River channel water regimen forecasting method and system based on digital twinning

Abstract

The invention relates to the technical field of water regimen forecasting, in particular to a river channel water regimen forecasting method and system based on digital twinning. The method comprises the following steps: arranging sensor nodes along a river channel and carrying out real-time monitoring on the river channel environment water regimen along the river channel to obtain real-time data of the water level along the river channel, real-time data of the flow along the river channel and real-time data of the weather along the river channel; performing digital twinborn construction and risk estimation division along the riverway to generate a riverway water regimen flood risk estimation period and a riverway water regimen drought risk estimation period; the method comprises the following steps: performing flood risk forecast processing in a river water regimen flood risk estimation period to execute corresponding river water regimen flood risk management decision-making work; and performing drought risk forecast processing in the river channel water regimen drought risk estimation time period to execute corresponding river channel water regimen drought risk management decision-making work. According to the invention, efficient and accurate water regimen prediction and decision support can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of water regime forecasting, and particularly to a river water regime forecasting method and system based on digital twin. Background Art

[0002] Digital twin realizes dynamic monitoring, prediction and optimization of physical entities by mapping entities or systems in the physical world to virtual models in real time, combining real-time data, simulation and artificial intelligence algorithms. Systems based on digital twin can simulate and predict the behavior of complex systems, especially in the fields of hydrological environment, meteorological monitoring, etc., showing great potential. In addition, in the field of river water regime forecasting, digital twin technology can obtain multi-source data (such as precipitation, flow velocity, water level, soil humidity, etc.) in the river and its basin in real time, and combine with an efficient simulation model to construct a virtual twin of the river hydrological system in real time, accurately reflecting the actual situation of the river basin. In addition, the digital twin system can also use machine learning and big data analysis to update water regime data in real time, and adjust the water regime prediction model according to changing environmental conditions, improving the accuracy and timeliness of forecasting. However, existing forecasting methods mainly rely on single historical data or fixed models, and cannot reflect the changes of dynamic factors such as river hydrology, meteorology, and terrain in real time, making it difficult to cope with sudden and complex water regime changes, resulting in poor accuracy and timeliness of forecasting results. Summary of the Invention

[0003] Based on this, it is necessary for the present invention to provide a river water regime forecasting method and system based on digital twin to solve at least one of the above technical problems.

[0004] To achieve the above object, a river water regime forecasting method based on digital twin includes the following steps:

[0005] Step S1: By arranging sensor nodes along the river and based on the sensor nodes, real-time monitoring of the river environmental water regime along the river is carried out to obtain real-time water level data, real-time flow data and real-time meteorological data along the river, where the real-time meteorological data along the river includes rainfall, temperature and wind speed along the river; using the real-time water level data, real-time flow data and real-time meteorological data along the river to construct a digital twin of the river along the river to generate a digital twin model of the river environmental water regime along the river;

[0006] Step S2: Based on the rainfall along the river, risk estimation and division are carried out on the corresponding river water regime time periods in the digital twin model of the river environmental water regime along the river to generate a river water regime flood risk estimation time period and a river water regime drought risk estimation time period;

[0007] Step S3: Obtain the corresponding water levels, flows, and wind speeds along the river channel during the flood risk estimation period of the river channel water regime, and perform flood risk forecasting processing on the corresponding digital twin model of the environmental water regime along the river channel based on the water levels, flows, and wind speeds along the river channel to generate flood risk forecasting results for the water regime along the river channel, so as to execute the corresponding river channel water regime flood risk management decision-making work;

[0008] Step S4: Obtain the corresponding water levels, flows, and temperatures along the river channel during the drought risk estimation period of the river channel water regime, and perform drought risk forecasting processing on the corresponding digital twin model of the environmental water regime along the river channel based on the water levels, flows, and temperatures along the river channel to generate drought risk forecasting results for the water regime along the river channel, so as to execute the corresponding river channel water regime drought risk management decision-making work.

[0009] Furthermore, Step S4 includes the following steps:

[0010] Step S41: Obtain the water levels, flows, and temperatures along the river channel corresponding to the digital twin model of the environmental water regime along the river channel during the drought risk period during the drought risk estimation period of the river channel water regime;

[0011] Step S42: Conduct a time-series fluctuation cross and lag assessment analysis on the water levels and flows along the river channel during the drought risk period to obtain the time-series fluctuation cross interaction and time-series fluctuation lag effect between the water levels and flows along the river channel;

[0012] Step S43: Conduct a time-series fluctuation synchronization analysis on the water levels and flows along the river channel during the drought risk period based on the time-series fluctuation cross interaction and time-series fluctuation lag effect between the water levels and flows along the river channel to generate a corresponding hydrological fluctuation response field along the river channel during the drought risk period;

[0013] Step S44: Conduct a hydrological evaporation rate assessment analysis on the corresponding hydrological fluctuation response field along the river channel during the drought risk period based on the temperature along the river channel to obtain the influence correlation relationship between the hydrological fluctuations along the river channel and the water surface evaporation rate of the river channel;

[0014] Step S45: Perform drought risk forecasting processing on the corresponding digital twin model of the environmental water regime along the river channel based on the influence correlation relationship between the hydrological fluctuations along the river channel and the water surface evaporation rate of the river channel to generate drought risk forecasting results for the water regime along the river channel, so as to execute the corresponding river channel water regime drought risk management decision-making work.

[0015] Furthermore, the present invention also provides a river water regime forecasting system based on digital twin for implementing the river water regime forecasting method based on digital twin as described above. The river water regime forecasting system based on digital twin includes:

[0016] A river water regime digital twin modeling module for deploying sensor nodes along the river course and performing real-time monitoring of the river environmental water regime along the river course based on the sensor nodes to obtain real-time water level data, real-time flow data, and real-time meteorological data along the river course. The real-time meteorological data along the river course includes rainfall, temperature, and wind speed along the river course; using the real-time water level data, real-time flow data, and real-time meteorological data along the river course to construct a digital twin of the river course to generate a digital twin model of the river environmental water regime along the river course;

[0017] A river water regime risk estimation time period division module for performing risk estimation and division of the corresponding river water regime time periods in the digital twin model of the river environmental water regime along the river course based on the rainfall along the river course to generate a river water regime flood risk estimation time period and a river water regime drought risk estimation time period;

[0018] A river water regime flood risk forecasting module for obtaining the corresponding water level, flow, and wind speed along the river course during the river water regime flood risk estimation time period and performing flood risk forecasting processing on the corresponding digital twin model of the river environmental water regime along the river course based on the water level, flow, and wind speed along the river course, thereby generating a river water regime flood risk forecasting result to implement the corresponding river water regime flood risk management decision-making work;

[0019] A river water regime drought risk forecasting module for obtaining the corresponding water level, flow, and temperature along the river course during the river water regime drought risk estimation time period and performing drought risk forecasting processing on the corresponding digital twin model of the river environmental water regime along the river course based on the water level, flow, and temperature along the river course, thereby generating a river water regime drought risk forecasting result to implement the corresponding river water regime drought risk management decision-making work.

[0020] Advantages of the present invention:

[0021] 1. The river water regime forecasting method based on digital twin proposed by the present invention, compared with the prior art, the beneficial effects of the present application are as follows: By deploying sensor nodes along the river, key environmental data of the river can be collected in real time. As the forefront of data collection, the sensor nodes can comprehensively monitor important information such as water level, flow rate, and meteorology along the river, thus providing an accurate data basis for subsequent water regime analysis and decision support. Through real-time monitoring of the river environmental water regime along the river based on sensor nodes, the water level sensor can not only automatically collect water level data, but also upload and process data with the cloud platform through the Internet of Things, and can timely identify the change trend of the water level. Through real-time monitoring of the flow rate data by the flow rate sensor, relevant departments can be helped to timely discover abnormal flow rate fluctuations and issue corresponding emergency warnings. Additionally, through real-time monitoring of the meteorology along the river by the meteorological monitoring sensor, important meteorological data including rainfall, temperature, and wind speed can be obtained in real time, so as to be able to reflect the changes of dynamic factors such as river hydrology, meteorology, and terrain in real time. At the same time, by uploading the real-time water level data, real-time flow rate data, and real-time meteorological data along the river to the cloud platform, and using the real-time water level data, real-time flow rate data, and real-time meteorological data along the river to construct a digital twin of the river along the line, a digital twin model of the river can be constructed using these data. The digital twin technology replicates the physical and environmental state of the river to the digital platform in a virtualized manner, enabling managers to monitor and simulate various changes in the river in real time. The digital twin model can be used to simulate the changes in river water level and flow rate during floods, predict the pressure changes of reservoirs or dams, and improve the accuracy of emergency response, thus being able to effectively respond to sudden and complex water regime changes. Secondly, by conducting risk assessment and division of the corresponding river water regime time periods in the digital twin model of the river environmental water regime along the river based on the rainfall along the river, the corresponding water regime risk time periods can be effectively identified and estimated. This process enables water regime monitoring to no longer stay merely at general water level and flow rate observations, but instead turn to spatio-temporal division based on actual risks. By segmenting the river water regime fluctuations according to flood and drought risks, real-time risk assessments can be provided for various extreme weather events, further optimizing water resources management and disaster prevention and mitigation work. This not only provides a refined decision-making basis for the prevention of subsequent floods and drought disasters, but also provides more comprehensive and in-depth data support for subsequent management decisions, thereby improving the accuracy and timeliness of the forecasting results.Then, the river water regime data during the flood risk period is obtained through the digital twin model, which can provide important parameters such as real-time and accurate water levels, flow rates, and wind speeds. These data provide the basis for subsequent analysis. Based on the water levels, flow rates, and wind speeds along the river channel, flood risk forecasting is carried out on the corresponding digital twin model of the environmental water regime along the river channel to generate the final water regime flood risk forecasting results. By comprehensively considering multiple factors such as water levels, flow rates, and wind speeds, and through the impact analysis of the dynamic response correlation field and microscopic change factors, a more accurate flood risk prediction can be generated. This process is not only data processing but also an in-depth integration and systematic modeling of various hydro-meteorological factors, thus forming a flood risk forecast with high predictability. The forecast results will directly affect the decision-making work of river water regime flood risk management, helping relevant departments make scientific decisions before floods occur, such as strengthening flood protection facilities, dredging river channels, and promptly deploying emergency measures such as evacuating the masses, so as to minimize the losses and impacts caused by floods. Finally, by using digital twin technology, the hydro-environment along the river channel can be accurately simulated and predicted, especially during the drought risk period, dynamically reflecting the changing trends of river water levels, flow rates, and temperatures, providing solid basic data for subsequent drought risk assessment. In addition, based on the water levels, flow rates, and temperatures along the river channel, drought risk forecasting is carried out on the corresponding digital twin model of the environmental water regime along the river channel, enabling more accurate drought risk forecasting. Drought risk forecasting is a key link in water resources management. It can predict in advance the time, scope, and intensity of droughts, providing early warning signals for the scheduling and management of water resources. Based on such forecast results, water resources management departments can promptly take countermeasures, such as adjusting reservoir operation, increasing water source allocation, and taking water-saving measures, and can also support a wider decision-making process, such as the planning of water resources protection areas, ecological restoration plans, and long-term development strategies for water resources use, thus realizing sustainable water resources management.

[0022] 2. The river water regime forecasting system based on digital twin proposed by the present invention is generally composed of a digital twin modeling module for river water regime, a module for dividing the river water regime risk estimation period, a river water regime flood risk forecasting module, and a river water regime drought risk forecasting module, and can implement any of the river water regime forecasting methods based on digital twin described in the present invention. It is used to realize the river water regime forecasting method based on digital twin through the operation between computer programs running on each module. The internal structure of the system cooperates with each other, which can greatly reduce repetitive work and manpower input, and can quickly and effectively provide a more accurate and efficient river water regime forecasting process based on digital twin, thus simplifying the operation process of the river water regime forecasting system based on digital twin. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Other features, objects, and advantages of the present invention will become more apparent from the following detailed description of non-limiting embodiments read in conjunction with the accompanying drawings:

[0024] Figure 1 It is a schematic diagram of the step flow of the river water regime forecasting method based on digital twin of the present invention;

[0025] Figure 2 For Figure 1 It is a detailed step flow schematic diagram of step S1 in Specific Embodiments

[0026] The technical method of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0027] To achieve the above object, please refer to Figures 1 to 2 , the present invention provides a river water regime forecasting method based on digital twin. In the embodiments of the present invention, please refer to Figure 1 As shown, it is a schematic diagram of the step flow of the river water regime forecasting method based on digital twin of the present invention. In this example, the river water regime forecasting method based on digital twin includes the following steps:

[0028] Step S1: By deploying sensor nodes along the river course and based on the sensor nodes, real-time monitoring of the river environment water regime along the river course is carried out to obtain real-time water level data, real-time flow data, and real-time meteorological data along the river course. The real-time meteorological data along the river course includes rainfall, temperature, and wind speed along the river course; the real-time water level data, real-time flow data, and real-time meteorological data along the river course are used to construct a digital twin of the river course environment to generate a digital twin model of the river course environment water regime;

[0029] In the embodiments of the present invention, by deploying sensor nodes along the river course, it is necessary to first conduct a geographical location survey along the river course to determine the deployment positions of each sensor node. The water level sensor should be set in the representative waters along the river course to ensure that it can reflect the changes in the river water level in real time. The flow sensor should be installed in an area with relatively stable water flow to accurately monitor the flow rate. The meteorological monitoring sensors should cover the entire river course area and be distributed under different geographical heights and climatic conditions. The sensor nodes are connected to the surrounding environment through wireless communication protocols (such as LoRaWAN, NB-IoT, etc.) to ensure that they can receive and send monitoring data to the central processing unit, and by implementing the connection between the Internet of Things technology and the cloud platform. First, the sensor nodes need to be configured with hardware modules with Internet of Things communication capabilities, such as wireless communication modules like Wi-Fi, LoRa, NB-IoT, etc. These modules wirelessly send the water level, flow rate, and meteorological data collected in real time to the cloud data platform. Also, by using the water level data of the river course collected by the water level sensors in the Internet of Things network, it can be uploaded to the cloud in real time, and the platform can display the changes in the river water level in real time, thereby obtaining the real-time water level data of the river course along the line. By using the flow sensors to conduct real-time monitoring of the water flow rate of the corresponding river course along the line, these sensors can measure the speed and flow rate of the water flow using the electromagnetic principle or the ultrasonic principle. By monitoring the changes in the water flow speed and the cross-sectional area of the water body, accurate flow rate data can be calculated, thereby obtaining the real-time flow rate data of the river course along the line. At the same time, by using the meteorological monitoring sensors to conduct real-time monitoring of the environmental meteorology along the river course, the meteorological monitoring sensors should adopt a variety of meteorological parameter detection modules, which are respectively used to monitor data such as rainfall, temperature, humidity, and wind speed. The meteorological sensor nodes are usually configured with high-precision rain gauges, temperature and humidity sensors, anemometers and other devices. These sensors collect meteorological data at regular intervals and send the data to the cloud platform through wireless communication, thereby obtaining the real-time meteorological data of the river course along the line, including the rainfall along the river course, the temperature along the river course, and the wind speed along the river course. Then, after uploading the real-time water level, flow rate, and meteorological real-time data of the river course along the line obtained from the previous real-time monitoring to the cloud platform, the platform will generate a digital twin model of the water situation of the river course along the line through digital twin technology. Digital twin technology first needs to construct a physical model based on the data collected by the sensors and add real-time data sources to the model to form a closed loop between each node and the data. The cloud platform will conduct multi-dimensional data analysis on the water situation of the river course along the line through machine learning and data modeling technologies based on the real-time water level, flow rate, meteorological data, and historical data, and conduct real-time digital twin display of the water situation of the river course along the line. The platform uses these data to simulate the changes in the water flow in the river course through algorithms, and reflects the rise and fall of the water level and the fluctuations in the flow rate in real time. It will also generate visual reports, graphs, and prediction results based on the output of the model, and finally generate a digital twin model of the environmental water situation of the river course along the line.

[0030] Step S2: Based on the rainfall along the river course, conduct risk assessment and division for the corresponding river water regime time periods in the digital twin model of the river water environment along the river course, so as to generate the flood risk prediction time periods and drought risk prediction time periods of the river water regime.

[0031] In the embodiment of the present invention, by collecting the rainfall data along the river course, these data are usually obtained by meteorological stations or remote sensing technologies and need to cover a certain time range, usually monthly or annual data. Next, based on the river water regime data in the digital twin model, especially the hydrological data such as water level, flow rate, and water storage synchronized with the rainfall, conduct spatio-temporal analysis to ensure the temporal consistency between the rainfall and the water regime data. Adopt correlation analysis methods (such as Pearson correlation coefficient, Spearman rank correlation, etc.) to calculate the correlation between the rainfall and the water regime fluctuations (flow rate, water storage, etc.), and then reveal the spatio-temporal variation laws of the rainfall and the water regime fluctuations. And through the spatio-temporal correlation relationship between the previously obtained rainfall and the water regime fluctuations, conduct further analysis on the time series characteristics of the water regime fluctuations. First, conduct time series decomposition on the rainfall and water regime fluctuation data in different water regime time periods (such as dry periods, rainy seasons, etc.) along the river course, and adopt methods such as wavelet analysis and Fourier transform to extract periodic and aperiodic fluctuation characteristics. The periodic fluctuation characteristics can be extracted through periodogram analysis or fluctuation amplitude frequency characteristics, while the aperiodic fluctuation characteristics can be obtained through methods such as detrending or differencing. Next, integrate these time series characteristic data into a characteristic data set of rainfall, flow rate fluctuations, and water storage changes. At the same time, by combining rainfall, rainfall change rate, river flow rate, maximum threshold of river flow rate, change amount of river water storage, maximum threshold of river water storage change, and related parameters, a suitable risk determination calculation formula for water regime fluctuations is formed to conduct risk determination and assessment calculation for the corresponding river water regime time periods in the digital twin model of the river water environment along the river course, so as to judge whether the time period enters the flood risk stage or the drought risk stage, thereby obtaining the flood and drought fluctuation risk determination parameters. Then, through extreme risk segmentation for each time period according to the aforementioned flood and drought fluctuation risk determination parameters. In this process, first compare the river water regime fluctuations corresponding to the river water regime time periods in the river water regime time periods with the flood risk and drought risk determination parameters according to the water regime fluctuation data. If the water regime fluctuations (such as flow rate fluctuations, water storage changes, etc.) in a certain time period exceed the predetermined flood risk determination range, then mark this time period as the flood risk prediction time period; on the contrary, if the water regime fluctuations are within the drought risk determination range, then this time period is determined as the drought risk prediction time period. In order to ensure the accuracy of the determination, a dynamic threshold judgment method can be adopted to adjust the threshold interval in real time according to the actual situation. This step can be implemented through conditional judgment logic in programming languages such as Python combined with the risk determination formula. The final output is a clear time period division, specifically identifying the risk prediction time periods of floods or droughts.

[0032] Step S3: Obtain the corresponding water levels, flows, and wind speeds along the river channel during the flood risk prediction period of the river channel water regime, and perform flood risk prediction processing on the digital twin model of the environmental water regime along the corresponding river channel based on the water levels, flows, and wind speeds along the river channel to generate the flood risk prediction results of the water regime along the river channel, so as to implement the corresponding flood risk management decision-making work for the river channel water regime;

[0033] In the embodiments of the present invention, during the flood risk prediction period, first, a digital twin model of the water regime along the river is obtained to ensure that the model has the function of reflecting the actual hydrological and hydraulic environment. In this model, data such as river water level, flow rate, and wind speed are used as key parameters. The real-time water level, flow rate, wind speed, etc. of the river are regularly obtained, and by obtaining historical river water level fluctuation data and climate patterns, they are used as the analysis basis. The evolution of the river water level is analyzed through historical observation data and climate simulation data. First, the river water level fluctuation data of the past several years are collected and analyzed. These data can be obtained from meteorological bureaus, hydrological departments, and local weather stations. Then, by using climate models to predict future climate change trends, especially factors such as changes in precipitation and temperature, combined with these historical data and climate patterns, a water level evolution analysis model is established to calculate the water level change trend during the flood risk period and generate a water level fluctuation field at this time. At the same time, by real-time monitoring the river flow rate during the flood risk period, flow rate data are obtained and the correlation between this flow rate and the upstream inflow, midstream precipitation, and downstream outflow is further analyzed. First, multiple flow monitoring points are set up, and devices such as current meters and flow meters are used to obtain the flow rate data of each part of the river in real time. Secondly, the data of remote sensing monitoring and hydrometeorological stations are used to estimate the upstream inflow and midstream precipitation, and the basin water balance equation in hydrology is used to input these data into the calculation model for coupling analysis between the flow rate and water level evolution. By establishing a response function between the flow rate change and the water level fluctuation, combined with the historical evolution trend of the water level, a dynamic response correlation field is generated. And through the impact factor evaluation analysis based on wind speed data, first, actual wind speed data are collected along the river by wind speed monitoring instruments. The wind speed sensors can be installed at different positions of the river, especially in areas vulnerable to wind speed changes. Combining with meteorological data, the microscopic impact of wind speed on the river water level and flow rate changes is evaluated. Through numerical simulation and fluid mechanics analysis, the impact degree of wind speed on the water surface and flow of the water body is determined. For example, wind speed will cause disturbances on the water surface, thus changing the distribution of the water flow and the water level change. Using a fluid dynamics model (such as a CFD model), the wind speed is added as an impact factor to the change models of the river water level and flow rate, so as to obtain the quantitative impact factor of wind speed on the water level and flow rate changes. Then, during the flood risk period, based on the microscopic change impact factors generated in the previous steps and using the digital twin model of the river water regime for flood risk forecasting. This process first combines the water level, flow rate, wind speed, etc. data obtained in the previous steps. By integrating all impact factors, a dynamic response model is established in the digital twin model of the water regime. This model can predict the changes in the water level and flow rate according to real-time monitoring data and historical trends, and make adjustments according to different flood scenarios. Specifically, input the real-time water level, flow rate, and wind speed data, and use numerical simulation methods for forecasting processing to output the forecasting results of the river water level and flow rate.Use the forecast results to judge the flood risk level, and accordingly provide decision-making support for the river management department, guide the water regime management and disaster prevention and mitigation work, and finally implement the corresponding river water regime flood risk management decision-making work.

[0034] Step S4: Obtain the corresponding water levels, flows, and temperatures along the river during the drought risk estimation period of the river water regime, and perform drought risk forecasting on the corresponding digital twin model of the river water environment based on the water levels, flows, and temperatures along the river to generate the drought risk forecast results of the river water regime, so as to implement the corresponding river water regime drought risk management decision-making work.

[0035] In the embodiments of the present invention, during the drought risk prediction period, water level, flow rate, and temperature data along the river channel within the corresponding drought risk period range are obtained by using a water regime model based on digital twin technology. First, a three-dimensional digital twin model of the river channel is constructed, including the geometric morphology of the river channel, historical hydrological data, and real-time sensor data. Combining the meteorological prediction model with real-time observation data, water level, flow rate, and temperature data of the river channel are collected in real time through remote sensing technology and Internet of Things sensors (such as water level sensors, flow meters, temperature sensors, etc.). After obtaining the water level and flow rate data along the river channel, an assessment and analysis of time series fluctuations and lag effects are carried out. The specific method is to use time series analysis technology to conduct a detailed analysis of the relationship between the water level and flow rate of the river channel. First, through statistical analysis methods, such as correlation analysis and cointegration analysis, the time series fluctuation cross-effect between the water level and flow rate is identified, and through the analysis of the cross-correlation function (CCF), the correlation between the water level and flow rate at different time points is calculated to find out their interaction relationship. Secondly, through the use of lag effect analysis, the impact delay time of water level changes on flow rate changes is evaluated, and the lag regression model or Granger causality test method is used to quantify the time lag effect of water level changes on flow rate. At the same time, after completing the analysis of time series fluctuations and lag effects of the water level and flow rate, based on these analysis results, a time series fluctuation synchronization analysis of the water level and flow rate is carried out. The synchronization analysis uses synchronization analysis techniques, such as waveform correlation and phase synchronization analysis, to quantify the synchronization and degree of synchronous changes of the water level and flow rate changes. On this basis, a hydrological fluctuation response field along the river channel is generated through a simulation model, and during the drought risk period, by evaluating the relationship between the temperature along the river channel and the hydrological fluctuation response field, further analysis of the hydrological evaporation rate is carried out. First, based on the temperature data along the river channel, combined with the hydrological fluctuation response field, an evaporation calculation model (such as the Penman-Monteith model or the Hargreaves model) is used to evaluate the evaporation rate under different temperature conditions. Through the association between environmental factors such as temperature, humidity, and wind speed and water level and flow rate fluctuations, the impact relationship between hydrological fluctuations and evaporation rate is quantified. For different river channel sections, according to the actually measured water surface temperature and environmental data, the corresponding evaporation rate is calculated, and through methods such as regression analysis and correlation analysis, the impact association relationship between the water surface evaporation rate and water level fluctuations is obtained.Then, based on the previously obtained influence correlation relationship between hydrological fluctuations and evaporation rate, combined with historical hydrological data and real-time monitoring data, drought risk forecasting of the water regime along the river channel is carried out. Through the digital twin model for water regime drought risk simulation, real-time analysis and prediction are carried out based on the obtained environmental data (such as water level, flow rate, temperature, etc.). The model is used for drought risk assessment. The model will forecast the future changes in the river channel water level and flow rate according to the hydrological fluctuation response field and the water surface evaporation rate, simulate the scope, intensity, and duration that the drought risk may affect, and output the risk forecast results. This result provides decision-making support for the water regime management of the river channel. Especially when the drought risk is relatively high, decision-makers can arrange water resource scheduling, drought mitigation measures, etc. according to this. According to the forecast results, relevant water regime management and emergency measures are taken to ensure the reasonable utilization and protection of the river channel water resources, and finally, the corresponding river channel water regime drought risk management decision-making work is carried out.

[0036] Further, as an embodiment of the present invention, refer to Figure 2 shown in Figure 1 the detailed step flow schematic diagram of step S1 in

[0037] Step S11: Sensor nodes are arranged along the river channel, and the sensor nodes include water level sensors, flow sensors, and meteorological monitoring sensors;

[0038] In the embodiment of the present invention, when arranging sensor nodes along the river channel, it is necessary to first conduct a geographical location survey along the river channel to determine the layout positions of each sensor node. The water level sensor should be set in the representative water areas along the river channel to ensure that it can reflect the river channel water level changes in real time. The flow sensor should be installed in the area where the water flow is relatively stable to accurately monitor the flow rate. The meteorological monitoring sensors should cover the entire river channel area and be distributed at different geographical heights and climate conditions. The sensor nodes are connected to the surrounding environment through wireless communication protocols (such as LoRaWAN, NB-IoT, etc.) to ensure that they can receive and send monitoring data to the central processing unit. The power supply system of each sensor node should have sufficient battery life. Especially for some sensor nodes in remote areas, solar energy or other environmental protection energy sources are usually used to ensure their long-term stable operation.

[0039] Step S12: Based on the sensor nodes, use the Internet of Things technology to connect to the cloud platform to generate an Internet of Things network for water regime monitoring along the river channel; use the water level sensors in the Internet of Things network for water regime monitoring along the river channel to obtain real-time river channel water level data;

[0040] In the embodiment of the present invention, by implementing the connection between the Internet of Things technology and the cloud platform, first, a hardware module with Internet of Things communication capabilities needs to be configured in the sensor node, such as wireless communication modules like Wi-Fi, LoRa, NB-IoT, etc. These modules send the water level, flow rate, and meteorological data collected in real time to the cloud data platform via wireless means. When implementing the Internet of Things network connection, the cloud platform needs to have high-performance data reception and processing capabilities, and be able to receive the data uploaded by each sensor node through various protocols (such as MQTT, HTTP, etc.). At the same time, corresponding access permissions and security verification mechanisms need to be set within the platform to ensure the security of data transmission, thereby connecting to generate a water regime monitoring Internet of Things network along the river course. By using the water level data of the river course collected by the water level sensors in the water regime monitoring Internet of Things network along the river course, it can be uploaded to the cloud in real time. The platform displays the changes in the river water level in real time, stores and analyzes the uploaded data, and finally obtains the real-time water level data of the river course along the line.

[0041] Step S13: Use the flow sensors in the water regime monitoring Internet of Things network along the river course to conduct real-time monitoring of the river flow rate along the river course to obtain real-time river flow rate data along the river course;

[0042] In the embodiment of the present invention, by using flow sensors to conduct real-time monitoring of the water flow rate of the corresponding river course along the line, the flow sensors should be deployed at appropriate river intersections or areas with relatively large and rapidly changing flow velocities. These sensors can measure the velocity and flow rate of the water flow using electromagnetic principles or ultrasonic principles. By monitoring the changes in the water flow velocity and the cross-sectional area of the water body, accurate flow rate data can be calculated. Under the Internet of Things network connection, the sensors upload the flow rate data to the cloud platform at regular intervals. The cloud platform automatically processes these data through algorithms, calculates the actual flow rate of the river at the current moment, and can conduct flow rate trend analysis based on historical data, and finally obtains the real-time river flow rate data along the river course.

[0043] Step S14: Use the meteorological monitoring sensors in the water regime monitoring Internet of Things network along the river course to conduct real-time monitoring of the river meteorology along the river course to obtain real-time river meteorological data along the river course, including the rainfall along the river course, the temperature along the river course, and the wind speed along the river course;

[0044] In the embodiments of the present invention, by using meteorological monitoring sensors to conduct real-time monitoring of the environmental meteorology along the river course, the meteorological monitoring sensors should adopt a variety of meteorological parameter detection modules, which are respectively used to monitor data such as rainfall, temperature, humidity, and wind speed. Meteorological sensor nodes are usually equipped with devices such as high-precision rain gauges, temperature and humidity sensors, and anemometers. These sensors collect meteorological data at regular intervals and send the data to the cloud platform through wireless communication. Rainfall data can be collected and uploaded in real time by the rain gauge to help monitor the precipitation in the river basin. Temperature and wind speed data are collected in real time by the integrated sensors. In the cloud platform, these meteorological data will be integrated and analyzed with the water level data and flow data to finally obtain the real-time meteorological data along the river course, including the rainfall along the river course, the temperature along the river course, and the wind speed along the river course.

[0045] Step S15: Upload the real-time water level data, real-time flow data, and real-time meteorological data along the river course to the cloud platform, and use the real-time water level data, real-time flow data, and real-time meteorological data along the river course to construct a digital twin of the river course to generate a digital twin model of the environmental water situation along the river course.

[0046] In the embodiments of the present invention, after uploading the real-time water level, flow, and meteorological data along the river course obtained from the previous real-time monitoring to the cloud platform, the platform will generate a digital twin model of the water situation along the river course through digital twin technology. Digital twin technology first needs to construct a physical model based on the data collected by the sensors and add real-time data sources to the model to form a closed loop between each node and the data. The cloud platform will conduct multi-dimensional data analysis on the water situation along the river course through machine learning and data modeling technologies based on the real-time water level, flow, meteorological data, and historical data, and conduct real-time digital twin display of the water situation along the river course. The platform uses these data to simulate the changes in the water flow in the river through algorithms, and reflects the rise and fall of the water level and the fluctuations in the flow in real time, thereby providing basic data support for future water situation prediction, flood warning, etc. It will also generate visual reports, graphs, and prediction results based on the output of the model, and finally generate a digital twin model of the environmental water situation along the river course.

[0047] Further, the construction of a digital twin of the river course by using the real-time water level data, real-time flow data, and real-time meteorological data along the river course in step S15 includes the following steps:

[0048] Conduct spatio-temporal correlation analysis on the real-time water level data and real-time flow data along the river course to obtain the spatio-temporal dynamic correlation relationship between the water level change and the flow fluctuation along the river course;

[0049] In the embodiments of the present invention, by deploying water level and flow monitoring devices along the river course, water level data and flow data are obtained in real time. These devices include buoys, water level sensors, flow velocity sensors, etc. The data is transmitted to the data center for processing through a sensor network. For the collected real-time water level and flow data, spatio-temporal data analysis methods, such as the dynamic time warping (DTW) algorithm and spatio-temporal correlation models, are used to reveal the correlation between the water level and the flow. The purpose of spatio-temporal correlation analysis is to identify the regularity of water level fluctuations and flow changes between different time and space points, and analyze their dynamic relationships at different time periods and geographical locations. For example, if the rise of the water level is highly correlated with the increase in the flow during a certain period of time, the corresponding spatio-temporal correlation pattern will be automatically captured and generated, reflecting the synchronous change trend of the two. Finally, the spatio-temporal dynamic correlation between the water level change and the flow fluctuation along the river course is obtained.

[0050] Preferably, the corresponding geographic information coordinate data along the river course is obtained, and based on the spatio-temporal dynamic correlation between the water level change and the flow fluctuation along the river course, spatio-temporal correlation mapping of the real-time water level data and the real-time flow data along the river course is performed in combination with the geographic information coordinate data to generate a spatio-temporal correlation feature model of the water regime along the river course;

[0051] In the embodiments of the present invention, the geographic coordinate data along the river course is obtained by using a geographic information system (GIS). These data are obtained through remote sensing images, topographic surveys, and existing geographic databases to ensure the accuracy of the coordinate data. Combining the spatio-temporal dynamic correlation between the water level and the flow along the river course, spatial analysis tools (such as spatial autocorrelation analysis and Kriging interpolation methods) are used to perform spatio-temporal mapping on the water level and flow data. Specifically, based on the above spatio-temporal correlation analysis results, spatial interpolation technology is used to combine the real-time water level and flow data with the geographic information coordinate data to achieve spatio-temporal correlation mapping of the water regime data. Through this process, the water level change and the flow fluctuation along the river course will be transformed into a spatio-temporal distribution map related to the geographic coordinates, forming a water regime data model with spatio-temporal dynamic characteristics. This model can accurately reflect the change rules of the water level and the flow at different geographical locations, and finally generate a spatio-temporal correlation feature model of the water regime along the river course.

[0052] Preferably, based on the real-time meteorological data along the river course, meteorological multi-source data fusion analysis is performed on the spatio-temporal correlation feature model of the water regime along the river course to generate a time series model of the environmental water regime along the river course;

[0053] In an embodiment of the present invention, by using meteorological data (such as precipitation, temperature, wind speed, humidity, etc.) to perform meteorological multi-source data fusion analysis on the spatio-temporal correlation feature model of the water regime along the river course, the meteorological data is obtained in real time through meteorological stations, satellite remote sensing, and meteorological prediction systems. When fusing these meteorological data with the water regime data along the river course, data fusion algorithms (such as Kalman filtering algorithm, multi-sensor fusion technology, etc.) are used to accurately pair the data from different sources. The fused data can eliminate the errors between different data sources and improve the accuracy of the prediction. In specific implementation, by using the correlation between meteorological factors and the changes in river water level and flow rate, a water regime time series model is constructed. By analyzing historical data, the time dependence of the water level and flow rate changes is identified, and the model is dynamically updated based on the real-time input of meteorological data. This model can ultimately reflect the change trend of the water regime along the river course in real time, further improving the accuracy and timeliness of the water regime prediction, and finally generating a time series model of the environmental water regime along the river course through fusion.

[0054] Preferably, the digital terrain data corresponding to the river course is obtained, including the riverbed slope and the shoreline contour, and the digital terrain data corresponding to the river course is subjected to terrain simulation analysis of the river basin to generate the terrain water flow simulation data of the river basin along the river course;

[0055] In an embodiment of the present invention, through digital terrain mapping of the river course, detailed terrain data including the riverbed slope, shoreline contour, basin range, ground elevation, etc. is obtained. These data are usually obtained through remote sensing technology, lidar (LiDAR) scanning, and terrain measurement equipment (such as total stations, differential GPS, etc.). After obtaining the digital terrain data, a basin hydrological model (such as SWAT model, HEC-RAS model, etc.) is used for terrain simulation analysis to simulate the water flow situation in the river basin. In specific implementation, first, a digital terrain model is established based on the terrain data, and then information such as the movement law, flow velocity, and flow rate of the river water is introduced into the basin water flow simulation system to simulate the distribution and flow of water under different slope and terrain conditions. Through this simulation analysis, the water flow simulation data of the river basin is generated, revealing the water flow change law at different positions in the basin. These simulation data will provide the necessary spatial basis for the construction of the environmental water regime digital twin model in the subsequent steps, and finally generate the terrain water flow simulation data of the river basin along the river course.

[0056] Preferably, based on the terrain water flow simulation data of the river basin along the river course, a digital twin fusion construction is performed on the time series model of the environmental water regime along the river course to generate a digital twin model of the environmental water regime along the river course.

[0057] In an embodiment of the present invention, based on the terrain water flow simulation data of the river basin, digital twin fusion is carried out with the previously generated environmental water regime time series model. Specifically, when implementing, digital twin technology is used to connect the hydrological data (such as water level, flow rate, meteorological data, etc.) in the real world with the water flow simulation data in the virtual world, and dynamic update is carried out through a two-way feedback mechanism. In this process, first, the terrain simulation data is mapped to various hydrological parameters in the time series model to ensure that the virtual model can accurately reflect the water regime dynamics of the real river channel. Secondly, big data analysis and machine learning algorithms (such as deep learning models, neural networks, etc.) are used to train and optimize the water regime data in the time series model to improve the prediction ability of the model, and a complete digital twin model of the environmental water regime along the river channel is constructed. This model can reflect the changes in hydrological parameters such as river water level and flow rate in real time, and at the same time consider environmental factors such as meteorology and terrain to achieve accurate water regime forecasting and dynamic monitoring, and finally generate a digital twin model of the environmental water regime along the river channel.

[0058] Further, step S2 includes the following steps:

[0059] Step S21: Based on the rainfall along the river channel, perform spatio-temporal fluctuation correlation analysis on the corresponding river water regime time period in the digital twin model of the environmental water regime along the river channel to obtain the spatio-temporal fluctuation correlation relationship between the rainfall along the river channel and the water regime fluctuation.

[0060] In an embodiment of the present invention, by collecting the rainfall data along the river channel, these data are usually obtained by meteorological stations or remote sensing technology and need to cover a certain time range, usually monthly or annual data. Next, based on the river water regime data in the digital twin model, especially the hydrological data such as water level, flow rate, and water storage synchronized with the rainfall, spatio-temporal analysis is carried out. First, through data cleaning, outliers and missing data are removed to ensure the consistency of rainfall and water regime data in time. Then, correlation analysis methods (such as Pearson correlation coefficient, Spearman rank correlation, etc.) are used to calculate the correlation between rainfall and water regime fluctuations (flow rate, water storage, etc.), and further reveal the spatio-temporal variation laws of rainfall and water regime fluctuations. This analysis can be implemented through statistical functions in data analysis tools such as MATLAB or Python or a dedicated hydrological analysis toolbox to obtain the spatio-temporal fluctuation correlation relationship between rainfall and water regime fluctuations, and finally obtain the spatio-temporal fluctuation correlation relationship between the rainfall along the river channel and the water regime fluctuation.

[0061] Step S22: Analyze the time-series characteristics of water level fluctuations for the rainfall along the river course and the corresponding river water level time periods in the digital twin model of the environmental water level along the river course based on the spatio-temporal fluctuation correlation relationship between the rainfall along the river course and the water level fluctuations, to obtain a rainfall-water level fluctuation time-series characteristic dataset along the river course, which includes the periodic and aperiodic fluctuation characteristics corresponding to rainfall, flow fluctuations, and storage changes;

[0062] In the embodiment of the present invention, through further analyzing the time-series characteristics of water level fluctuations according to the previously obtained spatio-temporal correlation relationship between rainfall and water level fluctuations, first, the time series of rainfall and water level fluctuation data for different water level time periods (such as dry periods, rainy seasons, etc.) along the river course are decomposed. Methods such as wavelet analysis and Fourier transform are used to extract periodic and aperiodic fluctuation characteristics. The periodic fluctuation characteristics can be extracted through periodogram analysis or fluctuation amplitude frequency characteristics, while the aperiodic fluctuation characteristics can be obtained through methods such as detrending or differencing. Next, these time-series characteristic data are integrated into a characteristic dataset of rainfall, flow fluctuations, and storage changes, forming a comprehensive time-series characteristic dataset, including information such as the frequency, amplitude, duration, and trend of the fluctuations. These time-series characteristic data can be operated and sorted using the pandas library in Python, and the mathematical models can be calculated through the NumPy library, thereby forming a time-series characteristic dataset that can be used for further analysis. Finally, a rainfall-water level fluctuation time-series characteristic dataset along the river course is obtained, which includes the periodic and aperiodic fluctuation characteristics corresponding to rainfall, flow fluctuations, and storage changes.

[0063] Step S23: Based on the rainfall-water level fluctuation time-series characteristic dataset along the river course, use the water level fluctuation risk determination calculation formula to perform risk determination and assessment calculations on the corresponding river water level time periods in the digital twin model of the environmental water level along the river course, to obtain the water level fluctuation risk determination parameters along the river course, including the flood fluctuation risk determination parameters and the drought fluctuation risk determination parameters along the river course;

[0064] In an embodiment of the present invention, by combining the initial time point, end time point, time variable parameter, rainfall, rainfall change rate, rainfall water regime fluctuation risk weight coefficient, river channel flow, maximum threshold of river channel flow, change in river channel water storage, maximum threshold of change in river channel water storage, risk weight coefficient of water storage change water regime fluctuation, risk weight coefficient of river channel flow water regime fluctuation, total number of flood tide events, average river channel flow of flood tide events, total number of drought events, standardized drought evaporation index, average evaporation index of drought events, and related parameters, a suitable calculation formula for determining the water regime fluctuation risk is constructed to perform risk determination and assessment calculation on the corresponding river channel water regime period in the digital twin model of the environmental water regime along the river channel, so as to determine whether the period enters the flood risk stage or the drought risk stage, and finally obtain the water regime fluctuation risk determination parameters along the river channel, including the flood fluctuation risk determination parameter and the drought fluctuation risk determination parameter along the river channel.

[0065] Step S24: Based on the water regime fluctuation risk determination parameters along the river channel, perform flood and drought extreme risk segmentation on the corresponding river channel water regime period in the digital twin model of the environmental water regime along the river channel. If the water regime fluctuation within the corresponding river channel water regime period is within the range corresponding to the flood fluctuation risk determination parameter along the river channel, then determine its river channel water regime period as the flood risk prediction period of the river channel water regime; if the water regime fluctuation within the corresponding river channel water regime period is within the range corresponding to the drought fluctuation risk determination parameter along the river channel, then determine its river channel water regime period as the drought risk prediction period of the river channel water regime.

[0066] In an embodiment of the present invention, by performing extreme risk segmentation on each period according to the aforementioned flood and drought fluctuation risk determination parameters, in this process, first compare the corresponding water regime fluctuation in the river channel water regime period with the flood risk and drought risk determination parameters according to the water regime fluctuation data. If the water regime fluctuation (such as flow fluctuation, water storage change, etc.) in a certain period exceeds the predetermined flood risk determination range, then mark this period as the flood risk prediction period; conversely, if the water regime fluctuation is within the drought risk determination range, then this period is determined as the drought risk prediction period. To ensure the accuracy of the determination, a dynamic threshold judgment method can be used to adjust the threshold interval in real time according to the actual situation. This step can be implemented through conditional judgment logic in programming languages such as Python combined with the risk determination formula. The final output is a clear time period division, specifically identifying the risk prediction periods of flood or drought occurrence.

[0067] Further, the specific calculation formula for determining the water regime fluctuation risk in step S23 is:

[0068]

[0069] Wherein, RH is a parameter for determining the flood fluctuation risk along the river course, R G is a parameter for determining the drought fluctuation risk along the river course, t0 is the initial time point corresponding to the river water regime period, t1 is the end time point corresponding to the river water regime period, t is a time variable parameter, P(t) is the rainfall at time t, is the rate of change of rainfall, α1 is the risk weight coefficient of rainfall-water regime fluctuation, Q(t) is the river flow at time t, Q max is the maximum threshold of river flow, H(t) is the change in river water storage at time t, H max is the maximum threshold of the change in river water storage, α2 is the risk weight coefficient of water storage change-water regime fluctuation, exp is the exponential function, β is the risk weight coefficient of river flow-water regime fluctuation, n is the total number of flood tide events, i is the item index of flood tide events, Q i is the river flow of the i-th flood tide event, Q avg is the average value of river flow of flood tide events, m is the total number of drought events, j is the item index of drought events, S j is the standardized drought evaporation index of the j-th drought event, S avg is the average value of evaporation indices of drought events, η1 is the correction coefficient of the parameter for determining the flood fluctuation risk along the river course, η2 is the correction coefficient of the parameter for determining the drought fluctuation risk along the river course.

[0070] The present invention obtains a calculation formula for determining the water regime fluctuation risk through the use of a specific mathematical model and verification, which is used to perform risk determination and evaluation calculations on the corresponding river water regime period in the digital twin model of the river water regime environment along the river course. This calculation formula for determining the water regime fluctuation risk takes into account the influence of rainfall changes The change in rainfall has a direct impact on the fluctuation of the river water regime, especially the change in rainfall in a short period of time (i.e., ) can reflect the rainfall intensity and change trend. By introducing the rate of change of rainfall as a factor affecting water regime fluctuation, the risk of heavy rain or sudden rainfall events can be captured in a timely manner, especially playing a key role in flood prediction. Before the occurrence of flood or drought events, a sharp increase in rainfall is an important warning signal. Quickly identifying the degree of rainfall change helps to predict the possibility of flood or drought occurrence earlier. The flow (Q(t)) is an important indicator of river water regime fluctuation. Especially in flood or drought early warning, an increase in river flow usually means an increase in water flow pressure, triggering floods; while a decrease or approaching zero of the river flow triggers corresponding drought events. By comparing the flow with the maximum flow threshold, it can be determined whether the current flow level is in the dangerous range. In the formula This item can quantify the gap between the current flow and the maximum flow and conduct a weighted assessment of the corresponding flood or drought risks. A larger flow gap means a higher risk. The water storage situation of the river channel is reflected by the change in water storage volume. Excessive water storage volume will lead to the risk of dam break or flood overflow, while too little water storage volume will trigger drought. The change in water storage volume relative to the maximum water storage volume threshold provides a standard for measuring the water reserve status of the reservoir or river channel. By monitoring the change in water storage volume, it is possible to identify which periods have a flood risk due to excessive water storage volume or which periods have a drought risk due to insufficient water storage volume. It also introduces the statistical characteristics of flow fluctuations This item's formula takes into account the total number of flood tide events and their fluctuation characteristics. By calculating the volatility of the flow, it can determine whether the water regime fluctuation of the river channel is abnormal. The degree of flow fluctuation directly affects the prediction accuracy of the water regime. Excessive fluctuation usually means an increase in risk. By statistically analyzing the flow of past flood tide events, it is possible to evaluate whether abnormal fluctuations may occur in the future water regime. Irregular fluctuations in flow are usually related to sudden flood events. Therefore, this item helps to detect and prevent flood risks in advance. Additionally, it also conducts a standardized analysis of drought events The standardized drought evaporation index helps to quantify the severity of drought. Through the standardized analysis of historical drought events, it is possible to identify whether the current water regime is in a stage with a relatively high drought risk, especially in cases of low flow and scarce precipitation. The standardized drought index helps to unify the drought assessment criteria in different regions and periods, enabling the comparison of drought fluctuation risks across different time periods and regions and providing support for the accurate prediction of drought. The introduction of risk correction coefficients is used to further adjust the risks in the formula. These coefficients consider the influence of other environmental factors or special conditions on the water regime fluctuation. The introduction of these correction coefficients makes the calculation formula more flexible, capable of adapting to different regions and environmental changes, and enhancing the accuracy and adaptability of risk assessment. This formula can comprehensively and systematically consider the spatio-temporal changes of the water regime fluctuation through the integral analysis of the water regime fluctuation at each time point, thereby obtaining a risk assessment for a continuous time period. The integration of time can avoid the impact of sudden fluctuations at a single time point on the risk assessment and improve the prediction accuracy. In summary, this formula fully considers the flood fluctuation risk determination parameter R H along the river channel, the drought fluctuation risk determination parameter R G along the river channel, the initial time point t0 corresponding to the water regime period of the river channel, the end time point t1 corresponding to the water regime period of the river channel, the time variable parameter t, the rainfall P(t) at time t, the rainfall change rate the rainfall water regime fluctuation risk weight coefficient α1, the river channel flow Q(t) at time t, the maximum threshold Q of the river channel flow max the change in river channel water storage H(t) at time t, the maximum threshold H of the change in river channel water storage max, the risk weight coefficient α2 of the water level fluctuation due to water storage change, the exponential function exp, the risk weight coefficient β of the water level fluctuation of the river channel flow, the total number n of flood tide events, the item index i of the flood tide event, the river channel flow Q of the i-th flood tide event i , the average value Q of the river channel flow of the flood tide event avg , the total number m of drought events, the item index j of the drought event, the standardized drought evaporation index S of the j-th drought event j , the average value S of the evaporation index of the drought event avg , the correction coefficient η1 of the risk determination parameter for flood fluctuations along the river channel, the correction coefficient η2 of the risk determination parameter for drought fluctuations along the river channel. Among them, by combining the initial time point t0 corresponding to the river channel water level period, the end time point t1 corresponding to the river channel water level period, the time variable parameter t, the rainfall P(t) at time t, and the rainfall change rate the risk weight coefficient α1 of the water level fluctuation due to rainfall, the river channel flow Q(t) at time t, and the maximum threshold Q of the river channel flow max , the change in river channel water storage H(t) at time t, and the maximum threshold H of the change in river channel water storage max , the risk weight coefficient α2 of the water level fluctuation due to water storage change, the exponential function exp, the risk weight coefficient β of the water level fluctuation of the river channel flow, the total number n of flood tide events, the item index i of the flood tide event, the river channel flow Q of the i-th flood tide event i and the average value Q of the river channel flow of the flood tide event avg constitute a functional relationship of a risk determination parameter R for flood fluctuations along the river channel H :

[0071]

[0072] Also, by combining the initial time point t0 corresponding to the river channel water level period, the end time point t1 corresponding to the river channel water level period, the time variable parameter t, the rainfall P(t) at time t, and the rainfall change rate the risk weight coefficient α1 of the water level fluctuation due to rainfall, the river channel flow Q(t) at time t, and the maximum threshold Q of the river channel flow max , the change in river channel water storage H(t) at time t, and the maximum threshold H of the change in river channel water storage max , the risk weight coefficient α2 of the water level fluctuation due to water storage change, the exponential function exp, the risk weight coefficient β of the water level fluctuation of the river channel flow, the total number m of drought events, the item index j of the drought event, the standardized drought evaporation index S of the j-th drought event i and the average value S of the evaporation index of the drought event avg constitute a functional relationship of a risk determination parameter R for drought fluctuations along the river channel G : This formula can implement the risk determination and assessment calculation process for the corresponding river water regime time period in the digital twin model of the environmental water regime along the river course. At the same time, by introducing the correction coefficient η1 of the flood fluctuation risk determination parameter along the river course and the correction coefficient η2 of the drought fluctuation risk determination parameter along the river course, it can be adjusted according to the error situation during the calculation process, thereby improving the accuracy and applicability of the water regime fluctuation risk determination calculation formula.

[0073] Further, step S3 includes the following steps:

[0074] Step S31: Obtain the water level along the river course, the flow rate along the river course, and the wind speed along the river course corresponding to the digital twin model of the environmental water regime along the river course during the flood risk period under the flood risk prediction period of the river water regime.

[0075] In the embodiment of the present invention, under the flood risk prediction period, first obtain the digital twin model of the water regime along the river course to ensure that the model has the function of reflecting the actual hydrological and hydraulic environment. In this model, data such as river water level, flow rate, and wind speed are used as key parameters. In actual operation, use remote sensing technology and the data acquisition system of hydrological monitoring stations to regularly obtain real-time data such as river water level, flow rate, and wind speed, and combine them with environmental parameters (such as precipitation, soil moisture, etc.) to construct a high-precision digital twin model of the water regime. The model integrates these data to simulate and predict the corresponding water level changes, flow rate fluctuations, and wind speed impacts during the flood risk period. This process uses a high-performance computing-based platform to quickly simulate and iteratively update the water regime model to ensure that the simulation results accurately reflect the current hydrological state in a short time, and finally obtain the water level along the river course, the flow rate along the river course, and the wind speed along the river course during the flood risk period.

[0076] Step S32: Obtain the historical river water level fluctuations and climate patterns, and conduct water level evolution analysis on the water level along the river course based on the historical river water level fluctuations and climate patterns to generate the corresponding water level evolution fluctuation field along the river course during the flood risk period.

[0077] In an embodiment of the present invention, by obtaining historical river water level fluctuation data and climate patterns and using them as the basis for analysis, the evolution of the river water level is analyzed through historical observation data and climate simulation data. First, the river water level fluctuation data for the past several years are collected and analyzed. These data can be obtained from meteorological bureaus, hydrological departments, and local weather stations. Then, by using a climate model to predict future climate change trends, especially factors such as changes in precipitation and temperature, combined with these historical data and climate patterns, a water level evolution analysis model is established. Based on the fluctuation law of historical water level data, the water level change trend during the flood risk period is deduced. In actual operation, tools such as time series analysis methods and machine learning regression models can be used to predict the water level evolution and generate a water level fluctuation field during this period. Finally, a corresponding river water level evolution fluctuation field along the river during the flood risk period is generated.

[0078] Step S33: Obtain the corresponding upstream inflow, midstream precipitation, and downstream outflow through the flow rate along the river during the flood risk period, and perform flow-related coupling analysis on the corresponding river water level changes in the river water level evolution fluctuation field along the river based on the upstream inflow, midstream precipitation, and downstream outflow to generate a dynamic response correlation field between the flow rate along the river and the water level change.

[0079] In an embodiment of the present invention, by real-time monitoring the river flow rate during the flood risk period, obtaining the flow rate data and further analyzing the correlation between the flow rate and the upstream inflow, midstream precipitation, and downstream outflow. First, multiple flow rate monitoring points are set up, and equipment such as current meters and flow meters are used to obtain the flow rate data of each part of the river in real time. Secondly, the data of remote sensing monitoring and hydrometeorological stations are used to estimate the upstream inflow and midstream precipitation, and the basin water balance equation in hydrology is used to input these data into the calculation model for coupling analysis between the flow rate and the water level evolution. By establishing a response function between the flow rate change and the water level fluctuation, combined with the historical evolution trend of the water level, a dynamic response correlation field is generated, thereby providing a quantitative basis for subsequent flood risk early warning. This process can use hydrological and hydraulic simulation software, such as HEC-RAS, etc., to perform accurate correlation analysis between the flow rate and the water level, and finally generate a dynamic response correlation field between the flow rate along the river and the water level change.

[0080] Step S34: Evaluate the influence factor of the wind speed along the river on the dynamic response correlation field between the flow rate along the river and the water level change based on the wind speed along the river during the flood risk period to obtain the microscopic change influence factor of the wind speed along the river on the river water level and the corresponding flow rate.

[0081] In the embodiments of the present invention, by evaluating and analyzing impact factors based on wind speed data, first, actual wind speed data is collected along the river course through a wind speed monitoring instrument. The wind speed sensor can be installed at different positions along the river course, especially in areas vulnerable to wind speed changes. Combining with meteorological data, the microscopic impact of wind speed on the river water level and flow changes is evaluated. Through numerical simulation and fluid mechanics analysis, the impact degree of wind speed on the water surface and flow is determined. For example, wind speed will cause disturbances on the water surface, thereby changing the distribution of water flow and water level changes. Using a fluid dynamics model (such as a CFD model), the wind speed is added as an impact factor to the change model of the river water level and flow, so as to obtain the quantitative impact factor of wind speed on the water level and flow changes. During the evaluation process, for different wind speed intervals, the microscopic changes in flow and water level caused by it can be quantified, and finally, the microscopic change impact factors corresponding to the wind speed along the river course on the river water level and flow are obtained.

[0082] Step S35: Based on the microscopic change impact factors corresponding to the river water level and flow along the river course, the digital twin model of the environmental water regime along the river course is processed for flood risk prediction, and the flood risk prediction result of the water regime along the river course is generated to perform the corresponding river water regime flood risk management decision-making work.

[0083] In the embodiments of the present invention, during the flood risk period, based on the microscopic change impact factors generated in the previous steps and using the digital twin model of the river water regime for flood risk prediction. This process first combines the data such as water level, flow, and wind speed obtained in the previous steps. By integrating all impact factors, a dynamic response model is established in the digital twin model of the water regime. This model can predict the changes in water level and flow according to real-time monitoring data and historical trends, and can be adjusted according to different flood scenarios. Specifically, input the real-time water level, flow, and wind speed data, and use numerical simulation methods for prediction processing, output the prediction results of the river water level and flow, use the prediction results to judge the flood risk level, and provide decision support for the river management department accordingly. The prediction system can generate specific flood risk warning reports to guide water regime management and disaster prevention and mitigation work. The entire process can use computer simulation platforms, such as programming languages like MATLAB and Python and dedicated hydrological software, for comprehensive data processing and risk assessment, and finally perform the corresponding river water regime flood risk management decision-making work.

[0084] Further, the flow correlation coupling analysis of the river water level change corresponding to the river water level evolution fluctuation field along the river course based on the upstream incoming water volume, the midstream precipitation, and the downstream outgoing water volume in step S33 includes the following steps:

[0085] Based on the upstream water inflow and the midstream precipitation, the upper and middle reaches of the river along the line corresponding to the water level evolution fluctuation field are subjected to the upper-middle water flow gradient analysis to obtain the upper-middle water flow change distribution gradient along the river line;

[0086] In the embodiment of the present invention, by obtaining the real-time data of the upstream water inflow and the midstream precipitation, which are usually collected through meteorological satellites, basin hydrological stations and water conservancy monitoring systems, these data are the basis for the analysis of the river water flow. For the water flow gradient analysis of the upstream of the river, a hydrodynamic model based on water level and flow can be used, combined with the measured water flow data for numerical simulation. In specific operations, multiple water level monitoring points are first set up in the upstream of the river. These monitoring points will update the water level change data in real time according to the actual flow and precipitation conditions. Next, the influencing factors of the water level change in the midstream area are calculated through the hydrodynamic model of the river, especially the contribution of precipitation to the water level change. According to this model, based on the flow velocity, flow rate, and river channel morphology (such as riverbed width, slope, etc.) of the water flow, the gradient analysis of the water flow change is carried out. The analysis process will adopt numerical solution methods (such as the finite difference method or the finite element method) to gradually deduce the change distribution of the water flow between the upstream and the midstream, and the change trend of the water flow between the upper and middle reaches of the river can be clarified, reflecting the evolution of the water flow in real time, and finally obtaining the upper-middle water flow change distribution gradient along the river line.

[0087] Preferably, based on the midstream precipitation and the downstream water outflow, the middle and lower reaches of the river along the line corresponding to the water level evolution fluctuation field are subjected to the middle-lower water flow gradient analysis to obtain the middle-lower water flow change distribution gradient along the river line;

[0088] In the embodiment of the present invention, through the gradient analysis of the middle-lower water flow based on the midstream precipitation and the downstream water outflow, first, the data of the midstream precipitation and the downstream water outflow are obtained. The midstream precipitation data can be obtained through meteorological forecasts, basin hydrological observation stations, and the hydrological data platform of the reservoir management department. The midstream precipitation affects the water level change in the downstream. Therefore, it is necessary to analyze the direct influence of precipitation on the water flow through a time series model. First, the midstream precipitation data are obtained in real time and combined with the water flow dynamics model to calculate the influence of the midstream precipitation on the water level change. Then, the downstream water outflow data are obtained, and these data are monitored in real time through the flow meters in the downstream river channel to ensure the accuracy of the data. By inputting the midstream precipitation and the downstream water outflow into the model, the water flow change trend of the middle and lower reaches of the river is calculated, and the water flow gradient analysis is carried out. In this process, similar numerical methods (such as the finite element method) are used to analyze the water flow gradient change in the middle and lower reaches to obtain the middle-lower water flow gradient distribution, and finally the middle-lower water flow change distribution gradient along the river line is obtained.

[0089] Preferably, the upstream and downstream flow error losses corresponding to the river channel are obtained through the upstream incoming water volume and the downstream outgoing water volume, and based on the upstream and downstream flow error losses of the river channel, the distribution gradients of the water flow changes in the upper and middle reaches and the lower and middle reaches along the river channel are analyzed for the water flow distribution losses of each section of the river channel, so as to generate the upstream-middle-downstream water flow distribution gradient loss field along the river channel;

[0090] In the embodiment of the present invention, the distribution losses of the water flow in each section of the river channel are analyzed through the upstream and downstream flow error losses. In actual operation, the difference between the upstream incoming water volume and the downstream outgoing water volume often generates a flow error. Especially in the case of sudden precipitation or untimely water volume regulation, the flow error causes violent fluctuations in the water level change. Therefore, it is necessary to calculate the upstream and downstream flow errors first, that is, to analyze the difference in the upstream and downstream water volumes through the flow balance formula. The calculation process is as follows: First, obtain the upstream incoming water volume, the downstream outgoing water volume and the water flow data of each intermediate section, calculate the water volume error between the upstream and downstream through the water flow model. The generation of the flow error can be estimated by simulating different water flow conditions, such as precipitation changes, river channel structure changes, reservoir water storage changes and other factors. These errors will be optimized and corrected through specific mathematical models (such as the least squares method, Kalman filter, etc.). Then, use these errors to calculate the distribution losses of the water flow in each section, considering the flow losses and gains between different sections (upstream, middle, downstream) of the river channel. The loss field is obtained through a segmented analysis method. Through the error loss analysis of the upstream incoming water volume and the downstream outgoing water volume, the water flow change losses of each section of the river channel are obtained, so as to generate a detailed water flow distribution gradient loss field, and finally the upstream-middle-downstream water flow distribution gradient loss field along the river channel is generated.

[0091] Preferably, the water level change amplitude analysis is carried out on the water level change corresponding to the water level evolution fluctuation field along the river channel to obtain the water level change fluctuation amplitude along the river channel;

[0092] In an embodiment of the present invention, the water level changes in various sections of the river are analyzed based on real-time water level monitoring data. This analysis process involves multiple aspects such as the amplitude, frequency and oscillation characteristics of water level fluctuations. In specific operations, it is necessary to set up water level monitoring points at multiple key nodes along the river, collect water level data regularly, and combine meteorological forecast data to analyze water level changes. Next, the water level change data is spectrally analyzed by using a frequency domain analysis method (such as fast Fourier transform FFT) to obtain the frequency distribution and amplitude of water level fluctuations. This analysis can reveal the strength of water level fluctuations and identify areas with large water level amplitudes. The amplitude and trend of water level changes are further determined by time domain analysis. In this process, other factors affecting water level changes, such as river morphology, reservoir scheduling, downstream drainage, etc., need to be considered. By combining these factors, the amplitude of water level changes is analyzed in detail to ensure accurate prediction of the amplitude of water level changes, and finally the amplitude of water level fluctuations along the river is obtained.

[0093] Preferably, a flow correlation coupling analysis is performed on the fluctuation amplitude of water level changes along the river channel based on the gradient loss field of water flow distribution in the upper, middle and lower reaches of the river channel to generate a dynamic response correlation field between flow and water level changes along the river channel.

[0094] In an embodiment of the present invention, a coupling analysis between flow and water level changes is performed based on the previously calculated upstream-middle-downstream water flow distribution gradient loss field and the water level change fluctuation amplitude. In order to achieve this analysis, it is necessary to model the correlation between water flow and water level changes. Methods such as multivariate regression analysis and neural network models can be used to establish a dynamic response relationship between water flow and water level changes. The analysis process will use a correlation analysis method based on the real-time acquired water flow data and water level change data to calculate the relationship strength between flow changes and water level changes. On this basis, a dynamic response association field is established, which can reflect the impact of water flow changes on water level changes in real time and make predictions for future water level change trends. Through this coupling analysis, the dynamic response association field obtained can provide accurate data support for river water situation forecasts, help decision makers take timely measures to respond to water level fluctuations, ensure the rational allocation and utilization of water resources, and ultimately generate a dynamic response association field between flow and water level changes along the river.

[0095] Further, step S34 includes the following steps:

[0096] Step S341: Based on the dynamic response correlation field between the wind speed along the river channel and the flow and water level change along the river channel during the flood risk period, a spatial distribution impact analysis is performed to obtain the spatial distribution impact characteristics of the wind speed along the river channel on the water level and flow change of the river channel;

[0097] In the embodiments of the present invention, by obtaining the wind speed data along the river course, using a high-precision meteorological model or meteorological data acquisition equipment, such as an automatic weather station or satellite remote sensing, the wind speed data for a specific period and location are obtained. These wind speed data need to cover different positions of the river course, especially the wind speed changes in the upper, middle, and lower reaches of the river course, to ensure the representativeness of the spatial distribution of the data. By matching these wind speed data with the river flow and water level change data, the dynamic response of the river flow and water level can be simulated and calculated through a hydrological and hydraulic model (such as HEC-RAS, MIKE11, etc.), the influence relationship of the wind speed on the water level and flow changes can be obtained, and through dynamic correlation analysis, it can be identified how the wind speed affects the water level and flow changes at different positions along the river course during floods. Using a spatial interpolation method (such as Kriging interpolation or inverse distance weighting method), a spatial distribution influence map of the wind speed on the river water level and flow changes is generated, so as to determine the specific influence characteristics of the wind speed at different positions along the river course on the water level and flow, and finally obtain the spatial distribution influence characteristics of the wind speed along the river course on the river water level and flow changes.

[0098] Step S342: Obtain the cross-sectional shapes and slopes of different river sections corresponding to the river course, and based on the cross-sectional shapes and slopes of different river sections corresponding to the river course, conduct an assessment calculation of the influence of the wind speed along the river course on the spatial distribution of the river water level and flow changes to obtain the degree of influence of the wind speed at different river sections along the river course on the spatial distribution between the river water level and flow changes.

[0099] In the embodiments of the present invention, by further analyzing the cross-sectional shapes and slopes of different river sections according to the obtained data along the river course, these data are usually obtained through topographic surveys, remote sensing images, or river course surveys. Specifically, techniques such as light detection and ranging (LiDAR) technology or unmanned aerial vehicle photogrammetry can be used to accurately measure the cross-sectional shape and slope changes of the river course, and through the combination of a geographic information system (GIS) platform, spatial analysis of the cross-sectional shape and slope data of the river section is carried out to accurately describe the water flow behavior of different river sections and the spatial differences in the influence of the wind speed on them. Based on these river section morphological characteristics, a hydrodynamic model (such as a two-dimensional flow model or a one-dimensional flow model) is further used to evaluate the influence of the wind speed on the water level and flow changes. Through model calculations, the influence degree of the wind speed at different river sections on the water level and flow can be obtained, and the differences in the response of each river section to the water level and flow under the wind speed change can be revealed, and a quantitative wind speed influence assessment result can be obtained, and finally the degree of influence of the wind speed at different river sections along the river course on the spatial distribution between the river water level and flow changes can be obtained.

[0100] Step S343: Based on the degree of influence of the wind speed in different river sections along the river on the spatial distribution between the river water level and the flow rate change, conduct an evaluation and analysis of the wind speed influence factors for the corresponding river water level and river flow rate along the river in the dynamic response correlation field between the flow rate and the water level change along the river, so as to obtain the micro influence factors of the wind speed along the river on the corresponding micro changes in the river water level and flow rate.

[0101] In the embodiment of the present invention, after obtaining the degree of influence of the wind speed in different river sections on the spatial distribution of the water level and flow rate changes, it is necessary to further analyze the water level and flow rate data along the river, so as to stratify different sections along the river according to the degree of influence of the wind speed based on the degree of influence of the spatial distribution. On this basis, by calculating the wind speed influence factors, evaluate the micro influence of the wind speed on the water level and flow rate changes. The specific implementation method is to analyze the correlation between the wind speed data and the water level and flow rate data, and use regression analysis or machine learning algorithms (such as decision trees, support vector machines, etc.) to identify the influence factors of the wind speed change on the water level and flow rate changes. This process can establish a mapping relationship between the wind speed and the water level and flow rate through the training of historical data, so as to obtain the specific influence coefficients of the wind speed on the water level and flow rate changes in different river sections and different time periods. During this process, it is necessary to evaluate the changes in the influence factors according to different time scales (such as hours, days, months, etc.), so as to obtain the micro influence factors of the wind speed on the micro changes in the water level and flow rate. Through this analysis, specific influence parameters can be accurately provided for the dynamic water regime forecast in the digital twin model, and finally the micro influence factors corresponding to the wind speed along the river on the river water level and flow rate can be obtained.

[0102] Further, step S4 includes the following steps:

[0103] Step S41: Obtain the river water level, river flow rate, and river temperature along the river corresponding to the digital twin model of the river environmental water regime during the drought risk period of the river water regime by predicting the drought risk period.

[0104] In an embodiment of the present invention, during the drought risk prediction period, water level, flow rate, and temperature data along the river channel within the corresponding drought risk period range are obtained by using a water regime model based on digital twin technology. First, a three-dimensional digital twin model of the river channel is constructed, including the geometric shape of the river channel, historical hydrological data, and real-time sensor data. Combining the meteorological prediction model with real-time observation data, water level, flow rate, and temperature data of the river channel are collected in real time through remote sensing technology and Internet of Things sensors (such as water level sensors, flow meters, temperature sensors, etc.). Subsequently, based on the digital twin platform, the predicted drought risk period (such as the next few days or weeks) and environmental change factors are input, and the changing trends of water level, flow rate, and temperature during these periods are simulated. The future hydrological changes are calculated through existing historical data and climate models to ensure the accuracy of the output results. Finally, the water level along the river channel, the flow rate along the river channel, and the temperature along the river channel during the drought risk period are obtained.

[0105] Step S42: Conduct a time-series fluctuation cross and lag assessment analysis on the water level along the river channel and the flow rate along the river channel during the drought risk period to obtain the time-series fluctuation cross interaction and time-series fluctuation lag effect between the water level and the flow rate along the river channel;

[0106] In an embodiment of the present invention, after obtaining the water level and flow rate data along the river channel, an assessment analysis of time-series fluctuation cross and lag effects is carried out. The specific method is to use time series analysis technology to conduct a detailed analysis of the relationship between the water level and the flow rate of the river channel. First, through statistical analysis methods, such as correlation analysis and cointegration analysis, the time-series fluctuation cross effect between the water level and the flow rate is identified, and through the analysis of the cross-correlation function (CCF), the correlation between the water level and the flow rate at different time points is calculated to find out their interaction relationship. Secondly, through the use of lag effect analysis, the impact delay time of water level changes on flow rate changes is evaluated, and a lag regression model or Granger causality test method is used to quantify the time lag effect of water level changes on flow rate. The lag effect analysis will help identify whether there is a delay effect in the flow rate responding to water level changes during the drought risk period. Finally, the time-series fluctuation cross interaction and time-series fluctuation lag effect between the water level and the flow rate along the river channel are obtained.

[0107] Step S43: Based on the time-series fluctuation cross interaction and time-series fluctuation lag effect between the water level and the flow rate along the river channel, conduct a time-series fluctuation synchronization analysis on the water level along the river channel and the flow rate along the river channel during the drought risk period to generate a corresponding hydrological fluctuation response field along the river channel during the drought risk period;

[0108] In an embodiment of the present invention, after analyzing the temporal fluctuations, crossovers, and lag effects of water levels and flows, temporal fluctuation synchronization analysis of water levels and flows is performed based on these analysis results. The synchronization analysis uses synchronization analysis techniques such as waveform correlation and phase synchronization analysis to quantify the synchronization and degree of synchronous changes in water level and flow changes. On this basis, a hydrological fluctuation response field along the river channel is generated through a simulation model to evaluate the fluctuation response pattern between water level and flow during drought risk periods. In specific operations, by comparing water level and flow data at different times and locations, a response field model is constructed to identify the hydrological change patterns that occur in the river channel during drought risk periods. The generated hydrological fluctuation response field is visually presented to show the changes in hydrological conditions during drought risk periods, and finally, a corresponding hydrological fluctuation response field along the river channel during drought risk periods is generated.

[0109] Step S44: Based on the temperature along the river channel, conduct a hydrological evaporation rate assessment analysis on the corresponding hydrological fluctuation response field along the river channel during drought risk periods to obtain the influence correlation relationship between the hydrological fluctuations along the river channel and the water surface evaporation rate of the river channel.

[0110] In an embodiment of the present invention, during drought risk periods, by evaluating the relationship between the temperature along the river channel and the hydrological fluctuation response field, further analysis of the hydrological evaporation rate is carried out. First, based on the temperature data along the river channel and in combination with the hydrological fluctuation response field, an evaporation calculation model (such as the Penman-Monteith model or the Hargreaves model) is used to evaluate the evaporation rate under different temperature conditions. Through the correlation between environmental factors such as temperature, humidity, and wind speed and water level and flow fluctuations, the influence relationship between hydrological fluctuations and evaporation rate is quantified. For different river sections, according to the actually measured water surface temperature and environmental data, the corresponding evaporation rate is calculated, and through methods such as regression analysis and correlation analysis, a statistical model between the water surface evaporation rate and water level fluctuations is obtained. This assessment process plays an important guiding role in the hydrological evaporation impact during drought periods, can predict water loss and guide water resources management, and finally obtains the influence correlation relationship between the hydrological fluctuations along the river channel and the water surface evaporation rate of the river channel.

[0111] Step S45: Based on the influence correlation relationship between the hydrological fluctuations along the river channel and the water surface evaporation rate of the river channel, perform drought risk forecasting on the corresponding digital twin model of the environmental water situation along the river channel to generate the drought risk forecasting result of the water situation along the river channel, so as to implement the corresponding drought risk management decision-making work for the river water situation.

[0112] In an embodiment of the present invention, based on the influence correlation relationship between the previously obtained hydrological fluctuations and evaporation rate, combining historical hydrological data and real-time monitoring data, a drought risk forecast for the water regime along the river is carried out. Through a digital twin model for simulating the drought risk of the water regime, real-time analysis and prediction are performed based on the obtained environmental data (such as water level, flow rate, temperature, etc.). A model is used for drought risk assessment. The model will predict the future changes in the river water level and flow rate according to the hydrological fluctuation response field and the water surface evaporation rate, simulate the scope, intensity, and duration that the drought risk may affect, and output the risk forecast result. This result provides decision-making support for the management of the river water regime. Especially when the drought risk is relatively high, decision-makers can arrange water resource scheduling, drought mitigation measures, etc. according to this. According to the forecast result, relevant water regime management and emergency measures are taken to ensure the rational utilization and protection of the river water resources, and finally, the corresponding river water regime drought risk management decision-making work is carried out.

[0113] Furthermore, the present invention also provides a river water regime forecasting system based on digital twin for implementing the above-mentioned river water regime forecasting method based on digital twin. The river water regime forecasting system based on digital twin includes:

[0114] A digital twin modeling module for the river water regime, which is used to deploy sensor nodes along the river and perform real-time monitoring of the river environmental water regime along the river based on the sensor nodes to obtain real-time water level data, real-time flow rate data, and real-time meteorological data along the river. The real-time meteorological data along the river includes rainfall along the river, temperature along the river, and wind speed along the river; using the real-time water level data, real-time flow rate data, and real-time meteorological data along the river to construct a digital twin of the river along the river to generate a digital twin model of the river environmental water regime along the river;

[0115] A module for dividing the risk prediction period of the river water regime, which is used to perform risk prediction and division of the corresponding river water regime period in the digital twin model of the river environmental water regime along the river based on the rainfall along the river to generate a flood risk prediction period and a drought risk prediction period of the river water regime;

[0116] A flood risk forecasting module for the river water regime, which is used to obtain the corresponding water level, flow rate, and wind speed along the river during the flood risk prediction period of the river water regime, and perform flood risk forecasting processing on the corresponding digital twin model of the river environmental water regime along the river based on the water level, flow rate, and wind speed along the river, so as to generate a flood risk forecasting result of the river water regime along the river to implement the corresponding flood risk management decision-making work for the river water regime;

[0117] The river water regime drought risk forecasting module is used to obtain the corresponding water levels, flows, and temperatures along the river during the river water regime drought risk estimation period, and perform drought risk forecasting processing on the corresponding digital twin model of the environmental water regime along the river based on the water levels, flows, and temperatures along the river, so as to generate the river water regime drought risk forecasting results and execute the corresponding river water regime drought risk management decision-making work.

[0118] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. A river water regime forecasting method based on digital twin, characterized in that, It includes the following steps: Step S1: By deploying sensor nodes along the river course and based on the sensor nodes, conducting real-time monitoring of the river environment water regime along the river course to obtain real-time water level data, real-time flow data, and real-time meteorological data along the river course. The real-time meteorological data along the river course includes rainfall along the river course, temperature along the river course, and wind speed along the river course; using the real-time water level data, real-time flow data, and real-time meteorological data along the river course to construct a digital twin of the river course environment to generate a digital twin model of the river course environment water regime; Step S2: Based on the rainfall along the river course, conduct risk prediction and division of the corresponding river course water regime time periods in the digital twin model of the river course environment water regime to generate a flood risk prediction time period and a drought risk prediction time period of the river course water regime; Step S3: By obtaining the corresponding water level, flow, and wind speed along the river course during the flood risk prediction time period of the river course water regime, and based on the water level, flow, and wind speed along the river course, conduct flood risk forecasting on the corresponding digital twin model of the river course environment water regime to generate a flood risk forecasting result of the river course water regime, so as to execute the corresponding flood risk management decision-making work of the river course water regime; Step S4: By obtaining the corresponding water level, flow, and temperature along the river course during the drought risk prediction time period of the river course water regime, and based on the water level, flow, and temperature along the river course, conduct drought risk forecasting on the corresponding digital twin model of the river course environment water regime to generate a drought risk forecasting result of the river course water regime, so as to execute the corresponding drought risk management decision-making work of the river course water regime.

2. The method for predicting river water regime based on digital twin according to claim 1, wherein Step S1 includes the following steps: Step S11: By deploying sensor nodes along the river course, where the sensor nodes include water level sensors, flow sensors, and meteorological monitoring sensors; Step S12: Based on the sensor nodes, use the Internet of Things technology to connect to the cloud platform to generate an Internet of Things network for water regime monitoring along the river course; use the water level sensors in the Internet of Things network for water regime monitoring along the river course to conduct real-time monitoring of the water level along the river course to obtain real-time water level data along the river course; Step S13: Use the flow sensors in the Internet of Things network for water regime monitoring along the river course to conduct real-time monitoring of the flow along the river course to obtain real-time flow data along the river course; Step S14: Use the meteorological monitoring sensors in the Internet of Things network for water regime monitoring along the river course to conduct real-time monitoring of the meteorology along the river course to obtain real-time meteorological data along the river course, including rainfall along the river course, temperature along the river course, and wind speed along the river course; Step S15: Upload the real-time water level data, real-time flow data, and real-time meteorological data along the river course to the cloud platform, and use the real-time water level data, real-time flow data, and real-time meteorological data along the river course to construct a digital twin of the river course environment to generate a digital twin model of the river course environment water regime.

3. The method for predicting river water regime based on digital twin according to claim 2, wherein, The digital twin construction of the river course along the line using the real-time water level data, real-time flow data, and real-time meteorological data along the river course in step S15 includes the following steps: Perform spatio-temporal correlation analysis on the real-time water level data and real-time flow data along the river course to obtain the spatio-temporal dynamic correlation relationship between the water level change and flow fluctuation along the river course; Obtain the corresponding geographic information coordinate data along the river course, and perform water regime spatio-temporal correlation mapping on the real-time water level data and real-time flow data along the river course and combine with the geographic information coordinate data based on the spatio-temporal dynamic correlation relationship between the water level change and flow fluctuation along the river course to generate a water regime spatio-temporal correlation feature model along the river course; Perform meteorological multi-source data fusion analysis on the water regime spatio-temporal correlation feature model along the river course based on the real-time meteorological data along the river course to generate a time series model of the environmental water regime along the river course; Obtain the corresponding digital terrain data along the river course, including the riverbed slope and shoreline contour, and perform river basin terrain simulation analysis on the corresponding digital terrain data along the river course to generate river basin terrain water flow simulation data along the river course; Perform digital twin fusion construction on the time series model of the environmental water regime along the river course based on the river basin terrain water flow simulation data along the river course to generate a digital twin model of the environmental water regime along the river course.

4. The method for predicting river water regime based on digital twin according to claim 1, wherein, Step S2 includes the following steps: Step S21: Perform water regime spatio-temporal fluctuation correlation analysis on the corresponding river water regime time period in the digital twin model of the environmental water regime along the river course based on the rainfall along the river course to obtain the spatio-temporal fluctuation correlation relationship between the rainfall along the river course and the water regime fluctuation; Step S22: Perform water regime fluctuation time series feature analysis on the rainfall along the river course and the corresponding river water regime time period in the digital twin model of the environmental water regime along the river course based on the spatio-temporal fluctuation correlation relationship between the rainfall along the river course and the water regime fluctuation to obtain a river rainfall-water regime fluctuation time series feature data set, which includes periodic and non-periodic fluctuation characteristics corresponding to rainfall, flow fluctuation, and water storage change; Step S23: Perform risk determination and assessment calculation on the corresponding river water regime time period in the digital twin model of the environmental water regime along the river course using the water regime fluctuation risk determination calculation formula based on the river rainfall-water regime fluctuation time series feature data set to obtain water regime fluctuation risk determination parameters along the river course, including flood fluctuation risk determination parameters and drought fluctuation risk determination parameters along the river course; Step S24: Perform flood and drought extreme risk segmentation on the corresponding river water regime time period in the digital twin model of the environmental water regime along the river course based on the water regime fluctuation risk determination parameters along the river course. If the water regime fluctuation in the corresponding river water regime time period is within the range corresponding to the flood fluctuation risk determination parameters along the river course, then determine its river water regime time period as the river water regime flood risk prediction time period; if the water regime fluctuation in the corresponding river water regime time period is within the range corresponding to the drought fluctuation risk determination parameters along the river course, then determine its river water regime time period as the river water regime drought risk prediction time period.

5. The method for predicting river water regime based on digital twin according to claim 4, characterized in that, The specific water regime fluctuation risk determination calculation formula in step S23 is: where R H is the flood fluctuation risk determination parameter along the river course, R G is the drought fluctuation risk determination parameter along the river course, t0 is the initial time point corresponding to the river water regime period, t1 is the end time point corresponding to the river water regime period, t is the time variable parameter, P(t) is the rainfall at time t, is the rainfall change rate, α1 is the rainfall water regime fluctuation risk weight coefficient, Q(t) is the river flow at time t, Q max is the maximum threshold of the river flow, H(t) is the change in river water storage at time t, H max is the maximum threshold of the change in river water storage, α2 is the water storage change water regime fluctuation risk weight coefficient, exp is the exponential function, β is the river flow water regime fluctuation risk weight coefficient, n is the total number of flood tide events, i is the item index of the flood tide event, Q i is the river flow of the i-th flood tide event, Q avg is the average value of the river flow of the flood tide event, m is the total number of drought events, j is the item index of the drought event, S j is the standardized drought evaporation index of the j-th drought event, S avg is the average value of the evaporation index of the drought event, η1 is the correction coefficient of the flood fluctuation risk determination parameter along the river course, η2 is the correction coefficient of the drought fluctuation risk determination parameter along the river course.

6. The method for predicting river water regime based on digital twin according to claim 1, wherein Step S3 includes the following steps: Step S31: Obtain the water levels, flow rates, and wind speeds along the river channel corresponding to the digital twin model of the environmental water regime along the river channel during the flood risk period under the river channel water regime flood risk prediction period; Step S32: Obtain the historical river channel water level fluctuations and climate patterns, and conduct water level evolution analysis on the water levels along the river channel based on the historical river channel water level fluctuations and climate patterns to generate the water level evolution fluctuation field along the river channel corresponding to the flood risk period; Step S33: Obtain the corresponding upstream inflow, midstream precipitation, and downstream outflow based on the flow rate along the river channel during the flood risk period, and conduct flow correlation coupling analysis on the water level changes along the river channel corresponding to the water level evolution fluctuation field along the river channel based on the upstream inflow, midstream precipitation, and downstream outflow to generate the dynamic response correlation field between the flow rate and water level changes along the river channel; Step S34: Conduct wind speed influence factor assessment analysis on the dynamic response correlation field between the flow rate and water level changes along the river channel based on the wind speed along the river channel during the flood risk period to obtain the microscopic change influence factors of the wind speed along the river channel on the water level and flow rate of the river channel; Step S35: Based on the microscopic change influence factors of the water level and flow rate along the river channel on the corresponding digital twin model of the environmental water regime along the river channel, conduct flood risk prediction processing to generate the flood risk prediction result of the water regime along the river channel, so as to execute the corresponding river channel water regime flood risk management decision-making work.

7. The method for predicting river water regime based on digital twin according to claim 6, wherein, The flow correlation coupling analysis of the water level changes along the river channel corresponding to the water level evolution fluctuation field along the river channel based on the upstream inflow, midstream precipitation, and downstream outflow in Step S33 includes the following steps: Conduct upper-middle water flow gradient analysis on the upper-middle reaches along the river channel corresponding to the water level evolution fluctuation field along the river channel based on the upstream inflow and midstream precipitation to obtain the upper-middle water flow change distribution gradient along the river channel; Conduct mid-lower water flow gradient analysis on the mid-lower reaches along the river channel corresponding to the water level evolution fluctuation field along the river channel based on the midstream precipitation and downstream outflow to obtain the mid-lower water flow change distribution gradient along the river channel; Obtain the corresponding upstream-downstream flow error loss along the river channel through the upstream inflow and downstream outflow, and conduct water flow distribution loss analysis on the upper-middle water flow change distribution gradient and the mid-lower water flow change distribution gradient along the river channel based on the upstream-downstream flow error loss along the river channel to generate the upper-middle-lower water flow distribution gradient loss field along the river channel; Conduct water level change amplitude analysis on the water level changes along the river channel corresponding to the water level evolution fluctuation field along the river channel to obtain the water level change fluctuation amplitude along the river channel; Conduct flow correlation coupling analysis on the water level change fluctuation amplitude along the river channel based on the upper-middle-lower water flow distribution gradient loss field along the river channel to generate the dynamic response correlation field between the flow rate and water level changes along the river channel.

8. The method for river water regime forecasting based on digital twin according to claim 6, wherein Step S34 includes the following steps: Step S341: Analyze the spatial distribution impact of the dynamic response correlation field between the flow rate and water level changes along the river channel based on the wind speed along the river channel during the flood risk period, and obtain the spatial distribution impact characteristics of the wind speed along the river channel on the water level and flow rate changes; Step S342: Obtain the cross-sectional shapes and slopes of different river sections corresponding to the river channel, and perform river section wind speed impact assessment calculations on the spatial distribution impact characteristics of the wind speed along the river channel on the water level and flow rate changes based on the cross-sectional shapes and slopes of different river sections corresponding to the river channel, to obtain the spatial distribution impact degree of the wind speed of different river sections along the river channel on the water level and flow rate changes; Step S343: Conduct wind speed impact factor assessment and analysis on the water level along the river channel and the flow rate along the river channel corresponding in the dynamic response correlation field between the flow rate and water level changes along the river channel based on the spatial distribution impact degree of the wind speed of different river sections along the river channel on the water level and flow rate changes, to obtain the microscopic change impact factors of the wind speed along the river channel on the water level and flow rate; 9. The method for predicting river water regime based on digital twin according to claim 1, characterized in that, Step S4 includes the following steps: Step S41: Obtain the water level along the river channel, the flow rate along the river channel, and the temperature along the river channel corresponding to the digital twin model of the environmental water conditions along the river channel during the drought risk period of the river channel water regime; Step S42: Conduct time series fluctuation cross and lag assessment and analysis on the water level along the river channel and the flow rate along the river channel during the drought risk period, to obtain the time series fluctuation cross interaction and time series fluctuation lag effect between the water level and flow rate along the river channel; Step S43: Conduct time series fluctuation synchronization analysis on the water level along the river channel and the flow rate along the river channel during the drought risk period based on the time series fluctuation cross interaction and time series fluctuation lag effect between the water level and flow rate along the river channel, to generate the corresponding hydrological fluctuation response field along the river channel during the drought risk period; Step S44: Conduct hydrological evaporation rate assessment and analysis on the corresponding hydrological fluctuation response field along the river channel during the drought risk period based on the temperature along the river channel, to obtain the impact correlation relationship between the hydrological fluctuations along the river channel and the water surface evaporation rate of the river channel; Step S45: Conduct drought risk forecasting processing on the corresponding digital twin model of the environmental water conditions along the river channel based on the impact correlation relationship between the hydrological fluctuations along the river channel and the water surface evaporation rate of the river channel, to generate the drought risk forecasting result of the water regime along the river channel, so as to execute the corresponding river channel water regime drought risk management decision-making work.

10. A river water regime forecasting system based on digital twin, characterized in that, For implementing the digital twin-based river channel water regime forecasting method as described in claim 1, the digital twin-based river channel water regime forecasting system includes: River water regime digital twin modeling module, which is used to deploy sensor nodes along the river course and conduct real-time monitoring of the river environment water regime along the river course based on the sensor nodes to obtain real-time water level data, real-time flow data and real-time meteorological data along the river course, where the real-time meteorological data along the river course includes rainfall, temperature and wind speed along the river course; use the real-time water level data, real-time flow data and real-time meteorological data along the river course to construct a digital twin of the river course to generate a digital twin model of the river environment water regime along the river course; River water regime risk prediction time period division module, which is used to conduct risk prediction and division of the corresponding river water regime time period in the digital twin model of the river environment water regime along the river course based on the rainfall along the river course to generate a flood risk prediction time period and a drought risk prediction time period of the river water regime; River water regime flood risk forecasting module, which is used to obtain the corresponding water level, flow and wind speed along the river course during the flood risk prediction time period of the river water regime, and conduct flood risk forecasting processing on the corresponding digital twin model of the river environment water regime along the river course based on the water level, flow and wind speed along the river course, so as to generate a flood risk forecasting result of the water regime along the river course to implement the corresponding river water regime flood risk management decision-making work; River water regime drought risk forecasting module, which is used to obtain the corresponding water level, flow and temperature along the river course during the drought risk prediction time period of the river water regime, and conduct drought risk forecasting processing on the corresponding digital twin model of the river environment water regime along the river course based on the water level, flow and temperature along the river course, so as to generate a drought risk forecasting result of the water regime along the river course to implement the corresponding river water regime drought risk management decision-making work.

Images