box estimation model is an estimation model that is identified based on the input / output data of the target without grasping the detailed configuration of the target, unlike the physical model that identifies and identifies the detailed configuration of the target. As for the configuration of the estimation model 24 created by the estimation model creation unit 23 and its creation technique, a known modeling technique related to the nonlinear black box estimation model may be used.

  Such nonlinear black box estimation models include a case base, a fuzzy inference base, and a model using a neural network. In particular, the case-based reasoning model is a well-known modeling technique that can be applied to general objects in which the continuity of the input / output relationship of the system is established based on the concept of topology (see, for example, Japanese Patent No. 2632117) ). In the present embodiment, a case where this case base is used as the estimation model 24 will be described as an example.

The adaptive learning unit 25 includes an arithmetic processing unit and has a function of revising the estimation model 24 based on the history data 50 including the river flow rate newly measured at the river observation point 30.
When the case base is used as the estimation model 24, the adaptive learning unit 25 uses the output value of the history data 50 to output the output value of the case data corresponding to the history data 50 among the case data constituting the case base. Change at a predetermined ratio. When there is no case data corresponding to the history data 50, the adaptive learning unit 25 adds the history data 50 to the estimation model 24 as new case data.

The output estimation unit 26 includes an arithmetic processing unit, and estimates an estimated river flow rate 70 at the river observation point 30 from an estimation condition data 60 including new precipitation in a specific area input from the input unit 21. 23 has a function of performing an estimation output using the estimation model 24 created in 23.
When the case base is used as the estimation model 24, the output estimation unit 26 searches for similar case data similar to the estimation condition data 60 from each case data constituting the case base. Then, the estimated river flow rate 70 corresponding to the estimation condition data 60 is estimated from the retrieved one or more similar case data, and for example, the estimated river flow rate 70 after 60 minutes to 120 minutes is output.

[Rainning influence range determination operation]
Next, with reference to FIG. 2, the rain influence range determination operation in the rain influence range determination apparatus according to the first embodiment of the present invention will be described. FIG. 2 is a flowchart showing a rainfall influence range determination process in the rainfall influence range determination apparatus according to the first embodiment of the present invention.
An arithmetic processing unit (not shown) of the rainfall influence range determination device 10 starts the rainfall influence range determination process of FIG. 2 in response to the operator's estimation request operation.

  First, the input unit 11 takes in the history data 40 according to an input operation of an external device, a recording medium, or an operator, and stores it in the storage unit (step 100). FIG. 3 shows precipitation data 41 captured as history data, and shows a time series change of precipitation in each district. FIG. 4 shows river flow data 42 taken in as history data, and shows a time series change in river flow at a river observation point.

  Next, the pattern matching analysis unit 12 selects an unprocessed integration period T that is specified in advance as an integration time, for example, 1 to 16 hours (step 101), and the river flow data captured by the input unit 11 42, the integrated river flow data Qa (T) is obtained by using the river flow Qa (T, t) accumulated retroactively over the integration period T from the river flow Q (t) at each measurement time t as the river flow at each measurement time t. Calculate (step 102).

  FIG. 5 is an explanatory diagram showing the accumulated river flow data. FIG. 5A shows the river flow data 42 inputted as the history data 40, and the river flow per hour (T = 1 hour is the same). ). FIG. 5 (b) shows the accumulated river flow data calculated when the accumulated time T = 3 hours, and is composed of the accumulated river flows obtained by summing up the river flows for the past 3 hours at each measurement time t. Yes. As shown in FIG. 5A, when the unit measurement period (1 hour) and the accumulated time (T = 1 hour) of the input river flow data 42 coincide with each other, the accumulation process is omitted and the river flow data 42 is omitted. Can be used as the integrated river flow rate.

  Subsequently, the pattern matching analysis unit 12 selects one of the unprocessed districts P among the districts in the candidate area set as the river basin at the river observation point 30 (step 103). Similarly to the precipitation data 41 of the area P, the precipitation Wa (P, T, t) accumulated retroactively over the accumulation period T from the precipitation W (P, t) at each measurement time t is measured at each measurement time point. Accumulated precipitation data Wa (P, T) as the precipitation of t is calculated (step 104).

  Next, the pattern matching analysis unit 12 performs pattern matching processing on the calculated integrated river flow data Qa (T) and integrated precipitation data Wa (P, T), and uses the maximum of both as an index indicating the degree of matching. Correlation value Cmax (P, T) is calculated (step 105). At this time, as shown in FIG. 6, for example, the accumulated precipitation data Wa (T, P) is sequentially shifted on the time axis to obtain the correlation values C (T, P) of the two, respectively. Correlation value Cmax (P, T) is selected as the correlation value of both. Further, as the accumulated river flow data Qa (T) and the accumulated precipitation data Wa (P, T) to be analyzed, a data sequence of river flow and precipitation measured over several years is used as a pattern.

  After the pattern matching analysis unit 12 performs the pattern matching process for the arbitrary section P in this way, has the pattern matching process been completed for all the districts in the candidate area set as the river basin of the river observation point 30? If it is determined (step 106) and there is an unprocessed area (step 106: NO), the process returns to step 103 to repeat the pattern matching process for the unprocessed area.

  On the other hand, when the pattern matching process for all the districts has been completed (step 106: YES), it is determined whether the pattern matching process has been completed for all the integration periods (step 107), and there is an unprocessed integration period. (Step 107: NO), the process returns to Step 101 to repeat the pattern matching process for the unprocessed integration period.

  When the pattern matching process for all the integration periods is completed (step 107: YES), the maximum correlation value Cmax (P, T) in any integration period T among the districts is equal to or greater than the threshold value Cth. Area P is selected as a specific area that constitutes a rain influence range that affects the estimated river flow at the river observation point 30 (step 108), and identification information indicating these specific areas is estimated as the rain influence range determination information 43. It outputs to the apparatus 20 (step 109), and a series of rain influence range determination processing is complete | finished.

FIG. 7 is a correlation value map of each district when the integration period T = 1 hour. FIG. 8 is a correlation value map of each district when the integration period T = 15 hours. In this case, each maximum correlation value is ranked and displayed by color for each of the districts provided in the candidate area 31 in a mesh shape.
In particular, in the case of FIG. 7, the highest rank area 32 having the maximum correlation value is concentrated in the vicinity of the river observation point 30. The existence of a complicated inflow route can be inferred. In the case of FIG. 8, since the highest rank area 32 of the maximum correlation value is not distributed and distributed uniformly in the area (mountainous part) away from the river observation point 30, The existence of a complicated inflow route can be inferred.

  FIG. 9 is a rainfall influence range map showing the result of pattern matching analysis. From the correlation value map of each accumulated time shown in FIG. 7 and FIG. 8, the highest rank area 32 is selected as a specific area, and the specific area of each accumulated time is combined (logically summed) to determine the rain influence range 33. The case where it was decided is shown.

[Estimated model creation operation]
Next, with reference to FIG. 10 and FIG. 11, an estimation model creation operation in the estimation apparatus according to the first embodiment of the present invention will be described. FIG. 10 is a flowchart showing an estimation model creation process in the estimation apparatus according to the first embodiment of the present invention. FIG. 11 is a flowchart relating to the estimation model creation operation in the estimation apparatus according to the first embodiment of the present invention.

An arithmetic processing unit (not shown) of the estimation device 20 starts the estimation model creation process of FIG. 10 in response to the operator's estimation model creation request operation. Here, as an example, an estimated model is created using precipitation and temperature in one or more specific districts and the day of the week as model input data, and the river flow measured at the river observation point 30 as model output data. explain.
In the present embodiment, a case where a case base is used as an example of a black box estimation model for estimating a river flow rate from estimation condition data including arbitrary weather parameters and time parameters will be described.

  First, the input unit 21 takes in the history data 50 including the weather data 51, the time data 52, and the river flow data 53 relating to each area in accordance with an external device, a recording medium, or an operator's input operation, and stores it in a storage unit (FIG. (Not shown) is stored as history data 22 (step 110). Further, the input unit 21 takes in the rainfall influence range determination information 43 from the rainfall influence range determination device 10 and stores it in the storage unit.

  Next, the estimated model creation unit 23 refers to the identification information of the area assigned to each of the weather data 51 of the history data 22 based on the rainfall influence range determination information 43 of the storage unit, and the rainfall influence range 33. Is selected from the meteorological data 51, the day of the week data on which this precipitation is measured is selected from the time data 52, and the river flow data 53 of the history data 22 is selected ( Step 111).

  Subsequently, the estimated model creation unit 23 sets the model input data 27A composed of precipitation (time series data), temperature (time series data) and day of the week for each specific area, and model output data 27B composed of river flow. (History) 27C is created for each time.

  For example, in FIG. 11, model input data including precipitation (time-series data) and temperature (time-series data) and the day of the week at time T10 in each of the specific areas A to N at times T0 to T10, and time One set 27C is created from the river flow rate at the river observation point 30 at T10. Moreover, it consists of precipitation amount (time series data) and temperature (time series data) in each of the specific areas A to N at time T1 to T11 shifted by unit time from time T0 to T10, and the day of the week at time T11. The next set 27C is created from the model input data 27A and the river flow rate at the river observation point 30 at time 11.

In addition, although the case where the time of the last data of precipitation (time series data) and temperature (time series data) and the time of river flow correspond in the above was explained as an example, precipitation (time series data) ) And temperature (time-series data) and the river flow rate need not coincide with each other, and there may be a time lag between the two.
For example, for each specific area, the correlation value is obtained by sequentially shifting the time positions of precipitation data (time series data), temperature (time series data) and river flow data (time series data), and the maximum correlation value is Based on the obtained time shift amount, the set 27C may be created by associating the precipitation amount of the specific area with the river flow rate. Thereby, a more accurate estimation model can be created.

  Moreover, although all the specific districts that make up the rainy influence range 33 may be targets for model creation, one or more districts selected from these specific districts may be targets for model creation. For example, a correlation value between the precipitation amount and the river flow rate in each specific area may be obtained, and a specific area having a large correlation value may be used as a model creation target. As a result, the number of model input data and the number of estimation condition data can be reduced, so the scale of the estimation model can be reduced, the processing burden at the time of model creation and model estimation can be greatly reduced, and areas that cause estimation errors. Therefore, it is possible to create a more accurate estimation model.

  After creating the sets 27C in this way, the estimation model creation unit 23 generates a plurality of case data consisting of pairs of input values and output values representing these one or more sets (histories) 27C. The estimation model 24 is created from the case base using these case data (steps 112 to 114), and the series of estimation model creation processing is terminated. The detailed processing procedure for creating the case base will be described below.

[Case base]
Next, with reference to FIG. 12 and FIG. 13, a case base used as an estimation model in the estimation apparatus according to the first embodiment of the present invention will be described. FIG. 12 is an explanatory diagram illustrating creation of a case base used in the estimation apparatus according to the first embodiment of the present invention. FIG. 13 is an explanatory diagram showing the definition of similarity on a case basis.

  Case-based reasoning (CBR) is a black box modeling that relates input / output relationships according to a predetermined algorithm from learning data without qualitative meaning of input / output relationships. This is a technique for deriving a desired solution by directly using past cases similar to a given problem.

In the present embodiment, a case where TCBM (Topological Case-Based Modeling) is used among such case-based reasoning will be described as an example.
TCBM is a modeling method that uses a framework of case-based reasoning on the premise that continuity is established in the input / output relationship in the inference target, and its feature is based on the concept of continuous mapping in mathematical topology (topology). Based on this, the case base corresponding to the output resolution, that is, the output error allowable range, and the similarity indicating the relationship between the cases are defined.

As shown in FIG. 12A, when a plurality of sets of model input data x1, x2 and model output data y are obtained as history data obtained in the past from the target, these history data are shown in FIG. As shown in b), they are arranged in the input space.
Here, when the estimation error required for the case base, that is, the output error allowable width ε is given, as shown in FIG. 12C, the input space is divided into partial sections called meshes using the output error allowable width ε. By dividing and quantizing, it is possible to define an input neighborhood corresponding to the size of the output neighborhood, that is, a case.

At this time, as shown in FIG. 12D, when a plurality of history data is distributed to the same mesh, an average value of the model output data y of each history data is used as an output value representing the case, The median value of the mesh is used as an input value representing the case, and each history data is integrated as one case.
As a result, for all cases, the error between the model output data of each history data distributed to the mesh of the case and the output value of the case satisfies the output error allowable range ε.

The similarity is a scale indicating how much similarity each case has with the new estimation condition, that is, the mesh corresponding to the input data, among the meshes provided in the input space of the case base. is there.
In FIG. 13, if a case exists in the central mesh corresponding to the input data, the case and the input data are defined as “similarity = 0”. In addition, the example existing next to the center mesh is “similarity = 1”, and thereafter, the degree of similarity increases by 1 each time the mesh is separated from the center mesh.

  Therefore, when estimation is performed, the estimated value based on the case of similarity i has an accuracy within (i + 1) × allowable output width. At this time, if the cases on both sides are successfully used for the input value to be estimated, it is expected that the output value has an accuracy better than (i + 1) × allowable output width. Further, when only one case is used for the value to be estimated, it is expected based on the continuity of input and output that the accuracy is about (i + 1) × allowable output width.

The estimated model creation unit 23 plots each set 27C in the input space based on the precipitation, temperature, and day of week values of the model input data 27A using such a modeling technique (FIG. 10: step 112), and outputs The input space is divided and quantized with a mesh having a size corresponding to the error tolerance ε (step 113).
Then, a mesh to which one or more history data is distributed among the meshes is selected as an example, input / output values and output values representing the history data in the mesh are calculated, and a set of these input / output values and output values is calculated. A case base is constructed from the case data consisting of (step 114), and is stored in the storage unit as the estimated model 24.

[River flow estimation]
Next, with reference to FIG. 14 and FIG. 15, the river flow rate estimation operation in the estimation apparatus according to the first embodiment of the present invention will be described. FIG. 14 is a flowchart showing a river flow rate estimation process in the estimation apparatus according to the first embodiment of the present invention. FIG. 15: is a flowchart concerning river flow estimation operation | movement with the estimation apparatus concerning the 1st Embodiment of this invention.

  An arithmetic processing unit (not shown) of the estimation device 20 starts the river flow rate estimation process of FIG. 14 in response to an operator's estimation request operation or periodically.

First, the input unit 21 receives precipitation (time series data) and temperature (time series) measured in each specific area or predicted as data in each specific area according to an input operation of an external device, a recording medium, or an operator. The estimation condition data 60 including the weather parameter 61 including the series data) and the time parameter 62 including the day of the week to be estimated is fetched and stored in the storage unit (not shown) (step 120).
The output estimation unit 26 reads the estimation condition data 60 stored in the storage unit, and searches the case base of the estimation model 24 of the storage unit for case data having an input value similar to the estimation condition data 60 (step 121). .

  Then, based on the similarity between the similar case data obtained by the search and the estimated condition data 60, the river flow for the estimated condition data 60 is estimated by calculating the output value of each similar case data (step 122). This river flow rate is output as the estimated river flow rate 70 with respect to the estimation condition data 60 (step 123), and a series of river flow rate estimation processing is terminated.

  For example, in FIG. 15, estimated condition data 60 including precipitation (time-series data) and temperature (time-series data) in each of the specific areas A to N and the day of the week at time T100 at times T90 to T100. It is captured. Then, the case data having an input value similar to the estimation condition data 60 is searched from the case base of the estimation model 24 as similar case data, and the output value of the searched similar case data is obtained at the river observation point 30 at time T100. A river flow rate 70 is calculated.

  FIG. 16 is a graph showing a result of river flow estimation by the estimation apparatus according to the present embodiment. The estimated river flow rate 70 is a river flow rate at the river observation point 30 estimated using the estimation model 24 based on the precipitation 71 measured in an arbitrary specific area. The actually measured river flow rate 72 actually measured at the river observation point 30 and the estimated river flow rate 70 are almost overlapped and plotted, and it can be seen that the river flow rate is estimated with extremely high accuracy.

  Note that the estimation model 24 according to the present embodiment is a model that estimates river flow in real time from input estimation condition data 60. That is, the river flow rate at a desired time is estimated from the precipitation and temperature of each district measured in a predetermined period until the desired time. Therefore, when predicting the river flow rate at a desired time in the future, the amount of precipitation and temperature of each district in a predetermined period until the desired time is required. In such a case, data provided as a forecast from a provider that provides general weather data may be used.

As described above, according to the present embodiment, the rainfall influence range determination device 10 uses the precipitation data indicating the time series change of precipitation in each area in the river basin and the time series change of the river flow at an arbitrary river observation point. Since the pattern matching analysis is performed on the river flow data showing the flow rate, and the rain influence range that affects the river flow at the river observation point is determined based on the analysis result, the inflow route of rainwater to the tributaries should be clarified. Rather, it is possible to determine the range of rainfall influence on the river flow at the river observation point.
Compared to the conventional case where the rainfall influence range is determined by creating the drainage line of the river basin from the topographic elevation data of the river basin and specifying the inflow route on the ground surface as in the past, In addition to the inflow route, it is possible to determine the rain influence range considering all inflow routes such as underground water veins and rainwater pipes, as well as inflow routes via sewage pipes and sewage treatment plants.

  Therefore, the estimation device 20 creates an estimation model using historical data including precipitation data in any specific area within the rain-affected area and river flow data at the river observation point, and calculates new precipitation in the specific area. By using the estimation model to estimate the estimated river flow at the river observation point from the estimation condition data including The river flow can be estimated with extremely high accuracy.

In the present embodiment, in the pattern matching analysis, the correlation value between the precipitation data and the river flow data of each district is calculated, and the district where the correlation value is equal to or greater than the threshold value is calculated. Since the influence range is set, the rain influence range can be determined with high accuracy without using complicated mathematical formulas and processing.
In addition, during pattern matching analysis, as precipitation data, integrated precipitation data is calculated for each integration period, with precipitation accumulated retrospectively over an arbitrary integration period from each measurement point, and precipitation at each measurement point. Since the area where the correlation value in any integration period exceeds the threshold is set as the rainfall influence range in each area, the delay of rainwater arrival from the specific area to the river observation point and its integration effect are considered. To determine the range of rainfall impact.

  Also, during the pattern matching analysis, the temporal position of precipitation data and river flow data is sequentially shifted to calculate the correlation value between them, and the maximum correlation value of these correlation values is used as the correlation value between them. Therefore, it is not necessary to use information and analysis processing to grasp in detail the inflow route from a specific area to the river observation point and the delay in the arrival of rainwater due to the inflow route, and the effects of rainfall using only precipitation and river flow The range can be determined.

  Further, in the estimation device, based on a plurality of history data composed of a set of model input data including precipitation in a specific area at an arbitrary time point and model output data consisting of a river flow rate at a river observation point at a corresponding time point. , Generate a plurality of case data consisting of pairs of input values and output values representing one or more of these historical data, create an estimation model from the case base using these case data, and match with the estimation condition data Case data having similar input values are searched from the case base of the estimation model, and the river flow corresponding to the estimation condition data is calculated based on the output value of the searched case data.

As a result, cases (problems and answers) experienced in the past are accumulated as a case base, and input / output cases that include the input / output relationships of the system are used. Therefore, a special model for expressing the input / output relationships is required. do not do. Therefore, only by preparing historical data measured in the past, an estimation model having estimation accuracy due to the historical data can be easily created.
In addition, since the estimated river flow (answer) for the newly entered estimation condition (problem) is calculated from the output value (answer) of the similar case retrieved, even if there is no case data that matches the estimation condition A desired estimated river flow rate can be obtained with an estimation accuracy corresponding to the similarity of similar cases.

[Second Embodiment]
Next, a river water level estimation system according to the second embodiment of the present invention will be described.
In the first embodiment described above, the model is estimated using model input data 27A including precipitation data measured in each specific area and model output data 27B composed of river flow data measured at the river observation point 30. A case has been described as an example in which 24 is created and the estimated river flow rate 70 is estimated with respect to arbitrary estimation condition data 60 using the estimation model 24.

  When conducting river projects, river flow is often required, but river water level is sometimes required. For example, in river flood control projects, it is necessary to estimate the river increase due to rainfall in the river basin and take appropriate maintenance and countermeasures. Therefore, the project is implemented based on the river water level at the river observation point as well as the river flow rate. There are many things.

  In this embodiment, the estimation device 20 according to the first embodiment described above estimates the river water level, not the river flow at the river observation point 30, by using the river water level instead of the river flow. It is a thing. Note that the configuration and operation of the river water level estimation system according to this embodiment are the same as those in the first embodiment described above, and a detailed description thereof is omitted here.

The estimation apparatus 20 according to the present embodiment creates an estimation model 24 based on historical data 50 using river water level data indicating time series changes in the river water level at the river observation point 30 instead of the river flow data 53, and performs estimation. Based on the condition data 60, a desired estimated river water level at the river observation point 30 is estimated.
As a result, it is possible to estimate the desired river water level using the precipitation in the specific area that affects the river flow rate at the river observation point without excess or deficiency, and to estimate the river water level with extremely high accuracy.

As the estimation model 24, an estimation model for estimating the river flow rate and an estimation model for estimating the river water level may be created, and both the river flow rate and the river water level at the river observation point can be estimated.
In addition, in the rain influence range determination apparatus 10, instead of the river flow data 43, the rain influence range is determined based on the history data 40 using the river water level data indicating the time series change of the river water level at the river observation point 30. Also good.

[Third Embodiment]
Next, a river flow rate estimation system according to the third embodiment of the present invention will be described with reference to FIGS. 17 and 18. FIG. 17 is an explanatory diagram showing the relationship between the river water level and the river cross-sectional shape. FIG. 18 is an explanatory diagram showing the relationship between river water level and running water cross-sectional area.

In the second embodiment described above, a case has been described in which the estimation device 20 estimates the river water level instead of the river flow at the river observation point 30 by using the river water level instead of the river flow.
In the present embodiment, a case will be described in which the river water level at the river observation point 30 is calculated from the estimated river flow rate 70 estimated by the estimation device 20 according to the first embodiment. Note that the configuration and operation of the river flow rate estimation system according to this embodiment are the same as those in the first embodiment described above, and a detailed description thereof is omitted here.

As shown in FIG. 17, the river water level H is defined by the height from the river bottom to the water surface. For this reason, if the cross-sectional shape of the riverbed is measured in advance, the relationship between the flow cross-sectional area S of the water flowing through the river and the river water level H can be calculated by the function F as shown in FIG.
On the other hand, the running water cross-sectional area S is obtained by dividing the river flow rate Q per unit time by the flow velocity V at that time.

  In the estimation device 20 according to the present embodiment, the output estimation unit 26 estimates the estimated river flow rate 70 in the same manner as in the first embodiment, and then divides the estimated river flow rate 70 by the flow velocity V to stop the water flow. The area S is obtained, and the river water level H corresponding to the flowing water cross-sectional area S is calculated using the function F indicating the relationship between the flowing water cross-sectional area S and the river water level H. Note that the flow velocity V and the function F may be measured in advance and stored in the storage unit. In particular, since the flow velocity V greatly depends on the slope of the river, a value specific to the river observation point 30 can also be used.

Thereby, it is possible to estimate the river water level with high accuracy without significantly changing the river flow rate estimation system according to the first embodiment.
FIG. 19 shows the river flow data used for the river water level calculation in the present embodiment, and FIG. 20 shows the river water level data calculated from the river flow data in FIG. 19 according to the present embodiment.

[Extended embodiment]
In each of the above embodiments, the case where the rainfall influence range determination device 10 and the estimation device 20 are configured as separate devices has been described as an example. However, the present invention is not limited to this. For example, one personal computer Thus, the rainfall influence range determination device 10 and the estimation device 20 may be realized.

  Alternatively, one rainfall influence range determination device 10 and a plurality of estimation devices 20 are connected via a network, and each rainfall basin to be estimated by each estimation device 20 is a single rain influence range determination device 10. For each of these, the optimum rainfall influence range may be determined. Thereby, a river flow rate estimation system and a river water level estimation system can be constructed efficiently.

  Moreover, although the case where the estimation model creation unit 23 selects the history data of the specific area specified by the rainfall influence range determination information 43 when creating the estimation model in the estimation device 20 has been described as an example, When the historical data 50 is taken in, the historical data of a specific area designated by the rainfall influence range determination information 43 may be selected with reference to the identification information of the area given to each historical data.

  Further, when the history data 50 is taken in by the input unit 21, the history of a specific area designated by the rainfall influence range determination information 43 with reference to the identification information of the area given to each history data from an external device or a recording medium Data may be selected and imported. Alternatively, only the history data 50 of a specific area designated by the rainfall influence range determination information 43 as the history data 50 may be selected by the external device and input to the estimation device 20.

  Each district may be provided corresponding to each measurement point in the river basin, but a plurality of measurement points may be integrated. In this case, the statistical values of precipitation and temperature measured at the measurement points to be integrated, for example, average values and representative values may be calculated and used as the precipitation and temperature in the area.

  Further, in each of the embodiments described above, the case where an estimated model is created by using temperature and day of the week as model input data in addition to precipitation has been described as an example, but precipitation has the greatest influence on river flow. Therefore, even when only precipitation is used as model input data, river flow can be estimated. By adding other data as model input data, such as temperature, day of the week, and time series data of river flow at the river observation point 20 during the period up to the time of estimation, more accurate river flow estimation can be realized. .

Further, in each of the above embodiments, the case where the rainfall influence range determination operation in the rain influence range determination device 10 and the estimation operation in the estimation device 20 are individually executed has been described as an example. You may let them.
For example, as soon as one or a plurality of estimation operations are completed, the output estimation unit 26 of the estimation device 20 may instruct the rain influence range determination device 10 to start the rain influence range determination operation.

Alternatively, the application learning unit 25 compares the estimated value with a corresponding actually measured value input later to obtain an estimation error, and when the estimated error exceeds a threshold value, the rainfall influence range determination device 10 receives the rainfall. The start of the influence range determination operation may be instructed.
As a result, the river flow rate and the river water level can always be predicted based on the accurate rainfall influence range, and high estimation accuracy can be obtained.

It is a block diagram which shows the structure of the river flow volume estimation system concerning the 1st Embodiment of this invention. It is a flowchart which shows the rainfall influence range determination process in the rain influence range determination apparatus concerning the 1st Embodiment of this invention. It is an example of precipitation data used as history data. It is an example of river flow data used as history data. It is explanatory drawing which shows integrated river flow data. It is explanatory drawing which shows a pattern matching analysis. It is an example of a correlation value map of each district (accumulation period T = 1 hour). It is an example of a correlation value map of each district (integration period T = 16 hours). It is a rainfall influence range map which shows a pattern matching analysis result. It is a flowchart which shows the estimation model creation process in the estimation apparatus concerning the 1st Embodiment of this invention. It is a flowchart which shows the estimation model preparation operation | movement with the estimation apparatus concerning the 1st Embodiment of this invention. It is explanatory drawing which shows preparation of the case base used with the estimation apparatus concerning the 1st Embodiment of this invention. It is explanatory drawing which shows the definition of the similarity in a case base. It is a flowchart which shows the river flow volume estimation process in the estimation apparatus concerning the 1st Embodiment of this invention. It is a flowchart which shows the river flow estimation operation | movement with the estimation apparatus concerning the 1st Embodiment of this invention. It is a graph which shows the river flow rate estimation result by the estimation apparatus concerning this Embodiment. It is explanatory drawing which shows the relationship between a river water level and river cross-sectional shape. It is explanatory drawing which shows the relationship between a river water level and a flowing water cross-sectional area. It is an example of the river flow data used for the river water level calculation in 3rd Embodiment. 20 is an example of river water level data calculated from the river flow data of FIG. 19 according to the third embodiment.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 10 ... Rainfall influence range determination apparatus, 11 ... Input part, 12 ... Pattern matching analysis part, 13 ... Rainfall influence range determination part, 20 ... Estimation apparatus, 21 ... Input part, 22 ... History data, 27A ... Model input data, 27B ... model output data, 27C ... set, 23 ... estimated model creation unit, 24 ... estimated model, 25 ... adaptive learning unit, 26 ... output estimation unit, 30 ... river observation point, 31 ... candidate area, 32 ... specific area, 33 ... Rainfall influence range, 40 ... History data, 41 ... Precipitation data, 42 ... River flow rate data, 43 ... Rainfall influence range determination information, 50 ... History data, 51 ... Meteorological data, 52 ... Time data, 53 ... River flow rate data 60 ... estimated condition data, 61 ... meteorological parameters, 62 ... time parameters, 70 ... estimated river flow, 71 ... precipitation, 72 ... actual river flow.

Claims (13)

A pattern matching analysis unit that performs pattern matching analysis on precipitation data indicating time series changes in precipitation in each area within the river basin and river flow data showing time series changes in river flow at any river observation point; and A rainfall impact range determination device having a rain impact range determination unit that determines a rain impact range that affects the river flow rate at the river observation point based on an analysis result;
An estimation model creation unit that creates an estimation model using historical data including precipitation data in an arbitrary specific area within the rain influence range determined by the rain influence range determination device and river flow data at the river observation point; And an estimation device having an output estimation unit that estimates the estimated river flow at the river observation point from the estimation condition data including new precipitation in the specific area using the estimation model. Flow estimation system. In the river flow estimation system according to claim 1,
The pattern matching analysis unit calculates a correlation value between precipitation data and river flow data of each district,
The rainfall influence range determination unit sets a district where the correlation value is equal to or greater than a threshold among the districts as a rainfall influence range. In the river flow estimation system according to claim 1,
The pattern matching analysis unit calculates, as the precipitation data, accumulated precipitation data for each accumulation period, with precipitation accumulated retrospectively over an arbitrary accumulation period from each measurement time point, as precipitation amounts at each measurement time point,
The river flow estimation system, wherein the rain influence range determination unit sets, as a rain influence range, a district in which a correlation value in an arbitrary integration period is equal to or greater than a threshold among the districts. In the river flow estimation system according to claim 2 or claim 3,
The pattern matching analysis unit sequentially shifts the time positions of the precipitation data and the river flow data to calculate the correlation values of the two, and sets the maximum correlation value among these correlation values as the correlation value of the two. A characteristic river flow estimation system. In the river flow estimation system according to claim 1,
The estimated model creation unit includes a plurality of history data including a set of model input data including precipitation in the specific area at an arbitrary time point and model output data including a river flow rate at the river observation point at a corresponding time point. And generating a plurality of case data consisting of a set of input values and output values representing one or more of these historical data, creating the estimation model from a case base using these case data,
The output estimation unit retrieves case data having an input value that matches or is similar to the estimation condition data from the case base of the estimation model, and based on the output value of the retrieved case data, the river flow corresponding to the estimation condition data A river flow rate estimation system characterized by calculating In the river flow estimation system according to claim 1,
The output estimation unit divides the estimated river flow rate by a predetermined flow velocity at the river observation point to obtain a flow cross-sectional area corresponding to the estimated river flow rate, and from the flow cross-sectional area, the flow cross-sectional area and the river at the river observation point are obtained. A river flow rate estimation system, wherein a river water level at the river observation point is calculated based on a function indicating a relationship with a water level. A pattern matching analysis unit that performs pattern matching analysis on precipitation data indicating time series changes in precipitation in each area within the river basin and river flow data showing time series changes in river flow at any river observation point; and A rainfall impact range determination device having a rain impact range determination unit that determines a rain impact range that affects the river flow rate at the river observation point based on an analysis result;
An estimation model creation unit that creates an estimation model using historical data including precipitation data in an arbitrary specific area within the rain influence range determined by the rain influence range determination device and river water level data of the river observation point; A river water level estimation device comprising: an output estimation unit that estimates the estimated river water level at the river observation point from the estimation condition data including new precipitation in the specific area using the estimation model. River level estimation system. A river flow estimation method used in a river flow estimation system for estimating an estimated river flow at a river observation point from arbitrary estimation condition data,
A pattern matching analysis step for pattern matching analysis of precipitation data indicating a time series change of precipitation in each district in the river basin and a river flow data indicating a time series change of the river flow at an arbitrary river observation point;
A rain influence range determination step for determining a rain influence range that affects the river flow rate at the river observation point based on the analysis result;
An estimation model creating step of creating an estimation model using historical data including precipitation data in any specific area within the rain-affected area and river flow data at the river observation point;
A river flow estimation method comprising: an output estimation step of estimating an estimated river flow at the river observation point from the estimation condition data including new precipitation in the specific area using the estimation model. In the river flow estimation method according to claim 8,
Divide the estimated river flow rate by the predetermined flow velocity at the river observation point to obtain the flow cross-sectional area corresponding to the estimated river flow rate, and show the relationship between the flow cross-sectional area at the river observation point and the river water level from this flow cross-sectional area A river flow estimation method, further comprising: calculating a river water level at the river observation point based on a function. A river water level estimation method used in a river water level estimation system for estimating an estimated river level at a river observation point from arbitrary estimation condition data,
A pattern matching analysis step for pattern matching analysis of precipitation data indicating a time series change of precipitation in each district in the river basin and a river flow data indicating a time series change of the river flow at an arbitrary river observation point;
A rain influence range determination step for determining a rain influence range that affects the river flow rate at the river observation point based on the analysis result;
An estimation model creation step of creating an estimation model using historical data including precipitation data in any specific area within the rain-affected area and river water level data of the river observation point;
A river water level estimation method comprising: an output estimation step of estimating an estimated river water level at the river observation point from the estimation condition data including new precipitation in the specific area using the estimation model. In the computer of the river flow estimation system that estimates the estimated river flow at the river observation point from arbitrary estimation condition data,
A pattern matching analysis step for pattern matching analysis of precipitation data indicating a time series change of precipitation in each district in the river basin and a river flow data indicating a time series change of the river flow at an arbitrary river observation point;
A rain influence range determination step for determining a rain influence range that affects the river flow rate at the river observation point based on the analysis result;
An estimation model creating step of creating an estimation model using historical data including precipitation data in any specific area within the rain-affected area and river flow data at the river observation point;
A program for executing an output estimation step of estimating an estimated river flow at the river observation point from the estimation condition data including new precipitation in the specific area using the estimation model. The program according to claim 11,
Divide the estimated river flow rate by the predetermined flow velocity at the river observation point to obtain the flow cross-sectional area corresponding to the estimated river flow rate, and show the relationship between the flow cross-sectional area at the river observation point and the river water level from this flow cross-sectional area A program for further executing a step of calculating a river water level at the river observation point based on a function. In the computer of the river water level estimation system that estimates the estimated river water level at the river observation point from arbitrary estimation condition data,
A pattern matching analysis step for pattern matching analysis of precipitation data indicating a time series change of precipitation in each area within the river basin and river flow data indicating a time series change of river flow at an arbitrary river observation point;
A rain influence range determination step for determining a rain influence range that affects the river flow rate at the river observation point based on the analysis result;
An estimation model creation step of creating an estimation model using historical data including precipitation data in any specific area within the rain-affected area and river water level data of the river observation point;
A program for executing an output estimation step of estimating an estimated river water level at the river observation point from the estimation condition data including new precipitation in the specific area using the estimation model.

Images