A method and system for predicting lake water level changes

Abstract

The technical scheme provided by the application is a lake water level change prediction method and system, comprising the following steps: determining a plurality of hydrological stations distributed in the upstream basin of a to-be-measured lake according to the geographical position of the lake, and obtaining geographical position information and historical water level data of the hydrological stations; obtaining historical water level data of the to-be-measured lake, and establishing a lake water level change prediction model according to the historical water level data and geographical position information of the plurality of hydrological stations and the historical water level data of the to-be-measured lake; obtaining real-time water level data of the plurality of hydrological stations and inputting the real-time water level data into the lake water level change prediction model, and the lake water level change prediction model outputs the water level change condition of the to-be-measured lake. The application can accurately predict the water level change condition of the lake.

Description

Technical Field

[0001] This invention relates to the field of lake water levels, and more specifically to a method and system for predicting lake water level changes. Background Technology

[0002] my country has a large number of lakes, which are widely distributed and diverse in type. Lakes are sensitive indicators of climate and environmental change and important information carriers for revealing global climate change and regional responses. The study of lake water level changes is the foundation of lake hydrology. These changes are closely related to factors such as regional rainfall, temperature, evaporation, humidity, and human activities. Long-term water level series can reflect the impact of regional climate change and human activities on lakes.

[0003] However, existing technologies often lack effective methods and systems for predicting lake conditions, making it impossible to provide accurate early warnings of lake changes during flood or drought seasons. Summary of the Invention

[0004] To address the aforementioned problems, this invention provides a method and system for predicting lake water level changes, which can accurately predict changes in lake water levels.

[0005] To address the above problems, the present invention provides a method for predicting lake water level changes, comprising the following steps:

[0006] Based on the geographical location of the lake to be measured, several hydrological stations distributed in the upstream basin of the lake were identified and their geographical location information and historical water level data were obtained;

[0007] Historical water level data of the lake to be measured is obtained, and a lake water level change prediction model is established based on the historical water level data and geographical location information of the various hydrological stations and the historical water level data of the lake to be measured.

[0008] The real-time water level data of the aforementioned hydrological stations are obtained and input into the lake water level change prediction model. The lake change prediction model outputs the water level change of the lake to be measured.

[0009] In the above technical solution, the process of establishing the lake water level change prediction model includes: establishing a water level relationship matrix and a location relationship matrix based on the historical water level data and geographical location information of the plurality of hydrological stations; the water level relationship matrix is ​​used to characterize the difference in the change of historical water level data of any two hydrological stations within a set time interval; the location relationship matrix is ​​used to characterize the Euclidean distance between the geographical locations of any two hydrological stations; training a convolutional neural network model with the product of the location relationship matrix and the water level relationship matrix as input and the historical water level change data of the lake to be measured as output; and using the trained convolutional neural network model as the lake water level change prediction model.

[0010] In the above technical solution, the process of establishing the water level relationship matrix includes: dividing the historical water level data of each hydrological station and the historical water level data of the lake to be measured according to a set time interval, and calculating the historical water level change of each hydrological station and the historical water level change of the lake to be measured within the set time interval respectively; the rows and columns of the water level relationship matrix represent the historical water level data of the hydrological station, and the elements at corresponding positions in the water level relationship matrix are the difference between the historical water level changes of two corresponding hydrological stations within the same time interval.

[0011] In the above technical solution, the rows and columns of the location relationship matrix represent the geographical locations of the hydrological stations, and the elements of the corresponding positions in the location relationship matrix are the Euclidean distance between the geographical locations of the two corresponding hydrological stations.

[0012] The above technical solution also includes the following steps: acquiring real-time water level data of the lake to be measured, and combining the lake change prediction model to output the water level change of the lake to be measured, and calculating the predicted water level of the lake to be measured; comparing the calculated predicted water level of the lake to be measured with the set warning water level, and outputting alarm information if the predicted water level is greater than or equal to the warning water level.

[0013] In the above technical solution, the lake to be tested is located in a warm and humid zone; the several hydrological stations are distributed in the upstream river that serves as the water source for the lake to be tested, and are used to collect water level information of the upstream river.

[0014] This invention provides a system for predicting lake water level changes, the system comprising:

[0015] The upstream water level information acquisition module is used to determine several hydrological stations distributed in the upstream basin of the lake based on the geographical location of the lake to be measured, and to acquire their geographical location information and historical water level data.

[0016] The lake water level change prediction model generation module is used to obtain historical water level data of the lake to be measured, and to establish a lake water level change prediction model based on the historical water level data and geographical location information of the various hydrological stations and the historical water level data of the lake to be measured.

[0017] The lake water level change prediction module is used to acquire real-time water level data from the aforementioned hydrological stations and input them into the lake water level change prediction model. The lake change prediction model outputs the water level change of the lake to be measured.

[0018] This invention provides an electronic device, comprising: at least one processor, at least one memory, a communication interface, and a bus;

[0019] The processor, memory, and communication interface communicate with each other through the bus.

[0020] The memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to implement the method described in the above technical solution.

[0021] The present invention provides a computer-readable storage medium that stores computer instructions that cause a computer to perform the methods described in the above technical solution.

[0022] Compared with existing technologies, this invention predicts the water level changes of a lake based on historical hydrological data from upstream hydrological stations, thereby plotting a predicted curve for the lake over a future period. Besides real-time water level monitoring, it also provides early warnings of future water level changes, improving the foresight of early warnings for the lake. This invention establishes location and water level relationship matrices based on historical water level data from various hydrological stations, and uses these to construct a lake water level change prediction model. This enables a quantitative representation of the water level data between the lake and the hydrological station data, improving the accuracy of water level predictions for the lake. Attached Figure Description

[0023] Figure 1 This is a schematic diagram of the process of the present invention;

[0024] Figure 2 This is a schematic diagram of the system of the present invention. Detailed Implementation

[0025] The present invention will be further illustrated below with reference to specific embodiments. It should be understood that these embodiments are for illustrative purposes only and are not intended to limit the scope of the invention. After reading the present invention, any modifications of the present invention in various equivalent forms by those skilled in the art will fall within the scope defined by the appended claims.

[0026] This invention provides a method for predicting lake water level changes, comprising the following steps:

[0027] Based on the geographical location of the lake to be measured, several hydrological stations distributed in the upstream basin of the lake were identified and their geographical location information and historical water level data were obtained;

[0028] Historical water level data of the lake to be measured is obtained, and a lake water level change prediction model is established based on the historical water level data and geographical location information of the various hydrological stations and the historical water level data of the lake to be measured.

[0029] The real-time water level data of the aforementioned hydrological stations are obtained and input into the lake water level change prediction model. The lake change prediction model outputs the water level change of the lake to be measured.

[0030] Specifically, the process of establishing the lake water level change prediction model includes: establishing a water level relationship matrix and a location relationship matrix based on the historical water level data and geographical location information of the plurality of hydrological stations; the water level relationship matrix is ​​used to characterize the difference in the change of historical water level data of any two hydrological stations within a set time interval; the location relationship matrix is ​​used to characterize the Euclidean distance between the geographical locations of any two hydrological stations; training a convolutional neural network model with the product of the location relationship matrix and the water level relationship matrix as input and the historical water level change data of the lake to be measured as output; and using the trained convolutional neural network model as the lake water level change prediction model.

[0031] Specifically, the process of establishing the water level relationship matrix includes: dividing the historical water level data of each hydrological station and the historical water level data of the lake to be measured according to a set time interval, and calculating the historical water level change of each hydrological station and the historical water level change of the lake to be measured within the set time interval respectively; the rows and columns of the water level relationship matrix represent the historical water level data of the hydrological station, and the elements at corresponding positions in the water level relationship matrix are the difference between the historical water level changes of two corresponding hydrological stations within the same time interval.

[0032] Specifically, the rows and columns of the location relationship matrix represent the geographical locations of the hydrological stations, and the elements at corresponding positions in the location relationship matrix represent the Euclidean distance between the geographical locations of the two corresponding hydrological stations.

[0033] Specifically, it also includes the following steps: obtaining real-time water level data of the lake to be measured, and combining it with the lake change prediction model to output the water level change of the lake to be measured, and calculating the predicted water level of the lake to be measured; comparing the calculated predicted water level of the lake to be measured with the set warning water level, and outputting an alarm message if the predicted water level is greater than or equal to the warning water level.

[0034] Specifically, the lake to be tested is located in a warm and humid region; the several hydrological stations are distributed in the upstream river that serves as the water source for the lake to be tested, and are used to collect water level information of the upstream river.

[0035] This specific embodiment analyzes historical water level data from an upstream hydrological station of the lake under test over a continuous time period. Combined with the water level changes of the lake under test within the corresponding continuous time period, a water level change prediction model is established. The specific steps include:

[0036] The first step is to divide the historical water level data of each upstream hydrological station and the historical water level data of the lake to be measured into a preset time interval, and calculate the historical water level change of each hydrological station and the historical water level change of the lake to be measured in each time interval.

[0037] After the water level of an upstream river changes, it takes a certain amount of time for it to affect the water level of a downstream lake. Therefore, the historical water level data of each hydrological station and the historical water level data of the lake being measured correspond in time, but there is a time difference between the historical water level data of each hydrological station and the historical water level data of the lake being measured. In this specific embodiment, this time difference is defined as the difference between the time point when the historical water level data of each hydrological station changes and the time point when the historical water level data of the lake being measured changes. The time point when the historical water level data of each hydrological station changes can be the time point when the water level of any one or more hydrological stations changes, or the time point when the water level of one or more hydrological stations at a specified location changes.

[0038] The second step is to establish a location relationship matrix W based on the locations of various hydrological stations in the area surrounding the current substation. The rows and columns of the location relationship matrix represent the locations of the hydrological stations. The elements corresponding to the locations in the location relationship matrix are the Euclidean distance dij between the locations of the two corresponding hydrological stations i and j. The elements on the diagonal are 0, that is, the element W[i,j] = dij in the i-th row and j-th column of matrix W.

[0039] The third step is to establish a water level relationship matrix Q based on the historical water level changes between each hydrological station within each time interval. The rows and columns of this water level relationship matrix represent the historical water level data of the hydrological stations. The element at the corresponding position in the water level relationship matrix is ​​the difference in the historical water level changes of two corresponding hydrological stations i and j within the same time interval Δt. That is, the element Q[i,j] in the i-th row and j-th column of matrix Q is ΔLi - ΔLj, where ΔLi is the historical water level change at hydrological station i within the time interval Δt, and ΔLj is the historical water level change at hydrological station j within the time interval Δt.

[0040] The fourth step involves training a lake water level change prediction model using the product of the location relationship matrix and the water level relationship matrix as input and the historical water level changes of the lake to be measured as output. The trained lake water level change prediction model is then used as the lake water level change prediction model.

[0041] This specific embodiment introduces a location relationship matrix and a water level relationship matrix when predicting the water level changes of the lake under test. The location relationship matrix of each hydrological station of the lake reflects the spatial relationship between the stations, characterizing the influence of the geographical location of the upstream river measured by the station on the water level changes of the downstream lake. The water level relationship matrix reflects the relationship between the water levels of each hydrological station over time, characterizing the influence of the upstream river on the water level of the downstream lake in the time dimension. By training the lake water level change prediction model with the product of the location relationship matrix and the water level relationship matrix as input and the historical water level changes of the lake under test as output, the lake water level change prediction model can intuitively reflect the spatiotemporal relationship between the water level changes of the lake under test and the location and monitoring data of the surrounding hydrological stations, thereby accurately predicting the water level changes of the lake under test.

[0042] The fifth step is to obtain the real-time water level data of each hydrological station and input it into the water level change prediction model to predict and output the water level change data of the lake to be measured in the future.

[0043] The sixth step is to conduct water level monitoring and early warning based on the predicted water level changes of the lake to be tested.

[0044] Due to the time difference between the hydrological station's water level data and the water level data of the lake to be measured, the predicted water level change of the lake to be measured can be superimposed with the real-time water level reading of the lake to obtain the predicted water level value of the lake to be measured, thereby drawing the predicted water level curve of the lake to be measured in real time.

[0045] Furthermore, by setting different time interval scales, water level change data at different time intervals can be obtained, enabling the prediction of water level forecast curves for a future period. Therefore, warning water levels can be set, and the time when the water level of the lake to be measured reaches the warning water level can be predicted based on the predicted water level curve, allowing for water level monitoring and early warning. When the predicted water level of the lake reaches the warning water level, an early warning procedure can be activated.

[0046] Specifically, the warning water level is based on different accident types of the lake to be measured. The historical water level data of the lake to be measured and the relevant accident data of different types are compared with the historical data and relevant accident data of the same type of lake. Corresponding warning water levels are set for different types of accidents. The warning water levels are set as first warning value, second warning value and third warning value increasing from small to large, or first warning value, second warning value and third warning value decreasing from large to small. Different warning water levels are set for different accident characteristics.

[0047] The methods for setting the first, second, and third alert values ​​include the following steps:

[0048] For a specific incident affecting a lake, its historical water level data is statistically analyzed against experience data from similar lakes to obtain a distribution model of the lake's historical water level data for that incident. The incidents include situations such as a drop in lake water level leading to fish deaths, or a rise in lake water level causing urban flooding.

[0049] Based on a statistical distribution model using historical water level data, warning water levels for various types of accidents are calculated. Then, a first, second, and third warning value are set based on these calculated warning water levels. The first warning value indicates that the lake has not shown any signs of an accident. The second warning value indicates the critical value at which an accident is likely to occur in the lake. The third warning value indicates the critical value at which an accident will occur in the lake.

[0050] In response to lake incidents caused by rising water levels, if the predicted water levels of all lakes under monitoring are determined to be below the corresponding first warning value, the lake water level is considered to be in a safe state. If the predicted water level of the lake under monitoring is determined to be above the corresponding first warning value but below the second warning value, a status monitoring program is activated for the lake under monitoring, increasing the sampling frequency of water level data from upstream hydrological stations to predict the water level of the lake under monitoring more frequently. If the predicted water level of the lake under monitoring is determined to be above the corresponding second warning value but below the third warning value, a monitoring and early warning program is activated for the lake under monitoring, issuing a notification message to relevant management personnel to prepare for the implementation of management measures. If the predicted water level of the lake under monitoring is determined to be above the corresponding third warning value, a fault alarm is activated for the lake under monitoring, notifying relevant management personnel to initiate relevant measures.

[0051] In response to lake incidents caused by declining water levels, if the predicted water levels of all lakes under monitoring are determined to be above the corresponding first warning value, the lake water level is considered to be in a safe state. If the predicted water level of the lake under monitoring is determined to be below the corresponding first warning value but above the second warning value, a status monitoring program is activated for the lake under monitoring, increasing the sampling frequency of water level data from upstream hydrological stations to predict the water level of the lake under monitoring more frequently. If the predicted water level of the lake under monitoring is determined to be below the corresponding second warning value but above the third warning value, a monitoring and early warning program is activated for the lake under monitoring, issuing a notification message to relevant management personnel to prepare for the implementation of management measures. If the predicted water level of the lake under monitoring is determined to be below the corresponding third warning value, a fault alarm is activated for the lake under monitoring, notifying relevant management personnel to initiate relevant measures.

[0052] like Figure 2 As shown, the present invention provides a prediction system for lake water level changes, the system comprising:

[0053] The upstream water level information acquisition module is used to determine several hydrological stations distributed in the upstream basin of the lake based on the geographical location of the lake to be measured, and to acquire their geographical location information and historical water level data.

[0054] The lake water level change prediction model generation module is used to obtain historical water level data of the lake to be measured, and to establish a lake water level change prediction model based on the historical water level data and geographical location information of the various hydrological stations and the historical water level data of the lake to be measured.

[0055] The lake water level change prediction module is used to acquire real-time water level data from the aforementioned hydrological stations and input them into the lake water level change prediction model. The lake change prediction model outputs the water level change of the lake to be measured.

[0056] In the above detailed description, various features are combined together in a single embodiment to simplify this disclosure. This approach to disclosure should not be construed as reflecting an intention that embodiments of the claimed subject matter require more features than are explicitly stated in each claim. Rather, as reflected in the appended claims, the invention is presented with fewer features than all of the features of the single disclosed embodiment. Therefore, the appended claims are hereby explicitly incorporated into the detailed description, wherein each claim stands alone as a preferred embodiment of the invention.

[0057] The disclosed embodiments have been described above to enable any person skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be applied to other embodiments without departing from the spirit and scope of this disclosure. Therefore, this disclosure is not limited to the embodiments given herein, but is consistent with the broadest scope of the principles and novel features disclosed in this application.

[0058] The foregoing description includes examples of one or more embodiments. It is certainly impossible to describe all possible combinations of components or methods in order to describe the above embodiments, but those skilled in the art will recognize that further combinations and arrangements of the various embodiments are possible. Therefore, the embodiments described herein are intended to cover all such changes, modifications, and variations that fall within the scope of the appended claims. Furthermore, the term "comprising" as used in the specification or claims is interpreted in a manner similar to the term "including," as interpreted when used as a conjunction in the claims. Additionally, the use of any term "or" in the specification of the claims is intended to mean "non-exclusive or."

[0059] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for predicting lake water level changes, characterized in that... Includes the following steps: Based on the geographical location of the lake to be measured, several hydrological stations distributed in the upstream basin of the lake are identified; and real-time water level data of the aforementioned hydrological stations are obtained. Historical water level data of the aforementioned hydrological stations and historical water level data of the lake to be measured are obtained, and a lake water level change prediction model is established based on the historical water level data of the aforementioned hydrological stations and historical water level data of the lake to be measured. The real-time water level data of the aforementioned hydrological stations are obtained and input into the lake water level change prediction model. The lake change prediction model outputs the water level change of the lake to be measured. The process of establishing the lake water level change prediction model includes: establishing a water level relationship matrix and a location relationship matrix based on the historical water level data and geographical location information of the aforementioned hydrological stations; the water level relationship matrix is ​​used to represent the difference in the change of historical water level data of any two hydrological stations within a set time period; the location relationship matrix is ​​used to represent the Euclidean distance between the geographical locations of any two hydrological stations; the product of the location relationship matrix and the water level relationship matrix is ​​used as input, and the historical water level change data of the lake to be measured is used as output to train a convolutional neural network model; the trained convolutional neural network model is used as the lake water level change prediction model. The process of establishing the water level relationship matrix includes: dividing the historical water level data of each hydrological station and the historical water level data of the lake to be measured according to a set time interval, and calculating the historical water level change of each hydrological station and the historical water level change of the lake to be measured within the set time interval; the rows and columns of the water level relationship matrix represent the historical water level data of the hydrological station, and the elements at corresponding positions in the water level relationship matrix are the difference between the historical water level changes of the two corresponding monitoring points within the same time interval; The rows and columns of the location relationship matrix represent the geographical locations of the hydrological stations, and the elements at corresponding positions in the location relationship matrix represent the Euclidean distance between the geographical locations of the two corresponding hydrological stations.

2. The method for predicting lake water level changes according to claim 1, characterized in that: It also includes the following steps: The system acquires real-time water level data of the lake to be measured, and outputs the water level change of the lake to be measured in combination with the lake change prediction model, and calculates the predicted water level of the lake to be measured. The calculated predicted water level of the lake to be measured is compared with the set warning water level. If the predicted water level is greater than or equal to the warning water level, an alarm message is output.

3. The method for predicting lake water level changes according to claim 2, characterized in that: The lake to be tested is located in a warm and humid region; the several hydrological stations are distributed in the upstream river that serves as the water source for the lake to be tested, and are used to collect water level information of the upstream river.

4. A lake water level change prediction system utilizing the lake water level change prediction method according to any one of claims 1 to 3, characterized in that: The system includes: The upstream water level information acquisition module is used to determine several hydrological stations distributed in the upstream basin of the lake based on the geographical location of the lake to be measured, and to acquire their geographical location information and historical water level data. The lake water level change prediction model generation module is used to obtain historical water level data of the lake to be measured, and to establish a lake water level change prediction model based on the historical water level data and geographical location information of the various hydrological stations and the historical water level data of the lake to be measured. The lake water level change prediction module is used to acquire real-time water level data from the aforementioned hydrological stations and input them into the lake water level change prediction model. The lake change prediction model outputs the water level change of the lake to be measured.

5. An electronic device, comprising: At least one processor, at least one memory, a communication interface, and a bus; The processor, memory, and communication interface communicate with each other through the bus. The memory stores program instructions that can be executed by the processor, characterized in that the processor calls the program instructions to implement the lake water level change prediction method as described in any one of claims 1 to 3.

6. A computer-readable storage medium storing computer instructions that cause a computer to implement the steps of the lake water level change prediction method as described in any one of claims 1 to 3.

Images