Canal ecology monitoring method and system based on multi-source heterogeneous data, and electronic equipment

Abstract

The invention discloses a canal ecology monitoring method and system based on multi-source heterogeneous data and electronic equipment, and relates to the field of canal monitoring, and the method comprises the steps: obtaining multi-source heterogeneous data obtained by monitoring the water ecology of a target canal, the multi-source heterogeneous data comprises multi-class sensor monitoring data, remote sensing and unmanned aerial vehicle monitoring data and routing inspection input data; performing classification processing on the multi-source heterogeneous data to obtain a multi-dimensional monitoring data sequence based on a data transmission period; standardizing the multi-dimensional monitoring data sequence, and analyzing the change trend of the water quality and hydro meteorological indexes based on the standardized multi-dimensional monitoring data sequence; and according to the change trend analysis result, generating a canal ecology monitoring report and a water ecology emergency plan. The technical problems that the monitoring mode of a canal water ecology monitoring system in the prior art is single, and multi-dimensional changes of a water ecosystem cannot be comprehensively reflected are solved.

Description

Technical Field

[0001] This invention relates to the field of canal monitoring technology or other related fields. Specifically, it relates to a canal ecological monitoring method and system, and electronic equipment based on multi-source heterogeneous data. Background Technology

[0002] With socio-economic development and continuous population growth, large canals, as important waterways and water resource allocation facilities, play an irreplaceable role in promoting regional economic development, improving the water environment, and maintaining ecological balance. However, the healthy operation of canal aquatic ecosystems faces various challenges, including but not limited to water pollution, hydrological and meteorological changes, and ecological imbalance.

[0003] However, the canal water ecological management methods in related technologies have significant shortcomings in data collection and processing, monitoring and early warning, and decision support. Traditional canal water ecological monitoring systems often rely on single monitoring methods, such as water quality sampling and analysis or routine meteorological observations. This results in limited coverage of monitoring data and an inability to fully reflect the multidimensional changes in the water ecosystem.

[0004] Furthermore, during the monitoring of the water ecology of large canals, changes in water quality and hydrological and meteorological indicators are influenced by multiple factors and exhibit complex characteristics across different time and spatial scales. The lack of scientifically effective models and algorithms to accurately analyze the changing trends and risks of different indicators leads to insufficient precision in the monitoring and early warning of water quality, hydrological and meteorological indicators, making it difficult to promptly detect potential environmental risks.

[0005] There is currently no effective solution to the above problems. Summary of the Invention

[0006] This invention provides a canal ecological monitoring method, system, and electronic equipment based on multi-source heterogeneous data, to at least solve the technical problem that the monitoring methods of canal water ecological monitoring systems in related technologies are singular and cannot fully reflect the multi-dimensional changes of the water ecosystem.

[0007] According to one aspect of the present invention, a canal ecological monitoring method based on multi-source heterogeneous data is provided, comprising: acquiring multi-source heterogeneous data obtained by monitoring the water ecology of a target canal, wherein the multi-source heterogeneous data includes: monitoring data from multiple types of sensors, remote sensing and UAV monitoring data, and inspection and data entry data; classifying the multi-source heterogeneous data to obtain a multi-dimensional monitoring data sequence based on the data transmission cycle; standardizing the multi-dimensional monitoring data sequence and analyzing the changing trends of water quality and hydro-meteorological indicators based on the standardized multi-dimensional monitoring data sequence; and generating a canal ecological monitoring report and a water ecology emergency plan based on the trend analysis results.

[0008] Optionally, the steps for obtaining multi-source heterogeneous data from monitoring the water ecology of the target canal include: collecting time-series data of multiple water quality indicators through water quality sensors, collecting time-series data of multiple meteorological indicators through meteorological sensors, collecting time-series data of multiple hydrological dynamic indicators through hydrological sensors, and monitoring the ecological environment data around the canal in real time through video monitoring equipment to obtain the multi-sensor monitoring data; monitoring the ecological status data of the target canal and its surrounding area through satellite remote sensing, and monitoring the ecological environment change data of the target canal and its surrounding area through drones to obtain the remote sensing and drone monitoring data; and receiving canal inspection data, emergency event data, and special inspection data entered by inspection personnel to obtain the inspection data.

[0009] Optionally, the step of classifying the multi-source heterogeneous data to obtain a multi-dimensional monitoring data sequence based on the data transmission cycle includes: obtaining a set of data transmission cycles in the water ecological monitoring needs of the target canal, wherein the set of data transmission cycles includes T data transmission cycles, where T is a positive integer; determining the data transmission cycle corresponding to each type of sensor monitoring data, the remote sensing and UAV monitoring data, and the inspection and recording data; classifying the multi-source heterogeneous data according to the data transmission cycle to form multiple data subsets; and constructing a multi-dimensional monitoring data sequence based on the data transmission cycle for each data subset corresponding to the data transmission cycle.

[0010] Optionally, the step of standardizing the multi-dimensional monitoring data sequence includes: performing a uniformity test on the distribution characteristics of the multi-dimensional monitoring data sequence; performing nonlinear standardization on the tested multi-dimensional monitoring data sequence to output a weighted optimized multi-dimensional monitoring data sequence, wherein, in the nonlinear standardization process, different weight factors are assigned to each data subset in the multi-dimensional monitoring data sequence for different time periods based on the canal's ecological conditions and environmental changes, and the weight factors are used to perform weighted optimization on the data subsets of different data transmission cycles.

[0011] Optionally, the step of analyzing the changing trends of water quality and hydro-meteorological indicators based on the standardized multi-dimensional monitoring data sequence includes: analyzing the water quality indicator data in the standardized multi-dimensional monitoring data sequence using a weighted least squares model to obtain the water quality change trend of the canal. During the water quality indicator data analysis, the parameters of the water quality indicators are calculated based on the weighted linear regression model corresponding to each type of water quality indicator and the weighting factors for different data collection periods. Combining the water quality change trend of the canal and the reference values ​​of the water quality indicators, the risk status of different water quality indicators in the aquatic ecosystem of the target canal is assessed to obtain the water quality assessment results and the first early warning information.

[0012] Optionally, the step of analyzing the changing trends of water quality and hydrometeorological indicators based on the standardized multi-dimensional monitoring data sequence further includes: obtaining a set of multiple types of hydrometeorological indicators and a calculation formula corresponding to each hydrometeorological indicator, wherein the set of multiple types of hydrometeorological indicators includes at least flow rate, water level, water temperature, and rainfall; extracting indicator data corresponding to each type of hydrometeorological indicator from the standardized multi-dimensional monitoring data sequence, and determining the indicator weight corresponding to the hydrometeorological indicator; inputting the indicator data and indicator weight into the calculation formula corresponding to the hydrometeorological indicator to obtain the changing trend of the hydrometeorological indicator; and assessing the risk of different hydrometeorological indicators in the water ecosystem of the target canal based on the changing trend of the hydrometeorological indicator and the meteorological indicator reference value, to obtain the hydrometeorological assessment result and the second early warning information.

[0013] Optionally, the step of generating a canal ecological monitoring report and a water ecological emergency plan based on the trend analysis results further includes: integrating the multi-dimensional monitoring data sequence, water quality assessment results and first early warning information, the hydrological and meteorological assessment results and second early warning information to generate the canal ecological monitoring report; and identifying the risks of canal water quality deterioration and hydrological disasters based on the trend analysis results, and matching them with a preset water ecological emergency plan.

[0014] According to another aspect of the present invention, a canal ecological monitoring system based on multi-source heterogeneous data is also provided, comprising: a multi-source heterogeneous data acquisition unit, used to acquire multi-source heterogeneous data obtained by monitoring the water ecology of a target canal, wherein the multi-source heterogeneous data includes: monitoring data from multiple types of sensors, remote sensing and UAV monitoring data, and inspection and data entry data; a data classification unit, used to classify the multi-source heterogeneous data to obtain a multi-dimensional monitoring data sequence based on the data transmission cycle; a data change trend analysis unit, used to standardize the multi-dimensional monitoring data sequence and analyze the change trends of water quality and hydro-meteorological indicators based on the standardized multi-dimensional monitoring data sequence; and a monitoring report generation unit, used to generate a canal ecological monitoring report and a water ecology emergency plan based on the change trend analysis results.

[0015] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to execute any of the above-described canal ecological monitoring methods based on multi-source heterogeneous data.

[0016] According to another aspect of the present invention, an electronic device is also provided, including one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the canal ecological monitoring method based on multi-source heterogeneous data as described above.

[0017] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements the steps of the canal ecological monitoring method based on multi-source heterogeneous data as described above.

[0018] In this disclosure, multi-source heterogeneous data is obtained from monitoring the water ecology of a target canal. This multi-source heterogeneous data includes monitoring data from various sensors, remote sensing and UAV monitoring data, and inspection and data entry data. The multi-source heterogeneous data is classified and processed to obtain a multi-dimensional monitoring data sequence based on the data transmission cycle. The multi-dimensional monitoring data sequence is standardized, and the changing trends of water quality and hydro-meteorological indicators are analyzed based on the standardized multi-dimensional monitoring data sequence. Based on the results of the trend analysis, a canal ecological monitoring report and a water ecology emergency plan are generated.

[0019] Based on the aforementioned publicly available information, it is possible to efficiently integrate multi-source heterogeneous data, including monitoring data from various sensors, remote sensing and drone monitoring data, and inspection and data entry data. By constructing multi-dimensional monitoring data sequences based on data transmission cycles, data from different sources and in different formats can be classified and integrated according to time series. This enables the analysis of changing trends in water quality and hydrological and meteorological indicators, achieving precise monitoring of multi-dimensional changes in the aquatic ecosystem. This comprehensively reflects the multi-dimensional changes in the aquatic ecosystem, thereby solving the technical problem that the monitoring methods of canal water ecosystem monitoring systems in related technologies are singular and cannot comprehensively reflect the multi-dimensional changes in the aquatic ecosystem. Attached Figure Description

[0020] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0021] Figure 1 This is a flowchart of an optional canal ecological monitoring method based on multi-source heterogeneous data according to an embodiment of the present invention;

[0022] Figure 2 This is a schematic diagram of an optional integrated intelligent management and control system for canal water ecology based on multi-source heterogeneous data according to an embodiment of the present invention;

[0023] Figure 3This is a schematic diagram of an optional canal ecological monitoring system based on multi-source heterogeneous data according to an embodiment of the present invention;

[0024] Figure 4 This is a hardware structure block diagram of an electronic device (or mobile device) that performs a canal ecological monitoring method based on multi-source heterogeneous data according to an embodiment of the present invention. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] To facilitate understanding of the present invention by those skilled in the art, some terms or nouns involved in the various embodiments of the present invention are explained below:

[0028] Dissolved oxygen (DO) is the amount of oxygen dissolved in water. Its value directly affects the survival status of aquatic organisms and the self-purification capacity of water, and is one of the important indicators in water quality monitoring.

[0029] pH value, an indicator that measures the concentration of hydrogen ions in a solution, is used to assess the acidity or alkalinity of water and has a significant impact on the health of aquatic ecosystems.

[0030] Chemical Oxygen Demand (COD) is the amount of oxygen required to oxidize organic pollutants in water. It is an important parameter for assessing the degree of water pollution and is used to monitor the organic matter content of water bodies.

[0031] Suspended solids (SS) refer to the solid matter that is suspended in water and does not settle. Their content can be used to assess the degree of pollution of water bodies by suspended particles and is an important indicator in water quality monitoring.

[0032] Geographic Information System (GIS) is a system for acquiring, storing, retrieving, analyzing, and displaying geographic data to support geographic location-related decision-making.

[0033] Radio Frequency Identification (RFID) uses radio signals for non-contact, two-way data communication to identify target objects and read relevant data. It can be used for rapid identification and entry of data during manual inspections, improving the efficiency and accuracy of data input.

[0034] Weighted Least Squares (WLS) is a statistical linear regression analysis method that optimizes the model's fit by assigning different weights to different data points. It is used in linear regression models for analyzing water quality change trends to improve prediction accuracy.

[0035] It should be noted that the information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, and displayed data) collected in this public disclosure are information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with the relevant laws, regulations, and standards of the relevant regions, necessary confidentiality measures have been taken, and they do not violate public order and good morals. Corresponding operation entry points are provided for users to choose to authorize or refuse. For example, this system has interfaces with relevant users or organizations. Before obtaining relevant information, a request to obtain the information needs to be sent to the aforementioned user or organization through the interface, and the relevant information is obtained only after receiving consent from the aforementioned user or organization.

[0036] It should be noted that in this disclosure, customer information is collected and analyzed, and users are provided with corresponding operation entry points to choose whether to agree to or reject the automated decision results; if the user chooses to reject, the process will proceed to the expert decision-making process.

[0037] The following embodiments of the present invention can be applied to various canal ecological monitoring systems based on multi-source heterogeneous data. The present invention is applicable to environmental monitoring scenarios, particularly in the application scenarios of large-scale canal water ecological monitoring and intelligent management. For example, the present invention can be applied to water resource management scenarios, providing comprehensive and real-time water quality and hydrological meteorological data to assist management departments in making scientific decisions on water resource allocation and water quality improvement in scenarios such as water resource allocation, water pollution control, and water ecological restoration. Alternatively, it can be applied to intelligent shipping scheduling scenarios. In canal shipping management, the present invention, combined with hydrological and meteorological data, can intelligently optimize ship scheduling and lock / dam opening and closing schemes to ensure the safety and efficiency of canal shipping while reducing the impact on the ecological environment.

[0038] This invention optimizes the data acquisition and processing workflow, enabling efficient integration of multi-source heterogeneous data to provide accurate and timely data support for subsequent analysis and decision-making. Simultaneously, this invention can accurately analyze the changing trends of water quality and hydrological meteorological indicators, achieving early warning of environmental risks and providing crucial information for timely intervention.

[0039] Furthermore, the present invention can automatically match and recommend emergency plans, improve the timeliness and effectiveness of emergency response, and reduce the impact of environmental incidents on the canal ecosystem and surrounding communities.

[0040] The present invention will now be described in detail with reference to various embodiments.

[0041] Example 1

[0042] According to an embodiment of the present invention, an embodiment of a canal ecological monitoring method based on multi-source heterogeneous data is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0043] Figure 1 This is a flowchart of an optional canal ecological monitoring method based on multi-source heterogeneous data according to an embodiment of the present invention, such as... Figure 1 As shown, the method includes the following steps:

[0044] Step S101: Obtain multi-source heterogeneous data from monitoring the water ecology of the target canal. The multi-source heterogeneous data includes: monitoring data from multiple types of sensors, remote sensing and UAV monitoring data, and inspection and data entry data.

[0045] Optionally, the steps for obtaining multi-source heterogeneous data from monitoring the water ecology of the target canal include: collecting time-series data of multiple water quality indicators through water quality sensors, collecting time-series data of multiple meteorological indicators through meteorological sensors, collecting time-series data of multiple hydrological dynamic indicators through hydrological sensors, and monitoring the ecological environment data around the canal in real time through video monitoring equipment to obtain multi-sensor monitoring data; monitoring the ecological status data of the target canal and its surrounding areas through satellite remote sensing, and monitoring the ecological environment change data of the target canal and its surrounding areas through drones to obtain remote sensing and drone monitoring data; and receiving canal inspection data, emergency event data, and special inspection data entered by inspection personnel to obtain inspection data.

[0046] The multi-source heterogeneous data involved in this embodiment covers multiple aspects of water quality, meteorology, hydrology, and ecological environment, including but not limited to a large amount of information recorded through various advanced sensors, remote sensing technology, drone monitoring, and manual inspections, aiming to build a comprehensive, three-dimensional, and real-time water ecological monitoring system.

[0047] For acquiring data from multiple types of sensors, the first step is water quality sensor monitoring. This involves deploying water quality sensors in the target canal to monitor various water quality indicators in real time, including dissolved oxygen (DO), pH, turbidity, and chemical oxygen demand (COD). These sensors typically feature high precision and high frequency, capturing minute fluctuations in water quality and providing fundamental data for water quality assessment. Secondly, meteorological sensor monitoring is conducted. Meteorological sensors collect parameters such as temperature, humidity, wind speed, and air pressure, helping to analyze the impact of meteorological conditions on the canal's aquatic ecosystem. For example, high temperatures may accelerate eutrophication, while increased rainfall may exacerbate non-point source pollution. Further, hydrological sensor monitoring is implemented, monitoring dynamic hydrological parameters such as water level, flow rate, and water temperature. This data is crucial for assessing the canal's water resource status, navigation safety, and ecological health. For example, low water levels may affect fish migration, while water volume regulation directly affects the canal's flood control and water supply capacity. In addition, there is video surveillance equipment monitoring, which captures the ecological environment around the canal in real time, such as the vegetation coverage on the banks, the water pollution status, and shipping activities. The video data can be intelligently analyzed to identify abnormal activities, such as illegal sewage discharge or illegal construction, and then respond in a timely manner.

[0048] For remote sensing and UAV monitoring data acquisition, satellite remote sensing monitoring utilizes satellite remote sensing technology to obtain ecological status data of the target canal and its surrounding area, including macroscopic information such as vegetation index, soil moisture, and changes in water area. This helps assess the health status and trends of the ecosystem. When conducting UAV monitoring, the flexibility of UAVs allows for low-altitude, high-resolution monitoring, covering hard-to-reach areas of the target canal and its surroundings. Monitoring content includes water quality, aquatic vegetation, and shoreline erosion, providing more detailed information for monitoring.

[0049] Regarding the acquisition of inspection data, daily inspection data refers to detailed data collected and entered by inspection personnel during their daily work, including data on water quality, shoreline, and facility inspections, as well as reports of problems discovered. This data reflects the real-time status of the canal's aquatic ecosystem and is an important component of manual monitoring within the monitoring system. Emergency event data refers to information such as event details, impact range, and preliminary assessments that inspection personnel record in real time when encountering sudden water pollution incidents, natural disasters, or other emergencies, providing immediate data support for emergency response and decision-making.

[0050] Step S102: Classify the multi-source heterogeneous data to obtain a multi-dimensional monitoring data sequence based on the data transmission cycle.

[0051] Optionally, step S102 includes: obtaining a set of data transmission cycles for the water ecological monitoring needs of the target canal, wherein the set of data transmission cycles includes T data transmission cycles, where T is a positive integer; determining the data transmission cycle corresponding to each type of sensor monitoring data, remote sensing and UAV monitoring data, and inspection and data entry data; classifying the multi-source heterogeneous data according to the data transmission cycle to form multiple data subsets; and constructing a multi-dimensional monitoring data sequence based on each data subset corresponding to the data transmission cycle.

[0052] This embodiment classifies and processes multi-source heterogeneous data, aiming to construct an ordered, time-series-based, multi-dimensional monitoring data sequence according to the data transmission cycle, ensuring that information obtained from different monitoring methods can be systematically organized and analyzed according to a predetermined periodic pattern.

[0053] First, this embodiment obtains a predefined set of data transmission cycles for the target canal water ecology monitoring system. This set contains T different data transmission cycles, representing the number of different time periods set in the system. The selection of the data transmission cycles is based on an understanding of the canal's water ecology change patterns and considerations of the timeliness of different monitoring data, ensuring that data can be transmitted to the system center within appropriate time intervals to support real-time monitoring and decision support.

[0054] Subsequently, this embodiment determines the data transmission cycle corresponding to each data subset based on the characteristics of various monitoring data. For example, water quality sensor data may be set to be transmitted every 2.5 hours to capture details of water quality changes; hydrological data, such as water level and flow rate, may have their transmission cycle adjusted according to seasonal and weather changes, being transmitted every 3 hours during non-flood and non-dry seasons, and then increased to every 1.5 hours during special periods; remote sensing and UAV monitoring data, due to the complexity of data processing and analysis involved, may be set to be transmitted every 24 hours or longer. The transmission cycle for manually entered data is set based on the actual time of generation of the inspection report.

[0055] Next, this embodiment classifies the collected multi-source heterogeneous data according to the determined data transmission cycle. Each data subset contains all monitoring data within the same transmission cycle, including sensor data, remote sensing data, UAV data, and manually entered data, ensuring data consistency on the same time scale and facilitating subsequent data integration and analysis.

[0056] This embodiment ultimately constructs a multi-dimensional monitoring data sequence based on the data transmission cycle, using the aforementioned categorized data subset. Each entry in the sequence corresponds to a specific data transmission cycle and includes a summary of all monitoring data within that cycle. This construction method not only preserves the temporal attributes of the data but also forms a continuous, multi-dimensional data stream by periodically integrating data from different sources, providing a more comprehensive and orderly data foundation for intelligent monitoring, early warning, and decision support.

[0057] Step S103: Standardize the multi-dimensional monitoring data sequence and analyze the changing trends of water quality and hydro-meteorological indicators based on the standardized multi-dimensional monitoring data sequence.

[0058] Optionally, the step of standardizing the multi-dimensional monitoring data sequence includes: performing a uniformity test on the distribution characteristics of the multi-dimensional monitoring data sequence; performing nonlinear standardization on the tested multi-dimensional monitoring data sequence, and outputting a weighted optimized multi-dimensional monitoring data sequence. In the nonlinear standardization process, different weight factors are assigned to each data subset in the multi-dimensional monitoring data sequence for different time periods based on the canal's ecological conditions and environmental changes, and the weight factors are used to perform weighted optimization on the data subsets of different data transmission cycles.

[0059] This embodiment first performs a uniformity test on the distribution characteristics of the multi-dimensional monitoring data sequence obtained in step S102. This test aims to verify the consistency of data distribution across different data transmission cycles, ensuring that the data does not exhibit significant deviations or abnormal distributions before standardization, thus avoiding impacting the accuracy and reliability of subsequent analyses. By applying statistical methods, this embodiment can identify potential non-uniformity in the data and adjust the standardization strategy based on the results, ensuring that the processed data better meets analytical requirements.

[0060] Next, this embodiment performs nonlinear standardization on the verified multidimensional monitoring data sequences, transforming data from different sources and formats to the same scale to facilitate subsequent integrated analysis. During the nonlinear standardization process, this embodiment assigns different weighting factors to each data subset in the multidimensional monitoring data sequences from different time periods, based on the canal's ecological conditions and environmental changes. These weighting factors reflect the importance and reliability of data within specific time periods. For example, data from the flood season and dry season may be assigned higher weights because monitoring data from these periods is crucial for assessing the health of the aquatic ecosystem. By optimizing the standardization process using weighting factors, this embodiment ensures that the characteristics of data from key time periods are more fully reflected in subsequent analyses.

[0061] Optionally, the steps for analyzing the changing trends of water quality and hydro-meteorological indicators based on standardized multi-dimensional monitoring data sequences include: analyzing water quality indicator data in the standardized multi-dimensional monitoring data sequences using a weighted least squares model to obtain the changing trends of canal water quality. Specifically, during the analysis of water quality indicator data, parameters of the water quality indicators are calculated based on the weighted linear regression model corresponding to each type of water quality indicator and the weighting factors for different data collection periods. Combining the changing trends of canal water quality and reference values ​​of water quality indicators, the risk status of different water quality indicators in the target canal's aquatic ecosystem is assessed to obtain water quality assessment results and the first early warning information.

[0062] This embodiment utilizes a weighted least squares (WLS) model to analyze water quality indicators, such as dissolved oxygen, pH, and turbidity, from a standardized multi-dimensional monitoring data sequence. During the analysis, this embodiment calculates the parameters of each water quality indicator based on a weighted linear regression model corresponding to each type of indicator and weighting factors for different data collection periods, thus more accurately reflecting water quality change trends. By incorporating weighting factors into the model, this embodiment improves prediction accuracy, especially when the canal's ecological conditions and environmental circumstances change; the dynamic adjustment of weighting factors ensures the timeliness and accuracy of the analysis results.

[0063] Based on the trend of canal water quality changes and reference values ​​of water quality indicators, this embodiment further assesses the risk of different water quality indicators in the target canal aquatic ecosystem. For example, by setting a threshold for dissolved oxygen concentration, if the analysis results show that dissolved oxygen decreases significantly over time, a low oxygen risk warning may be triggered, requiring emergency measures such as increasing the operation of aeration equipment or adjusting the sluice gate scheduling to maintain the ecological balance of the aquatic body.

[0064] Optionally, the step of analyzing the changing trends of water quality and hydrometeorological indicators based on the standardized multi-dimensional monitoring data sequence further includes: obtaining a set of multiple hydrometeorological indicators and the calculation formula corresponding to each hydrometeorological indicator, wherein the set of multiple hydrometeorological indicators includes at least flow, water level, water temperature, and rainfall; extracting indicator data corresponding to each type of hydrometeorological indicator from the standardized multi-dimensional monitoring data sequence and determining the indicator weights corresponding to the hydrometeorological indicators; inputting the indicator data and indicator weights into the calculation formulas corresponding to the hydrometeorological indicators to obtain the changing trends of the hydrometeorological indicators; and assessing the risk status of different hydrometeorological indicators in the water ecosystem of the target canal based on the changing trends of the hydrometeorological indicators and the reference values ​​of the meteorological indicators to obtain the hydrometeorological assessment results and the second early warning information.

[0065] This embodiment also acquires a set of multiple hydrological and meteorological indicators, including but not limited to flow rate, water level, water temperature, and rainfall, as well as the calculation formula corresponding to each indicator. From the standardized multi-dimensional monitoring data sequence, this embodiment extracts the indicator data corresponding to each type of hydrological and meteorological indicator and determines the indicator weights corresponding to the hydrological and meteorological indicators. These weights reflect the relative importance of different indicators under specific environmental conditions. For example, rainfall may be given a higher weight during the flood season because its impact on water level and flow rate is more significant.

[0066] By inputting the extracted indicator data and indicator weights into the corresponding calculation formulas, this embodiment obtains the changing trends of hydrological and meteorological indicators. Through analysis of these trends, combined with meteorological indicator reference values, the risk of different hydrological and meteorological indicators in the target canal's aquatic ecosystem can be assessed. For example, excessively low flow may lead to aquatic ecosystem degradation, while abnormally high water levels pose a flood risk. Based on the analysis results, this embodiment generates hydrological and meteorological assessment results and corresponding early warning information.

[0067] Step S104: Based on the trend analysis results, generate a canal ecological monitoring report and a water ecological emergency plan.

[0068] Optionally, the steps of generating a canal ecological monitoring report and a water ecological emergency plan based on the trend analysis results also include: integrating multi-dimensional monitoring data sequences, water quality assessment results and first warning information, hydrological and meteorological assessment results and second warning information to generate a canal ecological monitoring report; and identifying the risks of canal water quality deterioration and hydrological disasters based on the trend analysis results, and matching them with the pre-set water ecological emergency plan.

[0069] This embodiment, after analyzing the changing trends of water quality and hydro-meteorological indicators, comprehensively integrates the standardized multi-dimensional monitoring data sequences, water quality assessment results and first early warning information, and hydro-meteorological assessment results and second early warning information to generate a detailed canal ecological monitoring report. This report compiles all monitoring data on the canal's ecological environment and their changing trends, including analysis of water quality indicator changes, prediction results of hydro-meteorological indicators, risk assessment, and corresponding early warning information. It provides canal maintenance managers with a comprehensive perspective to understand the current ecological status and potential environmental risks of the canal.

[0070] The canal ecological monitoring report combines historical data, environmental benchmarks, and expert knowledge to provide an in-depth interpretation of the significance of data changes, identifying potential ecological problems, analyzing their causes, and assessing their impact on ecosystem health. The report may also include data visualizations in the form of charts, graphs, and heat maps to visually demonstrate fluctuations in water quality and hydrological and meteorological indicators.

[0071] This embodiment further matches pre-set water ecological emergency plans with the results of trend analysis, particularly the identification of water quality deterioration risks and hydrological disaster risks. By comparing and analyzing water quality change trends with established water quality indicator reference values, corresponding early warning mechanisms are immediately triggered when monitoring data exceeds or approaches warning thresholds, such as risks of hypoxia, eutrophication, or water pollution. Similarly, by analyzing the trends of hydrological and meteorological indicators, when prediction results indicate that water levels, flow rates, or rainfall are in abnormal states, hydrological disasters such as flood and drought risks can also be identified in a timely manner.

[0072] Based on risk identification, this embodiment will automatically search a pre-set water ecological emergency response plan database to find a plan that matches the current risk situation. The plan may cover emergency response steps, resource allocation plans, coordination mechanisms, and recovery measures to ensure rapid action can be taken when a risk occurs, minimizing ecological damage and economic losses. For example, for the risk of water quality deterioration, the plan may include measures such as increasing the frequency of water quality sampling, activating purification facilities, issuing water quality warnings, and investigating and controlling potential pollution sources. For hydrological disaster risks, such as flooding, the plan may cover emergency measures such as urgently evacuating people in low-lying areas, activating hydrological storage facilities, reinforcing flood control dikes, and adjusting the opening and closing status of dams and sluices in real time.

[0073] Through the above steps, multi-source heterogeneous data can be obtained from monitoring the water ecology of the target canal. This multi-source heterogeneous data includes monitoring data from various sensors, remote sensing and UAV monitoring data, and inspection and data entry data. The multi-source heterogeneous data is then classified and processed to obtain a multi-dimensional monitoring data sequence based on the data transmission cycle. This multi-dimensional monitoring data sequence is then standardized, and the changing trends of water quality and hydrological and meteorological indicators are analyzed based on the standardized multi-dimensional monitoring data sequence. Based on the trend analysis results, a canal ecological monitoring report and a water ecology emergency plan are generated. In this embodiment, multi-source heterogeneous data, including monitoring data from various sensors, remote sensing and UAV monitoring data, and inspection and data entry data, are efficiently integrated. By constructing a multi-dimensional monitoring data sequence based on the data transmission cycle, data from different sources and in different formats are classified and integrated according to time series. This enables the analysis of changing trends of water quality and hydrological and meteorological indicators, achieving accurate monitoring of multi-dimensional changes in the water ecosystem and comprehensively reflecting these changes. This solves the technical problem in related technologies where canal water ecology monitoring systems rely on a single monitoring method and cannot comprehensively reflect the multi-dimensional changes in the water ecosystem.

[0074] The following describes in detail another optional implementation method.

[0075] The integrated intelligent management and control system for canal water ecology, based on multi-source heterogeneous data, enables comprehensive, real-time, and intelligent monitoring and management of the ecological environment of large canals. This system integrates data from different data sources and in various formats, and utilizes technologies such as big data analysis, artificial intelligence, and the Internet of Things to ensure the healthy and sustainable development of the canal's ecological environment.

[0076] Figure 2 This is a schematic diagram of an optional integrated intelligent management and control system for canal water ecology based on multi-source heterogeneous data according to an embodiment of the present invention, such as... Figure 2 As shown, the system includes: a multi-source data acquisition module, a data analysis and processing module, an intelligent monitoring and early warning module, and a decision management module. The following describes each module of the system.

[0077] I. Multi-source data acquisition module.

[0078] 1. The multi-source data acquisition module includes multiple data acquisition units, including a sensor network unit, a remote sensing and UAV monitoring unit, and a data entry unit.

[0079] Sensor network unit: Deploys multiple types of sensors covering water quality (such as key indicators like dissolved oxygen, pH, and turbidity), meteorology (such as environmental parameters like temperature, humidity, and wind speed), and hydrology (such as dynamic information like water level and flow rate), and is paired with video monitoring equipment to build a comprehensive, multi-layered real-time data acquisition network, ensuring the effective acquisition of various basic data on the canal's ecological environment.

[0080] Remote sensing and UAV monitoring unit: Combining satellite remote sensing technology, it acquires ecological information over a wide area of ​​the canal and its surrounding region from a macro perspective. At the same time, it combines UAVs to carry out low-altitude, high-resolution monitoring operations, effectively making up for the limitations of ground sensors in terms of spatial coverage and monitoring accuracy, so as to achieve integrated space-ground monitoring.

[0081] Manual data entry unit: A standardized data entry interface is set up, allowing manual input of detailed data and various event reports found during the inspection process, thereby further enriching the data sources and ensuring the integrity and comprehensiveness of the data.

[0082] 2. Based on historical monitoring data of large canal water, the data acquisition time period (data acquisition cycle) and information transmission time period (data transmission cycle) of the data acquisition unit are set separately.

[0083] To ensure the scientific validity, effectiveness, and practicality of the data acquisition cycle, this embodiment sets the acquisition time cycle and data transmission cycle for the sensor network unit, remote sensing and UAV monitoring unit, and manual data entry unit based on historical monitoring data of large canals.

[0084] (1) Sensor network unit acquisition time period setting.

[0085] As a key component of real-time data acquisition, the sensor network unit's acquisition time period is closely aligned with the changing patterns of various indicators in the historical monitoring data of large canals.

[0086] Among them, water quality sensors: Historical monitoring data shows that water quality indicators such as dissolved oxygen, pH, and turbidity exhibit certain patterns in their daily changes. Under normal weather and routine operating conditions, these indicators remain relatively stable, but fluctuate significantly under special circumstances such as rainfall and industrial wastewater discharge. For example, during normal periods, setting the water quality sensors to collect data every 2.5 hours captures daily water quality trends while avoiding data redundancy from overly frequent collection. However, during periods such as 24 hours before and after rainfall, and during industrial wastewater discharge warnings, the collection cycle is shortened to once every 0.5 hours to promptly obtain abnormal water quality data and provide a basis for subsequent emergency response.

[0087] Among them, meteorological sensors collect meteorological parameters such as temperature, humidity, and wind speed, which exhibit significant diurnal and seasonal variations. Historical monitoring data shows that meteorological parameters fluctuate relatively regularly throughout the day, but also show greater differences during seasonal transitions. For example, setting meteorological sensors to collect data every hour can reflect the daily trends of meteorological parameters and promptly detect sudden meteorological changes, such as strong winds and heavy rain, providing timely meteorological information support for flood control and navigation safety in the canal.

[0088] Among them, hydrological sensors: hydrological dynamic information such as water level and flow rate is crucial for the navigation scheduling and water resource management of the canal. Historical data shows that the changes in water level and flow rate within a day are relatively small, but significant fluctuations occur during special periods such as flood season and dry season. For example, in non-flood season and non-dry season, this embodiment sets the hydrological sensors to collect data every 3 hours; while in flood season and dry season, the collection cycle is shortened to once every 1.5 hours, so as to promptly grasp the changes in water level and flow rate and provide accurate data support for flood control and drought relief decisions.

[0089] The video surveillance equipment is primarily used for real-time monitoring of the ecological environment and activities surrounding the canal, with a data collection cycle set for 24-hour uninterrupted real-time monitoring. Through continuous video collection, abnormal situations around the canal, such as illegal sewage discharge, unauthorized construction, and vessels navigating illegally, can be detected promptly, providing direct evidence for the ecological protection and safety management of the canal.

[0090] (2) Set the data collection time cycle for remote sensing and UAV monitoring units.

[0091] The remote sensing and UAV monitoring unit provides an important supplement to the monitoring of the canal's ecological environment at both the macro and micro levels. The setting of its data collection time period fully considers the spatiotemporal characteristics of changes in the canal's ecological environment and the monitoring needs.

[0092] Among these methods, satellite remote sensing monitoring is employed. Satellite remote sensing technology offers wide coverage and strong macroscopic capabilities, making it suitable for periodic ecological status assessments of canals and their surrounding areas. Based on the seasonal and annual variations in the canal's ecological environment from historical monitoring data, the satellite remote sensing monitoring cycle is set to once a month. Monthly satellite remote sensing monitoring can acquire information on ecological changes in the canal and its surrounding areas within a specific timeframe, such as changes in vegetation cover and water area, providing data support for long-term monitoring and assessment of the canal's ecological environment. Furthermore, in the event of major ecological and environmental events (such as large-scale water pollution or ecological disasters), the monitoring frequency can be increased as needed, such as monitoring every two weeks, to promptly grasp the development trend and scope of the event's impact.

[0093] Among these methods, drone monitoring offers advantages such as high flexibility and resolution, compensating for the shortcomings of satellite remote sensing in terms of spatial coverage and monitoring accuracy. For key areas of the canal (such as water source protection areas, ecologically sensitive areas, and busy shipping areas), where ecological changes are highly sensitive and crucial to the canal's ecological security and water resource protection, drone monitoring is scheduled weekly. For example, weekly drone monitoring allows for the timely detection of ecological problems in these key areas, such as shoreline erosion, and the implementation of appropriate measures. For general areas of the canal, the drone monitoring cycle can be appropriately extended to once a month to ensure monitoring effectiveness while reasonably controlling monitoring costs.

[0094] (3) Data entry unit collection time cycle setting.

[0095] As an important supplementary means of data collection, the data entry unit's collection time cycle is mainly determined based on the arrangement of inspection work and the timeliness requirements of data entry.

[0096] Among these, daily inspection data entry involves the following: During daily inspections, inspectors will conduct detailed checks on the canal's water quality, shoreline, facilities, etc., and record relevant data and any problems found. To ensure that manually entered data reflects the canal's actual condition in a timely manner, data discovered during daily inspections and incident reports should be entered within 24 hours of the inspection's completion.

[0097] Specifically, data entry for emergency events should be more timely during special inspections (such as water quality surveys and ecological restoration effectiveness assessments) or when encountering emergencies (such as sudden water pollution incidents or natural disasters). Data from special inspections and emergency events is often highly time-sensitive and important, requiring prompt entry into the system after the event to provide a basis for decision-making. Therefore, data from special inspections and emergency events must be entered within 12 hours of the inspection or event handling being completed.

[0098] Furthermore, regarding the data transmission cycle, this embodiment sets a uniform time cycle for transmitting data to the system database. Although the collection time cycles of each data acquisition unit are different, in order to facilitate centralized management, analysis and sharing of data, the time cycle for transmitting data from each data acquisition unit to the database needs to be set to be the same. The setting of the data transmission cycle needs to be determined according to the canal's ecological conditions and emergency events. For example, under normal circumstances, the time transmission cycle can be set to 24 hours, while in the event of water pollution incidents, natural disasters, etc., the time transmission cycle can be adjusted to 8 hours.

[0099] In one embodiment, data is sent to the database every 24 hours, as detailed below:

[0100] Sensor Network Unit: Within each 24-hour cycle, it aggregates and organizes the collected water quality, meteorological, hydrological, and video monitoring data, and transmits them to the database at the end of the cycle. For data collected in encrypted form during special periods (such as abnormal water quality or severe weather), it is temporarily stored and preliminarily processed locally before being transmitted together at the end of the 24-hour cycle.

[0101] Remote sensing and UAV monitoring unit: Satellite remote sensing data is processed and analyzed promptly after monthly monitoring is completed, and transmitted to the database within the next 24-hour cycle. UAV monitoring data is also processed locally after each monitoring session and transmitted uniformly at the end of the 24-hour cycle for that day. If a major ecological and environmental event occurs and the monitoring frequency is increased, the newly added monitoring data will also be transmitted once every 24 hours.

[0102] Data entry unit: Whether it is daily inspection data, special inspection data, or emergency event data, after the data entry is completed, the data is first verified and organized locally, and then at the end of the 24-hour cycle, all the data entered that day is uniformly sent to the database.

[0103] Furthermore, based on the data acquisition time period (data acquisition cycle) of each data acquisition unit and the system information transmission time period (data transmission cycle), multi-source heterogeneous data of the system can be obtained.

[0104] By reasonably setting the collection time period of each data acquisition unit and unifying the time period for data transmission to the database, it is possible to aggregate multi-source heterogeneous data from different channels, formats, and characteristics, thereby obtaining multi-source heterogeneous data for the system and providing data support for the ecological environment protection, water resource management, and navigation safety of the canal.

[0105] II. Data Analysis and Processing Module.

[0106] With the development of computer technology and automatic monitoring technology, more and more automated data monitoring systems have been built and put into operation, realizing the automation of data monitoring and databases. However, since the relevant systems automatically collect and transmit data according to a set time, the system can automatically transmit monitoring data to the database, which brings about the problem of the authenticity of the system monitoring data. In this embodiment, in order to ensure the authenticity and availability of multi-source heterogeneous data entering the database, it is necessary to analyze and process the multi-source heterogeneous data in the large-scale canal water ecology integrated intelligent management and control system.

[0107] 1. Based on the system's data transmission cycle, classify the collected multi-source heterogeneous data and establish a multi-dimensional monitoring data sequence based on the data transmission cycle.

[0108] In an optional embodiment, the set of data transmission cycles is denoted as T, where T = {T1, T2, ..., T}. n}, which respectively represent different data transmission cycles, T1 represents the first data transmission cycle (start), T2 represents the second data transmission cycle (start), T n This indicates the end of the nth data transmission cycle.

[0109] Therefore, the multi-dimensional monitoring data sequence is as follows; Where X represents the set of multi-dimensional monitoring data sequences, X(T1) represents the subset of data corresponding to period T1, X(T2) represents the subset of data corresponding to period T2, and X(T... n ) represents T n The data subset corresponding to the period.

[0110] 2. Standardize the multi-dimensional monitoring data sequences.

[0111] Based on historical information about the canal's water ecology, it is known that the monitoring data for each time series are subject to differences and fluctuations due to environmental conditions, necessitating standardization of the multi-dimensional monitoring data series.

[0112] Step 2.1 Detect the distribution characteristics of the multi-dimensional monitoring data to obtain the multi-dimensional monitoring data after uniformity test.

[0113] Since the multi-dimensional monitoring data of the system may not conform to the uniform distribution characteristics, directly performing data standardization steps will result in uneven distribution of the data after standardization. In this embodiment, a non-linear standardization method is adopted, such as logarithmic transformation, Box-Cox transformation, etc., to make the multi-dimensional monitoring data of the system more in line with the normal distribution or other desired distribution. Then, the multi-dimensional monitoring data after uniformity test is subjected to data standardization processing.

[0114] Logarithmic transformation can be applied to situations where data grows or decays exponentially; Box-Cox transformation can automatically select appropriate transformation parameters based on the distribution of the data, making the transformed data closer to a normal distribution.

[0115] Using nonlinear standardization methods can make the multi-dimensional monitoring data of the system more consistent with a normal distribution or other desired distribution, enabling subsequent data analysis and processing model construction. After performing regression analysis or cluster analysis, the optimized data distribution can improve the model's fitting effect and prediction accuracy.

[0116] Step 2.2 Standardize the multidimensional monitoring data after the uniformity test.

[0117] The standardization function is as follows:

[0118]

[0119] Among them, X(T) n ) * Represents the standardized X(T) n ), X(T) n ) represents T n The data subset corresponding to the period, X(T) n ) min X(T) represents n The minimum value in ), X(T) n ) max X(T) represents n The maximum value in ).

[0120] Furthermore, due to the occurrence of daily monitoring, special inspections, and emergency events within the Grand Canal's aquatic ecosystem, data from different transport cycles have varying importance and sensitivity depending on the circumstances. In an optional embodiment, the set of transport cycles during the canal's flood season is T = {T1, T2, ..., T...} n Based on the system equipment, it is known that T2, T4, and T5 are the peak flood seasons of the canal. Therefore, the above three data transmission cycles can better reflect the water ecological conditions of the canal during the flood season and can be given greater weight. In the standardization process, it is necessary to match different weight factors to the data of different transmission cycles in different periods based on the canal ecological conditions and environmental changes, and further optimize the data of different transmission cycles by weighting.

[0121] Based on the above process, a weight is assigned to each of the different data subsets in the multi-dimensional monitoring data sequence, so that the data of important periods can play a greater role in subsequent analysis.

[0122] Optionally, in this embodiment, when standardizing the data, data from different formats and sources can be integrated into a unified data format to facilitate subsequent analysis and processing. Based on daily monitoring, special inspections, or emergency events of the Grand Canal's aquatic ecosystem, different weighting factors are assigned to data from different transport cycles, highlighting the characteristics of data from important cycles. For example, during the canal's flood season, data from peak periods are given greater weight, allowing these data to play a more significant role in subsequent analysis and thus better reflect the aquatic ecological conditions of the canal during the flood season.

[0123] Based on the data analysis and processing workflow in the data analysis and processing module, and taking into account the system's data transmission cycle and the canal's ecological conditions, the data analysis and processing module finally outputs an optimized multi-dimensional monitoring data sequence.

[0124] Optionally, the multi-dimensional monitoring data sequence is as follows: Where X * Let X(T1) represent the set of multi-dimensional monitoring data sequences after optimization.* The optimized subset of data T1 is shown in the table, where w1 represents X(T1). * The corresponding weighting coefficient, X(T2). * The optimized subset of data T2 is shown in the table, where w2 represents X(T2). * The corresponding weighting coefficient, X(T) n ) * Table T after optimization n Data subset, w n X(T) represents n ) * The corresponding weighting coefficients.

[0125] III. Intelligent Monitoring and Early Warning Module.

[0126] The intelligent monitoring and early warning module can receive multi-dimensional monitoring data sequences in real time, and based on big data analysis technology, perform data monitoring and reference indicator analysis and prediction on the fused multi-dimensional monitoring data to extract the water ecological information of the Grand Canal and analyze the water ecological change patterns.

[0127] 1. Analysis of water quality change trends.

[0128] Based on the weighting coefficients of different data collection periods in the multi-dimensional monitoring data sequence, a linear regression model is introduced to analyze the changing trends of different water quality indicators (such as dissolved oxygen, pH, turbidity, etc.) in the canal aquatic ecosystem over time. In this embodiment, considering the differences in monitoring data from different data collection periods, such as fluctuations during the flood season and dry season, the linear regression model is optimized and adjusted by combining the weighting coefficients of different data collection periods. A weighted least squares model is then constructed to predict and analyze the trends of different water quality indicators in the river aquatic ecosystem.

[0129] 1.1 The random error term is obtained based on the weighting coefficients of different data collection periods, and it follows a weighted normal distribution:

[0130]

[0131] in, Let w represent the random error term, σ represent the variance of the error term (global noise level), and w represent the global noise level. n The weighting coefficients representing different data collection periods can reflect the reliability or importance of relevant data in different data collection periods.

[0132] 1.2 Based on this, let y represent different water quality indicators in the canal's aquatic ecosystem, and t represent time. Then, combining the linear regression model of different water quality indicators in the random error term example, the following relationship needs to be satisfied:

[0133]

[0134] Where y represents different water quality indicators in the canal's aquatic ecosystem (such as dissolved oxygen concentration, pH value, turbidity, etc.), a represents the slope of different water quality indicators, t represents the time variable (such as the sequence number corresponding to the data transmission time), the rate of change of different water quality indicators over time, and b represents the reference value of the water quality indicators at the initial moment. This represents the random error term.

[0135] 1.3 Based on the linear regression models of different water quality indicators and the weighting coefficients of different data collection periods, the slope value a and reference value b in the linear regression model are solved by combining the least squares method.

[0136]

[0137] Where 'a' represents the slope of different water quality indicators, 'N' represents the total number of data points, 'n' represents the number of different data collection periods, and 'w' represents the slope of different water quality indicators. n The weighting coefficient t represents the data collection period in which the data point is located. n y represents the time variable corresponding to different data points. n b represents the observed water quality index values ​​at different data points, and b represents the reference value of the water quality index at the initial time.

[0138] The formula for calculating the slope value 'a' incorporates a weighted covariance term in the numerator, which effectively measures the joint change of time and water quality indicators; the addition of a weighted variance term to the denominator helps measure the degree of dispersion over time. Specifically, 'a>0' indicates that the water quality indicator increases over time (e.g., dissolved oxygen increases); 'a≤0' indicates that the water quality indicator decreases over time (e.g., turbidity decreases).

[0139] The numerator of the formula for calculating the reference value b includes the sum of weighted water quality indicators minus the product of the slope and the weighted time; the denominator is the sum of weights, which is mainly used for normalization.

[0140] Step 1.4 Finally, based on the slope 'a' of different water quality indicators and the reference value 'b' of the water quality indicators at the initial moment, assess the risk of different water quality indicators in the early warning canal ecosystem.

[0141] If 'a' is positive, it indicates that the water quality index is increasing over time; if 'a' is negative, it indicates that the water quality index is decreasing over time. This method can effectively analyze the trend of water quality changes and provide a direct understanding of the long-term trend of water quality indicators.

[0142] Among them, a slope threshold a0 is set based on the historical information of the canal's water ecology: the risk level of water quality indicators is divided by combining water quality standards and historical data with the slope threshold a0.

[0143] In an optional embodiment, the risk level is set based on water quality indicator-related data as follows:

[0144] High risk: |a| > 0.1;

[0145] Medium risk: 0.05 < |a| ≤ 0.1;

[0146] Low risk: |a|≤0.05.

[0147] 2. Hydrological and meteorological index prediction and analysis.

[0148] Because the flow rate in the canal reflects changes in river runoff and is related to water dilution and self-purification capacity; water level affects water volume, flow velocity and ecological habitat; water temperature affects dissolved oxygen saturation, microbial activity and aquatic metabolism; and extreme rainfall during the flood season or dry season may cause sudden changes in water quality (such as non-point source pollution).

[0149] 1. Based on the optimized multi-dimensional monitoring data sequence output by the data analysis and processing module, hydrological and meteorological indicators were selected, and calculation formulas for the hydrological and meteorological indicators were set.

[0150] 1.1 Hydrological and meteorological indicators include flow, water level, water temperature, and rainfall in the Grand Canal's aquatic ecosystem;

[0151] 1.2 The calculation formulas for different hydrological and meteorological indicators are as follows:

[0152] 1.2.1 Flow rate (Q) reflects the river's runoff capacity and affects the efficiency of pollutant dilution and self-purification.

[0153]

[0154] Where Q(t) represents the total flow rate within time t, n represents the total number of monitoring sections, and V i (t) represents the flow velocity at different monitoring sections at time t, A i (t) represents the cross-sectional area of ​​different monitoring sections at time t, μ i The weight index represents the weight of different monitoring sections.

[0155] Among them, for dynamic area correction, A i (t) The variation of water level H avoids the assumption of a fixed cross section and can more accurately reflect the dilution capacity of canal runoff on pollutants.

[0156] 1.2.2 Water level (H) determines water volume and flow velocity, affecting habitat connectivity.

[0157]

[0158] Where H(t) represents the water level at time t, H0 represents the reference water level of the canal, n represents the total number of monitoring sections, and ΔH i (t) represents the change in water volume at different monitoring sections within time t, ρ iThe index represents the weighting of different monitoring sections to the water level, and C represents the bias term fitted based on historical canal data.

[0159] 1.2.3 Water temperature (T) is mainly used to control dissolved oxygen saturation and biological metabolic rate.

[0160]

[0161] Where W(t) represents the water temperature at time t, and ∈ represents the air-water heat exchange weight in the environment. A (t) represents the ambient air temperature at time t, N represents the total number of water temperature sensors, and W i (t) represents the measured value of different water temperature sensors at time t, and τ represents the temperature error of the canal environment within time t.

[0162] 1.2.4 Rainfall (P) can control dissolved oxygen saturation and biological metabolic rate.

[0163]

[0164] Where P(t) represents the total rainfall in the canal system within time t, n represents the number of rain gauges in the system, and p i (t) represents the measured rainfall intensity at time t using different rain gauges, η i Δt represents the coverage index of different rain gauges, K(t) represents the monitoring time step, and K(t) represents the runoff coefficient of the canal at time t.

[0165] 2. By using relevant calculation formulas for hydrological and meteorological indicators, different hydrological and meteorological indicators in the canal ecosystem are assessed, predicted, and given early warnings.

[0166] 2.1 Construct a hydrological and meteorological assessment and early warning system based on different hydrological and meteorological indicators.

[0167] The assessment parameters for the hydro-meteorological assessment and early warning system include:

[0168] Flow rate (Q) assesses the ability to dilute pollutants and self-clean up efficiency, and identifies low flow rate risks (such as algal blooms).

[0169] Water level (H) monitoring measures changes in water volume and flow velocity to provide early warnings of habitat fragmentation or flood risks.

[0170] Water temperature (T) controls dissolved oxygen saturation and biological metabolic rate, and identifies hypoxia or hypothermia caused by high temperature.

[0171] Rainfall (P) data can be used to warn of non-point source pollution and runoff impact, and to prevent sudden changes in water quality (such as excessive levels of ammonia nitrogen and total phosphorus).

[0172] 2.2 Joint hydrological and meteorological assessment and early warning system, calculation formula of hydrological and meteorological indicators, and multi-dimensional monitoring data series are used to conduct early warning and linkage analysis on the canal's hydrology and meteorology.

[0173] 2.2.1 Flow rate (Q).

[0174] (1) Set the flow rate early warning thresholds Qmin and Qmax; the flow rate early warning threshold Qmin represents the low flow rate early warning threshold. When the value is lower than this, the water self-purification ability decreases, which may trigger algal blooms or ecological degradation; Qmax represents the high flow rate early warning threshold. When the value exceeds this, floods, levee breaches or river channel erosion may be triggered. [[ID

[0175] The above flow rate early warning thresholds need to be dynamically adjusted according to the canal monitoring time (seasonal climate). During the flood season (June - September) of the canal, Qmax can be increased to adapt to heavy rainfall; during the dry season (November - February) of the canal, Qmin can be decreased to ensure agricultural water use.

[0176] (2) Combine the flow rate calculation results and the flow rate for early warning analysis.

[0177] Low flow rate early warning: Q(t) < Qmin, trigger algal monitoring and sluice and dam operation.

[0178] The real-time flow rate Q(t) continuously remains lower than Qmin for more than 10 hours.

[0179] Early warning measures include: increasing the sampling frequency of algal monitoring, monitoring chlorophyll a and nutrients; sluice and dam operation giving priority to ensuring ecological flow rate and reducing agricultural or industrial water use; if the sluices and dams cannot meet the demand, start emergency water replenishment, and water can be diverted from upstream reservoirs.

[0180] High flow rate early warning: Q(t) > Qmax, start the flood control emergency plan. The real-time flow rate Q(t) exceeds Qmax and lasts for 0.5 hours. Early warning measures include: evacuating residents in low-lying areas in the flood control emergency plan, closing the gates in dangerous areas; starting the flood diversion area to reduce the peak flow rate of the main river channel; increasing the sampling frequency of water quality monitoring, monitoring suspended solids (SS), chemical oxygen demand (COD) and heavy metals.

[0181] 2.2.2 Water level (H).

[0182] (1) Set the warning values of the canal water level, Hflood and Hmin; where Hflood represents the flood warning value, and when it is exceeded, flood disasters or levee breaches may be triggered; Hmin represents the warning value of habitat fragmentation, and when it is lower than this value, it may block the fish migration channels or cause the wetland to dry up. The determination of the Hflood flood warning value is mainly based on the analysis of historical flood events, and the historical flood events are statistically analyzed to determine the threshold. The determination of the Hmin habitat fragmentation warning value introduces the ecological water requirement method, and based on the ecological flow and water depth requirements of the canal, the minimum water level to maintain fish migration and wetland functions is determined.

[0183] (2) Combine the water level calculation results and the canal water level for warning analysis.

[0184] Flood warning: H(t) > Hflood (such as 12m), close the gates in the low-lying areas.

[0185] The real-time water level H(t) exceeds Hflood and lasts for 0.5 hours.

[0186] The warning measures include: closing the gates in the low-lying areas, giving priority to closing the gates near residential areas to prevent flood backflow; if the gates cannot be completely closed, start temporary water-blocking facilities (such as sandbags); evacuate the residents in the low-lying areas to safe areas and provide emergency supplies.

[0187] Habitat fragmentation warning: H(t) < Hmin (such as 8m), evaluate the risk of blocking fish migration channels.

[0188] The real-time water level H(t) is lower than Hmin and lasts for 10 hours.

[0189] The warning measures include: evaluating the risk of blocking fish migration channels by simulating the impact of water level decline on fish migration through a hydraulic model; conducting field investigations on the distribution of fish populations and the quality of habitats; ecological water replenishment. If the evaluation shows a high risk of blocking the migration channels, start emergency water replenishment (such as diverting water from the upstream reservoir).

[0190] 2.2.3 Water temperature (T).

[0191] (1) Set the warning values of the canal water body temperature, T(high) and T(down); where T(high) represents the warning temperature value of low oxygen, and when the water temperature exceeds this value, high temperature will accelerate the decomposition of organic matter, consume dissolved oxygen (DO) and cause low oxygen, which may trigger the risk of low oxygen in the canal; T(down) represents the warning temperature value of low temperature stress, and low temperature will inhibit fish metabolism, reduce immunity and even cause death, and when the water temperature is lower than this value, it may trigger the risk of fish overwintering.

[0192] Principle for setting the low - oxygen warning temperature value T(high): Based on the correlation analysis of historical data of the canal, the relationship between historical water temperature and dissolved oxygen (DO) is statistically analyzed to determine the water temperature threshold corresponding to DO < 5mg / L. Principle for setting the low - oxygen warning temperature value T(down): Mainly referring to the research information on fish physiology, based on the physiological data of fish's tolerance to low temperature (semi - lethal temperature), the threshold is determined.

[0193] (2) Conduct warning analysis by combining the water level calculation result and the water temperature warning value of the water body.

[0194] Low - oxygen warning: When T(t) > T(high), monitor the dissolved oxygen (start aeration when DO < 5mg / L).

[0195] The real - time water temperature T(t) exceeds T(high) and lasts for 5 hours.

[0196] Warning measures include: increasing the sampling frequency of dissolved oxygen monitoring, monitoring the DO concentration; starting the aeration equipment.

[0197] Low - temperature stress warning: When T(t) < T(down), evaluate the over - wintering risk of fish.

[0198] The real - time water temperature T(t) is lower than T(down) and lasts for 10 hours.

[0199] Warning measures include: evaluating the fish population distribution and habitat suitability through ecological models or field investigations; if the evaluation shows a high over - wintering risk, start emergency water replenishment to raise the water temperature.

[0200] 2.2.4 Rainfall (P).

[0201] (1) Set the canal rainfall warning values P(max) and P(min); where P(max) represents the maximum rainfall warning threshold, exceeding which may cause non - point source pollution; P(min) represents the minimum rainfall warning threshold, continuously being lower than which may cause drought in the dry season.

[0202] Method for determining P(max), the maximum rainfall warning threshold: Based on the analysis of historical pollution events of the canal, the relationship between historical rainfall events and water quality deterioration is statistically analyzed to determine the rainfall threshold that causes non - point source pollution. Method for determining P(min), the minimum rainfall warning threshold: Combine the drought index method and the ecological water demand assessment method to set and calculate the minimum rainfall for maintaining ecological functions. The canal rainfall warning values can be dynamically adjusted. Seasonal adjustments include increasing P(max) (such as increasing by 5mm) during the flood season (June - September) to adapt to high - intensity rainfall; reducing P(min) (such as reducing by 2mm) during the dry season (November - February) to ensure ecological water use.

[0203] (2) Conduct warning analysis by combining the water level calculation result and the canal rainfall warning value.

[0204] Non-point source pollution warning: P(t) > P(max), intensify water quality sampling (such as ammonia nitrogen, total phosphorus).

[0205] The real-time rainfall P(t) exceeds P(max) and lasts for 3 hours.

[0206] The warning measures include: intensify the sampling frequency, monitor the concentrations of pollutants such as ammonia nitrogen and total phosphorus; identify and control non-point source pollution in agriculture (such as reducing the use of chemical fertilizers) and urban runoff pollution (such as cleaning rainwater inlets).

[0207] Dry season drought warning: P(t) < P(min) lasts for 7 days, initiate the need for ecological water replenishment.

[0208] The rainfall P(t) is lower than P(min) for a cumulative of 5 days;

[0209] IV. Decision-making management module.

[0210] By integrating multi-dimensional monitoring data sequences, hydrological and meteorological assessment and warning systems, and historical data, the decision-making can be made intelligent, precise, and efficient.

[0211] Among them, the decision-making management module can achieve data integration and display, integrate multi-dimensional monitoring data sequences, hydrological and meteorological assessment results, and warning information, and display them to canal maintenance and decision-makers through a visual interface, which is conducive to comprehensively understanding the canal ecological environment status. Based on the data analysis results and warning information, provide targeted decision-making suggestions for decision-makers, such as water quality improvement measures, sluice and dam scheduling plans, ecological water replenishment plans, etc. Establish an emergency plan library, including emergency plans for flood control, drought resistance, water pollution incidents, etc., and automatically match and recommend corresponding emergency plans according to the warning information.

[0212] In an optional embodiment, the implementation steps of the decision-making management module include:

[0213] 1. Integrate and visualize the output results and relevant data of the data analysis and processing module and the intelligent monitoring and warning module.

[0214] Integrate multi-dimensional monitoring data sequences, hydrological and meteorological assessment results, and warning information to form a unified decision support data set; through forms such as GIS maps, charts, and dashboards, visually display the integrated data to decision-makers, facilitating their intuitive understanding of the canal ecological environment status.

[0215] 2. Generate canal decision-making suggestions based on the output results and analysis information of other modules.

[0216] Based on preset decision-making rules, such as water quality thresholds and flow warning thresholds, the system automatically generates decision recommendations. When water quality indicators exceed the thresholds, it recommends initiating water quality improvement measures; when flow is below the warning threshold, it recommends adjusting the dam and gate scheduling plan. Machine learning and deep learning models can also be used to mine and analyze the integrated data, generating more accurate decision recommendations. Predictive models can forecast water quality trends over a future period, providing forward-looking decision support for decision-makers.

[0217] 3. Introduce a canal emergency plan database to match and recommend canal management and early warning plans based on information from each module.

[0218] The canal emergency response database includes emergency plans for flood control, drought relief, and water pollution incidents. Each plan contains information such as plan name, scope of application, response measures, and responsible department. Based on early warning information, the database automatically matches and recommends appropriate emergency plans. When a flood warning is triggered, a flood control emergency plan is recommended; when a non-point source pollution warning is triggered, a water pollution incident emergency plan is recommended.

[0219] 4. Decision implementation and effect evaluation.

[0220] The generated decision recommendations and recommended emergency response plans are issued to relevant departments for implementation, and the progress and effectiveness of implementation are tracked. By comparing monitoring data before and after the implementation of the decisions, the effectiveness of the decisions and areas for improvement are analyzed. For example, by comparing changes in water quality indicators and flow rates before and after the implementation of the decisions, the effect of the decisions on improving the ecological environment of the canal is evaluated. Based on the results of the effectiveness evaluation, the decision recommendations and emergency response plans are adjusted to improve the scientific nature and accuracy of the decisions.

[0221] In one optional embodiment, the changing trends and anomalies of water quality indicators such as dissolved oxygen, pH value, and turbidity are analyzed to identify water pollution sources and pathways. Based on the analysis results of water quality indicators, targeted water quality improvement measures can be proposed, such as increasing aeration equipment, adjusting dam scheduling, and strengthening pollution source control.

[0222] In an optional embodiment, the changing trends and anomalies of hydrological and meteorological indicators such as flow rate and water level are analyzed to assess the water resource status of the canal. Based on the flow rate and water level analysis results, targeted water resource scheduling schemes are proposed, such as dam scheduling, ecological water replenishment, and inter-regional water transfer. At the same time, the potential risks of water resource scheduling schemes, such as flood risk, drought risk, and ecological risk, are assessed, and corresponding risk response measures are proposed.

[0223] In one optional embodiment, an ecological model is used to assess the ecological status of the canal, including indicators such as vegetation cover, water area, and biodiversity. Based on the assessment results, targeted ecological protection measures are proposed, such as wetland restoration, fish stocking, and ecological water replenishment. The ecological status of the canal is continuously monitored and assessed, providing data support for ecological protection decisions.

[0224] In one optional embodiment, emergency events occurring on the canal, such as water pollution incidents and floods, are identified through early warning information and real-time monitoring data. Based on the type and severity of the emergency, corresponding emergency plans are activated, and their implementation progress and effectiveness are tracked. Simultaneously, emergency resources, such as rescue teams, supplies, and equipment, are allocated according to the needs of the emergency plan to ensure the timeliness and effectiveness of the emergency response.

[0225] Through the above embodiments, analytical frameworks for water quality and hydrological parameters can be constructed respectively, enabling accurate analysis of the changing trends and risks of water quality and hydro-meteorological indicators. This allows for precise monitoring and early warning of water quality, hydro-meteorological, and other indicators, timely detection of potential environmental risks, and provides strong support for the protection and management of the canal ecosystem, thereby enhancing the monitoring and early warning capabilities of water ecological indicators. Furthermore, based on the results of data analysis and intelligent monitoring and early warning, this invention can implement targeted water quality improvement measures, dam scheduling schemes, ecological water replenishment plans, and emergency response plans, ensuring the healthy and sustainable development of the canal's ecological environment.

[0226] The following is a detailed description with reference to another embodiment.

[0227] Example 2

[0228] The canal ecological monitoring system based on multi-source heterogeneous data provided in this embodiment includes multiple implementation units, each of which corresponds to a specific implementation step in Embodiment 1 above.

[0229] Figure 3 This is a schematic diagram of an optional canal ecological monitoring system based on multi-source heterogeneous data according to an embodiment of the present invention, such as... Figure 3 As shown, the canal ecological monitoring system based on multi-source heterogeneous data may include: a multi-source heterogeneous data acquisition unit 31, a data classification unit 32, a data change trend analysis unit 33, and a monitoring report generation unit 34.

[0230] Among them, the multi-source heterogeneous data acquisition unit 31 is used to acquire multi-source heterogeneous data obtained from monitoring the water ecology of the target canal. The multi-source heterogeneous data includes: monitoring data from multiple types of sensors, remote sensing and UAV monitoring data, and inspection and data entry data.

[0231] The data classification unit 32 is used to classify and process multi-source heterogeneous data to obtain a multi-dimensional monitoring data sequence based on the data transmission cycle.

[0232] The data change trend analysis unit 33 is used to standardize the multi-dimensional monitoring data sequence and analyze the changing trends of water quality and hydro-meteorological indicators based on the standardized multi-dimensional monitoring data sequence.

[0233] The monitoring report generation unit 34 is used to generate a canal ecological monitoring report and a water ecological emergency plan based on the analysis results of the changing trends.

[0234] The aforementioned canal ecological monitoring system based on multi-source heterogeneous data can acquire multi-source heterogeneous data for monitoring the water ecology of the target canal through the multi-source heterogeneous data acquisition unit 31. The multi-source heterogeneous data includes monitoring data from multiple sensors, remote sensing and UAV monitoring data, and inspection and data entry data. The multi-source heterogeneous data is classified and processed by the data classification unit 32 to obtain a multi-dimensional monitoring data sequence based on the data transmission cycle. The multi-dimensional monitoring data sequence is standardized by the data change trend analysis unit 33, and the change trends of water quality and hydro-meteorological indicators are analyzed based on the standardized multi-dimensional monitoring data sequence. The monitoring report generation unit 34 generates a canal ecological monitoring report and a water ecology emergency plan based on the change trend analysis results. In this embodiment, multi-source heterogeneous data, including monitoring data from various sensors, remote sensing and UAV monitoring data, and inspection data, are efficiently integrated. By constructing a multi-dimensional monitoring data sequence based on the data transmission cycle, data from different sources and in different formats are classified and integrated according to time series. This enables the analysis of the changing trends of water quality and hydrological and meteorological indicators, achieving accurate monitoring of multi-dimensional changes in the aquatic ecosystem and comprehensively reflecting these changes. This solves the technical problem in related technologies where canal water ecosystem monitoring systems have a single monitoring method and cannot comprehensively reflect the multi-dimensional changes in the aquatic ecosystem.

[0235] Optionally, the multi-source heterogeneous data acquisition unit includes: a sensor data acquisition module, used to acquire time-series data of various water quality indicators through water quality sensors, time-series data of various meteorological indicators through meteorological sensors, time-series data of various hydrological dynamic indicators through hydrological sensors, and real-time monitoring of the ecological environment data around the canal through video monitoring equipment, to obtain multi-sensor monitoring data; a remote sensing and drone data acquisition module, used to monitor the ecological status data of the target canal and its surrounding area through satellite remote sensing, and to monitor the ecological environment change data of the target canal and its surrounding area through drones, to obtain remote sensing and drone monitoring data; and an inspection and data entry module, used to receive canal inspection data, emergency event data, and special inspection data entered by inspection personnel, to obtain inspection and data entry data.

[0236] Optionally, the data classification unit includes: a data transmission cycle acquisition module, used to acquire a set of data transmission cycles in the water ecological monitoring needs of the target canal, wherein the set of data transmission cycles includes T data transmission cycles, where T is a positive integer; a transmission cycle matching module, used to determine the data transmission cycle corresponding to each type of sensor monitoring data, remote sensing and UAV monitoring data, and inspection and data entry data; a data classification module, used to classify multi-source heterogeneous data according to the data transmission cycle to form multiple data subsets; and a monitoring data sequence construction module, used to construct a multi-dimensional monitoring data sequence based on each data subset corresponding to the data transmission cycle.

[0237] Optionally, the data change trend analysis unit includes: a verification module for verifying the uniformity of the distribution characteristics of the multi-dimensional monitoring data sequence; and a standardization module for performing nonlinear standardization on the verified multi-dimensional monitoring data sequence and outputting a weighted optimized multi-dimensional monitoring data sequence. In the nonlinear standardization process, different weight factors are assigned to each data subset in the multi-dimensional monitoring data sequence for different time periods based on the canal's ecological conditions and environmental changes, and the weight factors are used to perform weighted optimization on the data subsets of different data transmission cycles.

[0238] Optionally, the data change trend analysis unit includes: a water quality index data analysis module, used to analyze water quality index data in the standardized multi-dimensional monitoring data sequence using a weighted least squares model to obtain the water quality change trend of the canal. In the process of water quality index data analysis, the parameters of water quality indexes are calculated based on the weighted linear regression model corresponding to each type of water quality index and the weighting factors of different data collection periods; and a water quality assessment module, used to assess the risk of different water quality indicators in the water ecosystem of the target canal by combining the water quality change trend of the canal and the reference values ​​of water quality indicators, and obtain the water quality assessment results and the first early warning information.

[0239] Optionally, the data change trend analysis unit further includes: a hydro-meteorological indicator acquisition module, used to acquire a set of multiple hydro-meteorological indicators and the calculation formula corresponding to each hydro-meteorological indicator, wherein the set of multiple hydro-meteorological indicators includes at least flow, water level, water temperature and rainfall; a water quality indicator data analysis module, used to extract indicator data corresponding to each type of hydro-meteorological indicator from the standardized multi-dimensional monitoring data sequence and determine the indicator weights corresponding to the hydro-meteorological indicators; a hydro-meteorological change trend analysis module, used to input the indicator data and indicator weights into the calculation formulas corresponding to the hydro-meteorological indicators to obtain the change trends of the hydro-meteorological indicators; and a hydro-meteorological assessment module, used to assess the risk status of different hydro-meteorological indicators in the water ecosystem of the target canal based on the change trends of hydro-meteorological indicators and meteorological indicator reference values, and obtain hydro-meteorological assessment results and second early warning information.

[0240] Optionally, the monitoring report generation unit also includes: a canal ecological monitoring report generation module, used to integrate multi-dimensional monitoring data sequences, water quality assessment results and first warning information, hydrological and meteorological assessment results and second warning information to generate a canal ecological monitoring report; and an emergency plan matching module, used to identify the risk of canal water quality deterioration and hydrological disaster based on the trend analysis results, and match the preset water ecological emergency plan.

[0241] The aforementioned canal ecological monitoring system based on multi-source heterogeneous data may also include a processor and a memory. The aforementioned multi-source heterogeneous data acquisition unit 31, data classification unit 32, data change trend analysis unit 33, monitoring report generation unit 34, etc., are all stored in the memory as program units, and the processor executes the aforementioned program units stored in the memory to realize the corresponding functions.

[0242] The aforementioned processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and adjusting kernel parameters enables integrated management and control of the canal's water ecology based on multi-source heterogeneous data.

[0243] The aforementioned memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0244] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored computer program, wherein, when the computer program is running, it controls the device where the computer-readable storage medium is located to execute any one of the above-described embodiments of the canal ecological monitoring method based on multi-source heterogeneous data.

[0245] According to another aspect of the present invention, an electronic device is also provided, including one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the canal ecological monitoring method based on multi-source heterogeneous data as described in any of the embodiments of the first invention.

[0246] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the canal ecological monitoring method based on multi-source heterogeneous data described in various embodiments of this application.

[0247] This application also provides a computer program product, including a non-volatile computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the canal ecological monitoring method based on multi-source heterogeneous data described in various embodiments of this application.

[0248] Figure 4 This is a hardware structure block diagram of an electronic device (or mobile device) for implementing a canal ecological monitoring method based on multi-source heterogeneous data, according to an embodiment of the present invention. Figure 4 As shown, an electronic device may include one or more ( Figure 4 The processor (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and memory 404 for storing data are illustrated using 402a, 402b, ..., 402n. In addition, it may include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a keyboard, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 4 The structure shown is for illustrative purposes only and does not limit the structure of the electronic system described above. For example, the electronic device may also include... Figure 4 The more or fewer components shown, or having the same Figure 4 The different configurations shown.

[0249] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0250] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0251] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The system embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection of units or modules may be electrical or other forms.

[0252] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0253] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0254] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0255] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for monitoring canal ecology based on multi-source heterogeneous data, characterized in that, include: Acquire multi-source heterogeneous data obtained from monitoring the water ecology of the target canal, wherein the multi-source heterogeneous data includes: monitoring data from multiple types of sensors, remote sensing and UAV monitoring data, and inspection and data entry data; The multi-source heterogeneous data is classified and processed to obtain a multi-dimensional monitoring data sequence based on the data transmission cycle; The multi-dimensional monitoring data sequence is standardized, and the changing trends of water quality and hydro-meteorological indicators are analyzed based on the standardized multi-dimensional monitoring data sequence. Based on the analysis of the changing trends, an ecological monitoring report and a water ecological emergency plan for the canal are generated.

2. The canal ecological monitoring method according to claim 1, characterized in that, The steps for obtaining multi-source heterogeneous data from monitoring the aquatic ecology of the target canal include: Time-series data of various water quality indicators are collected by water quality sensors, time-series data of various meteorological indicators are collected by meteorological sensors, time-series data of various hydrological dynamic indicators are collected by hydrological sensors, and the ecological environment data around the canal is monitored in real time by video monitoring equipment to obtain the monitoring data of the various sensors. The ecological conditions of the target canal and its surrounding area are monitored by satellite remote sensing, and the ecological environment changes of the target canal and its surrounding area are monitored by drones to obtain the remote sensing and drone monitoring data. The system receives canal inspection data, emergency event data, and special inspection data entered by inspection personnel, and obtains the inspection data.

3. The canal ecological monitoring method according to claim 1, characterized in that, The steps of classifying the multi-source heterogeneous data to obtain a multi-dimensional monitoring data sequence based on the data transmission cycle include: Obtain the set of data transmission cycles for the water ecological monitoring needs of the target canal, wherein the set of data transmission cycles includes T data transmission cycles, where T is a positive integer; Determine the data transmission cycle corresponding to each type of sensor monitoring data, the remote sensing and UAV monitoring data, and the inspection and data entry data; The multi-source heterogeneous data is classified according to the data transmission cycle to form multiple data subsets; Based on each data subset corresponding to the data transmission cycle, a multi-dimensional monitoring data sequence based on the data transmission cycle is constructed.

4. The canal ecological monitoring method according to claim 1, characterized in that, The steps for standardizing the multi-dimensional monitoring data sequence include: The uniformity of the distribution characteristics of the multi-dimensional monitoring data sequence is tested. The multidimensional monitoring data sequence after verification is subjected to nonlinear standardization processing to output a weighted and optimized multidimensional monitoring data sequence. In the nonlinear standardization process, different weight factors are assigned to each data subset in the multidimensional monitoring data sequence of different time periods based on the canal's ecological conditions and environmental changes. The weight factors are then used to perform weighted optimization on the data subsets of different data transmission cycles.

5. The canal ecological monitoring method according to claim 1, characterized in that, The steps for analyzing the changing trends of water quality and hydrometeorological indicators based on the standardized multi-dimensional monitoring data sequence include: The water quality index data in the standardized multi-dimensional monitoring data sequence were analyzed using the weighted least squares model to obtain the trend of canal water quality change. In the process of analyzing water quality index data, the parameters of water quality index were calculated based on the weighted linear regression model corresponding to each type of water quality index and the weight factors of different data collection periods. Based on the water quality change trend and reference values ​​of the canal, the risk of different water quality indicators in the aquatic ecosystem of the target canal is assessed, and the water quality assessment results and the first early warning information are obtained.

6. The canal ecological monitoring method according to claim 5, characterized in that, The steps for analyzing the changing trends of water quality and hydrometeorological indicators based on the standardized multidimensional monitoring data sequence also include: Obtain a set of multiple hydro-meteorological indicators and the calculation formula corresponding to each hydro-meteorological indicator, wherein the set of multiple hydro-meteorological indicators includes at least flow rate, water level, water temperature and rainfall. Extract the index data corresponding to each type of hydrological and meteorological index from the standardized multi-dimensional monitoring data sequence, and determine the index weight corresponding to the hydrological and meteorological index. The indicator data and indicator weights are input into the calculation formula corresponding to the hydrological and meteorological indicators to obtain the changing trend of the hydrological and meteorological indicators. Based on the changing trends of the hydro-meteorological indicators and the reference values ​​of the meteorological indicators, the risk of different hydro-meteorological indicators in the water ecosystem of the target canal is assessed, and the hydro-meteorological assessment results and the second early warning information are obtained.

7. The canal ecological monitoring method according to claim 6, characterized in that, Based on the analysis of changing trends, the steps for generating a canal ecological monitoring report and a water ecological emergency plan also include: The canal ecological monitoring report is generated by integrating the multi-dimensional monitoring data sequence, water quality assessment results and first early warning information, the hydro-meteorological assessment results and second early warning information. Based on the analysis results of the aforementioned trends, the risks of water quality deterioration and hydrological disasters in the canal are identified, and a pre-set water ecological emergency plan is matched.

8. A canal ecological monitoring system based on multi-source heterogeneous data, characterized in that, include: The multi-source heterogeneous data acquisition unit is used to acquire multi-source heterogeneous data obtained from monitoring the water ecology of the target canal. The multi-source heterogeneous data includes: monitoring data from multiple types of sensors, remote sensing and UAV monitoring data, and inspection and data entry data. A data classification unit is used to classify the multi-source heterogeneous data to obtain a multi-dimensional monitoring data sequence based on the data transmission cycle; The data change trend analysis unit is used to standardize the multi-dimensional monitoring data sequence and analyze the change trends of water quality and hydro-meteorological indicators based on the standardized multi-dimensional monitoring data sequence. The monitoring report generation unit is used to generate canal ecological monitoring reports and water ecological emergency plans based on the analysis results of change trends.

9. An electronic device, characterized in that, It includes one or more processors and a memory, the memory being used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the canal ecological monitoring method based on multi-source heterogeneous data as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the canal ecological monitoring method based on multi-source heterogeneous data as described in any one of claims 1 to 7.

Images