Prediction method and device for water flow information of river section, equipment and medium

Abstract

The invention provides a river cross section water flow information prediction method and device, equipment and a medium. The method comprises the steps of obtaining position information of a target river cross section and water flow measurement data of a past time period; based on the position information, grid meteorological data of an upstream basin space vector of the target river section in a target time period are determined, the target time period comprises a past time period before the current moment and a prediction time period after the current moment, and the upstream basin space vector comprises at least one key meteorological grid covering the upstream basin; the precipitation amount in the grid meteorological data is extracted, and a space-time precipitation vector of the upstream basin space vector is generated; and obtaining water flow prediction information of the target river section in the prediction time period by using the river section prediction model based on the space-time precipitation vector and the water flow measurement data. In this way, the future situation of the water flow of the river section can be accurately predicted.

Description

Technical Field

[0001] The present application relates to the technical field of hydrological prediction, and in particular to a method, device, equipment and medium for predicting water flow information of a river cross section. Background Art

[0002] A river cross section is a cross-section perpendicular to the flow of water. Flow information from this cross section is essential data for water resource management, ecological conservation, bridge protection, and waterway safety. For example, high water levels can inundate areas along the river, causing flooding. Alternatively, rapid water flow can impact bridge piers, leading to their destruction.

[0003] Currently, water flow information is measured using an array of sensors (such as water level sensors, flow rate sensors, etc.) installed in the river. However, this sensor array measurement method has problems such as lack of predictive ability and insufficient coverage, which seriously restricts the predictability and accuracy of disasters. Summary of the Invention

[0004] In view of this, the present application provides a method, device, equipment and medium for predicting water flow information of a river section, which can accurately predict the future water flow conditions of a river section through long-term grid meteorological data and water flow measurement data of the river section over a long period of time in the past.

[0005] In a first aspect, a method for predicting water flow information of a river section is provided, comprising: obtaining position information of a target river section and water flow measurement data of a past time period; determining, based on the position information, grid meteorological data of an upstream watershed space vector of the target river section in a target time period, wherein the target time period includes a past time period before a current moment and a predicted time period after a current moment, and the upstream watershed space vector includes at least one key meteorological grid covering the upstream watershed; extracting precipitation from the grid meteorological data, and generating a spatiotemporal precipitation vector of the upstream watershed space vector; utilizing a river section prediction model, and based on the spatiotemporal precipitation vector and the water flow measurement data, obtaining water flow prediction information of the target river section in the prediction time period, wherein the water flow prediction information includes water level and flow velocity.

[0006] In a second aspect, a device for predicting water flow information of a river section is provided, comprising: an acquisition module for acquiring position information of a target river section and water flow measurement data of a past time period; a determination module for determining, based on the position information, grid meteorological data of an upstream watershed space vector of the target river section in a target time period, wherein the target time period includes a past time period before a current moment and a predicted time period after a current moment, and the upstream watershed space vector includes at least one key meteorological grid covering the upstream watershed; a generation module for extracting precipitation from the grid meteorological data and generating a spatiotemporal precipitation vector of the upstream watershed space vector; a prediction module for obtaining water flow prediction information of the target river section in a prediction time period based on the spatiotemporal precipitation vector and the water flow measurement data using a river section prediction model. The water flow prediction information includes water level and flow velocity.

[0007] In a third aspect, an electronic device is provided, comprising a processor, a memory, and a program stored in the memory and capable of running on the processor, wherein when the program is executed by the processor, the steps of the method for predicting water flow information of a river cross section provided in any one of the embodiments of the present application are implemented.

[0008] A fourth aspect provides a computer-readable storage medium storing instructions, which, when executed by a processor, implement the steps of any method for predicting water flow information of a river section provided in the embodiments of the present application.

[0009] In summary, the method, apparatus, device, and medium for predicting water flow information for a river section provided in this application have the following beneficial effects: By using the location information of a target river section and water flow measurement data from past time periods, the spatial position of the target river section can be accurately located, and the long-term dynamic variation patterns of water flow information can be provided to the river section prediction model. Furthermore, based on the location information, the gridded meteorological data of the upstream basin spatial vector of the target river section during the target time period is determined, and the precipitation during the target time period is extracted to generate a spatiotemporal precipitation vector. This allows the key external factors affecting water flow changes to be quantified, thus incorporating more comprehensive environmental variables into the prediction model. Furthermore, by combining water flow measurement data from past time periods with the spatiotemporal precipitation vector and utilizing an advanced river section prediction model, accurate predictions of water flow information for the river section during the prediction period can be achieved. Thus, by fusing real-world measurement data with environmental variables, the inherent mechanisms and external driving factors affecting water flow changes in the river section can be fully captured without the need for specific attribute parameters of the river section, significantly improving the accuracy and credibility of the prediction results, thereby increasing the predictability and accuracy of disasters. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the following is a brief introduction to the drawings required for use in the specific implementation methods or the description of the prior art. Obviously, the drawings described below are some implementation methods of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without any creative work.

[0011] Figure 1 A schematic diagram showing a flow chart of a method for predicting water flow information of a river cross section provided by an embodiment of the present application;

[0012] Figure 2 A schematic diagram showing the positional relationship between a target river section and a meteorological grid provided in one embodiment of the present application is shown;

[0013] Figure 3 A schematic diagram showing the structure of a device for predicting water flow information of a river cross section provided by one embodiment of the present application;

[0014] Figure 4 A schematic structural diagram of an electronic device provided in one embodiment of the present application is shown. DETAILED DESCRIPTION

[0015] In order to make the above and other features and advantages of the present application more clear, the present application is further described below with reference to the accompanying drawings. It should be understood that the specific embodiments given herein are for the purpose of explaining to those skilled in the art and are only exemplary and not restrictive.

[0016] In the following description, many specific details are set forth to provide a thorough understanding of the present application. However, it will be apparent to those skilled in the art that it is not necessary to adopt the specific details to practice the present application. In other cases, well-known steps or operations are not described in detail to avoid obscuring the present application.

[0017] The inventors have discovered that changes in water flow across river sections often lag behind precipitation events. Correlation analysis, combined with long-term precipitation data spanning multiple days or even weeks, is required to accurately reveal the evolution of water flow across a given river section. Consequently, the present invention proposes a technical solution that accurately measures precipitation in the upstream basin of a river section during a target time period by using key meteorological grids covering the upstream basin of the river section. This precipitation is then used as an input parameter in a river section prediction model, enabling precise prediction of water flow information for the river section in the future.

[0018] On the one hand, the present invention provides a method for predicting water flow information of a river section. Figure 1 A flow chart showing a method for predicting water flow information of a river section provided by an embodiment of the present application is shown as follows: Figure 1As shown, the method for predicting the water flow information of the river section may include the following steps.

[0019] Step S11 , obtaining the location information of the target river section and the water flow measurement data of the river section in the past time period.

[0020] The target river cross section involved in an embodiment of the present application may be a cross section at any position of any river. The location information may be geographic location information, including but not limited to a place name, address, or latitude and longitude coordinates.

[0021] It should be noted that the target river cross section may be a cross section at a special location of the river, such as a reservoir.

[0022] The past time period involved in one embodiment of the present application includes a time period starting from N days before the current moment to the current moment, where N can be determined based on the longest continuous rainfall duration in the upstream basin of the target river section.

[0023] In one embodiment of the present application, N may be the rounded result of the longest continuous rainfall duration × the cycle multiple - the predicted duration, wherein the cycle multiple is not less than 1 and not greater than 2. The predicted duration may be the duration of the predicted time period.

[0024] For example, the longest continuous rainfall duration is 15 days, the cycle multiple is 1.5, the forecast duration is 1 day, and N is the rounded result of 15×1.5-1, which is 22.

[0025] The water flow measurement data involved in one embodiment of the present application may be obtained by detecting sensors installed in a target river cross section. The sensors may be installed at multiple measurement points at different locations in the target river cross section. The water flow measurement data for a past time period may include a water flow measurement value for each time step in the past time period. The water flow measurement values ​​may include water level and water flow velocity.

[0026] Step S12: determining the grid meteorological data of the upstream watershed space vector of the target river section in the target time period based on the location information.

[0027] The upstream basin spatial vector involved in one embodiment of the present application may include at least one key meteorological grid covering the upstream basin. That is, the upstream basin spatial vector is a one-dimensional vector, and each element in the upstream basin spatial vector represents the relevant information of a key meteorological grid. The relevant information may include at least the grid number and the grid longitude and latitude. The upstream basin spatial vector may be represented as [key meteorological grid 1, key meteorological grid 2, ...].

[0028] Key meteorological grids are those covering upstream watersheds whose precipitation can affect the target river section. The upstream watershed refers to all catchment areas upstream of the target river section in the direction of flow. The upstream watershed can be determined by analyzing the river's hydrological information.

[0029] A meteorological grid is a grid cell formed by spatially discretizing a geographic area. Grid meteorological data is a collection of meteorological element values ​​for all key meteorological grids during a target period. This grid meteorological data includes at least temperature, precipitation, wind speed, and humidity.

[0030] The target time period involved in one embodiment of the present application includes a past time period before the current moment and a predicted time period after the current moment. The predicted time period includes a continuous time interval starting from the current moment and ending M days after the current moment. M days can be the length of the predicted time period, i.e., the predicted duration. In one embodiment of the present application, N is much greater than M, i.e., N is at least 10 greater than M. Optionally, M is 1.

[0031] In one embodiment of the present application, the duration of the target time period is determined based on the longest continuous rainfall duration in at least one key meteorological grid. Optionally, the duration of the target time period is the number of days obtained by rounding up the result of multiplying the longest continuous rainfall duration by the cycle multiple.

[0032] For example, the longest continuous rainfall duration is 15 days, the cycle multiple is 1.5, the target time period is rounded to 23 days, the past time period is 22 days, and the forecast time period is 1 day.

[0033] The grid meteorological data in the target time period involved in one embodiment of the present application includes grid meteorological data in the past time period and grid meteorological data in the forecast time period. The grid meteorological data in the forecast time period is forecast weather data, and the grid meteorological data in the past time period is historical weather data.

[0034] The grid meteorological data for the upstream watershed spatial vector during the target time period in one embodiment of the present application includes meteorological element values ​​for each time step of all key meteorological grids in the upstream watershed spatial vector during the target time period. The time step is set based on demand, for example, a time step of 1 hour.

[0035] In addition, there is no restriction on the spatial resolution of key meteorological grids, which can be 1 km * 1 km, 2 km * 2 km, 5 km * 5 km, and 10 km * 10 km, etc.

[0036] In one embodiment of the present application, the upstream watershed space vector is determined based on the location information of the target river section, and the grid meteorological data of the upstream watershed space vector in the target time period is determined from the meteorological platform.

[0037] Step S13: extracting precipitation from the grid meteorological data to generate a spatiotemporal precipitation vector of the upstream watershed spatial vector.

[0038] In one embodiment of the present application, the spatiotemporal precipitation vector of the upstream watershed space vector includes the precipitation of each key meteorological grid in the upstream watershed space vector at each time step within the target time period.

[0039] In one embodiment of the present application, the precipitation amount at each time step within the target time period is extracted from the gridded meteorological data for each key meteorological grid. All precipitation amounts are then arranged by grid and time to form a spatiotemporal precipitation vector. Each row of the spatiotemporal precipitation vector represents the precipitation amount at each time step within the target time period for each key meteorological grid, and each column of the spatiotemporal precipitation vector represents the precipitation amount at the same time step for all key meteorological grids.

[0040] Step S14, using the river section prediction model, based on the spatiotemporal precipitation vector and the water flow measurement data of the river section in the past time period, obtain the water flow prediction information of the target river section in the prediction time period.

[0041] The river section prediction model involved in one embodiment of the present application is a prediction model that uniquely corresponds to the target river section. That is, a river section at a given location corresponds to a river section prediction model, and different river section prediction models have different parameters. The river section prediction model can be based on a deep learning model or a machine learning model that can complete multiple prediction tasks. The multiple prediction tasks include at least the task of predicting the water level at each point in the river section and the task of predicting the water flow velocity at each point in the river section.

[0042] In one embodiment of the present application, the river section prediction model is trained based on historical river section measurement data, historical river section information, and historical spatiotemporal precipitation vectors for the target river section. In other words, the training set of the river section prediction model includes the historical river section measurement data, historical river section information, and historical spatiotemporal precipitation vectors for the target river section.

[0043] The historical river cross-section measurement data may be data obtained from measurements at different measurement points within the target river cross-section within a historical time period. The historical river cross-section measurement data may include historical flow velocity measurement data and historical water level measurement data. The historical time period may be any time period prior to the current time, and the duration of the historical time period must be no less than the duration of the target time period.

[0044] The historical river cross-section information may include the water level at each point of the target river cross-section within the historical time period, and the water flow velocity at each point of the target river cross-section within the historical time period.

[0045] The historical spatiotemporal precipitation vector involved in an embodiment of the present application may include the precipitation of all key meteorological grids within a historical time period. The historical spatiotemporal precipitation vector may be formed based on the grid meteorological data within the historical time period.

[0046] In one embodiment of the present application, historical river cross-section information can be obtained based on historical river cross-section measurement data. For example, the historical river cross-section information can be calculated using a fluid dynamics model based on the historical river cross-section measurement data and the shape of the target river cross-section.

[0047] In one embodiment of the present application, before training, the historical river section measurement data, historical river section information, and historical spatiotemporal precipitation vectors of the target river section need to be processed into training samples of multiple different time periods, and the duration of each training sample is the same as the duration of the target time period, which can be expressed as T. The training samples are divided into input data and label data, wherein the input data are the river section measurement data of the previous (TN) days in the training sample and the precipitation vector corresponding to T days, and the label data are the historical river section information of the last M days in the training sample. During the training process, the input data is input into the river section prediction model, and the river section information of the target river section in the last M days is output, and the parameters of the river section prediction model are adjusted according to the difference between the river section information of the target river section in the last M days and the label data.

[0048] In this way, the trained river section prediction model can capture the water level and flow velocity of the target river section within a fixed period based on the long-term different rainfall intensity and distribution in the upstream basin.

[0049] The water flow prediction information involved in one embodiment of the present application may include water level prediction information and water flow velocity prediction information. The water flow prediction information for a target river cross section within a prediction time period may include water flow prediction information for each point on the target river cross section at each time step within the prediction time period. For example, water flow prediction information for each point on the target river cross section for each hour within the prediction time period may be included.

[0050] In one embodiment of the present application, the spatiotemporal precipitation vector and the water flow measurement data of the past time period are input as input parameters into the river section prediction model, and the water flow prediction information of the target river section within the prediction time period is output through processing by the river section prediction model.

[0051] In some of the aforementioned embodiments, the location information of a target river section and flow measurement data from past time periods can be used to precisely locate the spatial position of the target river section and provide the long-term dynamic variation patterns of flow information for the river section prediction model. Furthermore, based on this location information, the gridded meteorological data for the upstream basin spatial vector of the target river section during the target time period is determined, and precipitation during the target time period is extracted to generate a spatiotemporal precipitation vector. This allows quantification of key external factors influencing flow variations, thus incorporating more comprehensive environmental variables into the prediction model. Furthermore, by combining flow measurement data from past time periods with spatiotemporal precipitation vectors and utilizing advanced river section prediction models, accurate predictions of flow information for the river section during the prediction period can be achieved. In this way, by integrating real-world measurement data with environmental variables, without the need for specific river section attribute parameters, the inherent mechanisms and external driving factors that influence changes in flow information in the river section can be fully captured, significantly improving the accuracy and credibility of the prediction results, thereby enhancing the predictability and accuracy of disasters.

[0052] In some embodiments, step S12, determining the grid meteorological data of the upstream basin space vector of the target river section in the target time period based on the location information, may include: determining the upstream basin boundary of the target river section based on the location information; determining at least one key meteorological grid covering the upstream basin based on the upstream basin boundary, and generating the upstream basin space vector based on the at least one key meteorological grid; determining the grid meteorological data of the upstream basin space vector in the target time period.

[0053] In one embodiment of the present application, the hydrological information of the target river can be determined based on the location of the target river section, and the watershed can be extracted based on the hydrological information of the target river using a hydrological analysis tool to obtain the upstream watershed boundary of the target river section.

[0054] In addition, after obtaining the upstream basin boundary of the target river section, the upstream basin boundary can be manually corrected.

[0055] In one embodiment of the present application, the upstream basin boundary is matched to a meteorological grid system. One or more key meteorological grids covering the upstream basin are identified from the meteorological grid system, and these key meteorological grids are sorted to generate an upstream basin spatial vector. Furthermore, based on each key meteorological grid in the upstream basin spatial vector and the time range of the target time period, meteorological data for all grids corresponding to the target time period is obtained from the meteorological platform.

[0056] In some of the above embodiments, the upstream basin boundary is determined based on the location information of the target river interface, so that the grid meteorological data of the corresponding key meteorological grid and the target time period can be accurately obtained, thereby achieving accurate matching of the meteorological grid data with the upstream basin location, ensuring the temporal and spatial consistency of the meteorological information with the actual conditions of the upstream basin, reducing the prediction error caused by data mismatch, and providing a basis for the subsequent prediction of water flow information.

[0057] When the upstream basin is large, the number of meteorological grids covering it is large, which means that the river cross-section prediction model needs to process more data and has a high computational load, which is not conducive to the prediction of water flow information. Therefore, it is proposed to use different selection strategies for meteorological grids based on the size of the upstream basin. In this way, when the area is large, the model needs to process less data and reduces the computational load, which is conducive to the prediction of water flow information in the target river cross-section.

[0058] In some embodiments, at least one key meteorological grid covering the upstream basin is determined based on the upstream basin boundary, including: determining the regional area of ​​the upstream basin based on the upstream basin boundary; determining a selection strategy for the key meteorological grid based on a comparison result between the regional area and a preset threshold; and selecting at least one key meteorological grid covering the upstream basin based on the selection strategy.

[0059] The selection strategy involved in one embodiment of the present application is a strategy for selecting key meteorological grids. The selection strategy may include a basic strategy and an optimization strategy. The basic strategy is a grid selection strategy when the area of ​​the upstream basin is small (i.e., not greater than a preset threshold), that is, each meteorological grid covering the upstream basin is regarded as a key meteorological grid covering the upstream basin.

[0060] The optimization strategy is a grid selection strategy for when the area of ​​the upstream basin is large (i.e., greater than a preset threshold). Compared with the basic strategy, the optimization strategy removes some unimportant meteorological grids from the meteorological grids covering the upstream basin.

[0061] The preset threshold involved in an embodiment of the present application can be set according to user needs. For example, the preset threshold can be 10 square kilometers.

[0062] In one embodiment of the present application, the area of ​​the upstream basin can be compared with a preset threshold to obtain a comparison result of the boundary area of ​​the upstream basin with the preset threshold. Based on the comparison result, an appropriate selection strategy is determined and executed to obtain all key meteorological grids covering the upstream basin.

[0063] In one embodiment of the present application, the selection strategy of the key meteorological grid is determined based on the comparison result between the regional area and the preset threshold, including: when the regional area is not greater than the preset threshold, determining the selection strategy of the key meteorological grid as the basic strategy; when the regional area is greater than the preset threshold, determining the selection strategy of the key meteorological grid as the optimization strategy.

[0064] In one embodiment of the present application, the optimization strategy includes screening a plurality of key meteorological grids from all meteorological grids covering the upstream basin according to the hydrological characteristics of the upstream basin.

[0065] The hydrological characteristics of the upstream basin involved in one embodiment of the present application may include precipitation characteristics, topographic characteristics, and runoff characteristics. Topographic characteristics include, but are not limited to, basin slope differences and elevation differences. Precipitation characteristics may include, for example, monthly average precipitation. Runoff characteristics may include monthly runoff volume, water level, and water velocity.

[0066] In one embodiment of the present application, the hydrological characteristics of the upstream basin can be obtained from meteorological data provided by the meteorological platform, runoff monitoring data provided by the hydrological station, and electronic maps.

[0067] In one embodiment of the present application, a screening condition can be used to select multiple key meteorological grids from all meteorological grids covering the upstream basin. The screening condition is set based on hydrological characteristics. For example, the screening condition may include selecting meteorological grids corresponding to areas with high precipitation in the upstream basin as key meteorological grids, selecting meteorological grids corresponding to areas with high runoff in the upstream basin as key meteorological grids, and selecting meteorological grids corresponding to high-altitude areas in the upstream basin as key meteorological grids, etc.

[0068] That is to say, the areas in the upstream basin that meet the screening conditions are determined according to the hydrological characteristics of the upstream basin, and all meteorological grids covering the upstream basin are determined, and the meteorological grids corresponding to the areas that meet the screening conditions (i.e., key meteorological grids) are screened out from all meteorological grids.

[0069] Figure 2 A schematic diagram showing the positional relationship between the target river section and the meteorological grid provided in one embodiment of the present application is shown in FIG. Figure 2 As shown, grids 1-17 belong to meteorological grids, double arrows indicate the location of the target river section, and single arrows indicate the target river. The upstream basin spatial vector includes at least grids 7 to 11.

[0070] In the above embodiment, by screening key meteorological grids based on the hydrological characteristics of the upstream basin, key meteorological grids that are strongly correlated with the hydrological characteristics of the basin can be efficiently screened out, providing a reliable basis for subsequent water level prediction.

[0071] In some embodiments, in step S13, after extracting the precipitation in the grid meteorological data and generating the spatiotemporal precipitation vector of the upstream watershed spatial vector, the method for predicting the water flow information of the river section may further include: determining the rendering color of the key meteorological grid within the target time period based on the correspondence between the precipitation and the rendering color and the spatiotemporal precipitation vector.

[0072] The rendering color involved in an embodiment of the present application refers to the color of the key meteorological grid rendered in the visualization interface. The corresponding relationship between precipitation and rendering color refers to the mapping rule between precipitation and rendering color.

[0073] In one embodiment of the present application, different precipitation amounts can be classified into different precipitation intensities based on meteorological precipitation intensity classification, and different precipitation intensities can be corresponding to different rendering colors. That is, the precipitation amount of each key meteorological grid at each time step within the forecast period is obtained, and the key meteorological grid is rendered according to the rendering color corresponding to the precipitation amount.

[0074] For example, when the precipitation of a key meteorological grid exceeds 60 mm, it indicates high-intensity precipitation, and the rendering color of the key meteorological grid is determined to be red, and the key meteorological grid is rendered in red on the visualization interface.

[0075] In some of the above embodiments, the rendering color of each key meteorological grid is determined according to the precipitation, so that each key meteorological grid on the visualization interface can be rendered in a different color, directly presenting the precipitation distribution of the basin, making it convenient for users to quickly find dangerous precipitation areas.

[0076] In some embodiments, in step S14, after obtaining the water flow prediction information of the target river section within the prediction time period using the river section prediction model based on the spatiotemporal precipitation vector and the water flow measurement data, the prediction method of the water flow information of the river section may further include: generating and pushing warning information when the water flow prediction information meets the warning conditions.

[0077] The warning conditions involved in one embodiment of the present application may include issuing a warning when the water level exceeds a preset water level or the water flow speed exceeds a preset water flow speed. The warning information includes at least the river name, the river cross-section location, the water level and water flow speed, and the time when the danger occurs.

[0078] In one embodiment of the present application, when the warning conditions are met, the push mechanism is immediately activated, and the warning information is pushed through appropriate channels based on the preferences of the target audience and the actual situation. For example, for the public, the push can be through social media, radio, television, and other channels; for traffic management departments, the push can be sent to the management platform via the Internet.

[0079] In the above embodiment, when the weather forecast information meets the preset alarm conditions, early warning information can be generated and pushed in a timely and accurate manner, providing effective early warnings for river managers and the public.

[0080] Another aspect of the present application provides a device for predicting water flow information of a river cross section. Figure 3 A schematic diagram showing the structure of a device for predicting water flow information of a river cross section provided by an embodiment of the present application is shown as follows: Figure 3 As shown, the device 30 for predicting the water flow information of the river section may include the following modules.

[0081] The acquisition module 31 is used to obtain the location information of the target river section and the water flow measurement data of the past time period.

[0082] The determination module 32 is used to determine the grid meteorological data of the upstream basin space vector of the target river section in the target time period based on the location information, wherein the target time period includes a past time period before the current moment and a predicted time period after the current moment, and the upstream basin space vector includes at least one key meteorological grid covering the upstream basin.

[0083] The generation module 33 is used to extract the precipitation in the grid meteorological data and generate the spatiotemporal precipitation vector of the upstream basin space vector.

[0084] The prediction module 34 is used to obtain the water flow prediction information of the target river section within the prediction time period using the river section prediction model based on the spatiotemporal precipitation vector and the water flow measurement data. The water flow prediction information includes water level and flow velocity.

[0085] In the above-described embodiment, the location information of the target river section and flow measurement data from past time periods can be used to precisely locate the spatial position of the target river section and provide the long-term dynamic variation patterns of flow information for the river section prediction model. Furthermore, based on this location information, the gridded meteorological data for the spatial vector of the upstream basin of the target river section during the target time period is determined, and the precipitation during the target time period is extracted to generate a spatiotemporal precipitation vector. This allows the key external factors influencing flow variations to be quantified, thus incorporating more comprehensive environmental variables into the prediction model. Furthermore, by combining flow measurement data from past time periods with the spatiotemporal precipitation vector and utilizing an advanced river section prediction model, accurate predictions of flow information for the river section during the prediction period can be achieved. In this way, by integrating real-world measurement data with environmental variables, the inherent mechanisms and external driving factors that influence flow variations in the river section can be fully captured without the need for specific river section attribute parameters, significantly improving the accuracy and credibility of the prediction results, thereby enhancing the predictability and accuracy of disasters.

[0086] In some embodiments, the determination module 32 is specifically used to determine the upstream basin boundary of the target river section based on the location information; determine at least one key meteorological grid covering the upstream basin according to the upstream basin boundary, and generate an upstream basin space vector based on at least one key meteorological grid; determine the grid meteorological data of the upstream basin space vector in the target time period.

[0087] In some embodiments, the determination module 32 is further specifically used to determine the regional area of ​​the upstream basin based on the upstream basin boundary; determine the selection strategy of the key meteorological grid based on the comparison result of the regional area and the preset threshold; and select at least one key meteorological grid covering the upstream basin according to the selection strategy.

[0088] In some embodiments, the determination module 32 is further configured to determine the selection strategy of the key meteorological grid as the basic strategy when the area of ​​the region is not greater than a preset threshold; and to determine the selection strategy of the key meteorological grid as the optimization strategy when the area of ​​the region is greater than the preset threshold.

[0089] It should be understood that the specific features, operations, and details described hereinabove with respect to the method of the present application may also be similarly applied to the apparatus and system of the present application, or vice versa. In addition, each step of the method of the present application described above may be performed by a corresponding component or unit of the apparatus or system of the present application.

[0090] It should be understood that the various modules / units of the apparatus of the present application may be implemented in whole or in part by software, hardware, firmware, or a combination thereof. Each module / unit may be embedded in the processor of the electronic device in the form of hardware or firmware or may be independent of the processor, or may be stored in the memory of the electronic device in the form of software for the processor to call to execute the operation of each module / unit. Each module / unit may be implemented as an independent component or module, or two or more modules / units may be implemented as a single component or module.

[0091] In another aspect of the present application, an electronic device is provided. Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present application is shown in FIG. Figure 4 As shown, the electronic device 40 includes a processor 41, a memory 42, and a program stored in the memory and capable of running on the processor. When the program is executed by the processor, the steps of the method for predicting water flow information of a river section provided in any of the above embodiments are implemented.

[0092] In one embodiment, the electronic device 40 may include a processor, memory, network interface, communication interface, etc. connected via a system bus. The processor of the electronic device 40 may be used to provide necessary computing, processing, and / or control capabilities. The memory of the electronic device 40 may include a non-volatile storage medium and internal memory. The non-volatile storage medium may store an operating system, computer programs, etc. The internal memory may provide an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface and communication interface of the electronic device 40 may be used to connect to and communicate with external devices via a network.

[0093] On the other hand, the present application provides a computer-readable storage medium storing instructions, wherein when the instructions are executed by a processor, the steps of the method for predicting water flow information of a river cross section provided in any of the above embodiments are implemented.

[0094] Those skilled in the art will appreciate that the method steps of the present application can be performed by instructing relevant hardware such as electronic devices or processors through a computer program, and the computer program can be stored in a non-transitory computer-readable storage medium, which causes the steps of the present application to be performed when the computer program is executed. Depending on the circumstances, any reference to memory, storage or other media herein may include non-volatile or volatile memory. Examples of non-volatile memory include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid-state disk, etc. Examples of volatile memory include random access memory (RAM), external cache memory, etc.

[0095] The various technical features described above can be combined arbitrarily. Although not all possible combinations of these technical features are described, any combination of these technical features should be considered to be covered by this specification as long as such combination does not conflict.

[0096] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for predicting water flow information of a river section, characterized in that: include: Obtain the location information of the target river section and the water flow measurement data of the past time period; determining, based on the location information, grid meteorological data of an upstream watershed space vector of the target river section in a target time period, the target time period including a past time period before a current moment and a predicted time period after the current moment, the upstream watershed space vector including at least one key meteorological grid covering the upstream watershed; Extracting precipitation from the grid meteorological data to generate a spatiotemporal precipitation vector of the upstream watershed spatial vector; The water flow prediction information of the target river section within the prediction time period is obtained by using a river section prediction model based on the spatiotemporal precipitation vector and the water flow measurement data. The water flow prediction information includes water level and flow velocity.

2. The method for predicting water flow information of a river section according to claim 1, characterized in that: Determining the grid meteorological data of the upstream watershed space vector of the target river section in the target time period based on the location information includes: Determining an upstream watershed boundary of the target river section based on the location information; determining, based on the upstream basin boundary, at least one key meteorological grid covering the upstream basin, and generating an upstream basin spatial vector based on the at least one key meteorological grid; Determine the grid meteorological data of the upstream watershed spatial vector in the target time period.

3. The method for predicting water flow information of a river section according to claim 2, characterized in that: The step of determining at least one key meteorological grid covering the upstream basin according to the upstream basin boundary includes: Determining the area of ​​the upstream watershed based on the upstream watershed boundary; Determining a selection strategy for the key meteorological grid based on a comparison result between the area of ​​the region and a preset threshold; According to the selection strategy, at least one key meteorological grid covering the upstream watershed is selected.

4. The method for predicting water flow data of a river section according to claim 3, characterized in that: The selection strategy includes a basic selection strategy and an optimized selection strategy. The selection strategy of the key meteorological grid is determined based on the comparison result between the area of ​​the region and the preset threshold, including: When the area of ​​the region is not greater than the preset threshold, determining the selection strategy of the key meteorological grid as the basic strategy; When the area of ​​the region is greater than the preset threshold, the selection strategy of the key meteorological grid is determined to be an optimization strategy.

5. The method for predicting water flow information of a river section according to claim 4, characterized in that: The optimization strategy includes screening a plurality of key meteorological grids from all meteorological grids covering the upstream basin according to the hydrological characteristics of the upstream basin.

6. The method for predicting water flow information of a river section according to claim 1, characterized in that: The duration of the target time period is determined according to the longest continuous rainfall duration in the target river section.

7. The method for predicting water flow information of a river section according to claim 1, characterized in that: The river section prediction model is obtained by training based on historical river section measurement data, historical river section information and historical spatiotemporal precipitation vectors of the target river section.

8. A device for predicting water flow information of a river section, characterized in that: include: An acquisition module is used to obtain the location information of the target river section and the water flow measurement data of the past time period; a determination module, configured to determine, based on the location information, grid meteorological data of an upstream watershed space vector of the target river section in a target time period, wherein the target time period includes a past time period before a current moment and a predicted time period after the current moment, and the upstream watershed space vector includes at least one key meteorological grid covering the upstream watershed; A generation module, configured to extract precipitation from the grid meteorological data and generate a spatiotemporal precipitation vector of the upstream basin spatial vector; The prediction module is used to obtain the water flow prediction information of the target river section within the prediction time period based on the spatiotemporal precipitation vector and the water flow measurement data using a river section prediction model, wherein the water flow prediction information includes water level and flow velocity.

9. An electronic device, characterized in that: The method comprises a processor, a memory and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the method implements the steps of the method for predicting water flow information of a river section as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed by the processor, the steps of the method for predicting water flow information of a river cross section according to any one of claims 1 to 7 are implemented.

Images