A method and system for monitoring drought at hydrological stations of rural water supply projects

Abstract

The present invention relates to the technical field of monitoring methods, and in particular to a method and system for monitoring drought at a hydrological station of a rural water supply project. The method comprises the following steps: obtaining a hydrological station monitoring data set; performing data preprocessing on the hydrological station monitoring data set to generate a hydrological processing data set; performing data encryption on the hydrological processing data set to generate a hydrological encrypted data set; transmitting the hydrological encrypted data set to a preset cloud platform to generate a hydrological cloud platform data set; performing horizontal verification, multi-dimensional parameter vertical verification and historical data verification on the hydrological cloud platform data set to generate horizontal hydrological data, vertical hydrological data and historical hydrological comparison data; therefore, the present invention solves the problems of insufficient data security, inconvenient information sharing and difficulty in identifying abnormal situations in traditional hydrological monitoring through systematic data collection, encryption, cloud transmission and multi-dimensional verification, and improves the efficiency and accuracy of hydrological monitoring.

Description

Technical Field

[0001] The present invention relates to the technical field of monitoring methods, and in particular to a method and system for monitoring drought at a hydrological station of a rural water supply project. Background Art

[0002] In the monitoring of hydrological sites in rural water supply projects, existing technologies face multiple deficiencies, which directly affect the accuracy and timeliness of monitoring. Traditional hydrological monitoring systems usually rely on fixed sites for data collection. This static monitoring method cannot fully cover the dynamically changing hydrological environment, resulting in slow response to water source changes and basin conditions, and it is difficult to reflect the full picture of hydrological changes in real time. This limitation is particularly evident when responding to sudden meteorological changes or drought events, and it is impossible to provide effective decision support in a timely manner. Existing monitoring systems often rely on a single monitoring parameter, such as flow or water level, while ignoring the integration of multi-dimensional data. The hydrological characteristics of rural areas are complex and there are many influencing factors. Monitoring from a single data source often leads to a one-sided understanding of the hydrological situation, thereby affecting the comprehensive evaluation of water resources management and use. Many traditional hydrological monitoring systems have a lag in data processing, and usually lack efficient data analysis tools and algorithms, resulting in insufficient real-time data analysis capabilities. This lag makes it impossible to provide timely warnings and response measures at critical moments, such as drought warnings and flood forecasts, which greatly affects the efficiency and effectiveness of emergency management. Finally, existing monitoring technologies are deficient in data sharing and integration. Most hydrological data are still stored in isolated forms, lacking effective cross-system and cross-platform data integration and analysis mechanisms, which not only limits the flow of information, but also affects the in-depth mining and utilization of hydrological data. Summary of the invention

[0003] Based on this, it is necessary to provide a method and system for drought monitoring at a hydrological station of a rural water supply project to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for monitoring drought at a hydrological station of a rural water supply project is provided, the method comprising the following steps:

[0005] Step S1: Acquire a hydrological site monitoring data set; perform data preprocessing on the hydrological site monitoring data set to generate a hydrological processing data set;

[0006] Step S2: Encrypting the hydrological processing data set to generate a hydrological encrypted data set; transmitting the hydrological encrypted data set to a preset cloud platform to generate a hydrological cloud platform data set;

[0007] Step S3: Perform horizontal verification, multi-dimensional parameter vertical verification and historical data verification on the hydrological cloud platform data set to generate horizontal hydrological data, vertical hydrological data and historical hydrological comparison data; draw a two-dimensional fitting graph of the horizontal hydrological data, vertical hydrological data and historical hydrological comparison data, confirm hydrological anomalies, and generate hydrological drought anomaly data;

[0008] Step S4: Acquire historical drought data; compare the hydrological drought anomaly data and historical drought data in layers, and map them to the water source area for distribution correction, thereby completing the drought monitoring operation of the hydrological station.

[0009] The beneficial effect of the present invention is that the reliability and accuracy of hydrological data are significantly improved through systematic steps and modular processing mechanisms. First, by obtaining the hydrological site monitoring data set and performing effective data processing, the integrity and validity of the data are ensured, which lays a solid foundation for subsequent analysis. The data encryption link not only ensures the security of the data, but also realizes the efficient integration and sharing of resources by transmitting the processed data to the cloud platform. This cloud data storage and management mode enables the data of different hydrological monitoring points to be updated in real time and easy to access, enhancing the flexibility and operability of monitoring. In the data verification stage, horizontal and vertical multi-dimensional parameter verification methods are adopted to effectively improve the accuracy and credibility of the data. Through the horizontal verification of the hydrological cloud platform data set, the flow and water level changes between different monitoring points are effectively compared, thereby identifying potential abnormalities. At the same time, the longitudinal verification method ensures the consistency of hydrological data in time series by analyzing different dimensional data (such as flow, rainfall and water quality) of the same water source, thereby eliminating the possibility of equipment failure or data transmission problems. Finally, by comparing the hydrological drought anomaly data with the historical drought data in layers and correcting the regional mapping, the method can dynamically adjust the monitoring strategy and more accurately reflect the regional hydrological conditions. This comprehensive analysis method not only improves the accuracy of drought monitoring, but also provides a scientific basis for decision makers, which helps to formulate effective water resource management strategies. Therefore, the present invention solves the problems of insufficient data security, inconvenient information sharing, and difficulty in identifying abnormal situations in traditional hydrological monitoring through systematic data collection, encryption, cloud transmission, and multi-dimensional verification, thereby improving the efficiency and accuracy of hydrological monitoring.

[0010] Preferably, step S1 comprises the following steps:

[0011] Step S11: Obtaining hydrological site monitoring data set;

[0012] Step S12: performing linear interpolation processing on the hydrological site monitoring data set to process missing values, and generating a hydrological missing value processing data set; performing noise filtering on the hydrological missing value processing data set to generate a hydrological cleaned data set; performing outlier removal processing on the hydrological cleaned data set to generate a hydrological outlier removal data set;

[0013] Step S13: performing scale normalization processing on the hydrological outlier removal data set to generate a hydrological preprocessing data set, wherein the hydrological preprocessing data set includes flow data, river water level change data, rainfall data and groundwater depth data.

[0014] The present invention lays the foundation for subsequent analysis by acquiring hydrological site monitoring data sets, ensuring the extensiveness and representativeness of data sources. The linear interpolation processing for missing values ​​not only effectively fills the data gaps, but also avoids the analysis deviation caused by missing data. This process enhances the continuity and stability of the data set. The subsequent noise filtering link aims to eliminate unnecessary random interference signals, thereby generating a more accurate hydrological cleaning data set. Through such processing, the signal-to-noise ratio of the data is improved, so that subsequent analysis can be based on clearer and more real signals, greatly improving the effectiveness of data analysis. Scale standardization processing further ensures that different types of hydrological data (such as flow, river water level changes, rainfall and groundwater infiltration) are compared and analyzed under the same standard. This standardization not only eliminates the errors caused by different dimensions, but also facilitates multidimensional data fusion, so that the correlation between data from different sources can be effectively mined. This systematic processing method enables the hydrological preprocessing data set to have high consistency and reliability in both space and time, providing a solid data foundation for subsequent model construction, data analysis and decision support.

[0015] Preferably, step S2 comprises the following steps:

[0016] Step S21: encrypting the hydrological processing data set by using a symmetric encryption algorithm to generate a hydrological encrypted data set and a symmetric key;

[0017] Step S22: Send the hydrological encrypted data set to the preset cloud platform through the encryption protocol for data decryption to generate a hydrological decrypted data set; perform MD5 verification on the hydrological decrypted data set to generate a hydrological cloud platform data set.

[0018] The present invention encrypts the hydrological processing data set by adopting a symmetric encryption algorithm to generate a hydrological encrypted data set and a symmetric key. This process not only protects the confidentiality of the data, avoids the risk of unauthorized access or tampering during transmission, but also ensures the integrity of the data. This encryption processing method is particularly important for protecting sensitive hydrological data (such as flow, river water level and rainfall, etc.), because the leakage of these data will have an irreversible impact on the ecological environment and water resources management. The hydrological encrypted data set is securely transmitted to the preset cloud platform through an encryption protocol, further enhancing the security of the data transmission process. In this process, the secure channel established by the encryption protocol is used to ensure the confidentiality and security of the data during transmission, reducing the risk of attacks and hijacking when the data is transmitted on the Internet. At the same time, as the core of data storage and processing, the cloud platform can realize efficient data management and analysis, and provide strong technical support for hydrological monitoring. In the process of generating a hydrological decrypted data set, the security and efficiency of the decryption process are ensured. Next, the integrity of the hydrological decrypted data set is checked through MD5 verification to generate the hydrological cloud platform data set. This step is crucial. By comparing the MD5 hash values ​​of the original data set and the decrypted data set, it ensures that the data has not changed during the encryption, transmission and decryption process, thereby further improving the reliability of the data. This verification mechanism can effectively identify potential problems in data transmission, ensure the authenticity of monitoring data, and provide a solid foundation for subsequent analysis.

[0019] Preferably, step S22 includes the following steps:

[0020] Step S221: Establish a secure transmission channel through the TLS encryption protocol to generate a hydrological encrypted transmission channel;

[0021] Step S222: sending the hydrological encrypted data set and the symmetric key to a preset cloud platform through a hydrological encrypted transmission channel, and decrypting the hydrological encrypted data set using the symmetric key to generate a hydrological decrypted data set;

[0022] Step S223: Perform MD5 hash generation on the hydrological processing data set and the hydrological decrypted data set to generate MD5 original hydrological hash value and MD5 hydrological cloud platform hash value; perform hash value integrity matching on the MD5 original hydrological hash value and the MD5 hydrological cloud platform hash value to generate a hydrological cloud platform data set, wherein the hydrological cloud platform data set includes reservoir outflow, river water level changes, groundwater infiltration and rainfall data.

[0023] The present invention provides a secure environment for the transmission of hydrological encrypted data sets by using a secure transmission channel established by the TLS encryption protocol, ensuring that the data is not easily intercepted or tampered with by a third party during the transmission process. This measure is crucial to ensuring the confidentiality of hydrological data (such as flow, river water level and rainfall, etc.), because these data involve regional water resources management and have extremely high requirements for their security. The hydrological encrypted data set and the symmetric key are sent to the cloud platform through a secure transmission channel, and the decryption operation is completed in the cloud to generate a hydrological decrypted data set. In this way, not only the efficiency of data transmission is improved, but also the security of the decryption process is ensured, and potential risks in the decryption process are avoided. This design allows the data to always maintain a high level of security and reliability in the storage and subsequent analysis of the cloud platform. MD5 hash generation is performed on the hydrological processing data set and the hydrological decryption data set to form the original hash value and the cloud platform hash value. The introduction of this step greatly enhances the effectiveness of data integrity verification. By comparing the hash values ​​of the original data set and the decrypted data set, any changes or damages that occur during the data transmission process can be quickly detected to ensure the integrity of the hydrological data in the transmission and storage links. This mechanism can detect abnormal situations in a timely manner and provide an accurate and reliable basis for subsequent data analysis.

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

[0025] Step S31: Perform horizontal verification, multi-dimensional parameter vertical verification and historical data verification on the hydrological cloud platform data set to generate horizontal hydrological data, vertical hydrological data and historical hydrological comparison data;

[0026] Step S32: Draw a two-dimensional fitting graph of the horizontal hydrological data, the vertical hydrological data and the historical hydrological comparison data to generate a hydrological two-dimensional data fitting graph; perform abnormal fluctuation analysis on the hydrological two-dimensional data fitting graph, mark it, and generate hydrological fitting abnormal data;

[0027] Step S33: performing secondary confirmation of the abnormal fluctuation value of the hydrological fitting abnormal data to generate hydrological drought abnormal data.

[0028] The present invention constructs a multi-dimensional data verification framework by performing horizontal verification, multi-dimensional parameter vertical verification and historical data verification on the hydrological cloud platform data set. This framework allows cross-comparison between different hydrological parameters, and compares the changes in river water levels with the corresponding flow and rainfall to confirm the consistency and rationality of the data. At the same time, through the introduction of historical data, the current monitoring data can be benchmarked based on past trends, revealing potential anomalies or deviations and enhancing the reliability of the data. The horizontal hydrological data, the vertical hydrological data and the historical hydrological comparison data are drawn into a two-dimensional fitting graph, and then a hydrological two-dimensional data fitting graph is generated. This process provides intuitive support for visual analysis. By graphically displaying the relationship between different data, potential abnormal fluctuations can be effectively identified, helping researchers to quickly locate the source of the problem. The abnormal fluctuation analysis of the hydrological two-dimensional data fitting graph enables these abnormal data to be marked and recorded in time, ensuring the pertinence and accuracy of subsequent analysis. The hydrological fitting abnormal data is reconfirmed, and hydrological drought abnormal data is further generated, which significantly improves the accuracy of abnormal identification. This confirmation mechanism can effectively filter out false positives and ensure that the drought anomaly data finally identified is a real phenomenon, rather than noise in data processing or monitoring. This level-by-level verification method not only enhances the scientific nature of the data, but also provides a solid basis for decision-making.

[0029] Preferably, step S31 includes the following steps:

[0030] Step S311: tracing the outflow of the reservoir upstream to generate the outflow of the upstream reservoir; searching the downstream water level change of the river channel water level change to generate the downstream river channel water level change data; performing flow delay calculation on the outflow of the upstream reservoir and the downstream river channel water level change data to generate the river channel flow delay data; performing horizontal delay analysis on the river channel flow delay data to generate the river channel flow time series data; performing horizontal correlation analysis on the groundwater infiltration and rainfall data to generate the groundwater infiltration correlation analysis data; performing horizontal verification on the river channel flow time series data and the groundwater infiltration correlation analysis data to generate the horizontal hydrological data;

[0031] Step S312: extract the water source points of the reservoir outflow and the river water level change in a unified manner to generate water level-flow isotope data; perform physical quantity synchronous analysis and processing on the water level-flow isotope data to generate water level-flow synchronous comparison data; perform longitudinal verification of multi-dimensional parameters of water level, flow and water quality data on the water level-flow synchronous comparison data to generate longitudinal hydrological data;

[0032] Step S313: Acquire a historical hydrological site dataset; identify outliers in the historical hydrological site dataset and the hydrological cloud platform dataset using a Z score to generate hydrological fitting anomaly data; perform historical data verification on the hydrological fitting anomaly data to generate historical hydrological comparison data.

[0033] The present invention forms a comprehensive perspective of water flow dynamics by tracing the upstream source of the reservoir outflow and searching the downstream for changes in river water level. This upstream and downstream data association provides a scientific basis for flow delay calculation, which helps to understand the timeliness of water flow and its impact on the downstream environment. In addition, the combination of the generation of river flow time series data and groundwater infiltration correlation analysis makes the understanding of the hydrological cycle process more three-dimensional, laying a solid foundation for subsequent verification work. A more accurate hydrological parameter relationship diagram is formed by extracting water level-flow co-location data and synchronously analyzing physical quantities. This process ensures the spatiotemporal consistency between water level and flow, and enhances the comprehensive analysis capability of multi-dimensional hydrological data. The longitudinal verification of water level, flow and water quality data enables in-depth discussion of the relationship between different hydrological parameters, providing comprehensive information support for water resources management. This multi-dimensional parameter verification method not only improves the scientific nature of the data, but also helps to identify potential anomalies and trends. By introducing historical hydrological site data sets, current data is compared with historical trends, forming a dynamic verification mechanism. The Z score is used for outlier identification, which not only improves the sensitivity of anomaly detection, but also effectively distinguishes actual hydrological phenomena from the noise in the data collection process. Through the verification of historical data, the generated historical hydrological comparison data provides richer background information for hydrological monitoring, which can effectively support decision makers to make scientific judgments when dealing with drought and other water resources management issues.

[0034] Preferably, step S32 includes the following steps:

[0035] Step S321: using the time series interpolation method to perform time stamp synchronization alignment processing on the horizontal hydrological data, the vertical hydrological data and the historical hydrological comparison data to generate a hydrological multi-dimensional time stamp aligned data set;

[0036] Step S322: fitting the variation trend of the hydrological multidimensional time stamp alignment data set through a radial basis function network to generate a multidimensional fitting analysis hydrological station data set;

[0037] Step S323: draw a two-dimensional fitting graph for the multi-dimensional fitting analysis hydrological station data set to generate a hydrological two-dimensional data fitting graph;

[0038] Step S324: performing deviation analysis on the hydrological two-dimensional data fitting graph, locating the abnormal fluctuation range, and generating hydrological fitting abnormal data.

[0039] The present invention uses a time series interpolation method to synchronize the timestamps of horizontal hydrological data, vertical hydrological data and historical hydrological comparison data, and the generated hydrological multidimensional timestamp alignment data set effectively eliminates the data inconsistency caused by time differences. This process provides a reliable basis for subsequent analysis, ensures the comparability between different data sources, and enables subsequent trend analysis and anomaly detection to be performed in the same time dimension, thereby enhancing the scientific nature of the analysis results. The radial basis function network is used to fit the change trend of the hydrological multidimensional timestamp alignment data set, which can not only capture the nonlinear relationship in the data, but also more accurately predict future trends. Compared with traditional linear fitting technology, this method provides a more flexible and effective data modeling capability, so that the change trend of hydrological data can be deeply excavated and accurately described. In addition, the generated multidimensional fitting analysis hydrological station data set not only reflects the complex relationship between various hydrological parameters, but also provides important support for decisions such as drought warning and resource allocation. Drawing a two-dimensional fitting graph based on the multidimensional fitting analysis data set makes the visualization of hydrological data more intuitive. This visualization result not only makes it easier for data analysts to quickly understand the overall trend of hydrological changes, but also provides a clear reference for decision makers, thereby improving the efficiency of information communication. By performing deviation analysis on the hydrological two-dimensional data fitting diagram, the abnormal fluctuation range can be effectively located and hydrological fitting abnormal data can be generated. This process enhances the ability to identify abnormal events, allowing potential hydrological risks to be discovered and handled in a timely manner, thereby providing strong support for drought monitoring and water resources management.

[0040] Preferably, step S4 comprises the following steps:

[0041] Step S41: Acquire historical drought data and geographic location data;

[0042] Step S42: performing layered comparison on the hydrological drought anomaly data and the historical drought data to generate a drought characteristic similarity data set; mapping the drought characteristic similarity data set to the water source area through the geographic location data to perform range consistency correction to generate a drought characteristic prediction optimization model;

[0043] Step S43: The drought characteristic prediction optimization model is used to predict drought trends, and multi-dimensional drought monitoring prediction data is generated, thereby completing the drought monitoring operation of the hydrological station.

[0044] The present invention lays the foundation for subsequent analysis by acquiring historical drought data and geographic location data, so that drought phenomena can be fully analyzed in spatial and temporal dimensions. Historical drought data provides empirical evidence for past drought events, while geographic location data provides important background information for the spatial distribution of drought characteristics. This combination provides a comprehensive perspective for understanding the complexity of drought phenomena. By layering and comparing hydrological drought anomaly data with historical drought data, the drought characteristic similarity data set generated effectively captures the similarities and differences between drought characteristics. This process not only improves the relevance of the data, but also provides necessary input for the establishment of subsequent feature prediction models. The range consistency correction of the drought characteristic similarity data set is performed through geographic location data, which further enhances the applicability and accuracy of the model, so that the drought characteristic prediction optimization model can more realistically reflect the characteristics of the water source area. The drought trend prediction of the drought characteristic prediction optimization model can not only generate multi-dimensional drought monitoring prediction data, but also provide important decision-making support for the dynamic monitoring of drought. This process uses the combination of historical data and spatial information to promote the prediction ability of future drought conditions, so that the identification and response measures of potential drought risks can be deployed in advance, thereby effectively reducing the negative impact of drought on water resources management.

[0045] Preferably, step S42 includes the following steps:

[0046] Step S421: Calculate the similarity between the hydrological drought anomaly data and the historical drought data to generate a drought similarity data set; perform layered comparison on the drought similarity data set to generate a drought characteristic similarity data set;

[0047] Step S422: Mapping the drought characteristic similarity data set to the water source area through the geographical location data to perform range consistency correction to generate regional drought correction data;

[0048] Step S423: Optimize the drought data level of the regional drought correction data, generate a drought disaster prediction model, and generate a drought characteristic prediction optimization model.

[0049] The present invention enables researchers to identify the commonality and change trend of drought phenomena by calculating the similarity between hydrological drought anomaly data and historical drought data, and the generated drought similarity data set provides key input information for subsequent analysis. By layering and comparing the drought similarity data set, a drought feature similarity data set is further generated, so that the data can be deeply analyzed at the feature level, thereby revealing the similarities and differences of different drought events, and providing a theoretical basis for understanding the complexity of drought. The drought feature similarity data set is corrected for range consistency through geographic location data, which not only enhances the spatial adaptability of the data, but also ensures the accuracy of drought characteristics in specific water source areas. This process effectively combines drought phenomena with their geographical environment, provides a more comprehensive perspective for drought feature prediction, and ensures that the corrected regional drought data has higher reliability and applicability. By hierarchically optimizing the regional drought correction data, the drought feature prediction optimization model generated not only improves the hierarchy of drought data, but also enhances the prediction ability of the model. This model can more accurately identify potential drought risks when analyzing and predicting drought disasters, and provides data support for relevant decisions. This series of steps has built a complete drought monitoring and forecasting system, promoted the multi-level integration and application of data, and effectively improved the early warning capability and response speed to drought events.

[0050] In this specification, a hydrological station drought monitoring system for a rural water supply project is provided, which is used to perform the above-mentioned hydrological station drought monitoring method for a rural water supply project. The hydrological station drought monitoring system for a rural water supply project includes:

[0051] Hydrological data acquisition and processing module: used to obtain hydrological site monitoring data sets; perform data preprocessing on the hydrological site monitoring data sets to generate hydrological processing data sets;

[0052] Data encryption and cloud transmission module: used to encrypt the hydrological processing data set to generate a hydrological encrypted data set; transmit the hydrological encrypted data set to the preset cloud platform to generate a hydrological cloud platform data set;

[0053] Multidimensional verification and anomaly detection module: used to perform horizontal verification, multidimensional parameter vertical verification and historical data verification on the hydrological cloud platform data set, generate horizontal hydrological data, vertical hydrological data and historical hydrological comparison data; draw two-dimensional fitting graphs of horizontal hydrological data, vertical hydrological data and historical hydrological comparison data, confirm hydrological anomalies, and generate hydrological drought anomaly data;

[0054] Historical data comparison and distribution correction module: used to obtain historical drought data; compare hydrological drought anomaly data and historical drought data in layers, and map them to water source areas for distribution correction, thereby completing drought monitoring operations at hydrological stations.

[0055] The beneficial effect of the present invention is that the reliability and accuracy of hydrological data are significantly improved through systematic steps and modular processing mechanisms. First, by obtaining the hydrological site monitoring data set and performing effective data processing, the integrity and validity of the data are ensured, which lays a solid foundation for subsequent analysis. The data encryption link not only ensures the security of the data, but also realizes the efficient integration and sharing of resources by transmitting the processed data to the cloud platform. This cloud data storage and management mode enables the data of different hydrological monitoring points to be updated in real time and easy to access, enhancing the flexibility and operability of monitoring. In the data verification stage, horizontal and vertical multi-dimensional parameter verification methods are adopted to effectively improve the accuracy and credibility of the data. Through the horizontal verification of the hydrological cloud platform data set, the flow and water level changes between different monitoring points are effectively compared, thereby identifying potential abnormalities. At the same time, the longitudinal verification method ensures the consistency of hydrological data in time series by analyzing different dimensional data (such as flow, rainfall and water quality) of the same water source, thereby eliminating the possibility of equipment failure or data transmission problems. Finally, by comparing the hydrological drought anomaly data with the historical drought data in layers and correcting the regional mapping, the method can dynamically adjust the monitoring strategy and more accurately reflect the regional hydrological conditions. This comprehensive analysis method not only improves the accuracy of drought monitoring, but also provides a scientific basis for decision makers, which helps to formulate effective water resource management strategies. Therefore, the present invention solves the problems of insufficient data security, inconvenient information sharing, and difficulty in identifying abnormal situations in traditional hydrological monitoring through systematic data collection, encryption, cloud transmission, and multi-dimensional verification, thereby improving the efficiency and accuracy of hydrological monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 A schematic flow chart of the steps of a method for monitoring drought at a hydrological station of a rural water supply project;

[0057] Figure 2 for Figure 1 Detailed implementation steps of step S3 in FIG.

[0058] Figure 3 for Figure 2 Detailed implementation steps of step S31 in FIG.

[0059] Figure 4 for Figure 2 Detailed implementation steps of step S32;

[0060] 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

[0061] The following is a clear and complete description of the technical method of the present invention 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.

[0062] In addition, the accompanying drawings are only schematic diagrams 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 thus their repeated description will be omitted. It should be understood that although the terms "first", "second", etc. may be used here to describe each unit, 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 embodiment, the first unit can be referred to as the second unit, and similarly the second unit can be referred to as the first unit. The term "and / or" used here includes any and all combinations of one or more of the listed associated items.

[0063] To achieve this, please refer to Figures 1 to 4 , a method for monitoring drought at a hydrological station of a rural water supply project, the method comprising the following steps:

[0064] Step S1: Acquire a hydrological site monitoring data set; perform data preprocessing on the hydrological site monitoring data set to generate a hydrological processing data set;

[0065] Step S2: Encrypting the hydrological processing data set to generate a hydrological encrypted data set; transmitting the hydrological encrypted data set to a preset cloud platform to generate a hydrological cloud platform data set;

[0066] Step S3: Perform horizontal verification, multi-dimensional parameter vertical verification and historical data verification on the hydrological cloud platform data set to generate horizontal hydrological data, vertical hydrological data and historical hydrological comparison data; draw a two-dimensional fitting graph of the horizontal hydrological data, vertical hydrological data and historical hydrological comparison data, confirm hydrological anomalies, and generate hydrological drought anomaly data;

[0067] Step S4: Acquire historical drought data; compare the hydrological drought anomaly data and historical drought data in layers, and map them to the water source area for distribution correction, thereby completing the drought monitoring operation of the hydrological station.

[0068] The beneficial effect of the present invention is that the reliability and accuracy of hydrological data are significantly improved through systematic steps and modular processing mechanisms. First, by obtaining the hydrological site monitoring data set and performing effective data processing, the integrity and validity of the data are ensured, which lays a solid foundation for subsequent analysis. The data encryption link not only ensures the security of the data, but also realizes the efficient integration and sharing of resources by transmitting the processed data to the cloud platform. This cloud data storage and management mode enables the data of different hydrological monitoring points to be updated in real time and easy to access, enhancing the flexibility and operability of monitoring. In the data verification stage, horizontal and vertical multi-dimensional parameter verification methods are adopted to effectively improve the accuracy and credibility of the data. Through the horizontal verification of the hydrological cloud platform data set, the flow and water level changes between different monitoring points are effectively compared, thereby identifying potential abnormalities. At the same time, the longitudinal verification method ensures the consistency of hydrological data in time series by analyzing different dimensional data (such as flow, rainfall and water quality) of the same water source, thereby eliminating the possibility of equipment failure or data transmission problems. Finally, by comparing the hydrological drought anomaly data with the historical drought data in layers and correcting the regional mapping, the method can dynamically adjust the monitoring strategy and more accurately reflect the regional hydrological conditions. This comprehensive analysis method not only improves the accuracy of drought monitoring, but also provides a scientific basis for decision makers, which helps to formulate effective water resource management strategies. Therefore, the present invention solves the problems of insufficient data security, inconvenient information sharing, and difficulty in identifying abnormal situations in traditional hydrological monitoring through systematic data collection, encryption, cloud transmission, and multi-dimensional verification, thereby improving the efficiency and accuracy of hydrological monitoring.

[0069] In the embodiment of the present invention, reference Figure 1 The above is a schematic flow chart of the steps of a method for monitoring drought at a hydrological station of a rural water supply project according to the present invention. In this example, the method for monitoring drought at a hydrological station of a rural water supply project comprises the following steps:

[0070] Step S1: Acquire a hydrological site monitoring data set; perform data preprocessing on the hydrological site monitoring data set to generate a hydrological processing data set;

[0071] In the embodiment of the present invention, the acquisition of the hydrological site monitoring data set comes from various monitoring equipment and sensors at the hydrological site, including water level meters, flow meters and meteorological stations, etc. These devices can collect key hydrological information such as rainfall, river water level, groundwater level, etc. in real time. After the acquired data is initially screened, there are problems such as missing values, outliers and noise, so effective data preprocessing is required. Data preprocessing is to improve the data quality and the accuracy of subsequent analysis. Specific technical means include linear interpolation, moving average and noise filtering. When facing missing values, linear interpolation can effectively fill these gaps and generate continuous hydrological time series by estimating based on the values ​​of adjacent data points. In addition, the moving average method can be used to smooth data, reduce the impact of short-term fluctuations on the overall trend, and improve the interpretability of data. In the cleaning stage of the data set, signal processing techniques such as Fourier transform or wavelet transform are applied to effectively filter out high-frequency noise, thereby retaining the true characteristics of the data and enhancing the quality of the signal. After these preprocessing techniques, the hydrological processing data set finally generated will have higher integrity and consistency, laying a solid foundation for subsequent analysis and modeling.

[0072] Step S2: Encrypting the hydrological processing data set to generate a hydrological encrypted data set; transmitting the hydrological encrypted data set to a preset cloud platform to generate a hydrological cloud platform data set;

[0073] In the embodiment of the present invention, data encryption is an important means to protect sensitive information from unauthorized access. A symmetric encryption algorithm (such as AES, i.e., Advanced Encryption Standard) can be used to effectively encrypt the hydrological processing data set to generate a hydrological encrypted data set. This process ensures that even if the data is intercepted, unauthorized third parties cannot interpret its content by performing mathematical operations on the data block and the key. After the hydrological encrypted data set is generated, the secure transmission of the data is also crucial. To achieve this goal, an encrypted communication channel is established using a secure transmission protocol (such as TLS, i.e., Transport Layer Security Protocol) to ensure that it is not stolen or tampered with during data transmission. Through this encrypted channel, the hydrological encrypted data set is securely sent to the preset cloud platform to generate a hydrological cloud platform data set. In this process, the data integrity verification during the transmission process cannot be ignored. A hash algorithm (such as SHA-256) is used to generate the hash value of the data to ensure that the recipient can verify whether the received data is consistent with the sender, thereby preventing data damage or tampering during the transmission process. After the implementation of these technical means, the generated hydrological cloud platform data set is not only effectively protected during storage and transmission, but also ensures the confidentiality and integrity of the data.

[0074] Step S3: Perform horizontal verification, multi-dimensional parameter vertical verification and historical data verification on the hydrological cloud platform data set to generate horizontal hydrological data, vertical hydrological data and historical hydrological comparison data; draw a two-dimensional fitting graph of the horizontal hydrological data, vertical hydrological data and historical hydrological comparison data, confirm hydrological anomalies, and generate hydrological drought anomaly data;

[0075] In the embodiment of the present invention, horizontal validation is to compare and analyze data under different time, space or conditions, aiming to identify the consistency and anomaly of the data. Specifically, this process involves data correlation analysis, using the Pearson correlation coefficient or the Spearman rank correlation coefficient to evaluate the relationship between different hydrological variables, thereby generating horizontal hydrological data. In addition, longitudinal validation focuses on analyzing the changes of the same hydrological variable at different time points, which involves time series analysis techniques such as the autoregressive integrated moving average model (ARIMA) or seasonal decomposition to reveal the trend and cyclical changes of hydrological data, thereby generating longitudinal hydrological data. Historical data validation detects the rationality of current data by comparing it with historical hydrological data. This process can use a time series prediction model, take historical data as a benchmark, and evaluate the degree of deviation of current data through indicators such as the root mean square error (RMSE) or the mean absolute percentage error (MAPE), thereby generating historical hydrological comparison data. After completing the data validation, further two-dimensional fitting graph drawing is to visualize the data and help researchers quickly identify anomalies in hydrological data. This process uses regression analysis techniques, such as polynomial regression or curve fitting, to achieve data visualization by building a fitting model. During the drawing process, researchers can intuitively observe the distribution trend of the data and its abnormal fluctuations, thereby confirming the existence of abnormal hydrological drought data.

[0076] Step S4: Acquire historical drought data; compare the hydrological drought anomaly data and historical drought data in layers, and map them to the water source area for distribution correction, thereby completing the drought monitoring operation of the hydrological station.

[0077] In the embodiment of the present invention, obtaining historical drought data is the basis for building a drought monitoring system. These data include important parameters such as meteorological information, soil moisture, and hydrological flow in multiple historical periods, which can provide background support for the identification of drought characteristics. Hierarchical comparison of hydrological drought anomaly data and historical drought data is a key technical means. This process uses statistical analysis methods, such as analysis of variance (ANOVA) or multiple comparison tests, to evaluate the differences between drought characteristics at different levels. This hierarchical analysis can reveal the drought performance and similarities in different water source areas, providing a necessary basis for subsequent mapping. Specifically, researchers can classify data according to factors such as regional climate characteristics, soil types, and human activities, so as to achieve more accurate comparative analysis. By combining drought feature similarity data with a geographic information system (GIS) and mapping them to water source areas for distribution correction, the spatial accuracy of the analysis is further enhanced. GIS technology can effectively integrate drought data with geographic location data, and realize visualization and range consistency correction of drought characteristics in water source areas through spatial analysis algorithms (such as Kriging interpolation or inverse distance weighted method). This process can not only identify the geographical patterns of drought distribution, but also adjust the drought monitoring model to make it more consistent with the actual geographical environment. Finally, through the comprehensive application of the above technical means, the drought monitoring operation of the hydrological station is completed.

[0078] Preferably, step S1 comprises the following steps:

[0079] Step S11: Obtaining hydrological site monitoring data set;

[0080] Step S12: performing linear interpolation processing on the hydrological site monitoring data set to process missing values, and generating a hydrological missing value processing data set; performing noise filtering on the hydrological missing value processing data set to generate a hydrological cleaned data set; performing outlier removal processing on the hydrological cleaned data set to generate a hydrological outlier removal data set;

[0081] Step S13: performing scale normalization processing on the hydrological outlier removal data set to generate a hydrological preprocessing data set, wherein the hydrological preprocessing data set includes flow data, river water level change data, rainfall data and groundwater depth data.

[0082] In the embodiment of the present invention, obtaining the hydrological site monitoring data set is the starting point of the entire process, which involves integrating relevant hydrological data from multiple monitoring sites, meteorological stations and hydrological databases, including flow, river water level changes, rainfall and groundwater infiltration, etc. This process needs to ensure the diversity and representativeness of the data source to cover the hydrological change characteristics under different geographical regions and climatic conditions. Linear interpolation is applied to process missing values ​​to generate a hydrological missing value processing data set. Linear interpolation is a commonly used numerical method that estimates missing values ​​through the linear relationship between known data points, thereby improving the integrity of the data set. In addition, it is crucial to perform noise filtering on the hydrological missing value processing data set, which uses techniques such as low-pass filters or median filters to remove outliers or random fluctuations to generate a hydrological cleaning data set. This process helps to improve the signal-to-noise ratio of the data, thereby providing more accurate and stable basic data for subsequent analysis. Scale standardization is another important technical means to eliminate the impact of different dimensions and scales on data analysis. By standardizing the various indicators in the hydrological cleaning data set, such as Z-score standardization or Min-Max normalization, it can be ensured that each data item is compared and analyzed at the same scale. The final hydrological preprocessing data set contains a variety of hydrological variables, providing a solid data foundation for further statistical analysis, model building and trend prediction.

[0083] Preferably, step S2 comprises the following steps:

[0084] Step S21: encrypting the hydrological processing data set by using a symmetric encryption algorithm to generate a hydrological encrypted data set and a symmetric key;

[0085] Step S22: Send the hydrological encrypted data set to the preset cloud platform through the encryption protocol for data decryption to generate a hydrological decrypted data set; perform MD5 verification on the hydrological decrypted data set to generate a hydrological cloud platform data set.

[0086] In the embodiment of the present invention, the hydrological processing data set is encrypted by a symmetric encryption algorithm to prevent unauthorized access and data leakage. Symmetric encryption algorithms such as AES (Advanced Encryption Standard) are efficient and secure. The encryption process uses the same key to encrypt and decrypt data, thereby generating a hydrological encrypted data set and a symmetric key. This technical means can effectively protect the security of data during transmission, ensuring that only authorized users holding the key can access and decrypt the data. The hydrological encrypted data set is sent to a preset cloud platform through an encryption protocol for data decryption, further enhancing the secure transmission of data. Encryption protocols such as TLS (Transport Layer Security Protocol) can establish a secure communication channel to prevent data from being intercepted or tampered with during transmission. On the cloud platform, the process of decrypting the hydrological encrypted data set using a symmetric key generates a hydrological decrypted data set, which not only ensures the integrity of the data, but also ensures the availability of the data after being stored in the cloud. MD5 verification of the hydrological decrypted data set is an important means to ensure the integrity of data transmission. The MD5 hash function can effectively detect whether the data has been tampered with during transmission by generating a unique hash value for the data. By generating a hydrological cloud platform dataset, the consistency between the decrypted data and the original data can be confirmed, thereby improving the credibility of the data.

[0087] Preferably, step S22 includes the following steps:

[0088] Step S221: Establish a secure transmission channel through the TLS encryption protocol to generate a hydrological encrypted transmission channel;

[0089] Step S222: sending the hydrological encrypted data set and the symmetric key to a preset cloud platform through a hydrological encrypted transmission channel, and decrypting the hydrological encrypted data set using the symmetric key to generate a hydrological decrypted data set;

[0090] Step S223: Perform MD5 hash generation on the hydrological processing data set and the hydrological decrypted data set to generate MD5 original hydrological hash value and MD5 hydrological cloud platform hash value; perform hash value integrity matching on the MD5 original hydrological hash value and the MD5 hydrological cloud platform hash value to generate a hydrological cloud platform data set, wherein the hydrological cloud platform data set includes reservoir outflow, river water level changes, groundwater infiltration and rainfall data.

[0091] In the embodiment of the present invention, a secure transmission channel is established through TLS (Transport Layer Security Protocol), which is an encryption protocol widely used in network communications. Its core is to provide confidentiality, integrity and identity authentication for data transmission. By establishing a secure hydrological encrypted transmission channel, it is possible to effectively prevent eavesdropping and tampering of data during transmission, ensuring that sensitive hydrological data can be safely transmitted from the local system to the cloud platform. The hydrological encrypted data set and the symmetric key are sent to the preset cloud platform through the hydrological encrypted transmission channel, and the hydrological encrypted data set is decrypted using the symmetric key to generate a hydrological decrypted data set. The use of the symmetric encryption algorithm ensures the confidentiality of the data during storage and transmission, and the implementation of the decryption process ensures that the cloud platform can correctly access and use the encrypted data. In this process, the security of the data is further enhanced by using an encrypted channel to transmit the symmetric key and data. Generating MD5 hashes for the hydrological processing data set and the hydrological decryption data set is an important step in ensuring data integrity. The MD5 hash function can quickly determine whether the data has been tampered with or damaged by generating a unique hash value. After generating the MD5 original hydrological hash value and the MD5 hydrological cloud platform hash value, the hash value integrity match is performed to effectively confirm the accuracy and consistency of the decrypted data. This verification process ensures the reliability of the hydrological cloud platform dataset, which includes reservoir outflow, river water level changes, groundwater infiltration and rainfall data.

[0092] As an example of the present invention, refer to Figure 2 As shown, in this example, step S3 includes:

[0093] Step S31: Perform horizontal verification, multi-dimensional parameter vertical verification and historical data verification on the hydrological cloud platform data set to generate horizontal hydrological data, vertical hydrological data and historical hydrological comparison data;

[0094] Step S32: Draw a two-dimensional fitting graph of the horizontal hydrological data, the vertical hydrological data and the historical hydrological comparison data to generate a hydrological two-dimensional data fitting graph; perform abnormal fluctuation analysis on the hydrological two-dimensional data fitting graph, mark it, and generate hydrological fitting abnormal data;

[0095] Step S33: performing secondary confirmation of the abnormal fluctuation value of the hydrological fitting abnormal data to generate hydrological drought abnormal data.

[0096] In the embodiment of the present invention, horizontal verification, multi-dimensional parameter longitudinal verification and historical data verification are performed. The combination of these three verification methods can comprehensively evaluate the reliability of the hydrological cloud platform data set from different dimensions. Horizontal verification ensures the consistency of data in different contexts by comparing data in different time periods or under similar conditions; multi-dimensional parameter longitudinal verification involves cross-analysis of multiple related parameters such as flow, water level, rainfall and groundwater depth to identify potential relationships and change trends; historical data verification compares current data with past records to help identify abnormal changes and long-term trends. Drawing a two-dimensional fitting graph using horizontal hydrological data, vertical hydrological data and historical hydrological comparison data is actually a data visualization technology that displays the relationship and trend between data in a graphical way. The two-dimensional fitting graph not only facilitates the understanding of the overall trend of the data, but also provides an intuitive basis for subsequent abnormal fluctuation analysis. On this basis, abnormal fluctuation analysis is performed and significant anomalies are marked to generate hydrological fitting abnormal data. This process combines statistical analysis methods, such as standard deviation and threshold judgment, to identify data points outside a specific confidence interval to ensure that potential hydrological anomalies can be effectively captured. The secondary confirmation of abnormal fluctuation values ​​of hydrological fitting abnormal data is aimed at improving the accuracy of anomaly detection. Through this secondary confirmation mechanism, it is ensured that the identified abnormal fluctuations are not just accidental phenomena, but real hydrological changes, and finally hydrological drought anomaly data are generated. The implementation of this series of technical means ensures that the whole process from data acquisition to anomaly detection is highly rigorous and reliable, which helps to effectively identify hydrological anomalies such as drought and provide a scientific basis for subsequent water resources management and decision-making.

[0097] As an example of the present invention, refer to Figure 3 As shown, in this example, step S31 includes:

[0098] Step S311: tracing the outflow of the reservoir upstream to generate the outflow of the upstream reservoir; searching the downstream water level change of the river channel water level change to generate the downstream river channel water level change data; performing flow delay calculation on the outflow of the upstream reservoir and the downstream river channel water level change data to generate the river channel flow delay data; performing horizontal delay analysis on the river channel flow delay data to generate the river channel flow time series data; performing horizontal correlation analysis on the groundwater infiltration and rainfall data to generate the groundwater infiltration correlation analysis data; performing horizontal verification on the river channel flow time series data and the groundwater infiltration correlation analysis data to generate the horizontal hydrological data;

[0099] Step S312: extract the water source points of the reservoir outflow and the river water level change in a unified manner to generate water level-flow isotope data; perform physical quantity synchronous analysis and processing on the water level-flow isotope data to generate water level-flow synchronous comparison data; perform longitudinal verification of multi-dimensional parameters of water level, flow and water quality data on the water level-flow synchronous comparison data to generate longitudinal hydrological data;

[0100] Step S313: Acquire a historical hydrological site dataset; identify outliers in the historical hydrological site dataset and the hydrological cloud platform dataset using a Z score to generate hydrological fitting anomaly data; perform historical data verification on the hydrological fitting anomaly data to generate historical hydrological comparison data.

[0101] In the embodiment of the present invention, tracing the upstream source of the reservoir outflow is an analysis method based on time series data, which aims to track the source changes of the reservoir flow and generate the upstream reservoir outflow flow data. At the same time, by searching for the downstream water level change, real-time information of the river water level can be obtained. The core of this process is to combine the upstream flow with the downstream water level change through flow delay calculation to generate river flow delay data, which is crucial for understanding hydrological dynamics. Further lateral delay analysis helps to capture the changing trend of flow time series data and lay the foundation for the lateral correlation analysis between groundwater infiltration and rainfall, thereby generating groundwater infiltration correlation analysis data, forming a multi-dimensional hydrological data network, and finally through lateral verification, synthesizing various data sets to generate lateral hydrological data to ensure the consistency between data from different sources. The technical means of unified water source point extraction helps to integrate the reservoir outflow and river water level change data to generate water level-flow co-location data. The key to this step is the synchronous analysis of physical quantities to ensure the correspondence between flow and water level data in time and space to generate water level-flow synchronous comparison data. Subsequently, further multi-dimensional parameter longitudinal verification can integrate water level, flow and water quality data to generate longitudinal hydrological data. Such comprehensive analysis provides a global perspective and enhances the understanding of hydrological dynamic changes. By obtaining historical hydrological site data sets and identifying outliers with Z scores with the hydrological cloud platform data set, the use of technical means has achieved accurate detection of hydrological data anomalies. Z score is a statistical method that identifies anomalies that exceed the preset threshold by calculating the standardized value of the data and generates hydrological fitting anomaly data. Next, historical data verification of these anomaly data can effectively determine the degree of abnormality of the current hydrological state and generate historical hydrological comparison data.

[0102] As an example of the present invention, refer to Figure 4 As shown, in this example, step S34 includes:

[0103] Step S321: using the time series interpolation method to perform time stamp synchronization alignment processing on the horizontal hydrological data, the vertical hydrological data and the historical hydrological comparison data to generate a hydrological multi-dimensional time stamp aligned data set;

[0104] Step S322: fitting the variation trend of the hydrological multidimensional time stamp alignment data set through a radial basis function network to generate a multidimensional fitting analysis hydrological station data set;

[0105] Step S323: draw a two-dimensional fitting graph for the multi-dimensional fitting analysis hydrological station data set to generate a hydrological two-dimensional data fitting graph;

[0106] Step S324: performing deviation analysis on the hydrological two-dimensional data fitting graph, locating the abnormal fluctuation range, and generating hydrological fitting abnormal data.

[0107] In an embodiment of the present invention, a time series interpolation method is used to perform time stamp synchronization alignment processing on horizontal hydrological data, vertical hydrological data and historical hydrological comparison data, aiming to eliminate data inconsistencies caused by time differences, thereby generating a hydrological multidimensional time stamp alignment data set. This method can effectively fill in the gaps in the data through interpolation technology, ensure that data at different time points can accurately correspond during the analysis process, and enhance the integrity and availability of the data set. The radial basis function network (RBFN) is used to fit the change trend of the generated hydrological multidimensional time stamp alignment data set. This technical means is particularly suitable for dealing with nonlinear problems, and can capture potential patterns and trends in the data to generate a multidimensional fitting analysis hydrological site data set. RBFN maps the input data to a high-dimensional space by constructing a set of local basis functions to achieve a more accurate fitting effect, thereby laying the foundation for subsequent analysis. Drawing a two-dimensional fitting graph for the multidimensional fitting analysis hydrological site data set is an important part of visual analysis. In a graphical way, researchers can intuitively identify the relationship between data and its changing trend, which is convenient for subsequent analysis and decision-making. This process not only enhances the readability of the data, but also helps identify potential correlations between data of different dimensions, providing visual support for understanding hydrological dynamics. Deviation analysis is performed on the hydrological two-dimensional data fitting graph, and the abnormal fluctuation range is located. This process involves statistical analysis technology. By analyzing the deviation of the fitting graph, abnormal points in the data can be effectively identified, and hydrological fitting abnormal data can be generated.

[0108] Preferably, step S4 comprises the following steps:

[0109] Step S41: Acquire historical drought data and geographic location data;

[0110] Step S42: performing layered comparison on the hydrological drought anomaly data and the historical drought data to generate a drought characteristic similarity data set; mapping the drought characteristic similarity data set to the water source area through the geographic location data to perform range consistency correction to generate a drought characteristic prediction optimization model;

[0111] Step S43: The drought characteristic prediction optimization model is used to predict drought trends, and multi-dimensional drought monitoring prediction data is generated, thereby completing the drought monitoring operation of the hydrological station.

[0112] In the embodiment of the present invention, the process of obtaining historical drought data and geographic location data lays the foundation for subsequent analysis. These data provide historical background and spatial reference for the extraction of drought characteristics, ensuring the comprehensiveness and accuracy of the analysis. By layering and comparing the hydrological drought anomaly data with the historical drought data, a drought characteristic similarity data set is generated. This process uses data mining and similarity calculation technology, which can effectively identify the similarity between the current drought situation and historical drought events, and provides a basis for in-depth analysis of drought characteristics. The generated drought characteristic similarity data set not only includes the time series characteristics of drought events, but also includes its spatial distribution characteristics, reflecting the changing laws of drought in different regions. The drought characteristic similarity data set is mapped to the water source area through the geographic location data for range consistency correction, and a drought characteristic prediction optimization model is generated. In this process, the geographic information system (GIS) technology is used for spatial analysis to ensure the consistency and applicability of drought characteristics in space. The establishment of this model not only takes into account the attributes of the drought characteristics themselves, but also integrates geographical factors to form a more comprehensive drought characteristic prediction model, so that the prediction results are more practical. The drought trend prediction of the drought characteristic prediction optimization model is performed to generate multi-dimensional drought monitoring prediction data. This process involves a variety of statistical analysis methods and machine learning algorithms, which can effectively capture the evolution trends and patterns of drought by learning and modeling historical data.

[0113] Preferably, step S42 includes the following steps:

[0114] Step S421: Calculate the similarity between the hydrological drought anomaly data and the historical drought data to generate a drought similarity data set; perform layered comparison on the drought similarity data set to generate a drought characteristic similarity data set;

[0115] Step S422: Mapping the drought characteristic similarity data set to the water source area through the geographical location data to perform range consistency correction to generate regional drought correction data;

[0116] Step S423: Optimize the drought data level of the regional drought correction data, generate a drought disaster prediction model, and generate a drought characteristic prediction optimization model.

[0117] In the embodiment of the present invention, similarity calculation is implemented to compare hydrological drought anomaly data with historical drought data to generate a drought similarity data set. This process uses methods such as cosine similarity and Euclidean distance to quantify the similarity between data and identify the correlation between drought events in time and space, thereby providing basic data support for subsequent analysis. A hierarchical comparison of drought similarity data sets is performed to generate a drought feature similarity data set. This step involves data classification and clustering technology. By analyzing drought features at different levels, similar drought patterns and trends are identified. This process not only improves the interpretability of the data, but also enhances the understanding of the diversity of drought features, so that drought performance under different conditions is more accurately described. The drought feature similarity data set is mapped to the water source area through geographic location data for range consistency correction to generate regional drought correction data. This process uses geographic information system (GIS) and spatial analysis technology to ensure the spatial adaptability and accuracy of the data by considering geographic features and their impact on drought features. In this process, interpolation methods (such as Kriging interpolation) and geographically weighted regression and other technologies can better reflect the changes in drought features in a specific geographical area and provide a more accurate reference for water resources management. The drought data level of the regional drought correction data is optimized and a drought disaster prediction model is generated. This process uses multiple regression analysis, machine learning models (such as random forests, support vector machines, etc.) and time series analysis methods to model the corrected data and identify potential risks and influencing factors of drought.

[0118] In this specification, a hydrological station drought monitoring system for a rural water supply project is provided, which is used to perform the above-mentioned hydrological station drought monitoring method for a rural water supply project. The hydrological station drought monitoring system for a rural water supply project includes:

[0119] Hydrological data acquisition and processing module: used to obtain hydrological site monitoring data sets; perform data preprocessing on the hydrological site monitoring data sets to generate hydrological processing data sets;

[0120] Data encryption and cloud transmission module: used to encrypt the hydrological processing data set to generate a hydrological encrypted data set; transmit the hydrological encrypted data set to the preset cloud platform to generate a hydrological cloud platform data set;

[0121] Multidimensional verification and anomaly detection module: used to perform horizontal verification, multidimensional parameter vertical verification and historical data verification on the hydrological cloud platform data set, generate horizontal hydrological data, vertical hydrological data and historical hydrological comparison data; draw two-dimensional fitting graphs of horizontal hydrological data, vertical hydrological data and historical hydrological comparison data, confirm hydrological anomalies, and generate hydrological drought anomaly data;

[0122] Historical data comparison and distribution correction module: used to obtain historical drought data; compare hydrological drought anomaly data and historical drought data in layers, and map them to water source areas for distribution correction, thereby completing drought monitoring operations at hydrological stations.

[0123] 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 intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0124] 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 monitoring drought at a hydrological station of a rural water supply project, characterized in that: The following steps are involved: Step S1: Acquire a hydrological site monitoring data set; perform data preprocessing on the hydrological site monitoring data set to generate a hydrological processing data set; Step S2: Encrypting the hydrological processing data set to generate a hydrological encrypted data set; transmitting the hydrological encrypted data set to a preset cloud platform to generate a hydrological cloud platform data set; Step S3: Perform horizontal verification, multi-dimensional parameter vertical verification and historical data verification on the hydrological cloud platform data set to generate horizontal hydrological data, vertical hydrological data and historical hydrological comparison data; draw a two-dimensional fitting graph of the horizontal hydrological data, vertical hydrological data and historical hydrological comparison data, confirm hydrological anomalies, and generate hydrological drought anomaly data, wherein step S3 includes the following steps: Step S31: Perform horizontal verification, multi-dimensional parameter vertical verification and historical data verification on the hydrological cloud platform data set to generate horizontal hydrological data, vertical hydrological data and historical hydrological comparison data; wherein step S31 includes the following steps: Step S311: tracing the outflow of the reservoir upstream to generate the outflow of the upstream reservoir; searching the downstream water level change of the river channel water level change to generate the downstream river channel water level change data; performing flow delay calculation on the outflow of the upstream reservoir and the downstream river channel water level change data to generate the river channel flow delay data; performing horizontal delay analysis on the river channel flow delay data to generate the river channel flow time series data; performing horizontal correlation analysis on the groundwater infiltration and rainfall data to generate the groundwater infiltration correlation analysis data; performing horizontal verification on the river channel flow time series data and the groundwater infiltration correlation analysis data to generate the horizontal hydrological data; Step S312: extract the water source points of the reservoir outflow and the river water level change in a unified manner to generate water level-flow isotope data; perform physical quantity synchronous analysis and processing on the water level-flow isotope data to generate water level-flow synchronous comparison data; perform longitudinal verification of multi-dimensional parameters of water level, flow and water quality data on the water level-flow synchronous comparison data to generate longitudinal hydrological data; Step S313: Acquire a historical hydrological site dataset; identify outliers on the historical hydrological site dataset and the hydrological cloud platform dataset using a Z score to generate hydrological fitting anomaly data; perform historical data verification on the hydrological fitting anomaly data to generate historical hydrological comparison data; Step S32: Draw a two-dimensional fitting graph of the horizontal hydrological data, the vertical hydrological data and the historical hydrological comparison data to generate a hydrological two-dimensional data fitting graph; perform abnormal fluctuation analysis on the hydrological two-dimensional data fitting graph, mark it, and generate hydrological fitting abnormal data; wherein step S32 includes the following steps: Step S321: using the time series interpolation method to perform time stamp synchronization alignment processing on the horizontal hydrological data, the vertical hydrological data and the historical hydrological comparison data to generate a hydrological multi-dimensional time stamp aligned data set; Step S322: fitting the variation trend of the hydrological multidimensional time stamp alignment data set through a radial basis function network to generate a multidimensional fitting analysis hydrological station data set; Step S323: draw a two-dimensional fitting graph for the multi-dimensional fitting analysis hydrological station data set to generate a hydrological two-dimensional data fitting graph; Step S324: performing deviation analysis on the hydrological two-dimensional data fitting graph, locating the abnormal fluctuation range, and generating hydrological fitting abnormal data; Step S33: performing secondary confirmation of abnormal fluctuation values ​​of hydrological fitting abnormal data to generate hydrological drought abnormal data; Step S4: Acquire historical drought data; compare the hydrological drought anomaly data and historical drought data in layers, and map them to the water source area for distribution correction, thereby completing the drought monitoring operation of the hydrological station.

2. The method for monitoring drought at a hydrological station of a rural water supply project according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Obtaining hydrological site monitoring data set; Step S12: performing linear interpolation processing on the hydrological site monitoring data set to process missing values, and generating a hydrological missing value processing data set; performing noise filtering on the hydrological missing value processing data set to generate a hydrological cleaned data set; performing outlier removal processing on the hydrological cleaned data set to generate a hydrological outlier removal data set; Step S13: performing scale normalization processing on the hydrological outlier removal data set to generate a hydrological preprocessing data set, wherein the hydrological preprocessing data set includes flow data, river water level change data, rainfall data and groundwater depth data.

3. The method for monitoring drought at a hydrological station of a rural water supply project according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: encrypting the hydrological processing data set by using a symmetric encryption algorithm to generate a hydrological encrypted data set and a symmetric key; Step S22: Send the hydrological encrypted data set to the preset cloud platform through the encryption protocol for data decryption to generate a hydrological decrypted data set; perform MD5 verification on the hydrological decrypted data set to generate a hydrological cloud platform data set.

4. The method for monitoring drought at a hydrological station of a rural water supply project according to claim 3, characterized in that: Step S22 includes the following steps: Step S221: Establish a secure transmission channel through the TLS encryption protocol to generate a hydrological encrypted transmission channel; Step S222: sending the hydrological encrypted data set and the symmetric key to a preset cloud platform through a hydrological encrypted transmission channel, and decrypting the hydrological encrypted data set using the symmetric key to generate a hydrological decrypted data set; Step S223: Perform MD5 hash generation on the hydrological processing data set and the hydrological decrypted data set to generate MD5 original hydrological hash value and MD5 hydrological cloud platform hash value; perform hash value integrity matching on the MD5 original hydrological hash value and the MD5 hydrological cloud platform hash value to generate a hydrological cloud platform data set, wherein the hydrological cloud platform data set includes reservoir outflow, river water level changes, groundwater infiltration and rainfall data.

5. The method for monitoring drought at a hydrological station of a rural water supply project according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: Acquire historical drought data and geographic location data; Step S42: performing layered comparison on the hydrological drought anomaly data and the historical drought data to generate a drought characteristic similarity data set; mapping the drought characteristic similarity data set to the water source area through the geographic location data to perform range consistency correction to generate a drought characteristic prediction optimization model; Step S43: The drought characteristic prediction optimization model is used to predict drought trends, and multi-dimensional drought monitoring prediction data is generated, thereby completing the drought monitoring operation of the hydrological station.

6. The method for monitoring drought at a hydrological station of a rural water supply project according to claim 5, characterized in that: Step S42 includes the following steps: Step S421: Calculate the similarity between the hydrological drought anomaly data and the historical drought data to generate a drought similarity data set; perform layered comparison on the drought similarity data set to generate a drought characteristic similarity data set; Step S422: Mapping the drought characteristic similarity data set to the water source area through the geographical location data to perform range consistency correction to generate regional drought correction data; Step S423: Optimize the drought data level of the regional drought correction data, generate a drought disaster prediction model, and generate a drought characteristic prediction optimization model.

7. A drought monitoring system for hydrological stations of rural water supply projects, characterized in that: For executing the method for monitoring drought at a hydrological station of a rural water supply project according to claim 1, the system for monitoring drought at a hydrological station of a rural water supply project comprises: Hydrological data acquisition and processing module: used to obtain hydrological site monitoring data sets; perform data preprocessing on the hydrological site monitoring data sets to generate hydrological processing data sets; Data encryption and cloud transmission module: used to encrypt the hydrological processing data set to generate a hydrological encrypted data set; transmit the hydrological encrypted data set to the preset cloud platform to generate a hydrological cloud platform data set; Multidimensional verification and anomaly detection module: used to perform horizontal verification, multidimensional parameter vertical verification and historical data verification on the hydrological cloud platform data set, generate horizontal hydrological data, vertical hydrological data and historical hydrological comparison data; draw two-dimensional fitting graphs of horizontal hydrological data, vertical hydrological data and historical hydrological comparison data, confirm hydrological anomalies, and generate hydrological drought anomaly data; Historical data comparison and distribution correction module: used to obtain historical drought data; compare hydrological drought anomaly data and historical drought data in layers, and map them to water source areas for distribution correction, thereby completing drought monitoring operations at hydrological stations.

Images