Drainage basin hydrological model parameter dynamic estimation method based on digital twinborn technology

Abstract

The invention discloses a watershed hydrological model parameter dynamic estimation method based on a digital twinborn technology, and relates to the technical field of watershed management, and the method comprises the following steps: carrying out the comprehensive modeling of the hydrological, meteorological and geographic features of a watershed through the multi-modal data and terrain and remote sensing data in the watershed; based on the topographic information and the meteorological data, a spatial clustering algorithm is used for partitioning the drainage basin, and a mountain torrent prone area is found out; and for each mountain flood prone area, extracting key features reflecting potential risks of regional mountain flood outbreak by using the acquired multi-modal data. According to the method, the accurate drainage basin model is constructed by fusing the multi-modal data and the geographic features, the mountain torrent prone areas are identified by adopting spatial clustering, and the risk is predicted through feature engineering and machine learning. In combination with space-time sensitivity intelligent adjustment, the system can respond to risk changes in real time, the prediction precision and the response speed are improved, accurate decision support is provided for drainage basin managers, and the influence of mountain torrent disasters is effectively prevented and relieved.

Description

Technical Field

[0001] The present invention relates to the technical field of watershed management, and in particular to a method for dynamic estimation of watershed hydrological model parameters based on digital twin technology. Background Art

[0002] Dynamic estimation of basin hydrological model parameters based on digital twin technology refers to the dynamic estimation and optimization of key parameters of the hydrological model by real-time collection of multi-source heterogeneous data (such as water level, flow, rainfall, temperature, etc.) in the basin, combined with the real-time feedback and adaptive correction mechanism of the digital twin model. In this process, multimodal data fusion technology is first used to align and dynamically fuse heterogeneous data in time and space to generate a unified hydrological dynamic data representation; then, a method based on an adaptive correction algorithm is used to adjust the model parameters by calculating the difference between real-time data and historical data, thereby accurately reflecting the changes in the hydrological state in the basin. In addition, the core parameters of the model are further optimized by combining the Bayesian dynamic network or adversarial learning algorithm, and its impact on the future hydrological state is predicted, thereby improving the accuracy and adaptability of the hydrological model in the optimization of basin water resources scheduling. Ultimately, the model can achieve automatic dynamic adjustment to ensure efficient response and accurate prediction of complex hydrological conditions.

[0003] The prior art has the following deficiencies: In adaptive zoning, the dynamic weight allocation of regions usually depends on hydrological characteristics (such as rainfall intensity, flow fluctuation amplitude, etc.). However, some areas (such as flash flood-prone areas) may fail to adjust the weights in time due to the complexity of the terrain or sudden local extreme climate conditions. For example, a small watershed suddenly experienced a strong flash flood during rainfall, and the model failed to assign enough weight to the small watershed. This will lead to insufficient estimation of the water level and flow in the small watershed, resulting in missed warnings, and ultimately leading to small-scale flash flood disasters, and even affecting the safety of downstream areas.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0005] The purpose of the present invention is to provide a method for dynamic estimation of watershed hydrological model parameters based on digital twin technology. By integrating multimodal data and geographical features, an accurate watershed model is established, and spatial clustering technology is used to identify areas prone to flash floods. By extracting key risk features through feature engineering technology and using machine learning for prediction, combined with intelligent adjustment of spatiotemporal sensitivity, the system can dynamically respond to changes in regional risks based on real-time data and flash flood prediction results, greatly improving the accuracy and response speed of flash flood risk prediction, ensuring that watershed managers can obtain more accurate and dynamic decision support in a timely manner, thereby effectively preventing and mitigating the impact of flash flood disasters, and solving the problems in the above-mentioned background technology.

[0006] In order to achieve the above object, the present invention provides the following technical solution: a method for dynamic estimation of basin hydrological model parameters based on digital twin technology, comprising the following steps: Comprehensively model the hydrological, meteorological and geographical characteristics of the basin through multimodal data, topographic and remote sensing data in the basin, where multimodal data includes real-time hydrological and meteorological data; Based on terrain information and meteorological data, spatial clustering algorithms are used to partition the watershed and identify areas prone to flash floods. For each flash flood prone area, the key features reflecting the potential risk of flash floods in the area are extracted using the collected multimodal data. The extracted features are deeply analyzed and processed through feature engineering technology, and the processed features are input as feature vectors into the trained and put into use machine learning model to predict potential flash floods. When there is a potential risk of flash floods in a flash flood-prone area, the spatiotemporal sensitivity threshold of the flash flood-prone area is intelligently adjusted based on the real-time flash flood prediction results of the area and its characteristics of changes over time and space. In the potential flash flood area, the spatiotemporal sensitivity is dynamically improved to enhance the response capability to risk changes, ensuring that river basin managers can obtain more accurate and timely decision-making support to deal with the potential threats brought by flash floods.

[0007] Preferably, the steps of comprehensively modeling the hydrological, meteorological and geographical characteristics of the basin by using multimodal data, topographic and remote sensing data in the basin include: Collect and integrate data from different sources, including real-time hydrological data, meteorological data, terrain information, and remote sensing image data; Preprocess the collected data, including denoising, standardization, and spatiotemporal alignment, to ensure data quality and consistency; The basin is geographically partitioned by spatial analysis methods, and the basin is divided into several sub-areas with similar hydrological and meteorological characteristics; Statistical methods are used to analyze and extract features from various types of data, and a multidimensional model that can reflect the hydrological, meteorological and geographical characteristics of the basin is constructed. Through multimodal data fusion technology, comprehensive modeling of hydrological, meteorological and geographical characteristics is achieved.

[0008] Preferably, the specific steps of using a spatial clustering algorithm to partition the watershed based on terrain information and meteorological data include: Collect and integrate topographic and meteorological data in the basin and convert them into feature vectors suitable for clustering algorithm processing; Select clustering algorithm for cluster analysis. The clustering results will reveal different areas in the basin and identify those areas that are highly correlated with flash floods, i.e. flash flood prone areas. The clustering results are displayed through visualization tools, and combined with multimodal data fusion technology, hydrological, meteorological and geographical characteristics are comprehensively integrated to build a comprehensive watershed model.

[0009] Preferably, for each flash flood-prone area, the collected multimodal data are used to extract key features that reflect the potential risk of regional flash floods, wherein the extracted features include the rise and fall of water levels and the frequency and magnitude of flow changes in the basin. During the monitoring period, the rise and fall of water levels and the frequency and magnitude of flow changes in the basin are deeply analyzed and processed through feature engineering technology to generate water level fluctuation reference values ​​and flow change reference values, respectively. The water level fluctuation reference values ​​and flow change reference values ​​are input as feature vectors into a machine learning model that has been trained and put into use, and potential flash floods are predicted by the flash flood risk index generated by the machine learning model.

[0010] Preferably, the flash flood risk index generated when the machine learning model that has been trained and put into use predicts potential flash floods is compared and analyzed with a preset flash flood risk index reference threshold to predict potential flash floods. The specific steps are as follows: If the flash flood risk index is greater than the flash flood risk index reference threshold, a risk signal is generated, indicating that there is a risk of flash floods in the flash flood-prone area; if the flash flood risk index is less than or equal to the flash flood risk index reference threshold, a normal signal is generated, indicating that the state of the flash flood-prone area is stable and there is no risk of flash floods.

[0011] Preferably, when there is a potential flash flood risk in a flash flood prone area, the temporal and spatial sensitivity threshold of the flash flood prone area is intelligently adjusted in combination with the real-time flash flood forecast results of the flash flood prone area and its characteristics of temporal and spatial changes. The specific steps are as follows: First, the temporal and spatial sensitivity thresholds of flash flood prone areas are calculated. The temporal and spatial sensitivity thresholds are dynamically adjusted according to the flash flood risk index and the flash flood risk index reference threshold. The calculation formula of the temporal and spatial sensitivity thresholds is as follows: ,in, is the spatiotemporal sensitivity threshold, is the flash flood risk index, which indicates the flash flood risk in the current basin. is the reference threshold of flash flood risk index, It represents the time change rate of the flash flood risk index, that is, the speed at which the flash flood risk index changes over time, reflecting the changing trend of the flash flood risk. and are preset weighting coefficients, which respectively represent the contribution weights of the current flash flood risk index and the flash flood risk index reference threshold to the temporal and spatial sensitivity threshold. The impact factor of temporal variation is used to weigh the impact of temporal variation on risk response within the basin; When the spatiotemporal sensitivity threshold is adjusted, the flash flood risk of the flash flood prone area is re-evaluated, and the risk level is determined according to the new spatiotemporal sensitivity threshold. When there is a potential flash flood risk in the flash flood prone area, the spatiotemporal sensitivity threshold of the flash flood prone area is intelligently adjusted. The dynamic adjustment expression of the new spatiotemporal sensitivity threshold is: ,in: is the spatiotemporal response adjustment factor, which is used to control the dynamic amplification of the spatiotemporal sensitivity threshold when the flash flood risk changes. The adjusted spatiotemporal sensitivity threshold is dynamically improved based on the impact of the deviation between the flash flood risk index and the flash flood risk index reference threshold, thereby enhancing the response capacity to flash flood risks.

[0012] Preferably, for each flash flood prone area, during the monitoring period, the specific steps of deeply analyzing and processing the rise and fall amplitudes of the water level in the basin through feature engineering technology to generate a water level fluctuation reference value are as follows: For each time window , the water level change amplification factor is introduced to identify the severity of water level changes in each time window. The calculation expression of the water level change amplification factor is: ,in: Represents the water level change amplification factor, which is used to quantify the intensity of water level fluctuations within the time window. It is j The water level value corresponding to the timestamp, is a parameter that controls the sensitivity of water level fluctuations and the degree of weighting of the control changes. It is the time window The number of data points in is the water level value at the previous time point; After completing the calculation of the water level fluctuation increase in each time window, the water level fluctuation reference value is further generated through local anomaly measurement. It is used to measure the deviation of water level change in each time window from the overall trend and local anomaly measurement. Defined as: ,in: is the predicted water level value obtained using the local weighted regression model, is a parameter that controls the sensitivity of the anomaly measurement; The final water level fluctuation reference value is obtained by combining the abnormal measurement of each time window with the water level change increase factor for weighted calculation. The calculation expression of the water level fluctuation reference value is: ,in: is the water level fluctuation reference value, is the weight factor, which is used to weight the fluctuations in each time window. i Indicates the monitoring period i time windows, that is, the basin water level data is divided into multiple time windows during the monitoring period. m Indicates the total number of time windows divided during the entire monitoring period, that is, the entire monitoring period is divided into m time window.

[0013] Preferably, for each flash flood prone area, during the monitoring period, the specific steps of deeply analyzing and processing the frequency and amplitude of flow changes in the basin through feature engineering technology to generate flow change reference values ​​are as follows: Perform high-order moment analysis on flow data to reveal complex patterns and abnormal fluctuations in flow changes, using skewness in high-order moments and Kurtosis To capture the asymmetry and extreme volatility of traffic distribution, skewness and Kurtosis The specific calculation formula is as follows: ,in: For the k The flow rate at the moment, is the mean flow rate, is the standard deviation of the flow rate, n is the total number of samples of the data; The complexity of traffic fluctuations is evaluated by fractal dimension. Fractal dimension is used to describe the self-similarity and complexity of traffic curves. It is a method to measure the details of traffic fluctuations. The fractal dimension of the traffic curve is calculated by the following formula: ,in: represents the fractal dimension, Indicated in scale The coverage number of the lower flow curve, that is, the level of detail of the flow change, is the scale parameter; Combined skewness , Kurtosis And fractal dimension The analysis results are used to calculate the flow change reference value. The calculation expression is: ,in: It represents the reference value of flow change, and comprehensively measures the change characteristics of flow by combining skewness, kurtosis and fractal dimension.

[0014] In the above technical solution, the technical effects and advantages provided by the present invention are: The present invention establishes an accurate watershed model by integrating multimodal data and geographic features, and uses spatial clustering technology to identify areas prone to flash floods. By extracting key risk features through feature engineering technology and using machine learning for prediction, combined with intelligent adjustment of spatiotemporal sensitivity, the system can dynamically respond to changes in regional risks based on real-time data and flash flood forecast results, greatly improving the accuracy and response speed of flash flood risk prediction, ensuring that watershed managers can obtain more accurate and dynamic decision support in a timely manner, thereby effectively preventing and mitigating the impact of flash flood disasters. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0016] Figure 1 This is a flow chart of the method for dynamic estimation of basin hydrological model parameters based on digital twin technology in the present invention. DETAILED DESCRIPTION

[0017] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0018] The present invention provides Figure 1 The method for dynamic estimation of watershed hydrological model parameters based on digital twin technology includes the following steps: Comprehensively model the hydrological, meteorological and geographical characteristics of the basin through multimodal data (such as rainfall, water level, flow, temperature, soil moisture, etc.) and topographic and remote sensing data in the basin. Multimodal data includes real-time hydrological and meteorological data. The steps to comprehensively model the hydrological, meteorological, and geographical characteristics of a watershed using multimodal data (such as rainfall, water level, flow, temperature, soil moisture, etc.) and topographic and remote sensing data within the watershed include: First, collect and integrate data from different sources, including real-time hydrological data (such as rainfall, flow, water level, etc.), meteorological data (such as temperature, humidity, wind speed, etc.), as well as terrain information (such as slope, altitude, watershed morphology, etc.) and remote sensing image data (such as land use type, vegetation coverage, etc.).

[0019] Next, these data were preprocessed, including denoising, normalization, and spatiotemporal alignment, to ensure data quality and consistency.

[0020] Then, the basin is geographically zoned by spatial analysis methods (such as GIS technology) and divided into several sub-areas with similar hydrological and meteorological characteristics.

[0021] On this basis, statistical methods are used to analyze and extract features of various types of data, and a multidimensional model that can reflect the hydrological, meteorological and geographical characteristics of the basin is constructed. Through multimodal data fusion technology, comprehensive modeling of hydrological, meteorological and geographical characteristics is achieved.

[0022] This modeling process provides a scientific basis for subsequent risk assessment, disaster prediction and emergency response.

[0023] Based on terrain information (such as slope, watershed morphology, etc.) and meteorological data (such as precipitation, temperature change, etc.), spatial clustering algorithms (such as K-means, DBSCAN) are used to partition the watershed and identify areas prone to flash floods; Based on terrain information (such as slope, watershed morphology, etc.) and meteorological data (such as precipitation, temperature change, etc.), the specific steps of using spatial clustering algorithms (such as K-means, DBSCAN) to partition the watershed include: First, collect and integrate the topographic and meteorological data in the basin and convert them into feature vectors suitable for clustering algorithm processing. For example, use slope, altitude, basin morphology, precipitation, temperature and other data as feature input.

[0024] Then, select an appropriate clustering algorithm (such as K-means, DBSCAN, etc.) for cluster analysis. The K-means algorithm iteratively divides the basin into K sub-regions, each with similar characteristics; while DBSCAN identifies flash flood-prone areas by density, and can automatically detect high-risk areas with dense precipitation and special terrain features. The clustering results will reveal different areas within the basin and specifically identify those areas that are highly correlated with flash floods, i.e., flash flood-prone areas.

[0025] Finally, the clustering results are displayed through visualization tools (such as GIS software), and multimodal data fusion technology is combined to comprehensively integrate hydrological, meteorological and geographical features to build a comprehensive watershed model to provide accurate data support for subsequent predictions and decision-making.

[0026] This process classifies areas with similar geographical and meteorological characteristics within the basin through spatial clustering, and accurately identifies areas prone to flash floods, providing support for disaster warning and resource dispatch.

[0027] For each flash flood prone area, the key features reflecting the potential risk of flash floods in the area are extracted using the collected multimodal data. The extracted features are deeply analyzed and processed through feature engineering technology, and the processed features are input as feature vectors into the trained and put into use machine learning model to predict potential flash floods. For each area prone to flash floods, the collected multimodal data are used to extract key features that reflect the potential risk of regional flash floods, among which the extracted features include the rise and fall of water levels and the frequency and magnitude of flow changes in the basin. During the monitoring period, the rise and fall of water levels and the frequency and magnitude of flow changes in the basin are deeply analyzed and processed through feature engineering technology to generate water level fluctuation reference values ​​and flow change reference values, respectively. The water level fluctuation reference values ​​and flow change reference values ​​are input as feature vectors into the trained and put into use machine learning model, and the flash flood risk index generated by the machine learning model is used to predict potential flash floods.

[0028] The trained machine learning model is a process of learning and tuning historical data through machine learning algorithms. In this process, the model automatically identifies the nonlinear or complex relationship between input features (such as water level fluctuations, flow changes, etc.) and flash floods from the data. The core purpose of the training process is to find the potential patterns in the data and gradually optimize the parameters of the model through back propagation (in neural networks) and gradient descent (in regression models) to make its prediction of input features more accurate.

[0029] Taking neural networks as an example, during the training process, the original hydrological data (including historical water level data, flow data, rainfall, etc.) is first input into the network. Through repeated forward and backward propagation, the network continuously adjusts its internal weights and biases until the model can accurately capture the complex relationship between characteristics such as water level fluctuations and flow changes and flash floods. After training is completed, the model will be tested with a validation set (that is, data not used for training) to evaluate the accuracy and robustness of the model in actual applications and ensure that it can effectively cope with different hydrological and meteorological conditions.

[0030] The trained model can not only generate prediction results based on historical data, but also respond quickly to input real-time data and predict the possibility of flash floods. This enables the model to be used as a real-time early warning system in practical applications. At this step, the model is no longer just a theoretical tool, but has been verified in practice and has the ability to continuously make effective predictions in complex and dynamic environments. The trained model is continuously optimized and adjusted by using the back propagation algorithm and different evaluation indicators (such as accuracy, recall rate, F1 value, etc.), and ultimately achieves accurate prediction of flash flood risks.

[0031] A machine learning model that has been put into use means that the model has been trained and applied in a real-world environment, and can receive new data in real time and generate corresponding prediction results. This stage is very critical in the prediction of flash floods because it ensures that the machine learning model can process real-time data in real scenarios and provide effective support for flash flood monitoring and early warning.

[0032] For the machine learning model of flash flood risk prediction, the use of it means the seamless connection of the model in data flow, model calculation and decision support system. The machine learning model monitors multimodal data such as water level, flow, rainfall in real time, inputs these data into the trained model, and generates prediction results about flash flood risk. For example, the model will calculate the "flash flood risk index" of the area based on the input water level fluctuation reference value and flow change reference value, using the patterns learned in previous training, and provide early warning information to basin managers based on this.

[0033] This process involves a "prediction-feedback-optimization" cycle. The model predicts the flash flood risk index of potential flash floods and reminds relevant management departments to take preventive measures; at the same time, in actual applications, basin managers will provide feedback on the model's prediction results, and these feedback data will continue to supplement the training data set to further optimize the model. With the continuous input of real-time data, the model will gradually improve the accuracy of its predictions. This "feedback learning" not only keeps the model efficient, but also copes with the uncertainties brought about by changes in climate, topography, etc., ensuring the long-term effectiveness of the model.

[0034] In actual use, the investment in machine learning models also means that it can be integrated into automated early warning systems and work in conjunction with other monitoring equipment (such as weather radars, remote sensing satellites, etc.). For example, when the water level in a flash flood-prone area exceeds a certain threshold, the model will automatically trigger an early warning and send risk warning information to relevant personnel through text messages, emails, APP push, etc. This makes early warning and emergency response to flash floods faster and more efficient.

[0035] In addition, the use of machine learning models also emphasizes their adaptability to real-time data. The model is able to adapt to various changes and generate accurate predictions under various climate conditions and terrain conditions. This ability makes machine learning models an indispensable tool in flash flood disaster prevention and mitigation work. It is not just a static analysis tool, but a dynamic and continuously optimized decision support system.

[0036] The rise and fall of water levels in a river basin is an important indicator for measuring the potential risk of flash floods. Generally, when the water level changes by a large amplitude, it means that the precipitation suddenly increases or the water bodies in the river basin gather rapidly, causing the water level to rise rapidly. Such drastic changes often occur under extreme meteorological conditions, especially heavy rain or concentrated precipitation events in a short period of time. In this case, the drainage capacity of the river basin may be insufficient, and flash floods are very likely to occur. In addition, the sharp drop in water levels may also reflect the rapid loss of water flow after flash floods, and the drastic changes in the hydrological conditions in the river basin, indicating that the water resources in the river basin have fluctuated greatly in a short period of time, which may cause flash floods. Therefore, areas with large fluctuations in water levels usually mean that the risk of flash floods in the area is high, while areas with small fluctuations in water levels may mean that the risk of flash floods is low. By monitoring the trend of water level changes, the potential risk of flash floods can be effectively predicted and assessed.

[0037] For each flash flood prone area, during the monitoring period, feature engineering technology is used to conduct in-depth analysis and processing of the rise and fall of water levels in the basin. The specific steps for generating water level fluctuation reference values ​​are as follows: First, the water level fluctuation sequence needs to be segmented according to the timestamp, and the trend of water level change in each time period needs to be calculated. Specifically, the change characteristics of the water level in each short time window are analyzed by calculating the local slope. (i.e., a set of watershed water level data selected within a time range), the water level change increase factor is introduced to identify the severity of water level changes in each small time window. The formula is expressed as: ,in: represents the water level change amplification factor, It is j The water level value corresponding to the timestamp, is a parameter that controls the sensitivity of water level fluctuations and the degree of weighting of the control changes. It is the time window The number of data points in It is the water level value at the previous time point. Water level change increase factor Used to quantify the intensity of water level fluctuations over a short time window; The purpose of this step is to highlight local drastic fluctuations through adaptive amplification factors and retain the nonlinear fluctuation characteristics of the data.

[0038] After completing the calculation of the water level fluctuation increase in each time window, the water level fluctuation reference value is further generated through local anomaly measurement. It is used to measure the deviation of water level changes in each time window from the overall trend, especially sudden events of rapid rise or fall, local anomaly measurement Defined as: ,in: is the predicted water level value obtained using a local weighted regression model (such as Gaussian weighted regression), is a parameter that controls the sensitivity of the anomaly measurement; Through this formula, the degree of abnormality of water level fluctuation can be quantified, considering whether the change of water level in a certain time window deviates significantly from the overall trend. Finally, the water level fluctuation reference value is obtained by combining the abnormal measurement of each time window with the water level change increase factor for weighted calculation. The expression of the water level fluctuation reference value is: ,in: is the water level fluctuation reference value, is the weight factor, which is used to weight the fluctuations in each time window. i Indicates the monitoring period i time windows, that is, the basin water level data is divided into multiple time windows during the monitoring period. m Indicates the total number of time windows divided during the entire monitoring period, that is, the entire monitoring period is divided into m time windows; The purpose of this step is to comprehensively evaluate the intensity and degree of water level fluctuation in different time windows, so as to obtain an overall water level fluctuation reference value with early warning capability. The water level fluctuation reference value can accurately reflect the drastic fluctuation of water level in the basin, and can be further used to assess the potential risk of flash floods.

[0039] It can be seen from the water level fluctuation reference value that for each flash flood prone area, during the monitoring period, the greater the performance value of the water level fluctuation reference value generated by in-depth analysis and processing of the rise and fall of the water level in the basin through feature engineering technology, the greater the risk of potential flash floods in the flash flood prone area. The water level fluctuation reference value is obtained by in-depth analysis of the rise and fall of the water level in the basin, which comprehensively reflects the degree of drastic changes in the water level in a short period of time. When the water level rises or falls rapidly, it usually means a sharp increase in precipitation or a sharp convergence of water bodies in the basin. This drastic water level fluctuation is a harbinger of flash floods. In flash flood prone areas, the increase in the water level fluctuation reference value usually indicates that the hydrological conditions in the basin have changed rapidly, which may exceed the drainage capacity of the basin, resulting in an increased risk of flash floods. Therefore, the larger the performance value of the water level fluctuation reference value, the more drastic the water level fluctuation, and the higher the possibility of flash floods; conversely, if the water level fluctuation reference value is small, it means that the water level changes are relatively stable and the potential risk of flash floods is low.

[0040] For each flash flood prone area, the frequency and magnitude of flow changes within the basin usually indicate a higher risk of flash floods in the area. The reasons for frequent and large flow changes are often related to sudden heavy precipitation, mountainous terrain features or other factors (such as soil saturation, river blockage, etc.). In flash flood prone areas, when precipitation is high, water is likely to quickly merge into streams or rivers, resulting in a sharp increase in flow. This rapid flow change reflects the speed and intensity of the basin's response to precipitation. Frequent and drastic flow fluctuations usually indicate that the drainage capacity of the area is poor, and the accumulation and rapid flow of water may exceed the carrying capacity of natural or artificial drainage facilities, thus forming conditions for flash floods. Therefore, the frequency and magnitude of flow changes are an important indicator of flash floods in flash flood prone areas.

[0041] For each flash flood prone area, during the monitoring period, the frequency and magnitude of flow changes in the basin are deeply analyzed and processed by feature engineering technology to generate flow change reference values. The specific steps are as follows: Perform high-order moment analysis on the flow data to reveal complex patterns and abnormal fluctuations in flow. High-order moment analysis focuses on the asymmetry and kurtosis (i.e., the sharpness of the fluctuation) of flow. In this step, skewness is used and Kurtosis To capture the asymmetry and extreme fluctuation characteristics of traffic distribution. The specific formula is as follows: ,in: For the k The flow rate at the moment, is the mean flow rate, is the standard deviation of the flow rate, n is the total number of samples of the data; Skewness is used to quantify the degree of deviation of flow changes (i.e., whether the changes tend to be upward or downward), while kurtosis is used to quantify the sharpness of flow fluctuations (i.e., whether there are sharp fluctuations or extreme changes). High skewness and kurtosis values ​​tend to indicate sharp fluctuations in flow, indicating potential flash flood risks; This step is mainly used to capture the asymmetry and abnormal fluctuation information of flow fluctuations, and provide basic nonlinear characteristics for the next step of flow change index calculation. This helps to reveal the complexity of flow changes, especially in the case of rapid changes or abnormal fluctuations.

[0042] The complexity of traffic fluctuations is evaluated by fractal dimension. Fractal dimension is used to describe the self-similarity and complexity of traffic curves and is a method to measure the details of traffic fluctuations. The fractal dimension of the traffic curve can be calculated by the following formula: ,in: represents the fractal dimension, Indicated in scale The coverage number of the lower flow curve, that is, the level of detail of the flow change, is the scale parameter. Specifically, is the number of segmentations of the traffic time series at different scales. Gradually decrease, The change in fractal dimension reflects the complexity of flow fluctuations. If the fractal dimension is high, it means that the flow fluctuations are more complex, which may indicate a strong hydrological response and potential flash flood risk; This step can reveal the nonlinear complexity of flow fluctuations through the calculation of fractal dimensions, further enhancing the accurate description of flow changes. A high fractal dimension means that flow changes are more complex and irregular, which is usually closely related to the risk of sudden flash floods.

[0043] Combined skewness , Kurtosis And fractal dimension The analysis results are used to calculate the flow change reference value. The calculation expression is: ,in: It represents the reference value of flow change, and comprehensively measures the change characteristics of flow by combining three important characteristics: skewness, kurtosis and fractal dimension. and Kurtosis Together, they reflect the asymmetry and extreme fluctuations of flow fluctuations, and the fractal dimension The complexity of flow fluctuations is quantified. Finally, the flow change reference value Ability to quantify the extent and complexity of flow fluctuations, thus providing effective prediction basis for potential risk of flash floods; Flow rate change reference value It can effectively aggregate multi-dimensional flow fluctuation characteristics into a digital risk assessment indicator, and provide accurate quantitative data support for flash flood risk prediction by quantifying the asymmetry, extreme fluctuations and complexity of flow.

[0044] It can be seen from the flow change reference value that for each flash flood prone area, during the monitoring period, the larger the performance value of the flow change reference value generated by in-depth analysis and processing of the frequency and amplitude of flow changes in the basin through feature engineering technology, the more drastic and complex the flow fluctuation in the basin is, which is usually accompanied by a larger hydrological response, which is especially important in flash flood prone areas. Frequent changes in flow and large fluctuations usually indicate that the probability of extreme precipitation or other extreme climatic conditions in the area in a short period of time is high, which in turn increases the risk of flash floods. The flow change reference value extracted by feature engineering technology can quantify the intensity and complexity of these fluctuations. If the flow change reference value is high, it means that the hydrological characteristics of the flash flood prone area show more irregular and drastic fluctuations, which is usually caused by the superposition effect of factors such as sudden precipitation, upstream water injection, and terrain characteristics. These factors greatly increase the potential risk of flash floods. On the contrary, if the flow change reference value is low, it means that the hydrological fluctuations in the basin are relatively stable, the impact of extreme weather events on the area is small, and the potential flash flood risk is low. Therefore, the flow change reference value can not only serve as an effective quantitative standard, but also provide a scientific basis for the prediction of flash flood risks.

[0045] The machine learning model is not specifically limited here, and can realize the reference value of water level fluctuation and flow rate change reference value Conduct comprehensive analysis to generate a flash flood risk index In order to realize the technical solution of the present invention, the present invention provides a specific implementation method; flash flood risk index The resulting calculation formula is: , where , are water level fluctuation reference values and flow rate change reference value The preset scaling factor of , All are greater than 0. Preset proportional coefficient ( and ) refers to the water level fluctuation reference value ( ) and flow rate change reference value ( ) are coefficients used to weight the risk of flash floods. The purpose of these preset proportional coefficients is to set the contribution ratio of different indicators to the final risk assessment based on actual hydrological models or historical data. Specifically, is the water level fluctuation reference value ( ) impact weight on flash flood risk, is the flow rate change reference value ( ) on the risk of flash floods. In practical applications, these preset proportionality coefficients help the model dynamically adjust the degree of influence on risk prediction according to changes in water level and flow, ensuring that the output of the model (i.e., the flash flood risk index) can accurately reflect the relative contribution of different hydrological characteristics to the risk of flash floods. and These are parameters obtained by fitting the model based on historical data or field experience, and usually require tuning to ensure the prediction accuracy of the model.

[0046] It can be seen from the flash flood risk index that for each flash flood-prone area, during the monitoring period, the greater the performance value of the water level fluctuation reference value generated by in-depth analysis and processing of the rise and fall of the water level in the basin through feature engineering technology, the greater the performance value of the flow change reference value generated by in-depth analysis and processing of the frequency and amplitude of flow changes in the basin through feature engineering technology. That is, the greater the performance value of the flash flood risk index generated when the machine learning model that has been trained and put into use is used to predict potential flash floods, the greater the risk of flash floods in the flash flood-prone area, and vice versa.

[0047] The flash flood risk index generated by the trained and put-in-use machine learning model when predicting potential flash floods is compared and analyzed with the pre-set flash flood risk index reference threshold to predict potential flash floods. The specific steps are as follows: If the flash flood risk index is greater than the flash flood risk index reference threshold, a risk signal is generated, indicating that there is a risk of flash floods in the flash flood-prone area; if the flash flood risk index is less than or equal to the flash flood risk index reference threshold, a normal signal is generated, indicating that the state of the flash flood-prone area is relatively stable and there is no risk of flash floods.

[0048] When there is a potential flash flood risk in a flash flood prone area, the temporal and spatial sensitivity threshold of the flash flood prone area is intelligently adjusted based on the real-time flash flood forecast results and its characteristics of temporal and spatial changes. In the potential flash flood area, the temporal and spatial sensitivity is dynamically improved to enhance the ability to respond to risk changes, ensuring that watershed managers can obtain more accurate and timely decision support to deal with the potential threats brought by flash floods. When there is a potential flash flood risk in a flash flood prone area, the temporal and spatial sensitivity thresholds of the flash flood prone area are intelligently adjusted based on the real-time flash flood forecast results and its characteristics of temporal and spatial changes. The specific steps are as follows: First, the temporal and spatial sensitivity thresholds of flash flood prone areas are calculated. The temporal and spatial sensitivity thresholds are dynamically adjusted according to the flash flood risk index and the flash flood risk index reference threshold. The calculation formula of the temporal and spatial sensitivity thresholds is as follows: ,in, is the spatiotemporal sensitivity threshold, is the flash flood risk index, which indicates the flash flood risk in the current basin. It is the reference threshold of flash flood risk index, which is usually set through historical data, expert judgment or simulation analysis. It indicates the time change rate of the flash flood risk index, that is, the speed at which the flash flood risk index changes over time, reflecting the changing trend of flash flood risk, especially in the event of sudden weather or hydrological events. and are preset weighting coefficients, which respectively represent the contribution weights of the current flash flood risk index and the flash flood risk index reference threshold to the temporal and spatial sensitivity threshold. The impact factor of temporal variation is used to weigh the impact of temporal variation on risk response within the basin; The purpose of this step is to dynamically adjust the spatiotemporal sensitivity threshold according to the gap between the real-time flash flood risk index and the flash flood risk index reference threshold, as well as the speed at which the flash flood risk index changes over time. Dynamically increasing spatiotemporal sensitivity means that when the flash flood risk index approaches or exceeds the flash flood risk index reference threshold, the spatiotemporal sensitivity threshold will be increased to enhance the ability to respond to changes. This adjustment ensures that the system responds quickly when the risk changes dramatically.

[0049] When the spatiotemporal sensitivity threshold is adjusted, the flash flood risk of the flash flood prone area is re-evaluated, and the risk level is determined according to the new spatiotemporal sensitivity threshold. When there is a potential flash flood risk in the flash flood prone area (that is, when the flash flood risk index is greater than the flash flood risk index reference threshold), the spatiotemporal sensitivity threshold of the flash flood prone area is intelligently adjusted. The dynamic adjustment expression of the new spatiotemporal sensitivity threshold is: ,in: is the spatiotemporal response adjustment factor, which is used to control the dynamic amplification of the spatiotemporal sensitivity threshold when the flash flood risk changes. The adjusted spatiotemporal sensitivity threshold is dynamically improved based on the impact of the deviation between the flash flood risk index and the flash flood risk index reference threshold, thereby enhancing the response capacity to flash flood risks.

[0050] By real-time monitoring and predicting the risk changes in flash flood-prone areas, the temporal and spatial sensitivity thresholds of the area are intelligently adjusted, thereby enhancing the system's ability to respond to potential threats of flash floods. When the risk changes dramatically, the system will dynamically increase the temporal and spatial sensitivity, making the early warning of flash floods more accurate and timely. Through this dynamic adjustment, it can ensure that basin managers can quickly obtain reliable risk assessments and take disaster prevention and mitigation measures in a timely manner when faced with sudden meteorological changes or hydrological anomalies, thereby minimizing the threat of flash floods to life and property and improving the efficiency and effectiveness of emergency response. This process improves the flexibility of the early warning system, enabling it to effectively respond to flash floods of different risk levels and ensure that prevention and control measures are effectively implemented at the most critical moment.

[0051] The dynamic estimation method of basin hydrological model parameters based on digital twin technology can effectively solve the problem that the model in the existing technology fails to adjust the weight in time and misses the flash flood warning. This method establishes an accurate basin model by integrating multimodal data (such as rainfall, water level, flow, etc.) and geographical features, and uses spatial clustering technology to identify flash flood-prone areas. By extracting key risk features through feature engineering technology and using machine learning for prediction, combined with intelligent adjustment of spatiotemporal sensitivity, the system can dynamically respond to changes in regional risks based on real-time data and flash flood prediction results. This solution greatly improves the accuracy and response speed of flash flood risk prediction, ensuring that basin managers can obtain more accurate and dynamic decision-making support in a timely manner, thereby effectively preventing and mitigating the impact of flash flood disasters.

[0052] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0053] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0054] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. A method for dynamic estimation of basin hydrological model parameters based on digital twin technology, characterized in that: The following steps are involved: Comprehensively model the hydrological, meteorological and geographical characteristics of the basin through multimodal data, topographic and remote sensing data in the basin, where multimodal data includes real-time hydrological and meteorological data; Based on terrain information and meteorological data, spatial clustering algorithms are used to partition the watershed and identify areas prone to flash floods. For each flash flood prone area, the key features reflecting the potential risk of flash floods in the area are extracted using the collected multimodal data. The extracted features are deeply analyzed and processed through feature engineering technology, and the processed features are input as feature vectors into the trained and put into use machine learning model to predict potential flash floods. When there is a potential risk of flash floods in a flash flood-prone area, the spatiotemporal sensitivity threshold of the flash flood-prone area is intelligently adjusted based on the real-time flash flood prediction results of the area and its characteristics of changes over time and space. In the potential flash flood area, the spatiotemporal sensitivity is dynamically improved to enhance the response capability to risk changes, ensuring that river basin managers can obtain more accurate and timely decision-making support to deal with the potential threats brought by flash floods.

2. The method for dynamic estimation of watershed hydrological model parameters based on digital twin technology according to claim 1 is characterized in that: The steps to comprehensively model the hydrological, meteorological, and geographical characteristics of a watershed using multimodal data, topographic, and remote sensing data include: Collect and integrate data from different sources, including real-time hydrological data, meteorological data, terrain information, and remote sensing image data; Preprocess the collected data, including denoising, standardization, and spatiotemporal alignment, to ensure data quality and consistency; The basin is geographically partitioned by spatial analysis methods, and the basin is divided into several sub-areas with similar hydrological and meteorological characteristics; Statistical methods are used to analyze and extract features from various types of data, and a multidimensional model that can reflect the hydrological, meteorological and geographical characteristics of the basin is constructed. Through multimodal data fusion technology, comprehensive modeling of hydrological, meteorological and geographical characteristics is achieved.

3. The method for dynamic estimation of watershed hydrological model parameters based on digital twin technology according to claim 1 is characterized in that: Based on terrain information and meteorological data, the specific steps of using spatial clustering algorithm to partition the watershed include: Collect and integrate topographic and meteorological data in the basin and convert them into feature vectors suitable for clustering algorithm processing; Select clustering algorithm for cluster analysis. The clustering results will reveal different areas in the basin and identify those areas that are highly correlated with flash floods, i.e. flash flood prone areas. The clustering results are displayed through visualization tools, and combined with multimodal data fusion technology, hydrological, meteorological and geographical characteristics are comprehensively integrated to build a comprehensive watershed model.

4. The method for dynamic estimation of watershed hydrological model parameters based on digital twin technology according to claim 1 is characterized in that: For each area prone to flash floods, the collected multimodal data are used to extract key features that reflect the potential risk of regional flash floods, among which the extracted features include the rise and fall of water levels and the frequency and magnitude of flow changes in the basin. During the monitoring period, the rise and fall of water levels and the frequency and magnitude of flow changes in the basin are deeply analyzed and processed through feature engineering technology to generate water level fluctuation reference values ​​and flow change reference values, respectively. The water level fluctuation reference values ​​and flow change reference values ​​are input as feature vectors into the trained and put into use machine learning model, and the flash flood risk index generated by the machine learning model is used to predict potential flash floods.

5. The method for dynamic estimation of watershed hydrological model parameters based on digital twin technology according to claim 4 is characterized in that: The flash flood risk index generated by the trained and put-in-use machine learning model when predicting potential flash floods is compared and analyzed with the pre-set flash flood risk index reference threshold to predict potential flash floods. The specific steps are as follows: If the flash flood risk index is greater than the flash flood risk index reference threshold, a risk signal is generated, indicating that there is a risk of flash floods in the flash flood-prone area; if the flash flood risk index is less than or equal to the flash flood risk index reference threshold, a normal signal is generated, indicating that the state of the flash flood-prone area is stable and there is no risk of flash floods.

6. The method for dynamic estimation of watershed hydrological model parameters based on digital twin technology according to claim 5 is characterized in that: When there is a potential flash flood risk in a flash flood prone area, the temporal and spatial sensitivity thresholds of the flash flood prone area are intelligently adjusted based on the real-time flash flood forecast results and its characteristics of temporal and spatial changes. The specific steps are as follows: First, the temporal and spatial sensitivity thresholds of flash flood prone areas are calculated. The temporal and spatial sensitivity thresholds are dynamically adjusted according to the flash flood risk index and the flash flood risk index reference threshold. The calculation formula of the temporal and spatial sensitivity thresholds is as follows: ,in, is the spatiotemporal sensitivity threshold, is the flash flood risk index, which indicates the flash flood risk in the current basin. is the reference threshold of flash flood risk index, It represents the time change rate of the flash flood risk index, that is, the speed at which the flash flood risk index changes over time, reflecting the changing trend of the flash flood risk. and are preset weighting coefficients, which respectively represent the contribution weights of the current flash flood risk index and the flash flood risk index reference threshold to the temporal and spatial sensitivity threshold. The impact factor of temporal variation is used to weigh the impact of temporal variation on risk response within the basin; When the spatiotemporal sensitivity threshold is adjusted, the flash flood risk of the flash flood prone area is re-evaluated, and the risk level is determined according to the new spatiotemporal sensitivity threshold. When there is a potential flash flood risk in the flash flood prone area, the spatiotemporal sensitivity threshold of the flash flood prone area is intelligently adjusted. The dynamic adjustment expression of the new spatiotemporal sensitivity threshold is: ,in: is the spatiotemporal response adjustment factor, which is used to control the dynamic amplification of the spatiotemporal sensitivity threshold when the flash flood risk changes. The adjusted spatiotemporal sensitivity threshold is dynamically improved based on the impact of the deviation between the flash flood risk index and the flash flood risk index reference threshold, thereby enhancing the response capacity to flash flood risks.

7. The method for dynamic estimation of watershed hydrological model parameters based on digital twin technology according to claim 4 is characterized in that: For each flash flood prone area, during the monitoring period, the specific steps of deeply analyzing and processing the rise and fall of water levels in the basin through feature engineering technology to generate water level fluctuation reference values ​​are as follows: For each time window , the water level change amplification factor is introduced to identify the severity of water level changes in each time window. The calculation expression of the water level change amplification factor is: ,in: Represents the water level change amplification factor, which is used to quantify the intensity of water level fluctuations within the time window. It is j The water level value corresponding to the timestamp, is a parameter that controls the sensitivity of water level fluctuations and the degree of weighting of the control changes. It is the time window The number of data points in is the water level value at the previous time point; After completing the calculation of the water level fluctuation increase in each time window, the water level fluctuation reference value is further generated through local anomaly measurement. It is used to measure the deviation of water level change in each time window from the overall trend and local anomaly measurement. Defined as: ,in: is the predicted water level value obtained using the local weighted regression model, is a parameter that controls the sensitivity of the anomaly measure; The final water level fluctuation reference value is obtained by combining the abnormal measurement of each time window with the water level change increase factor for weighted calculation. The calculation expression of the water level fluctuation reference value is: ,in: is the reference value of water level fluctuation, is the weight factor, which is used to weight the fluctuations in each time window. i Indicates the monitoring period i time windows, that is, the basin water level data is divided into multiple time windows during the monitoring period. m Indicates the total number of time windows divided during the entire monitoring period, that is, the entire monitoring period is divided into m time window.

8. The method for dynamic estimation of watershed hydrological model parameters based on digital twin technology according to claim 4 is characterized in that: For each flash flood prone area, during the monitoring period, the frequency and magnitude of flow changes in the basin are deeply analyzed and processed by feature engineering technology to generate flow change reference values. The specific steps are as follows: Perform high-order moment analysis on flow data to reveal complex patterns and abnormal fluctuations in flow changes, using skewness in high-order moments and Kurtosis To capture the asymmetry and extreme volatility of traffic distribution, skewness and Kurtosis The specific calculation formula is as follows: ,in: For the k The flow rate at the moment, is the mean flow rate, is the standard deviation of the flow rate, n is the total number of samples of the data; The complexity of traffic fluctuations is evaluated by fractal dimension. Fractal dimension is used to describe the self-similarity and complexity of traffic curves. It is a method to measure the details of traffic fluctuations. The fractal dimension of the traffic curve is calculated by the following formula: ,in: represents the fractal dimension, Indicated in scale The coverage number of the lower flow curve, that is, the level of detail of the flow change, is the scale parameter; Combined skewness , Kurtosis And fractal dimension The analysis results are used to calculate the flow change reference value. The calculation expression is: ,in: It represents the reference value of flow change, and comprehensively measures the change characteristics of flow by combining skewness, kurtosis and fractal dimension.

Images