A method for constructing a large hydrological model integrating multi-source fusion and dynamic optimization

Abstract

The present invention relates to the field of data processing and prediction technology, and in particular to a method for constructing a large hydrological model that integrates multi-source fusion and dynamic optimization. The method comprises the following steps: acquiring hydrological monitoring data; performing data preprocessing on the hydrological monitoring data to obtain standard hydrological monitoring data; performing multidimensional feature recognition on the standard hydrological monitoring data to obtain multidimensional hydrological characteristic data; performing runoff feature extraction on the multidimensional hydrological characteristic data to obtain hydrological runoff characteristic data. The present invention uses data processing technology, pattern recognition technology, geographic information system technology and deep learning technology to evaluate the impact of seasonal changes on hydrological monitoring data; and realizes dynamic optimization of the hydrological monitoring model based on hydrological geographical location information and hydrological change assessment data, so that the response speed of the hydrological monitoring model is faster and the prediction result is more accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing and prediction, and in particular to a method for constructing a large hydrological model integrating multi-source fusion and dynamic optimization. Background Art

[0002] Hydrological statistics is an important tool for quantitative hydrological research, and can play an important role in hydrological situation prediction, water resources evaluation and management, and comprehensive system planning. In the early days of hydrological statistics, researchers collected hydrological information through hydrological monitoring stations, constructed river basin hydrological models according to historical hydrological conditions, and analyzed and judged the river basin hydrological conditions based on the researchers' experience. With the application of remote sensing technology and water cycle tracing technology in the field of hydrological analysis, the monitoring and prevention of hydrological conditions have been enhanced. However, hydrological monitoring data are massive, multidimensional, and complex. Current hydrological analysis methods fail to evaluate the impact of seasonal changes on hydrological monitoring data. In addition, it is difficult to dynamically optimize the hydrological monitoring model based on hydrological geographic location information and hydrological change assessment data, resulting in slow response of the hydrological monitoring model and low accuracy of prediction results. Summary of the invention

[0003] Based on this, it is necessary to provide a method for constructing a large hydrological model that integrates multi-source fusion and dynamic optimization to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a method for constructing a large hydrological model integrating multi-source fusion and dynamic optimization is provided, the method comprising the following steps:

[0005] Step S1: acquiring hydrological monitoring data; performing data preprocessing on the hydrological monitoring data to obtain standard hydrological monitoring data; performing multidimensional feature recognition on the standard hydrological monitoring data to obtain multidimensional hydrological feature data;

[0006] Step S2: extracting runoff characteristics from the multi-dimensional hydrological characteristic data to obtain hydrological runoff characteristic data; calculating river network density from the hydrological runoff characteristic data to generate hydrological river network density data; identifying hydrological topography and geomorphology from the hydrological river network density data to generate hydrological topography and geomorphology characteristic data; determining the geographical location of the hydrological topography and geomorphology characteristic data using geographic information system technology to obtain hydrological geographical location information;

[0007] Step S3: monitor the runoff change of the hydrological runoff characteristic data to obtain runoff change data; perform seasonal analysis on the runoff change data based on the hydrological geographical location information to generate hydrological seasonal change data; perform hydrological impact assessment on the hydrological seasonal change data to obtain hydrological impact assessment data; perform multi-source correlation analysis on the hydrological geographical location information and the hydrological change assessment data to obtain hydrological multi-source correlation data;

[0008] Step S4: construct a hydrological monitoring model using hydrological multi-source correlation data to obtain a hydrological monitoring model; dynamically optimize the hydrological monitoring model to obtain a hydrological monitoring early warning model; predict hydrological conditions based on the hydrological monitoring data based on the hydrological monitoring early warning model to generate a hydrological condition prediction report; detect hydrological anomalies in the hydrological condition prediction report based on the hydrological monitoring early warning model to generate hydrological anomaly detection data; upload the hydrological condition prediction report and hydrological anomaly detection data to the blockchain network distributed storage to perform intelligent hydrological monitoring operations.

[0009] The present invention first obtains hydrological monitoring data to ensure comprehensive acquisition of hydrological conditions; pre-processes the hydrological monitoring data and converts it into standard hydrological monitoring data, thereby improving the availability and accuracy of the data; further performs multi-dimensional feature recognition on the standard hydrological monitoring data, thereby providing a data basis for subsequent in-depth analysis of hydrological characteristics; performs runoff feature extraction on the multi-dimensional hydrological characteristic data, thereby being able to identify and analyze key features of hydrological runoff; performs river network density measurement on the hydrological runoff characteristic data, thereby helping to evaluate the distribution and density of the river network; performs hydrological topography and geomorphology recognition on the hydrological river network density data, thereby clarifying the impact of topography and geomorphology on hydrological characteristics; utilizes geographic information system technology to determine the geographical location of the hydrological topography and geomorphology characteristic data, thereby providing accurate data support for the spatial positioning of the hydrological characteristics; performs runoff change monitoring on the hydrological runoff characteristic data, thereby tracking and monitoring the dynamic changes of the runoff; performs seasonal analysis on the runoff change data based on the hydrological geographical location information, thereby helping to identify the seasons The hydrological change pattern is analyzed; the hydrological impact assessment is conducted on the hydrological seasonal change data to clarify the impact of hydrological changes on the environment; the multi-source correlation analysis of hydrological geographical location information and hydrological change assessment data can comprehensively analyze the correlation between hydrological characteristics and geographical location; the hydrological monitoring model is constructed using hydrological multi-source correlation data to obtain the hydrological monitoring model, which provides a scientific analysis model for hydrological monitoring; the hydrological monitoring model is dynamically optimized to improve the timeliness and early warning capabilities of hydrological monitoring; the hydrological situation is predicted based on the hydrological monitoring data based on the hydrological monitoring and early warning model, providing predictive information for hydrological management and decision-making; the hydrological anomaly detection is performed on the hydrological situation prediction report based on the hydrological monitoring and early warning model to ensure timely discovery and response to hydrological anomalies; the hydrological situation prediction report and hydrological anomaly detection data are uploaded to the blockchain network distributed storage to perform intelligent hydrological monitoring operations, ensuring the security and transparency of the data, while improving the efficiency and reliability of hydrological monitoring operations. Therefore, the present invention evaluates the impact of seasonal changes on hydrological monitoring data through data processing technology, pattern recognition technology, geographic information system technology and deep learning technology; and dynamically optimizes the hydrological monitoring model according to the hydrological geographical location information and hydrological change assessment data, so that the response speed of the hydrological monitoring model is faster and the prediction result is more accurate.

[0010] Preferably, step S2 comprises the following steps:

[0011] Step S21: marking the multi-dimensional hydrological characteristic data into river sections to generate river section data; identifying the river sections of the river section data to generate river section data; extracting the runoff characteristics of the multi-dimensional hydrological characteristic data based on the river section data and the river section data to obtain the hydrological runoff characteristic data;

[0012] Step S22: using the river segmentation data to measure the length of the segmented river on the hydrological runoff characteristic data, to obtain the river segmentation length data; using the river cross-section data to measure the river basin area on the hydrological runoff characteristic data, to generate the river basin area data; using the river segmentation length data and the river basin area data to calculate the river network density, to generate the hydrological river network density data;

[0013] Step S23: Perform hydrological topography and geomorphic recognition on the hydrological river network density data to generate hydrological topography and geomorphic feature data;

[0014] Step S24: perform terrain classification on the hydrological topography and geomorphological feature data to obtain terrain and geomorphological type data; perform terrain spatial area detection on the terrain and geomorphological type data to generate terrain spatial area data; use geographic information system technology to perform geographic coordinate annotation on the terrain spatial area data to obtain terrain spatial geographic coordinates; determine the geographical location of the hydrological topography and geomorphological feature data based on the terrain spatial geographic coordinates to obtain hydrological geographical location information.

[0015] The present invention performs river segmentation marking on multi-dimensional hydrological characteristic data, and can distinguish the hydrological characteristics of different river sections; performs river section identification on river segmentation data, so as to reveal the cross-sectional characteristics of the river; extracts runoff characteristics from multi-dimensional hydrological characteristic data based on river segmentation data and river section data, and provides key information for understanding and predicting the runoff changes of rivers; uses river segmentation data to calculate the length of segmented rivers on hydrological runoff characteristic data, and clarifies the specific length distribution of rivers; uses river section data to measure the river basin area on hydrological runoff characteristic data, and calculates the river network density, which provides a basis for evaluating the density of river networks. Quantitative indicators; hydrological topography and geomorphology identification is performed on hydrological river network density data, which can identify and classify the topography and geomorphology characteristics of the river basin; topography and geomorphology classification is performed on hydrological topography and geomorphology feature data, which is helpful for systematic classification of topography and geomorphology; terrain spatial area detection is performed on terrain and geomorphology type data, which can identify the spatial distribution of different terrain and geomorphology; geographic information system technology is used to mark the geographic coordinates of terrain spatial area data, and the geographical location of hydrological topography and geomorphology feature data is determined based on the terrain spatial geographic coordinates, ensuring the accurate correspondence between hydrological feature data and actual geographical location, and providing reliable geographic information for hydrological monitoring and analysis.

[0016] Preferably, step S23 includes the following steps:

[0017] Step S231: identifying the river network shape characteristics of the hydrological river network density data to obtain river network shape characteristic data; determining the water flow direction of the hydrological river network density data according to the river network shape characteristic data to generate river flow direction data; monitoring the flow velocity of the river flow direction data to obtain river flow velocity data;

[0018] Step S232: performing hydrological vegetation coverage terrain recognition on the multi-dimensional hydrological characteristic data based on the river network shape characteristic data and the river flow direction data to generate hydrological vegetation coverage terrain data;

[0019] Step S233: determining the hydrological topographic drop of the multi-dimensional hydrological characteristic data based on the river flow direction data and the river flow velocity data, and generating hydrological topographic drop data;

[0020] Step S234: identifying landform fluctuation characteristics according to the hydrological vegetation coverage landform data and the hydrological landform drop data to obtain hydrological landform fluctuation characteristic data; determining the fluctuation degree of the hydrological landform fluctuation characteristic data to generate hydrological landform fluctuation degree data;

[0021] Step S235: using the hydro-geomorphic fluctuation degree data to identify the geomorphic fluctuation rock layer structure of the hydro-geomorphic drop data, and obtaining the fluctuation rock layer structure data; performing hydro-fault geological extraction on the fluctuation rock layer structure data, and generating hydro-fault geological data;

[0022] Step S236: merge the hydrological vegetation coverage terrain data, the hydrological terrain drop data, the hydrological geomorphic fluctuation degree data and the hydrological fault geological data to obtain the hydrological terrain and geomorphic characteristic data.

[0023] The present invention identifies the shape characteristics of the river network based on the hydrological river network density data, and clarifies the morphological characteristics of the river network; determines the water flow direction of the hydrological river network density data based on the river network shape characteristic data, and monitors the flow velocity of the river flow direction data, thereby obtaining the river flow velocity data; identifies the hydrological vegetation coverage terrain based on the river network shape characteristic data and the river flow direction data, and can analyze the vegetation coverage in the river basin and its influence on the hydrological characteristics; determines the hydrological terrain difference based on the river flow direction data and the river flow velocity data, so as to identify the terrain height difference in the river basin; and identifies the hydrological vegetation coverage terrain data and the hydrological terrain difference data based on the hydrological vegetation coverage terrain data and the hydrological terrain difference data. The terrain undulation characteristics are identified based on the data to clarify the complexity and changes of the terrain; the degree of undulation of the hydro-geomorphological undulation characteristic data is measured to quantify the terrain undulation value; the geomorphological undulation rock structure is identified through the hydro-geomorphological undulation degree data on the hydro-topographic drop data, so that the influence of the terrain structure on the water flow can be analyzed; the hydro-fault geology is extracted from the undulating rock structure data to identify the geological faults and their influence on the hydrological characteristics; the hydro-vegetation coverage terrain data, the hydro-topographic drop data, the hydro-geomorphological undulation degree data and the hydro-fault geology data are merged for hydro-topography and geomorphology, which integrates a variety of terrain and geomorphological information and provides a data basis for the hydro-topography and geomorphology for subsequent hydrological analysis.

[0024] Preferably, step S3 comprises the following steps:

[0025] Step S31: identifying the runoff flow state of the hydrological runoff characteristic data to obtain the runoff flow state data; recording the water level of the runoff flow state data to generate the water level data; calculating the difference between the water level of ...

[0026] Step S32: monitoring the hydrological annual change of the hydrological runoff characteristic data according to the flood and dry water level difference data to generate hydrological annual change data; calculating the runoff change of the hydrological annual change data to obtain runoff change data;

[0027] Step S33: performing monthly change statistics on the runoff change data to obtain the runoff monthly change data; performing seasonal division on the runoff monthly change data based on the hydrological geographical location information to generate the runoff seasonal change data; performing seasonal water level feature extraction on the runoff seasonal change data to obtain seasonal water level feature data; performing seasonal change identification on the runoff change data according to the seasonal water level feature data to generate the hydrological seasonal change data;

[0028] Step S34: Performing hydrological impact assessment on the hydrological seasonal variation data to obtain hydrological impact assessment data;

[0029] Step S35: Perform multi-source correlation analysis on the hydrological geographical location information and the hydrological change assessment data to obtain hydrological multi-source correlation data.

[0030] The present invention identifies the wet and dry state of runoff on hydrological runoff characteristic data, and can distinguish the water volume conditions of rivers in different time periods; records the wet and dry state water level of runoff wet and dry state data, and provides a direct record for monitoring the change of river water level; calculates the wet and dry water level difference of the wet and dry state water level data, and clarifies the numerical information of the seasonal change amplitude of the river water level; monitors the hydrological annual change of hydrological runoff characteristic data according to the wet and dry water level difference data, and clarifies the change trend of the river within one year; calculates the runoff change of the hydrological annual change data, and can quantify the change of the annual runoff of the river; performs monthly change statistics on the runoff change data, and divides the monthly runoff change data into seasons based on the hydrological geographical location information, and can identify the seasonal hydrological pattern of a specific area; extracts seasonal water level characteristics from the seasonal change data of the runoff, and identifies the seasonal change of the runoff change data according to the seasonal water level characteristic data, thereby obtaining hydrological seasonal change data and revealing the seasonal hydrological change. Conducting hydrological impact assessment on hydrological seasonal change data helps to evaluate the impact of seasonal hydrological changes and provides important information for water resources management and disaster prevention. Multi-source correlation analysis of hydrological geographic location information and hydrological change assessment data integrates information on geographic location and hydrological changes, providing multi-dimensional data support for predicting hydrological changes and enhancing the accuracy and effectiveness of the hydrological monitoring and early warning system.

[0031] Preferably, step S34 includes the following steps:

[0032] Step S341: performing seasonal pattern recognition on the hydrological seasonal variation data to obtain seasonal pattern data; recording the precipitation frequency of the seasonal pattern data to generate seasonal precipitation frequency data; and performing seasonal precipitation monitoring on the seasonal pattern data in combination with the seasonal precipitation frequency data to obtain seasonal precipitation data;

[0033] Step S342: extract seasonal water level peak and valley values ​​from seasonal precipitation data to generate seasonal water level peak and valley values; match seasonal water level rise and fall values ​​with seasonal water level rise and fall values ​​to generate seasonal water level rise and fall data; evaluate seasonal precipitation impact on hydrological seasonal change data based on seasonal water level rise and fall data to obtain seasonal precipitation impact data;

[0034] Step S343: seasonal temperature monitoring is performed on the seasonal pattern data to generate seasonal temperature data; temperature range measurement is performed on the seasonal temperature data to obtain seasonal temperature range data; water temperature measurement is performed on the hydrological seasonal change data according to the seasonal temperature range data to generate seasonal water temperature data;

[0035] Step S344: extracting the water surface freezing temperature from the seasonal water temperature data to obtain water surface freezing temperature information; recording the water surface freezing period of the hydrological seasonal change data according to the water surface freezing temperature information to generate seasonal hydrological freezing period data; performing seasonal hydrological flow monitoring on the seasonal hydrological freezing period data to obtain freezing period hydrological flow data; performing freezing period impact assessment on the hydrological seasonal change data based on the freezing period hydrological flow data to obtain freezing period impact data;

[0036] Step S345: Combine the seasonal precipitation impact data and the freezing period impact data for hydrological impact assessment to generate hydrological impact assessment data.

[0037] The present invention performs seasonal pattern recognition on hydrological seasonal variation data to clarify the periodic laws of hydrological variation; records precipitation frequency on seasonal pattern data to provide data support for monitoring the frequency of precipitation events; performs seasonal precipitation monitoring on seasonal pattern data in combination with seasonal precipitation frequency data to provide quantitative information for evaluating seasonal variation of precipitation; extracts seasonal water level peak and valley values ​​on seasonal precipitation data to help identify seasonal highest and lowest points of water level; matches seasonal water level peak and valley values ​​with seasonal water level rise and fall to reveal seasonal variation trends of water level; performs seasonal precipitation impact assessment on hydrological seasonal variation data based on seasonal water level rise and fall data to assess the degree of impact of precipitation on water level; performs seasonal temperature monitoring on seasonal pattern data to clarify the seasonality of temperature. The system can also be used to monitor the temperature of hydrological seasonal change data and provide data support for evaluating the amplitude of temperature change; measure the water temperature of hydrological seasonal change data based on seasonal temperature range data, and provide important information for monitoring water temperature change; extract the water surface freezing temperature from seasonal water temperature data, and record the water surface freezing period of hydrological seasonal change data based on the water surface freezing temperature information to clarify the river freezing period; conduct seasonal hydrological flow monitoring on seasonal hydrological freezing period data, and conduct freezing period impact assessment on hydrological seasonal change data based on freezing period hydrological flow data, which provides a scientific basis for evaluating the impact of freezing period on hydrology; combine seasonal precipitation impact data and freezing period impact data for hydrological impact assessment, and provide comprehensive assessment data for hydrological monitoring and disaster prevention.

[0038] Preferably, step S35 includes the following steps:

[0039] Step S351: Identify the regional precipitation type based on the hydrological geographic location information to obtain regional precipitation type data; determine the precipitation period based on the regional precipitation type data to generate regional precipitation period data;

[0040] Step S352: mapping seasonal precipitation period changes on seasonal precipitation influence data based on regional precipitation period data to obtain seasonal precipitation period mapping data; calculating precipitation period duration on seasonal precipitation period mapping data to generate precipitation period duration data; associating precipitation influence time with seasonal precipitation influence data to obtain precipitation influence time association data;

[0041] Step S353: monitoring the regional temperature conditions based on the hydrological geographic location information to obtain regional temperature condition data; determining the regional temperature distribution state based on the regional temperature condition data to generate regional temperature distribution state data;

[0042] Step S354: Correlate the freezing period influencing data with the temperature distribution of the river section freezing period according to the regional temperature distribution data to obtain freezing period temperature correlation data;

[0043] Step S355: Perform multi-source correlation analysis on the precipitation impact time correlation data and the freezing period temperature correlation data to obtain hydrological multi-source correlation data.

[0044] The present invention identifies regional precipitation types based on hydrological geographic location information, so as to distinguish precipitation characteristics in different regions; determines precipitation time periods based on regional precipitation type data, and provides time information for identifying specific time periods when precipitation occurs; maps seasonal precipitation time period changes to seasonal precipitation influence data based on regional precipitation time period data, so as to clarify the changing rules of precipitation in different seasons; measures the duration of precipitation periods based on seasonal precipitation time period mapping data, and provides quantitative data for evaluating the continuous impact of precipitation events; correlates precipitation time period duration data with seasonal precipitation influence data, thereby obtaining precipitation influence time correlation data ; Monitor regional temperature conditions based on hydrological geographic location information to clarify temperature changes in different regions; determine regional temperature distribution status based on regional temperature condition data to reveal the spatial distribution of temperature; correlate freezing period influencing data with river freezing period temperature distribution based on regional temperature distribution status data, which helps to evaluate the impact of temperature on river freezing period and provides key information for subsequent hydrological monitoring and prediction; conduct multi-source correlation analysis on precipitation impact time correlation data and freezing period temperature correlation data to obtain hydrological multi-source correlation data, which integrates the impact of precipitation and temperature on the hydrological system and provides comprehensive evaluation data for hydrological monitoring and disaster prevention.

[0045] Preferably, step S4 comprises the following steps:

[0046] Step S41: constructing a hydrological monitoring model using hydrological multi-source associated data to obtain a hydrological monitoring model; recording hydrological real-time changes in the hydrological multi-source associated data to generate multi-source hydrological real-time change data; dynamically optimizing the hydrological monitoring model based on the multi-source hydrological real-time change data to obtain a hydrological monitoring early warning model;

[0047] Step S42: Based on the hydrological monitoring and early warning model, the hydrological monitoring data is subjected to hydrological condition prediction to obtain hydrological condition prediction data; the hydrological condition prediction data is subjected to data visualization to generate a hydrological condition prediction report;

[0048] Step S43: Perform hydrological anomaly detection on the hydrological situation forecast report based on the hydrological monitoring and early warning model to generate hydrological anomaly detection data;

[0049] Step S44: Perform early warning identification on the hydrological anomaly detection data to obtain hydrological anomaly warning information; upload the hydrological situation prediction data, hydrological anomaly detection data and hydrological anomaly warning information to the blockchain network distributed storage to perform intelligent hydrological monitoring operations.

[0050] The present invention uses hydrological multi-source associated data to construct a hydrological monitoring model to obtain a hydrological monitoring model, which provides a scientific analysis framework for hydrological monitoring; records real-time hydrological changes in hydrological multi-source associated data to ensure that the real-time dynamics of hydrological parameters are captured; dynamically optimizes the hydrological monitoring model based on multi-source hydrological real-time change data, so that the model can adapt to real-time data changes, thereby improving the accuracy and response speed of early warning; predicts hydrological conditions based on the hydrological monitoring data based on the hydrological monitoring early warning model, which can provide prediction information for the hydrological conditions; visualizes the hydrological situation prediction data, making the prediction results more intuitive and easy to understand, and convenient for researchers to understand and use; based on the hydrological monitoring early warning model Hydrological anomaly detection is carried out on hydrological situation forecast reports, so that potential hydrological anomalies can be discovered in time, providing a basis for taking preventive measures; early warning identification is carried out on hydrological anomaly detection data to obtain hydrological anomaly warning information, which provides key information for early warning of hydrological disasters; hydrological situation forecast data, hydrological anomaly detection data and hydrological anomaly warning information are uploaded to the blockchain network distributed storage to perform intelligent hydrological monitoring operations, ensuring the security and transparency of the data, while improving the efficiency and reliability of hydrological monitoring operations; through the application of blockchain technology, the integrity and non-tamperability of hydrological monitoring data are guaranteed, providing a solid data foundation for water resources management and disaster prevention.

[0051] Preferably, step S41 includes the following steps:

[0052] Step S411: constructing a hydrological monitoring model according to the hydrological multi-source associated data to obtain a hydrological monitoring pre-model; and training the hydrological monitoring pre-model using the hydrological multi-source associated data to obtain a hydrological monitoring training model;

[0053] Step S412: performing model cross-validation evaluation on the hydrological monitoring training model to obtain hydrological monitoring training model evaluation data; adjusting model parameters of the hydrological monitoring training model using the hydrological monitoring training model evaluation data to obtain a hydrological monitoring model;

[0054] Step S413: Compare the hydrological change characteristics of the hydrological multi-source associated data with the hydrological monitoring data to obtain hydrological change characteristic data; record the hydrological real-time changes of the hydrological multi-source associated data based on the hydrological change characteristic data to generate multi-source hydrological real-time change data;

[0055] Step S414: extracting multi-source change features from multi-source hydrological real-time change data to obtain multi-source change feature data; performing multi-source change incremental updates on the hydrological monitoring model based on the multi-source change feature data to obtain multi-source incremental update information;

[0056] Step S415: abnormal hydrological changes are identified on the multi-source change feature data to generate multi-source abnormal hydrological change data; dynamic parameter optimization is performed on the hydrological monitoring model according to the multi-source abnormal hydrological change data and multi-source incremental update information to obtain a hydrological monitoring and early warning model.

[0057] The present invention constructs a hydrological monitoring model based on hydrological multi-source associated data to obtain a hydrological monitoring pre-model, which provides a preliminary analysis tool for hydrological monitoring; uses hydrological multi-source associated data to train the hydrological monitoring pre-model to obtain a hydrological monitoring training model, so that the model can learn the characteristics of historical data, providing a basis for subsequent prediction and early warning; performs model cross-validation evaluation on the hydrological monitoring training model, which helps to verify the accuracy and stability of the model; adjusts the model parameters of the hydrological monitoring training model through the evaluation data of the hydrological monitoring training model, optimizes the model performance, and improves the reliability of the monitoring results; compares the hydrological change characteristics of the hydrological multi-source associated data with the hydrological monitoring data, and can identify the change trend of the hydrological parameters. The system can record the real-time hydrological changes of multi-source related data based on the hydrological change characteristic data, providing detailed data support for real-time monitoring of hydrological changes; extract multi-source change characteristics of multi-source hydrological real-time change data, which is helpful to deeply understand the complexity of hydrological changes; update the hydrological monitoring model with multi-source change increments based on multi-source change characteristic data, so that the model can adapt to new data and maintain the timeliness and accuracy of prediction; identify abnormal hydrological changes based on multi-source change characteristic data, and timely discover potential hydrological anomalies; dynamically optimize the parameters of the hydrological monitoring model according to the multi-source abnormal hydrological change data and multi-source incremental update information, which improves the model's response ability to abnormal situations and enhances the early warning function of hydrological monitoring.

[0058] Preferably, step S43 includes the following steps:

[0059] Step S431: Based on the hydrological monitoring and early warning model, the hydrological situation prediction is used to perform river runoff anomaly detection to obtain runoff anomaly data; the runoff anomaly data is used to calculate the hydrological runoff anomaly degree to generate hydrological runoff anomaly degree data;

[0060] Step S432: Based on the hydrological monitoring and early warning model, the hydrological situation prediction is subjected to river freezing period anomaly detection to obtain freezing period anomaly data; the freezing period anomaly data is subjected to hydrological freezing period anomaly cycle calculation to generate hydrological freezing period anomaly cycle data;

[0061] Step S433: performing hydrological seasonal change anomaly detection on the hydrological situation forecast according to the hydrological runoff abnormality degree data and the hydrological freezing period abnormality period data to obtain seasonal change abnormality data; performing seasonal abnormality duration measurement on the seasonal change abnormality data to generate the hydrological seasonal abnormality duration;

[0062] Step S434: The hydrological runoff abnormality degree data, the hydrological freezing period abnormality cycle data and the hydrological seasonal abnormality duration data are combined to generate hydrological anomaly detection data.

[0063] The present invention performs abnormal detection of river runoff on hydrological situation prediction based on a hydrological monitoring and early warning model, and can identify abnormal changes in river runoff; performs hydrological runoff abnormality degree calculation on runoff abnormality data, and provides a quantitative index for evaluating the severity of runoff abnormality; performs abnormal detection of river freezing period on hydrological situation prediction based on a hydrological monitoring and early warning model, and can discover abnormal situations during the freezing period of the river; performs abnormal cycle calculation of hydrological freezing period on abnormal freezing period data, and provides accurate data for determining the specific time period of abnormal freezing period; performs abnormal detection of hydrological seasonal changes on hydrological situation prediction based on hydrological runoff abnormality degree data and hydrological freezing period abnormal cycle data, and clarifies abnormal patterns in seasonal hydrological changes; performs seasonal abnormal duration measurement on seasonal change abnormal data, and provides data of time dimension for evaluating the continuous impact of seasonal abnormal events; performs hydrological abnormality merging of hydrological runoff abnormality degree data, hydrological freezing period abnormal cycle data and hydrological seasonal abnormal duration, and can integrate a variety of hydrological abnormal information, and provide detailed data support for comprehensively evaluating hydrological abnormal events, thereby enhancing the early warning capability of hydrological monitoring and the capability of responding to abnormal events.

[0064] Preferably, step S44 includes the following steps:

[0065] Step S441: marking the hydrological anomaly detection data with a hydrological anomaly type to generate hydrological anomaly type marking data; classifying the hydrological anomaly detection data into anomaly types based on the hydrological anomaly type marking data to obtain hydrological anomaly type data; extracting the anomaly degree from the hydrological anomaly type data to generate hydrological anomaly degree data;

[0066] Step S442: generating hydrological early warning information according to the hydrological anomaly type data and the hydrological anomaly degree data to obtain hydrological anomaly warning information;

[0067] Step S443: Use blockchain technology to upload hydrological situation prediction data, hydrological anomaly detection data and hydrological anomaly warning information to blockchain nodes, and distribute and store hydrological situation prediction data, hydrological anomaly detection data and hydrological anomaly warning information through blockchain nodes to perform intelligent hydrological monitoring operations.

[0068] The present invention marks the hydrological anomaly type of the hydrological anomaly detection data, and divides the hydrological anomaly detection data into anomaly types based on the hydrological anomaly type marking data, so as to clarify the hydrological anomaly type information; extracts the anomaly degree of the hydrological anomaly type data, and provides quantitative data support for evaluating the severity of the abnormal event; generates hydrological early warning information according to the hydrological anomaly type data and the hydrological anomaly degree data, so that the early warning information is more targeted and accurate, which helps to take countermeasures in time, thereby reducing the impact of hydrological abnormal events; uses blockchain technology to upload hydrological situation prediction data, hydrological anomaly detection data and hydrological anomaly warning information to blockchain nodes, and distributes and stores these data through blockchain nodes to perform intelligent hydrological monitoring operations; ensures the security, transparency and non-tamperability of the data, improves the efficiency and reliability of data management, and at the same time provides a decentralized data storage solution for hydrological monitoring, thereby enhancing the robustness and trustworthiness of the hydrological monitoring system. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 A schematic diagram of the steps of a method for constructing a large hydrological model integrating multi-source fusion and dynamic optimization;

[0070] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0071] Figure 3 for Figure 2 Detailed implementation steps of step S23;

[0072] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0073] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0074] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0075] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0076] To achieve this, please refer to Figures 1 to 3 , a method for constructing a large hydrological model integrating multi-source fusion and dynamic optimization, the method comprising the following steps:

[0077] Step S1: acquiring hydrological monitoring data; performing data preprocessing on the hydrological monitoring data to obtain standard hydrological monitoring data; performing multidimensional feature recognition on the standard hydrological monitoring data to obtain multidimensional hydrological feature data;

[0078] Step S2: extracting runoff characteristics from the multi-dimensional hydrological characteristic data to obtain hydrological runoff characteristic data; calculating river network density from the hydrological runoff characteristic data to generate hydrological river network density data; identifying hydrological topography and geomorphology from the hydrological river network density data to generate hydrological topography and geomorphology characteristic data; determining the geographical location of the hydrological topography and geomorphology characteristic data using geographic information system technology to obtain hydrological geographical location information;

[0079] Step S3: monitor the runoff change of the hydrological runoff characteristic data to obtain runoff change data; perform seasonal analysis on the runoff change data based on the hydrological geographical location information to generate hydrological seasonal change data; perform hydrological impact assessment on the hydrological seasonal change data to obtain hydrological impact assessment data; perform multi-source correlation analysis on the hydrological geographical location information and the hydrological change assessment data to obtain hydrological multi-source correlation data;

[0080] Step S4: construct a hydrological monitoring model using hydrological multi-source correlation data to obtain a hydrological monitoring model; dynamically optimize the hydrological monitoring model to obtain a hydrological monitoring early warning model; predict hydrological conditions based on the hydrological monitoring data based on the hydrological monitoring early warning model to generate a hydrological condition prediction report; detect hydrological anomalies in the hydrological condition prediction report based on the hydrological monitoring early warning model to generate hydrological anomaly detection data; upload the hydrological condition prediction report and hydrological anomaly detection data to the blockchain network distributed storage to perform intelligent hydrological monitoring operations.

[0081] The present invention first obtains hydrological monitoring data to ensure comprehensive acquisition of hydrological conditions; pre-processes the hydrological monitoring data and converts it into standard hydrological monitoring data, thereby improving the availability and accuracy of the data; further performs multi-dimensional feature recognition on the standard hydrological monitoring data, thereby providing a data basis for subsequent in-depth analysis of hydrological characteristics; performs runoff feature extraction on the multi-dimensional hydrological characteristic data, thereby being able to identify and analyze key features of hydrological runoff; performs river network density measurement on the hydrological runoff characteristic data, thereby helping to evaluate the distribution and density of the river network; performs hydrological topography and geomorphology recognition on the hydrological river network density data, thereby clarifying the impact of topography and geomorphology on hydrological characteristics; utilizes geographic information system technology to determine the geographical location of the hydrological topography and geomorphology characteristic data, thereby providing accurate data support for the spatial positioning of the hydrological characteristics; performs runoff change monitoring on the hydrological runoff characteristic data, thereby tracking and monitoring the dynamic changes of the runoff; performs seasonal analysis on the runoff change data based on the hydrological geographical location information, thereby helping to identify the seasons The hydrological change pattern is analyzed; the hydrological impact assessment is conducted on the hydrological seasonal change data to clarify the impact of hydrological changes on the environment; the multi-source correlation analysis of hydrological geographical location information and hydrological change assessment data can comprehensively analyze the correlation between hydrological characteristics and geographical location; the hydrological monitoring model is constructed using hydrological multi-source correlation data to obtain the hydrological monitoring model, which provides a scientific analysis model for hydrological monitoring; the hydrological monitoring model is dynamically optimized to improve the timeliness and early warning capabilities of hydrological monitoring; the hydrological situation is predicted based on the hydrological monitoring data based on the hydrological monitoring and early warning model, providing predictive information for hydrological management and decision-making; the hydrological anomaly detection is performed on the hydrological situation prediction report based on the hydrological monitoring and early warning model to ensure timely discovery and response to hydrological anomalies; the hydrological situation prediction report and hydrological anomaly detection data are uploaded to the blockchain network distributed storage to perform intelligent hydrological monitoring operations, ensuring the security and transparency of the data, while improving the efficiency and reliability of hydrological monitoring operations. Therefore, the present invention evaluates the impact of seasonal changes on hydrological monitoring data through data processing technology, pattern recognition technology, geographic information system technology and deep learning technology; and dynamically optimizes the hydrological monitoring model according to the hydrological geographical location information and hydrological change assessment data, so that the response speed of the hydrological monitoring model is faster and the prediction result is more accurate.

[0082] In the embodiment of the present invention, reference Figure 1 The above is a schematic diagram of the steps of a method for constructing a hydrological model integrating multi-source fusion and dynamic optimization of the present invention. In this example, the method for constructing a hydrological model integrating multi-source fusion and dynamic optimization includes the following steps:

[0083] Step S1: acquiring hydrological monitoring data; performing data preprocessing on the hydrological monitoring data to obtain standard hydrological monitoring data; performing multidimensional feature recognition on the standard hydrological monitoring data to obtain multidimensional hydrological feature data;

[0084] In an embodiment of the present invention, satellite remote sensing technology is used to obtain information such as precipitation, temperature and vegetation coverage in the watershed; real-time hydrological data, including flow, water level and water quality, are obtained from ground monitoring stations; Python programming language is used in conjunction with the Pandas library to perform data preprocessing on the hydrological monitoring data; specifically, the dropna() function is used to remove missing values, and the drop_duplicates() function is used to delete duplicate records; in order to eliminate the influence of different dimensions, it is also necessary to perform data standardization processing on the hydrological monitoring data, and finally obtain standard hydrological monitoring data; machine learning algorithms, such as random forests, are used to extract features and recognize patterns from the data; further, deep learning technology, especially recurrent neural networks (RNNs), is used to conduct in-depth analysis of time series data, specifically capturing the dynamic changes of hydrological processes, thereby generating multidimensional hydrological feature data.

[0085] Step S2: extracting runoff characteristics from the multi-dimensional hydrological characteristic data to obtain hydrological runoff characteristic data; calculating river network density from the hydrological runoff characteristic data to generate hydrological river network density data; identifying hydrological topography and geomorphology from the hydrological river network density data to generate hydrological topography and geomorphology characteristic data; determining the geographical location of the hydrological topography and geomorphology characteristic data using geographic information system technology to obtain hydrological geographical location information;

[0086] In the embodiment of the present invention, geographic information system (GIS) software, such as a hydrological analysis tool, is used to process multidimensional hydrological characteristic data; specifically, the flow direction and flow accumulation value of each grid unit are calculated through the flow direction and flow accumulation function of the hydrological analysis tool, and the hydrological runoff characteristic data are extracted; the fishnet creation function of the GIS software is used to create a regular grid coverage area, and an appropriate grid size (for example, 1 km) is set; then, the river network water system data is intersected with the grid using the intersection function, and the river network in each grid is marked; each grid is mapped using the attribute table function The total length of the river network within the grid is counted, and the area of ​​each grid is calculated; finally, the hydrological river network density data is calculated using the formula (total length of the river network / grid area); by analyzing the daily runoff data, the respective multi-year average runoff is calculated, and the macro- and micro-scale terrain factors of the basin and the water system morphology indicators are analyzed to generate hydrological topography and geomorphological characteristic data; GIS technology is used to determine the geographical location of the hydrological topography and geomorphological characteristic data; specifically, through the mapping function of the GIS platform, hydrological maps are produced and the hydrological geographical location information is determined, and finally the hydrological geographical location information is obtained.

[0087] Step S3: monitor the runoff change of the hydrological runoff characteristic data to obtain runoff change data; perform seasonal analysis on the runoff change data based on the hydrological geographical location information to generate hydrological seasonal change data; perform hydrological impact assessment on the hydrological seasonal change data to obtain hydrological impact assessment data; perform multi-source correlation analysis on the hydrological geographical location information and the hydrological change assessment data to obtain hydrological multi-source correlation data;

[0088] In the embodiment of the present invention, monitoring technology is used to monitor the real-time runoff change of hydrological runoff characteristic data, specifically monitor the real-time hydrological status of the basin, and calculate the spatiotemporal change of runoff to generate runoff change data; based on the hydrological geographical location information, a time series analysis method, such as an autoregressive integrated moving average (ARIMA) model, is used to seasonally decompose the runoff change data; by analyzing the seasonal patterns and trends in the data, the runoff change characteristics of different seasons are specifically identified, thereby obtaining hydrological seasonal change data; combined with the hydrological seasonal change data, the impact of different hydrological conditions on phosphorus load is evaluated, specifically by simulating different The hydrological response under the land use and land cover change (LUCC) scenario is used to obtain the hydrological impact assessment data; the geographic information system (GIS) technology is used to perform spatial correlation analysis on the hydrological geographical location information and the hydrological impact assessment data; specifically, the multi-source data fusion pre-processing function of ArcGIS software is used to match the hydrological data with the land use remote sensing information to generate hydrological multi-source correlation data; this step involves the generation of sorting files for sub-basins, slope grids and river networks, as well as the generation of land use type files, ensuring that the multi-source data information can be accurately matched according to the location of each grid unit or sub-basin and the corresponding land use situation.

[0089] Step S4: construct a hydrological monitoring model using hydrological multi-source correlation data to obtain a hydrological monitoring model; dynamically optimize the hydrological monitoring model to obtain a hydrological monitoring early warning model; predict hydrological conditions based on the hydrological monitoring data based on the hydrological monitoring early warning model to generate a hydrological condition prediction report; detect hydrological anomalies in the hydrological condition prediction report based on the hydrological monitoring early warning model to generate hydrological anomaly detection data; upload the hydrological condition prediction report and hydrological anomaly detection data to the blockchain network distributed storage to perform intelligent hydrological monitoring operations.

[0090] In the embodiment of the present invention, the SWAT model is selected as the basic model, the SWAT model is trained using hydrological multi-source correlation data, and training options such as the maximum number of iterations, gradient threshold and initial learning rate are set; the time dependency between hydrological data is learned by the training model, thereby obtaining a hydrological monitoring model; the CMA-ES algorithm is used to dynamically optimize the hydrological monitoring model; CMA-ES is an effective parameter optimization algorithm that improves the prediction accuracy of the model by automatically adjusting the model parameters; in the model calibration process, 72 candidate solutions are set, and the optimal parameter combination is found through iterative evolution to obtain a hydrological monitoring and early warning model; based on the optimized hydrological monitoring and early warning model, the hydrological monitoring data is predicted; by simulating the basin response under different rainfall conditions; for example, for a specific For the river basin, the model is used to predict the flow and water level changes in the next week, thereby generating a detailed hydrological forecast report; the sliding window technology is used in combination with the hydrological monitoring and early warning model to perform anomaly detection on the hydrological forecast report, and by setting the window size and threshold, abnormal events that are significantly different from historical data are identified; for example, for the daily average water level and flow data, by comparing the actual observations with the model predictions, abnormal values ​​that deviate from the normal range are identified, and hydrological anomaly detection data are generated; the hydrological forecast report and hydrological anomaly detection data are uploaded to the blockchain network for distributed storage; blockchain technology provides a decentralized data storage solution to ensure the security and immutability of data; through smart contracts, the data upload and verification process is automatically executed to realize intelligent hydrological monitoring operations.

[0091] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes:

[0092] Step S21: marking the multi-dimensional hydrological characteristic data into river sections to generate river section data; identifying the river sections of the river section data to generate river section data; extracting the runoff characteristics of the multi-dimensional hydrological characteristic data based on the river section data and the river section data to obtain the hydrological runoff characteristic data;

[0093] Step S22: using the river segmentation data to measure the length of the segmented river on the hydrological runoff characteristic data, to obtain the river segmentation length data; using the river cross-section data to measure the river basin area on the hydrological runoff characteristic data, to generate the river basin area data; using the river segmentation length data and the river basin area data to calculate the river network density, to generate the hydrological river network density data;

[0094] Step S23: Perform hydrological topography and geomorphic recognition on the hydrological river network density data to generate hydrological topography and geomorphic feature data;

[0095] Step S24: perform terrain classification on the hydrological topography and geomorphological feature data to obtain terrain and geomorphological type data; perform terrain spatial area detection on the terrain and geomorphological type data to generate terrain spatial area data; use geographic information system technology to perform geographic coordinate annotation on the terrain spatial area data to obtain terrain spatial geographic coordinates; determine the geographical location of the hydrological topography and geomorphological feature data based on the terrain spatial geographic coordinates to obtain hydrological geographical location information.

[0096] In the embodiment of the present invention, remote sensing technology is combined with GIS technology to identify river sections, and characteristic information formed by river sections, such as watershed area, width-to-depth ratio and terrain slope, is specifically determined. The characteristic information formed by river sections is used to establish river section shape parameters, and the relationship between environmental factors and river section parameters is reconstructed to identify river sections. Based on river segmentation data and river section data, ArcGIS hydrological analysis tools, especially flow accumulation function, are used to extract runoff characteristics from multidimensional hydrological characteristic data. Based on river segmentation data, ArcGIS attribute table function is used to measure the river length of each segment. The geometric length of each segment is calculated to obtain river segment length data. According to the river section data, the river basin area of ​​the hydrological runoff characteristic data is measured to obtain river basin area data. The river segment length data and the river basin area data are used to calculate the river network density to obtain the hydrological river network density data. The terrain analysis tool of ArcGIS is used to identify the hydrological topography and landform of the hydrological river network density data. Identify different topographic and geomorphic features to obtain hydrological topographic and geomorphic feature data; classify the hydrological topographic and geomorphic feature data through feature classification technology; use ArcGIS software to detect the spatial area of ​​topographic and geomorphic type data, specifically, extract the spatial distribution areas of different landform types according to the topographic and geomorphic type data through the Extract Polygon function in ArcGIS's spatial analysis toolbox; then use the Extract Polygon tool to generate spatial area data of different landform types according to the topographic and geomorphic type attributes, that is, topographic spatial area data; use geographic information system (GIS) technology to mark the geographic coordinates of the topographic spatial area data; in ArcGIS, use the geocoding function to associate each topographic spatial area with its corresponding geographic coordinates; specifically input the boundaries or key points of the topographic spatial area, ArcGIS automatically matches and marks the corresponding longitude and latitude values, thereby obtaining the topographic spatial geographic coordinates; determine the geographical location of the hydrological topographic and geomorphic feature data based on the topographic spatial geographic coordinates to obtain hydrological geographical location information.

[0097] As an example of the present invention, refer to Figure 3 As shown, in this example, step S23 includes:

[0098] Step S231: identifying the river network shape characteristics of the hydrological river network density data to obtain river network shape characteristic data; determining the water flow direction of the hydrological river network density data according to the river network shape characteristic data to generate river flow direction data; monitoring the flow velocity of the river flow direction data to obtain river flow velocity data;

[0099] Step S232: performing hydrological vegetation coverage terrain recognition on the multi-dimensional hydrological characteristic data based on the river network shape characteristic data and the river flow direction data to generate hydrological vegetation coverage terrain data;

[0100] Step S233: determining the hydrological topographic drop of the multi-dimensional hydrological characteristic data based on the river flow direction data and the river flow velocity data, and generating hydrological topographic drop data;

[0101] Step S234: identifying landform fluctuation characteristics according to the hydrological vegetation coverage landform data and the hydrological landform drop data to obtain hydrological landform fluctuation characteristic data; determining the fluctuation degree of the hydrological landform fluctuation characteristic data to generate hydrological landform fluctuation degree data;

[0102] Step S235: using the hydro-geomorphic fluctuation degree data to identify the geomorphic fluctuation rock layer structure of the hydro-geomorphic drop data, and obtaining the fluctuation rock layer structure data; performing hydro-fault geological extraction on the fluctuation rock layer structure data, and generating hydro-fault geological data;

[0103] Step S236: merge the hydrological vegetation coverage terrain data, the hydrological terrain drop data, the hydrological geomorphic fluctuation degree data and the hydrological fault geological data to obtain the hydrological terrain and geomorphic characteristic data.

[0104] In an embodiment of the present invention, a method based on the Tokunaga network is used to quantify the morphological characteristics of the river network. The specific operations include counting the number of branches (RB) and the length ratio (RL) of the river, and calculating the fractal dimension (DT) and the shape parameter (D); finally obtaining the shape characteristic data of the river network; using the spatial analysis tool of ArcGIS to extract the water flow direction; calculating the water flow direction of each grid unit to generate the water flow direction data of the river channel; using electromagnetic flowmeter and radar flow monitoring technology to monitor the flow velocity, and the specific electromagnetic flowmeter is suitable for rivers with high sediment content, and can measure the flow velocity at different levels in the water body, while the radar flow monitoring calculates the water flow velocity by analyzing the frequency change of the reflected signal of the water surface; based on the shape characteristic data of the river network and the water flow direction data of the river channel, remote sensing technology and GIS technology are used to identify the hydrological vegetation coverage terrain; using the water flow direction data and the water velocity data of the river channel to determine the hydrological terrain drop; by analyzing the Based on the elevation change and flow velocity distribution, the terrain drop is calculated to obtain the hydrological terrain drop data; the landform undulation characteristics are identified according to the hydrological vegetation coverage terrain data and the hydrological terrain drop data, and the undulation characteristics of the landform are identified by analyzing the elevation change and vegetation coverage of the terrain; the degree of landform undulation is determined by calculating the elevation change rate and slope of the terrain; the landform undulation rock structure is identified by the hydrological terrain drop data through the hydrological terrain undulation degree data, and the elevation and structural characteristics of the terrain are analyzed using geological knowledge and GIS technology to identify the rock structure; the hydrological fault geology is extracted from the undulating rock structure data, and the fault geology characteristics are identified through geological analysis and GIS technology; the hydrological vegetation coverage terrain data, the hydrological terrain drop data, the hydrological geomorphic undulation degree data and the hydrological fault geology data are merged; these data layers are superimposed and analyzed using GIS technology to obtain comprehensive hydrological terrain and geomorphological characteristic data.

[0105] Preferably, step S3 comprises the following steps:

[0106] Step S31: identifying the runoff flow state of the hydrological runoff characteristic data to obtain the runoff flow state data; recording the water level of the runoff flow state data to generate the water level data; calculating the difference between the water level of ...

[0107] Step S32: monitoring the hydrological annual change of the hydrological runoff characteristic data according to the flood and dry water level difference data to generate hydrological annual change data; calculating the runoff change of the hydrological annual change data to obtain runoff change data;

[0108] Step S33: performing monthly change statistics on the runoff change data to obtain the runoff monthly change data; performing seasonal division on the runoff monthly change data based on the hydrological geographical location information to generate the runoff seasonal change data; performing seasonal water level feature extraction on the runoff seasonal change data to obtain seasonal water level feature data; performing seasonal change identification on the runoff change data according to the seasonal water level feature data to generate the hydrological seasonal change data;

[0109] Step S34: Performing hydrological impact assessment on the hydrological seasonal variation data to obtain hydrological impact assessment data;

[0110] Step S35: Perform multi-source correlation analysis on the hydrological geographical location information and the hydrological change assessment data to obtain hydrological multi-source correlation data.

[0111] In the embodiment of the present invention, a statistical method is used to determine the thresholds of the flood season and the dry season based on the historical runoff data (for example, the dry season is set to 70% of the runoff; the low season is set to 50% of the runoff); the flood and dry states of the runoff are identified by calculating the deviation between the annual runoff and the multi-year average runoff; the water level recorder of the hydrological station is used to record the water level data under different flood and dry states; the difference between the flood and dry water levels is specifically calculated by comparing the water level records of the flood season and the dry season; the cumulative anomaly method is used to analyze the trend of the runoff series changes, and the hydrological year changes are monitored; the runoff changes are measured for the hydrological year change data, so as to obtain the runoff change data; the monthly change statistics of the runoff change data are performed using statistical tools to obtain the monthly runoff The runoff monthly variation data are divided into seasons based on the hydrological geographical location information to obtain the runoff seasonal variation data; the seasonal water level characteristics are extracted from the runoff seasonal variation data using feature extraction technology to obtain the seasonal water level characteristic data; the seasonal variation of the runoff variation data is identified based on the seasonal water level characteristic data using pattern recognition technology to generate hydrological seasonal variation data; the hydrological impact assessment is performed on the hydrological seasonal variation data, specifically by analyzing the impact of runoff variation on agriculture, ecology and urban water supply, to obtain the hydrological impact assessment data; the hydrological geographical location information and the hydrological variation assessment data are analyzed for multi-source correlation through GIS technology and data fusion technology to obtain the hydrological multi-source correlation data.

[0112] Preferably, step S34 includes the following steps:

[0113] Step S341: performing seasonal pattern recognition on the hydrological seasonal variation data to obtain seasonal pattern data; recording the precipitation frequency of the seasonal pattern data to generate seasonal precipitation frequency data; and performing seasonal precipitation monitoring on the seasonal pattern data in combination with the seasonal precipitation frequency data to obtain seasonal precipitation data;

[0114] Step S342: extract seasonal water level peak and valley values ​​from seasonal precipitation data to generate seasonal water level peak and valley values; match seasonal water level rise and fall values ​​with seasonal water level rise and fall values ​​to generate seasonal water level rise and fall data; evaluate seasonal precipitation impact on hydrological seasonal change data based on seasonal water level rise and fall data to obtain seasonal precipitation impact data;

[0115] Step S343: seasonal temperature monitoring is performed on the seasonal pattern data to generate seasonal temperature data; temperature range measurement is performed on the seasonal temperature data to obtain seasonal temperature range data; water temperature measurement is performed on the hydrological seasonal change data according to the seasonal temperature range data to generate seasonal water temperature data;

[0116] Step S344: extracting the water surface freezing temperature from the seasonal water temperature data to obtain water surface freezing temperature information; recording the water surface freezing period of the hydrological seasonal change data according to the water surface freezing temperature information to generate seasonal hydrological freezing period data; performing seasonal hydrological flow monitoring on the seasonal hydrological freezing period data to obtain freezing period hydrological flow data; performing freezing period impact assessment on the hydrological seasonal change data based on the freezing period hydrological flow data to obtain freezing period impact data;

[0117] Step S345: Combine the seasonal precipitation impact data and the freezing period impact data for hydrological impact assessment to generate hydrological impact assessment data.

[0118] In the embodiment of the present invention, the periodogram technology in time series analysis is used to identify seasonal patterns by calculating the Fourier transform of the time series, and the identification function in Python is used to perform periodogram analysis on the hydrological seasonal change data, so as to obtain seasonal pattern data; the automatic recorder of the weather station is used to record the number of precipitation events in each season to obtain seasonal precipitation frequency data; in combination with the seasonal precipitation frequency data, remote sensing technology and ground meteorological station data are used to specifically monitor the precipitation in each season; the STL method in time series analysis is used to extract the peak and valley values ​​of the seasonal water level from the seasonal precipitation data to obtain the peak and valley values ​​of the seasonal water level; the extracted peak and valley values ​​of the seasonal water level are used to match the rising and falling trends of the seasonal water level by comparing the water level changes in consecutive seasons; based on the seasonal water level rise and fall data, the impact of seasonal precipitation on water level changes is specifically analyzed. impact; use the temperature recorder at the weather station to monitor the average temperature changes in each season; determine the temperature range of each season through statistical analysis methods; calculate the temperature of the water body based on the seasonal temperature range data and combined with the thermodynamic characteristics of the water body; use water body thermodynamic technology in combination with meteorological data to extract the temperature threshold for water surface freezing (set the temperature threshold for water surface freezing to 0 degrees); record the freezing period of the water body based on the water surface freezing temperature information; during the freezing period, use ADCP (Acoustic Doppler Current Profiler) and other monitoring equipment to monitor the hydrological flow; evaluate the impact of the freezing period on the hydrological conditions based on the hydrological flow data during the freezing period, and specifically evaluate the hydrological flow rate, flow, and river area temperature during the freezing period; use data merging technology to merge the seasonal precipitation impact data and the freezing period impact data for hydrological impact assessment, thereby obtaining the hydrological impact assessment data.

[0119] Preferably, step S35 includes the following steps:

[0120] Step S351: Identify the regional precipitation type based on the hydrological geographic location information to obtain regional precipitation type data; determine the precipitation period based on the regional precipitation type data to generate regional precipitation period data;

[0121] Step S352: mapping seasonal precipitation period changes on seasonal precipitation influence data based on regional precipitation period data to obtain seasonal precipitation period mapping data; calculating precipitation period duration on seasonal precipitation period mapping data to generate precipitation period duration data; associating precipitation influence time with seasonal precipitation influence data to obtain precipitation influence time association data;

[0122] Step S353: monitoring the regional temperature conditions based on the hydrological geographic location information to obtain regional temperature condition data; determining the regional temperature distribution state based on the regional temperature condition data to generate regional temperature distribution state data;

[0123] Step S354: Correlate the freezing period influencing data with the temperature distribution of the river section freezing period according to the regional temperature distribution data to obtain freezing period temperature correlation data;

[0124] Step S355: Perform multi-source correlation analysis on the precipitation impact time correlation data and the freezing period temperature correlation data to obtain hydrological multi-source correlation data.

[0125] In the embodiment of the present invention, satellite remote sensing technology and ground meteorological station data are used in combination with a decision tree classification method to identify regional precipitation types based on hydrological geographic location information; the type of precipitation (such as convective rain or frontal rain, etc.) is determined by analyzing satellite images and precipitation data from meteorological stations to form regional precipitation type data; based on the regional precipitation type data, a time series analysis method is used to determine the precipitation period, and regional precipitation period data is obtained by counting the start and end time of precipitation events in each season; based on the regional precipitation period data, seasonal precipitation influencing data is mapped to seasonal precipitation period changes, and seasonal precipitation data is spatially and temporally associated with regional precipitation period data through GIS technology to obtain seasonal precipitation period mapping data; seasonal precipitation period mapping data is analyzed to calculate the duration of each seasonal precipitation period, and precipitation period duration is generated. Time data; correlate the duration data of precipitation periods with seasonal precipitation impact data to determine the time of precipitation impact on hydrological conditions; use temperature monitoring technology to monitor regional temperature conditions for hydrological geographical location information to obtain regional temperature condition data; use spatial interpolation methods (such as Kriging interpolation) to determine the regional temperature distribution state of regional temperature condition data and generate regional temperature distribution state data; correlate the freezing period impact data with the temperature distribution of the river section freezing period based on the regional temperature distribution state data, determine the impact of temperature on the freezing period by analyzing the relationship between temperature and freezing period, and generate freezing period temperature correlation data; conduct multi-source correlation analysis on precipitation impact time correlation data and freezing period temperature correlation data, use GIS technology and statistical analysis methods to comprehensively consider the impact of precipitation and temperature on hydrological conditions, and obtain hydrological multi-source correlation data.

[0126] Preferably, step S4 comprises the following steps:

[0127] Step S41: constructing a hydrological monitoring model using hydrological multi-source associated data to obtain a hydrological monitoring model; recording hydrological real-time changes in the hydrological multi-source associated data to generate multi-source hydrological real-time change data; dynamically optimizing the hydrological monitoring model based on the multi-source hydrological real-time change data to obtain a hydrological monitoring early warning model;

[0128] Step S42: Based on the hydrological monitoring and early warning model, the hydrological monitoring data is subjected to hydrological condition prediction to obtain hydrological condition prediction data; the hydrological condition prediction data is subjected to data visualization to generate a hydrological condition prediction report;

[0129] Step S43: Perform hydrological anomaly detection on the hydrological situation forecast report based on the hydrological monitoring and early warning model to generate hydrological anomaly detection data;

[0130] Step S44: Perform early warning identification on the hydrological anomaly detection data to obtain hydrological anomaly warning information; upload the hydrological situation prediction data, hydrological anomaly detection data and hydrological anomaly warning information to the blockchain network distributed storage to perform intelligent hydrological monitoring operations.

[0131] In the embodiment of the present invention, a hydrological monitoring model is constructed by using machine learning technology, especially a decision tree regression model (DecisionTreeRegressor) and a linear regression model (LinearRegression); first, the hydrological multi-source associated data is preprocessed, and then the data is divided into a training set and a test set; the decision tree regression model is trained using the training set data, and then the linear regression model is trained based on the output of the model, thereby obtaining a hydrological monitoring model; a database management system, such as SQL, is used to record the real-time changes of the hydrological multi-source associated data; by writing SQL queries, data is obtained from the hydrological monitoring site in real time and stored in the database to form multi-source hydrological real-time change data; based on the multi-source hydrological real-time change data, the CMA-ES algorithm is used to dynamically optimize the hydrological monitoring model, specifically by automatically adjusting the model parameters to improve the prediction accuracy of the model, thereby obtaining a hydrological monitoring and early warning model; based on the optimized hydrological monitoring and early warning model, the hydrological monitoring data is predicted, and the historical data is back-tested using the model to verify The prediction ability of the model is used to predict future hydrological conditions and generate hydrological prediction data; data visualization technology, such as Python's Matplotlib library, is used to display hydrological prediction data in the form of graphs; intuitive hydrological prediction reports are generated by drawing curves showing flow and water level changes over time; hydrological prediction reports are analyzed based on the hydrological monitoring and early warning model to identify abnormal events that are significantly different from normal hydrological conditions, and abnormal data are identified by setting thresholds and using statistical methods, such as standard deviation analysis, to obtain hydrological anomaly detection data; hydrological anomaly detection data is analyzed, and classification algorithms, such as support vector machines (SVMs), are used to identify abnormal data and divide them into warning levels; corresponding hydrological anomaly warning information is generated according to the warning level; hydrological prediction data, hydrological anomaly detection data, and hydrological anomaly warning information are uploaded to the blockchain network for distributed storage, and the immutability and distributed characteristics of the blockchain are used to ensure the security and reliability of the data and perform intelligent hydrological monitoring operations.

[0132] Preferably, step S41 includes the following steps:

[0133] Step S411: constructing a hydrological monitoring model according to the hydrological multi-source associated data to obtain a hydrological monitoring pre-model; and training the hydrological monitoring pre-model using the hydrological multi-source associated data to obtain a hydrological monitoring training model;

[0134] Step S412: performing model cross-validation evaluation on the hydrological monitoring training model to obtain hydrological monitoring training model evaluation data; adjusting model parameters of the hydrological monitoring training model using the hydrological monitoring training model evaluation data to obtain a hydrological monitoring model;

[0135] Step S413: Compare the hydrological change characteristics of the hydrological multi-source associated data with the hydrological monitoring data to obtain hydrological change characteristic data; record the hydrological real-time changes of the hydrological multi-source associated data based on the hydrological change characteristic data to generate multi-source hydrological real-time change data;

[0136] Step S414: extracting multi-source change features from multi-source hydrological real-time change data to obtain multi-source change feature data; performing multi-source change incremental updates on the hydrological monitoring model based on the multi-source change feature data to obtain multi-source incremental update information;

[0137] Step S415: abnormal hydrological changes are identified on the multi-source change feature data to generate multi-source abnormal hydrological change data; dynamic parameter optimization is performed on the hydrological monitoring model according to the multi-source abnormal hydrological change data and multi-source incremental update information to obtain a hydrological monitoring and early warning model.

[0138] In the embodiment of the present invention, the SWAT model (Soil and Water Assessment Tool) is used as a hydrological monitoring pre-model; the SWAT model is a basin-based simulation tool used to evaluate the impact of land management practices on the hydrological cycle and water quality over a long period of time. Set up a SWAT project in the ArcGIS environment, create a new SWAT project, and specify the project directory and database; import the land use index table (such as luc.dbf) and the soil index table (such as soilc.dbf), which are the key input data of the SWAT model; process the elevation data (dem), set the Z unit of the elevation grid to "meter", and load the mask grid (such as amazon) to define the basin boundary; thereby obtaining a hydrological monitoring pre-model; train the hydrological monitoring pre-model using hydrological multi-source correlation data, and during the model training process, adjust parameters such as the Manning coefficient (such as 0.014) as needed to match the actual hydrological conditions to obtain a hydrological monitoring training model; and perform cross-validation evaluation on the hydrological monitoring training model. This usually involves dividing the dataset into a training set and a validation set, using the training set to train the model, and then using the validation set to evaluate the model's performance; evaluation metrics include basic water balance and total runoff calibration, as well as calibration of flow process lines, including peaks, retreat, and consideration of preconditions. Based on the evaluation data, the model parameters are adjusted; for example, if the surface runoff is too high, adjust the CN2 value until the surface runoff meets the requirements; if the simulated groundwater runoff value is too high, increase the groundwater reevaporation coefficient to 0.20; if the simulated baseflow value is too low, check the flow of water to the aquifer and adjust accordingly, and finally obtain a hydrological monitoring model.By using multi-source heterogeneous data fusion technology, the characteristics of hydrological multi-source correlation data and hydrological monitoring data are compared. By building the underlying architecture for spatiotemporal big data processing, the three methods of data-level fusion, feature-level fusion and decision-level fusion are integrated to realize the extraction of hydrological change characteristic data; based on the hydrological change characteristic data, sensor technology is used to monitor the hydrological multi-source correlation data in real time; by designing water level monitoring equipment, writing data collection and transmission programs, and connecting to the cloud or other devices, remote transmission and monitoring of data are realized, thereby obtaining multi-source hydrological real-time change data; using feature recognition technology, multi-source change features are extracted from multi-source hydrological real-time change data to obtain multi-source change characteristic data; using data By combining the assimilation method and the optimization algorithm simultaneously, the hydrological monitoring model is incrementally updated based on the multi-source change characteristic data. Abnormal hydrological changes are identified in the multi-source change characteristic data, and the hydrological sequence outlier detection method is used to detect abnormal hydrological changes in the multi-source change characteristic data through sliding window values, thereby obtaining multi-source abnormal hydrological change data. The stable Gauss-Newton algorithm is used to dynamically optimize the parameters of the hydrological monitoring model. The algorithm improves the global convergence of the gradient algorithm by changing the differential step size, mines the sampling point information in the gradient calculation process to accelerate the convergence of the gradient algorithm, and uses zero space jumps to improve the resistance of the gradient algorithm to insensitive parameters, ultimately obtaining a hydrological monitoring and early warning model.

[0139] Preferably, step S43 includes the following steps:

[0140] Step S431: Based on the hydrological monitoring and early warning model, the hydrological situation prediction is used to perform river runoff anomaly detection to obtain runoff anomaly data; the runoff anomaly data is used to calculate the hydrological runoff anomaly degree to generate hydrological runoff anomaly degree data;

[0141] Step S432: Based on the hydrological monitoring and early warning model, the hydrological situation prediction is subjected to river freezing period anomaly detection to obtain freezing period anomaly data; the freezing period anomaly data is subjected to hydrological freezing period anomaly cycle calculation to generate hydrological freezing period anomaly cycle data;

[0142] Step S433: performing hydrological seasonal change anomaly detection on the hydrological situation forecast according to the hydrological runoff abnormality degree data and the hydrological freezing period abnormality period data to obtain seasonal change abnormality data; performing seasonal abnormality duration measurement on the seasonal change abnormality data to generate the hydrological seasonal abnormality duration;

[0143] Step S434: The hydrological runoff abnormality degree data, the hydrological freezing period abnormality cycle data and the hydrological seasonal abnormality duration data are combined to generate hydrological anomaly detection data.

[0144] In the embodiment of the present invention, based on the hydrological monitoring and early warning model, a decision tree algorithm is used to predict the hydrological situation, and the river runoff anomaly detection is performed. The threshold is selected by the Gini index, and the features are classified by binary method, so as to identify abnormal samples. Specifically, the feature set used for classification is first determined, and then the runoff data is classified by constructing a decision tree to identify abnormal samples and obtain abnormal runoff data. The abnormal degree of the abnormal runoff data is calculated, and the degree of deviation between the abnormal data and the normal data is calculated by using a statistical method. For example, the deviation ratio between the average daily flow and the average monthly flow is calculated. Based on the hydrological monitoring and early warning model, the hydrological situation is predicted to detect the abnormality of the river freezing period, remote sensing technology is used to monitor the changes in the ice conditions of the river, and the freezing period anomalies are identified in combination with meteorological data and hydrological models. Analyze the abnormal data and calculate the abnormal period of freezing period; determine the length of abnormal period by comparing the difference between actual freezing period and historical average freezing period; perform seasonal change anomaly detection on hydrological situation forecast based on hydrological runoff abnormality degree data and hydrological freezing period abnormality period data, and use time series analysis methods, such as seasonal decomposition time series prediction (STL), to identify abnormal patterns in seasonal changes; analyze seasonal change abnormal data and specifically determine the duration of seasonal anomalies; determine the abnormal duration period by calculating the start and end time of abnormal events; use multi-source information fusion technology to merge hydrological anomaly conditions with hydrological runoff abnormality degree data, hydrological freezing period abnormality period data and hydrological seasonal anomaly duration to generate hydrological anomaly detection data.

[0145] Preferably, step S44 includes the following steps:

[0146] Step S441: marking the hydrological anomaly detection data with a hydrological anomaly type to generate hydrological anomaly type marking data; classifying the hydrological anomaly detection data into anomaly types based on the hydrological anomaly type marking data to obtain hydrological anomaly type data; extracting the anomaly degree from the hydrological anomaly type data to generate hydrological anomaly degree data;

[0147] Step S442: generating hydrological early warning information according to the hydrological anomaly type data and the hydrological anomaly degree data to obtain hydrological anomaly warning information;

[0148] Step S443: Use blockchain technology to upload hydrological situation prediction data, hydrological anomaly detection data and hydrological anomaly warning information to blockchain nodes, and distribute and store hydrological situation prediction data, hydrological anomaly detection data and hydrological anomaly warning information through blockchain nodes to perform intelligent hydrological monitoring operations.

[0149] In the embodiment of the present invention, feature labeling technology is used to label the hydrological anomaly detection data with anomaly types. Specifically, by establishing a hydrological monitoring database management system, combined with structured feature analysis of data sources, and using a feature analysis method with semantic constraints of hydrological changes, anomaly features are extracted to obtain hydrological anomaly type labeling data; a decision tree algorithm is used to divide the hydrological anomaly type labeling data into anomaly types, and specifically, the features are classified by binary classification to identify different types of anomalies; feature extraction technology is used to extract the degree of anomaly from the hydrological anomaly type data to obtain hydrological anomaly degree data; hydrological early warning information is generated based on the hydrological anomaly type data and the hydrological anomaly degree data, and the specific hydrological early warning information includes the hydrological anomaly type, the degree of hydrological anomaly, and the scope of impact of the hydrological anomaly; blockchain technology is used to upload hydrological situation prediction data, hydrological anomaly detection data, and hydrological anomaly warning information to blockchain nodes, and the data upload and verification process is automatically executed through smart contracts to achieve data transparency and automated management, and perform intelligent hydrological monitoring operations.

[0150] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0151] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may 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 the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for constructing a large hydrological model integrating multi-source fusion and dynamic optimization, characterized in that: The following steps are involved: Step S1: obtaining hydrological monitoring data; performing data preprocessing on the hydrological monitoring data to obtain standard hydrological monitoring data; Perform multi-dimensional feature recognition on standard hydrological monitoring data to obtain multi-dimensional hydrological feature data; Step S2: extracting runoff characteristics from the multi-dimensional hydrological characteristic data to obtain hydrological runoff characteristic data; calculating river network density from the hydrological runoff characteristic data to generate hydrological river network density data; identifying hydrological topography and geomorphology from the hydrological river network density data to generate hydrological topography and geomorphology characteristic data; determining the geographical location of the hydrological topography and geomorphology characteristic data using geographic information system technology to obtain hydrological geographical location information; Step S3: monitor the runoff change of the hydrological runoff characteristic data to obtain runoff change data; perform seasonal analysis on the runoff change data based on the hydrological geographical location information to generate hydrological seasonal change data; perform hydrological impact assessment on the hydrological seasonal change data to obtain hydrological impact assessment data; perform multi-source correlation analysis on the hydrological geographical location information and the hydrological impact assessment data to obtain hydrological multi-source correlation data; Step S4: construct a hydrological monitoring model using hydrological multi-source correlation data to obtain a hydrological monitoring model; dynamically optimize the hydrological monitoring model to obtain a hydrological monitoring early warning model; predict hydrological conditions based on the hydrological monitoring data based on the hydrological monitoring early warning model to generate a hydrological condition prediction report; detect hydrological anomalies in the hydrological condition prediction report based on the hydrological monitoring early warning model to generate hydrological anomaly detection data; upload the hydrological condition prediction report and hydrological anomaly detection data to the blockchain network distributed storage to perform intelligent hydrological monitoring operations.

2. The method for constructing a large hydrological model integrating multi-source fusion and dynamic optimization according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: marking the multi-dimensional hydrological characteristic data into river sections to generate river section data; identifying the river sections of the river section data to generate river section data; extracting the runoff characteristics of the multi-dimensional hydrological characteristic data based on the river section data and the river section data to obtain the hydrological runoff characteristic data; Step S22: using the river segmentation data to measure the length of the segmented river on the hydrological runoff characteristic data, to obtain the river segmentation length data; using the river cross-section data to measure the river basin area on the hydrological runoff characteristic data, to generate the river basin area data; using the river segmentation length data and the river basin area data to calculate the river network density, to generate the hydrological river network density data; Step S23: Perform hydrological topography and geomorphic recognition on the hydrological river network density data to generate hydrological topography and geomorphic feature data; Step S24: perform terrain classification on the hydrological topography and geomorphological feature data to obtain terrain and geomorphological type data; perform terrain spatial area detection on the terrain and geomorphological type data to generate terrain spatial area data; use geographic information system technology to perform geographic coordinate annotation on the terrain spatial area data to obtain terrain spatial geographic coordinates; determine the geographical location of the hydrological topography and geomorphological feature data based on the terrain spatial geographic coordinates to obtain hydrological geographical location information.

3. The method for constructing a large hydrological model integrating multi-source fusion and dynamic optimization according to claim 2 is characterized in that: Step S23 includes the following steps: Step S231: identifying the river network shape characteristics of the hydrological river network density data to obtain river network shape characteristic data; determining the water flow direction of the hydrological river network density data according to the river network shape characteristic data to generate river flow direction data; monitoring the flow velocity of the river flow direction data to obtain river flow velocity data; Step S232: performing hydrological vegetation coverage terrain recognition on the multi-dimensional hydrological characteristic data based on the river network shape characteristic data and the river flow direction data to generate hydrological vegetation coverage terrain data; Step S233: determining the hydrological topographic drop of the multi-dimensional hydrological characteristic data based on the river flow direction data and the river flow velocity data, and generating hydrological topographic drop data; Step S234: identifying landform fluctuation characteristics according to the hydrological vegetation coverage landform data and the hydrological landform drop data to obtain hydrological landform fluctuation characteristic data; determining the fluctuation degree of the hydrological landform fluctuation characteristic data to generate hydrological landform fluctuation degree data; Step S235: using the hydro-geomorphic fluctuation degree data to identify the geomorphic fluctuation rock layer structure of the hydro-geomorphic drop data, and obtaining the fluctuation rock layer structure data; performing hydro-fault geological extraction on the fluctuation rock layer structure data, and generating hydro-fault geological data; Step S236: merge the hydrological vegetation coverage terrain data, the hydrological terrain drop data, the hydrological geomorphic fluctuation degree data and the hydrological fault geological data to obtain the hydrological terrain and geomorphic characteristic data.

4. The method for constructing a large hydrological model integrating multi-source fusion and dynamic optimization according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: identifying the runoff flow state of the hydrological runoff characteristic data to obtain the runoff flow state data; recording the water level of the runoff flow state data to generate the water level data; calculating the difference between the water level of ... Step S32: monitoring the hydrological annual change of the hydrological runoff characteristic data according to the flood and dry water level difference data to generate hydrological annual change data; calculating the runoff change of the hydrological annual change data to obtain runoff change data; Step S33: performing monthly change statistics on the runoff change data to obtain the runoff monthly change data; performing seasonal division on the runoff monthly change data based on the hydrological geographical location information to generate the runoff seasonal change data; performing seasonal water level feature extraction on the runoff seasonal change data to obtain seasonal water level feature data; performing seasonal change identification on the runoff change data according to the seasonal water level feature data to generate the hydrological seasonal change data; Step S34: Performing hydrological impact assessment on the hydrological seasonal variation data to obtain hydrological impact assessment data; Step S35: Perform multi-source correlation analysis on the hydrological geographical location information and the hydrological impact assessment data to obtain hydrological multi-source correlation data.

5. The method for constructing a large hydrological model integrating multi-source fusion and dynamic optimization according to claim 4 is characterized in that: Step S34 includes the following steps: Step S341: performing seasonal pattern recognition on the hydrological seasonal variation data to obtain seasonal pattern data; recording the precipitation frequency of the seasonal pattern data to generate seasonal precipitation frequency data; and performing seasonal precipitation monitoring on the seasonal pattern data in combination with the seasonal precipitation frequency data to obtain seasonal precipitation data; Step S342: extract seasonal water level peak and valley values ​​from seasonal precipitation data to generate seasonal water level peak and valley values; match seasonal water level rise and fall values ​​with seasonal water level rise and fall values ​​to generate seasonal water level rise and fall data; evaluate seasonal precipitation impact on hydrological seasonal change data based on seasonal water level rise and fall data to obtain seasonal precipitation impact data; Step S343: seasonal temperature monitoring is performed on the seasonal pattern data to generate seasonal temperature data; temperature range measurement is performed on the seasonal temperature data to obtain seasonal temperature range data; water temperature measurement is performed on the hydrological seasonal change data according to the seasonal temperature range data to generate seasonal water temperature data; Step S344: extracting the water surface freezing temperature from the seasonal water temperature data to obtain water surface freezing temperature information; recording the water surface freezing period of the hydrological seasonal change data according to the water surface freezing temperature information to generate seasonal hydrological freezing period data; performing seasonal hydrological flow monitoring on the seasonal hydrological freezing period data to obtain freezing period hydrological flow data; performing freezing period impact assessment on the hydrological seasonal change data based on the freezing period hydrological flow data to obtain freezing period impact data; Step S345: Combine the seasonal precipitation impact data and the freezing period impact data for hydrological impact assessment to generate hydrological impact assessment data.

6. The method for constructing a large hydrological model integrating multi-source fusion and dynamic optimization according to claim 5 is characterized in that: Step S35 includes the following steps: Step S351: Identify the regional precipitation type based on the hydrological geographic location information to obtain regional precipitation type data; determine the precipitation period based on the regional precipitation type data to generate regional precipitation period data; Step S352: mapping seasonal precipitation period changes on seasonal precipitation influence data based on regional precipitation period data to obtain seasonal precipitation period mapping data; calculating precipitation period duration on seasonal precipitation period mapping data to generate precipitation period duration data; associating precipitation influence time with seasonal precipitation influence data to obtain precipitation influence time association data; Step S353: monitoring the regional temperature conditions based on the hydrological geographic location information to obtain regional temperature condition data; determining the regional temperature distribution state based on the regional temperature condition data to generate regional temperature distribution state data; Step S354: Correlate the freezing period influencing data with the temperature distribution of the river section freezing period according to the regional temperature distribution data to obtain freezing period temperature correlation data; Step S355: Perform multi-source correlation analysis on the precipitation impact time correlation data and the freezing period temperature correlation data to obtain hydrological multi-source correlation data.

7. The method for constructing a large hydrological model integrating multi-source fusion and dynamic optimization according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: constructing a hydrological monitoring model using hydrological multi-source associated data to obtain a hydrological monitoring model; recording hydrological real-time changes in the hydrological multi-source associated data to generate multi-source hydrological real-time change data; dynamically optimizing the hydrological monitoring model based on the multi-source hydrological real-time change data to obtain a hydrological monitoring early warning model; Step S42: Based on the hydrological monitoring and early warning model, the hydrological monitoring data is subjected to hydrological condition prediction to obtain hydrological condition prediction data; the hydrological condition prediction data is subjected to data visualization to generate a hydrological condition prediction report; Step S43: Perform hydrological anomaly detection on the hydrological situation forecast report based on the hydrological monitoring and early warning model to generate hydrological anomaly detection data; Step S44: Perform early warning identification on the hydrological anomaly detection data to obtain hydrological anomaly warning information; upload the hydrological situation prediction data, hydrological anomaly detection data and hydrological anomaly warning information to the blockchain network distributed storage to perform intelligent hydrological monitoring operations.

8. The method for constructing a large hydrological model integrating multi-source fusion and dynamic optimization according to claim 7 is characterized in that: Step S41 includes the following steps: Step S411: constructing a hydrological monitoring model according to the hydrological multi-source associated data to obtain a hydrological monitoring pre-model; and training the hydrological monitoring pre-model using the hydrological multi-source associated data to obtain a hydrological monitoring training model; Step S412: performing model cross-validation evaluation on the hydrological monitoring training model to obtain hydrological monitoring training model evaluation data; adjusting model parameters of the hydrological monitoring training model using the hydrological monitoring training model evaluation data to obtain a hydrological monitoring model; Step S413: Compare the hydrological change characteristics of the hydrological multi-source associated data with the hydrological monitoring data to obtain hydrological change characteristic data; record the hydrological real-time changes of the hydrological multi-source associated data based on the hydrological change characteristic data to generate multi-source hydrological real-time change data; Step S414: extracting multi-source change features from multi-source hydrological real-time change data to obtain multi-source change feature data; performing multi-source change incremental updates on the hydrological monitoring model based on the multi-source change feature data to obtain multi-source incremental update information; Step S415: abnormal hydrological changes are identified on the multi-source change feature data to generate multi-source abnormal hydrological change data; dynamic parameter optimization is performed on the hydrological monitoring model according to the multi-source abnormal hydrological change data and multi-source incremental update information to obtain a hydrological monitoring and early warning model.

9. The method for constructing a large hydrological model integrating multi-source fusion and dynamic optimization according to claim 7 is characterized in that: Step S43 includes the following steps: Step S431: Based on the hydrological monitoring and early warning model, the hydrological situation forecast report is subjected to river runoff anomaly detection to obtain runoff anomaly data; the hydrological runoff anomaly degree is calculated for the runoff anomaly data to generate hydrological runoff anomaly degree data; Step S432: Based on the hydrological monitoring and early warning model, the hydrological situation forecast report is subjected to river freezing period anomaly detection to obtain freezing period anomaly data; the freezing period anomaly data is subjected to hydrological freezing period anomaly cycle calculation to generate hydrological freezing period anomaly cycle data; Step S433: performing hydrological seasonal change anomaly detection on the hydrological situation forecast report according to the hydrological runoff abnormality degree data and the hydrological freezing period abnormality cycle data to obtain seasonal change abnormality data; performing seasonal abnormality duration measurement on the seasonal change abnormality data to generate the hydrological seasonal abnormality duration; Step S434: The hydrological runoff abnormality degree data, the hydrological freezing period abnormality cycle data and the hydrological seasonal abnormality duration data are combined to generate hydrological anomaly detection data.

10. The method for constructing a large hydrological model integrating multi-source fusion and dynamic optimization according to claim 7, characterized in that: Step S44 includes the following steps: Step S441: marking the hydrological anomaly detection data with a hydrological anomaly type to generate hydrological anomaly type marking data; classifying the hydrological anomaly detection data into anomaly types based on the hydrological anomaly type marking data to obtain hydrological anomaly type data; extracting the anomaly degree from the hydrological anomaly type data to generate hydrological anomaly degree data; Step S442: generating hydrological early warning information according to the hydrological anomaly type data and the hydrological anomaly degree data to obtain hydrological anomaly warning information; Step S443: Use blockchain technology to upload hydrological situation prediction data, hydrological anomaly detection data and hydrological anomaly warning information to blockchain nodes, and distribute and store hydrological situation prediction data, hydrological anomaly detection data and hydrological anomaly warning information through blockchain nodes to perform intelligent hydrological monitoring operations.

Images