A water temperature information monitoring system and method

Abstract

The present invention relates to the field of water temperature monitoring technology, and in particular to a water temperature information monitoring system and method. The method comprises the following steps: performing water environment function analysis on the target monitoring water area to obtain water environment characteristic data; deploying a water temperature monitoring network based on the water environment characteristic data; performing periodic water depth estimation processing according to the water temperature monitoring network, and performing water level correction processing on the monitoring device to generate real-time water level correction data; performing adaptive sampling strategy adjustment according to the real-time water level correction data to obtain adaptive water temperature sampling data; performing outlier masking on the adaptive water temperature sampling data to obtain purified temperature cube data; performing environmental compensation correction processing according to the purified temperature cube data to generate corrected water temperature field data; performing water body circulation characteristic analysis according to the corrected water temperature field data to generate water body circulation pattern data. The present invention realizes water body temperature monitoring efficiently through adaptive water temperature stratified sampling control.

Description

Technical Field

[0001] The present invention relates to the technical field of water temperature monitoring, and in particular to a water temperature information monitoring system and method. Background Art

[0002] With the rapid development of social economy and the continuous improvement of people's living standards, the effective management and rational use of water resources have become a major issue of global concern. Especially in the fields of agricultural irrigation, industrial production, urban water supply, ecological protection and aquaculture, water temperature is an important parameter for measuring water quality, affecting biological growth and reproduction, and indicating environmental changes. Its accurate monitoring and control are particularly important. However, traditional water temperature monitoring methods usually rely on manual regular sampling and measurement, which is not only inefficient, but also the real-time, continuity and accuracy of the data cannot be effectively guaranteed. For example, the measurement methods using mercury thermometers and thermocouples are easily affected by environmental factors, the measurement results are inaccurate, the response time is slow, and it is difficult to achieve remote monitoring. Problems such as these cannot meet the refined needs of modern water temperature monitoring. Summary of the invention

[0003] Based on this, the present invention provides a water temperature information monitoring system and method to solve at least one of the above technical problems.

[0004] To achieve the above purpose, a water temperature information monitoring method comprises the following steps:

[0005] Step S1: Performing water environment function analysis on the target monitoring water area to obtain water environment characteristic data; deploying the best monitoring device for the target monitoring water area using the intelligent water temperature monitoring device based on the water environment characteristic data to obtain a water temperature monitoring network;

[0006] Step S2: Perform periodic water depth estimation processing according to the water temperature monitoring network to generate spatial water depth interpolation fusion data; perform monitoring device water level correction processing according to the spatial water depth interpolation fusion data to generate real-time water level correction data;

[0007] Step S3: Perform monitoring water layer analysis based on the real-time water level correction data to generate target monitoring water layer data; perform water temperature layer sampling based on the target monitoring water layer data to generate initial water temperature layer sampling data; perform adaptive sampling strategy adjustment based on the initial water temperature layer sampling data to obtain adaptive water temperature sampling data;

[0008] Step S4: performing temperature tensor normalization processing on the adaptive water temperature sampling data to generate standard water temperature sampling data; performing outlier masking based on the standard water temperature sampling data to obtain purified temperature cube data; performing environmental compensation correction processing based on the purified temperature cube data to generate corrected water temperature field data;

[0009] Step S5: Reconstruct the three-dimensional water temperature profile based on the corrected water temperature field data to generate reconstructed water temperature profile data; dynamically monitor the thermal layer based on the reconstructed water temperature profile data to generate dynamic water temperature thermal layer monitoring data; perform water body circulation characteristic analysis on the dynamic water temperature thermal layer monitoring data to generate water body circulation pattern data.

[0010] The present invention performs water environment function analysis on the target monitoring water area, and can deeply understand various environmental characteristics of the target monitoring water area, including but not limited to information such as water quality, water flow, and biological community. This helps to accurately evaluate the overall environmental status of the water area. By using an intelligent water temperature monitoring device to analyze the water environment characteristic data, the layout of the monitoring network can be effectively optimized to ensure that the coverage and density of the monitoring device can reflect the actual situation of the water area to the greatest extent, thereby improving the monitoring efficiency and accuracy. According to the water temperature monitoring network, periodic water depth estimation processing can be performed to calculate the water depth of the detection device in different time periods. According to the water depth data, the water level measured by the monitoring device is corrected to eliminate the error caused by the change of water depth and generate more accurate real-time water level correction data. The real-time water level correction data is used to analyze the monitored water layer, determine the different water layer structures and characteristics of the water body, and deeply understand the water body movement and distribution inside the water area. According to the target water layer data, water temperature sampling is carried out in a targeted manner to obtain water temperature data of different water layers. Through such operations, the water temperature conditions of different depths in the water area can be obtained. The sampling strategy is adjusted according to the initial sampling data to make the sampling more efficient and accurate. By adjusting the adaptive strategy, the selection of sampling points, the arrangement of frequency and sampling time can be optimized, and the representativeness and reliability of the sampling data can be improved. The sampling data is standardized so that the temperature data of different sampling points are comparable. The outliers in the sampling data can be effectively identified and eliminated by masking the outliers according to the standard water temperature sampling data. The temperature data can be corrected according to the environmental conditions, and the influence of the specific environmental factors of the water area on the temperature can be considered to more accurately reflect the actual temperature distribution of the water area. Using the corrected water temperature field data and combining it with the three-dimensional space reconstruction technology, we can deeply understand the spatial distribution of the temperature inside the water area. Through real-time monitoring and analysis of water temperature profile data, we can track the temperature changes inside the water area and identify and analyze the dynamic change characteristics of the thermal layer. This helps to gain a deeper understanding of the temperature stratification of the water body and the formation and evolution mechanism of the thermal layer. Through the comprehensive analysis of the monitoring data, the circulation characteristics of the water body can be revealed, including information such as the flow direction, speed, and circulation pattern of the water body. Therefore, a water temperature information monitoring method of the present invention analyzes the environmental characteristics of the target monitored water area, intelligently deploys water temperature monitoring devices, considers the real-time water level data of the monitoring device, and adaptively collects the original stratified water temperature data to make sampling more efficient and accurate; the sampled water temperature data is compensated and corrected for environmental factors to eliminate the influence of environmental factors on water temperature stratification measurement; the monitored water temperature stratification data is used to perform time-series water body circulation characteristic analysis to realize the analysis of the hydrological environment characteristics within the water area; the edge terminal nodes and the intelligent monitoring device are deployed to process the data in real time to improve the monitoring response capability, and at the same time realize the water temperature remote monitoring function.

[0011] Preferably, step S1 comprises the following steps:

[0012] Step S11: collecting water area remote sensing images of the target monitoring water area to generate remote sensing impact data of the target water area;

[0013] Step S12: Performing water environment function analysis based on the remote sensing impact data of the target water area to obtain water environment characteristic data, wherein the water environment characteristic data includes a deep water measurement area, a shallow beach measurement area, and a waterweed measurement area;

[0014] Step S13: performing optimal monitoring device deployment strategy processing based on the water environment characteristic data to obtain the optimal monitoring device deployment strategy;

[0015] Step S14: deploy the intelligent water temperature monitoring device in the target monitoring water area through the optimal monitoring device deployment strategy, so as to build a water temperature monitoring network.

[0016] The beneficial effect of the present invention on the acquisition of water area remote sensing images of the target monitoring water area is to obtain high-resolution water area remote sensing image data. These data can provide spatial information such as the geometric shape, topography and landform of the water area, and help determine the structure and characteristics of the water area. By analyzing the characteristics of the deep water measurement area, the shallow water measurement area and the aquatic grass coverage area of ​​the water area, the ecosystem status and biodiversity of the water area can be comprehensively evaluated. By considering the characteristics and environmental conditions of the water area, the optimal monitoring device deployment plan is determined, including the location, density and coverage of the monitoring points, to ensure that the monitoring device can comprehensively and accurately monitor the environmental changes of the target water area. Through the optimal monitoring device deployment strategy, the intelligent water temperature monitoring device is deployed in the target monitoring water area to build a water temperature monitoring network. Such a network can monitor the temperature changes of the water area in real time and provide reliable data support for water environment management and protection.

[0017] Preferably, step S14 comprises the following steps:

[0018] Step S141: constructing water area environment characteristic indexes according to the water area environment characteristic data to obtain environment characteristic index system data, wherein the environment characteristic index system data includes a water depth index, a water area bottom hardness index, and aquatic plant growth density index;

[0019] Step S142: Performing water area level environmental sensitivity assessment processing based on the environmental characteristic index system data to obtain water area level environmental characteristic assessment data;

[0020] Step S143: quantifying the performance of the intelligent water temperature monitoring device through the water environment characteristic data to generate quantified performance data of the monitoring device;

[0021] Step S144: using the water area level environmental characteristic assessment data to perform monitoring demand weighting processing on the monitoring device performance quantification data to obtain water area monitoring demand weight data;

[0022] Step S145: Optimize the monitoring node density according to the water area monitoring demand weight data to obtain monitoring node density data;

[0023] Step S146: performing deployment connectivity analysis on the water environment characteristic data by monitoring node density data to obtain monitoring node topology data;

[0024] Step S147: Optimize the minimum number of nodes according to the monitoring node topology data to generate the best monitoring device deployment strategy.

[0025] The beneficial effect of the present invention in constructing water area environmental characteristic indexes according to water area environmental characteristic data is that a comprehensive environmental characteristic index system is established. This index system includes indicators such as water depth index, water area bottom hardness index and waterweed growth density index, which can fully reflect the environmental characteristics of the water area. By analyzing and evaluating the environmental characteristic indicators of the water area, the environmental sensitivity of the water area, that is, the responsiveness and adaptability of the water area to external factors can be determined. By analyzing the water area environmental characteristic data to quantitatively evaluate the performance of the monitoring device, the performance of the monitoring device under different water environment can be understood, including its adaptability to water depth, bottom hardness and waterweed growth. According to the relationship between the water area environmental characteristics and the performance of the monitoring device, the monitoring requirements are weighted, and the importance of different monitoring nodes in water area environmental monitoring can be determined. By considering the weight of the monitoring requirements, the number and arrangement of the monitoring nodes can be reasonably determined, so that the monitoring network has a wider coverage, can more comprehensively and accurately reflect the changes in the water environment, and improve the monitoring efficiency and accuracy. By analyzing the spatial distribution and connectivity of the monitoring nodes, the degree of association between the monitoring nodes and the connectivity strength of the monitoring network can be determined. Through the optimization of the minimum number of nodes, the minimum number of monitoring nodes can be determined to meet the requirements of water environment monitoring while ensuring the connectivity and effectiveness of the monitoring network, thereby achieving the best monitoring device deployment strategy.

[0026] Preferably, step S2 comprises the following steps:

[0027] Step S21: using a pressure sensor to collect water body pressure factors based on a preset pressure collection cycle to generate water body static pressure collection data;

[0028] Step S22: using a microprocessor to perform reverse fluid water depth estimation on the water body pressure factor collection data to generate water depth estimation data;

[0029] Step S23: using the water temperature monitoring network to transmit the water depth estimation data to the edge computing terminal node through the wireless communication module, and performing spatial interpolation fusion processing to obtain spatial water depth interpolation fusion data;

[0030] Step S24: performing water depth distribution analysis based on the spatial water depth interpolation fusion data to obtain water depth distribution map data;

[0031] Step S25: estimating the water level gradient according to the water depth distribution map data to obtain monitoring water level estimation data;

[0032] Step S26: selecting multiple water level reference points for the monitored water level estimation data to generate reference point water level estimation data;

[0033] Step S27: performing water level deviation analysis on the monitoring water level estimation data by using the reference point water level estimation data to generate water level deviation analysis data;

[0034] Step S28: Performing monitoring device water level correction processing on the water level deviation analysis data through a preset linear regression model to generate real-time water level correction data.

[0035] The present invention can obtain the pressure conditions of the water body at different depths by collecting the static pressure data of the water body. The static pressure data of the water body is used to infer the depth information of the water body through the reverse fluid water depth estimation algorithm, thereby obtaining the water depth estimation data. The water depth estimation data is transmitted to the edge computing terminal node by using the communication function of the water temperature monitoring network to provide more accurate spatial information. The spatial water depth interpolation fusion data is analyzed to obtain the depth distribution of the water body at different positions, providing an intuitive visual expression for the depth characteristics of the water area. According to the water depth distribution map data, the water level gradient of the water body is calculated to obtain the estimated data of the monitored water level. By selecting multiple water level reference points, the accuracy and deviation of the monitored water level can be more comprehensively evaluated, and the accuracy and reliability of the water level estimation can be improved. The deviation between the monitored water level and the reference point water level is analyzed, and the error of the monitoring device is calculated. According to the water level deviation analysis data, the water level correction processing is performed using a linear regression model to correct the water level data of the monitoring device.

[0036] Preferably, step S3 comprises the following steps:

[0037] Step S31: Perform monitoring water layer analysis based on real-time water level correction data to generate target monitoring water layer data;

[0038] Step S32: Processing the temperature sampling instruction according to the target monitored water layer data to generate temperature sampling instruction data;

[0039] Step S33: transmitting the temperature sampling instruction data to the matching intelligent water temperature monitoring device, using a microprocessor to perform instruction parsing on the temperature sampling instruction data, and controlling the temperature sensor of the monitoring water layer to perform water temperature layer sampling operation, thereby generating initial water temperature layer sampling data;

[0040] Step S34: using a microprocessor to perform data preprocessing on the initial water temperature level sampling data to generate cleaning initial water temperature sampling data;

[0041] Step S35: performing adaptive water temperature sampling strategy processing according to the initial water temperature sampling data of cleaning to generate an adaptive water temperature sampling strategy;

[0042] Step S36: adjusting the sampling strategy based on the adaptive water temperature sampling strategy, and performing stratified water temperature sampling processing to obtain adaptive water temperature sampling data.

[0043] The present invention uses real-time water level correction data to analyze the water layers in the water area and determine the target water layers to be monitored, including the depth and distribution of the water body. Based on the information of the target water layer, a temperature sampling instruction is formulated to determine the location and depth of the temperature sampling. The intelligent water temperature monitoring device is remotely controlled to accurately control the water temperature sensor according to the sampling instruction to obtain the initial water temperature layer sampling data. The sampled data is preprocessed, including removing noise, smoothing data, etc., to ensure the quality and reliability of the sampled data. Based on the cleaned initial sampling data, a sampling strategy that adapts to the water temperature distribution is formulated to ensure the comprehensiveness and representativeness of the sampling data. The sampling scheme is adjusted according to the adaptive sampling strategy to achieve targeted water temperature sampling and obtain more accurate and comprehensive water temperature data.

[0044] Preferably, step S35 includes the following steps:

[0045] Step S351: using a preset time window to perform sampling data division processing on the initial water temperature sampling data of the cleaning, and generating time series window water temperature sampling data;

[0046] Step S352: Process the temperature variation according to the water temperature sampling data in the time series window to generate temperature difference data;

[0047] Step S353: calculating the water temperature change rate of the temperature difference data through a preset time window to obtain water temperature change rate data;

[0048] Step S354: Processing the water temperature fluctuation degree according to the water temperature change rate data to generate water temperature fluctuation degree data;

[0049] Step S355: performing temperature change trend analysis based on the water temperature change rate data to generate temperature change trend data;

[0050] Step S356: performing time series temperature change pattern analysis on the temperature change trend data to generate water temperature change pattern data;

[0051] Step S356: evaluating the sampling adjustment trigger condition based on the water temperature fluctuation degree data and the temperature change trend data, and generating adjustment condition trigger result data;

[0052] Step S357: When the adjustment condition trigger result data is failure, the current water temperature sampling strategy is maintained; when the adjustment condition trigger result data is success, step S38 is executed;

[0053] Step S358: determining the sampling frequency adjustment direction according to the water temperature conversion mode data, and generating sampling frequency adjustment direction data; performing comprehensive sampling adjustment weight calculation according to the water temperature fluctuation degree data and the water temperature change rate data, and generating comprehensive sampling adjustment weight data;

[0054] Step S359: Calculate the sampling adjustment amplitude based on the comprehensive sampling adjustment weight data and the sampling frequency adjustment direction data, and optimize the sampling adjustment amplitude through a preset adjustment amplitude limiting strategy, so as to obtain an adaptive water temperature sampling strategy.

[0055] The present invention divides the sampling data according to a preset time window to form continuous time series data, so that the changing trend of water temperature over time can be better observed. The temperature change amount is processed according to the water temperature sampling data in the time series window, and the temperature change amount between adjacent time points, that is, the change range of water temperature, is calculated, so that the fluctuation of water temperature can be quantified. The rate of change of water temperature in unit time, that is, the speed of change of water temperature, is calculated, so that the speed of water temperature change can be reflected. The degree of water temperature fluctuation is processed according to the water temperature change rate data, and the degree of water temperature fluctuation, that is, the range of water temperature change within a certain period of time, can be quantified, so that the stability and change range of water temperature can be evaluated. The trend of water temperature change, that is, the direction and trend of water temperature change, can be analyzed, so that the future change trend of water temperature can be predicted. The time series pattern of water temperature change is analyzed, including characteristics such as periodicity and trend, so that the regularity of water temperature change can be identified. The degree of water temperature fluctuation and the change trend are comprehensively considered, the adaptability of the current sampling strategy is evaluated, and it is judged whether sampling adjustment is needed. It is decided whether to perform sampling adjustment according to the evaluation result to ensure the stability and effectiveness of the sampling strategy. Determine the direction and amplitude of sampling adjustment, taking into account the water temperature change pattern, fluctuation degree and change rate. Calculate the amplitude of sampling adjustment based on the comprehensive weight and adjustment direction, and optimize the adjustment amplitude through the restriction strategy to ensure the rationality and controllability of sampling adjustment, and finally form a sampling strategy that adapts to water temperature changes.

[0056] Preferably, step S4 comprises the following steps:

[0057] Step S41: using the intelligent water temperature monitoring device to obtain position information and obtain monitoring position data;

[0058] Step S42: Binding the monitoring position data with the adaptive water temperature sampling data, and transmitting them to the edge computing terminal node to generate position-water temperature sampling data;

[0059] Step S43: performing temperature tensor normalization processing on the orientation-water temperature sampling data to generate standard water temperature sampling data; constructing a stratified water temperature matrix based on the standard water temperature sampling data to generate original stratified water temperature matrix data;

[0060] Step S44: performing outlier mask identification on the original stratified water temperature matrix data through a preset confidence temperature interval to generate outlier mask tensor data;

[0061] Step S45: performing data elimination processing on the abnormal mask tensor data through the original layered water temperature matrix data to obtain purified temperature cube data;

[0062] Step S46: Perform environmental compensation correction processing according to the purification temperature cube data to generate corrected water temperature field data.

[0063] The present invention obtains the specific coordinate information of each position in the water area through a monitoring device, thereby realizing the accurate positioning of the monitoring point. The monitoring orientation information is associated with the sampling data to form a binding relationship between the spatial position and the water temperature data. The water temperature data is standardized to ensure the uniformity and comparability of the data, and at the same time, a matrix of water temperature changes with spatial position is constructed. The original layered water temperature matrix data is marked with an outlier mask through a preset confidence temperature interval, and the outliers in the original data are identified and marked, reducing the interference of outliers on water temperature analysis, and improving the accuracy and credibility of the data. The abnormal mask tensor data is subjected to data elimination processing, in which cleaner and more reliable water temperature data is obtained after removing the outliers. The water temperature data is corrected according to the actual environmental conditions, and more real and reliable water temperature field data is obtained by taking into account the characteristics of the water area and external influencing factors.

[0064] Preferably, step S46 includes the following steps:

[0065] Step S461: acquiring real-time external environment data, wherein the real-time external environment data includes water flow velocity data, external environment temperature data, and external weather data;

[0066] Step S462: Perform environmental factor impact analysis based on real-time external environmental data to generate environmental factor impact assessment data;

[0067] Step S463: performing overall environmental disturbance calculation according to the environmental factor impact analysis data to generate an overall environmental disturbance value;

[0068] Step S464: performing real-time disturbance compensation calculation on the overall environmental disturbance value through the real-time external environmental data to obtain real-time disturbance compensation data;

[0069] Step S465: performing spatiotemporal water temperature related hypersurface segmentation on the purified temperature cube data to obtain spatiotemporal water temperature related hypersurface data;

[0070] Step S466: using the real-time disturbance compensation data to perform environmental disturbance elimination processing on the spatiotemporal related water temperature hypersurface data to generate environmental disturbance elimination field data;

[0071] Step S467: performing sensor confidence vector processing according to the purified temperature cube data to generate sensor confidence vector data;

[0072] Step S468: Perform temperature field fusion correction processing on the environmental disturbance elimination field data using the sensor confidence vector data to obtain corrected water temperature field data.

[0073] The present invention obtains external environmental factor data related to water temperature changes, such as water flow velocity, temperature and weather conditions. Environmental factor impact analysis is performed based on real-time external environmental data to analyze the degree of influence of external environmental factors on water temperature, including factors such as water flow velocity, temperature and weather. Overall environmental disturbance calculation is performed based on environmental factor impact analysis data, and the degree of influence of various environmental factors is comprehensively considered to quantify the comprehensive impact of the overall environment on water temperature. The overall environmental disturbance value is dynamically adjusted based on real-time external environmental data to achieve real-time compensation of water temperature, making water temperature monitoring more accurate and reliable, and improving the credibility and stability of the data.

[0074] Preferably, step S5 comprises the following steps:

[0075] Step S51: performing three-dimensional water temperature profile reconstruction processing according to the corrected water temperature field data to generate reconstructed water temperature profile data;

[0076] Step S52: performing thermal layer stratification identification according to the reconstructed water temperature profile data to obtain water body thermal layer stratification data;

[0077] Step S53: Perform continuous dynamic monitoring of the thermal layer based on the water body thermal layer stratification data to generate dynamic water temperature thermal layer monitoring data;

[0078] Step S54: Calculate the vertical gradient of water temperature according to the dynamic water temperature thermal layer monitoring data to generate water temperature gradient data;

[0079] Step S55: evaluating the water mixing efficiency of the water temperature gradient data to obtain water mixing efficiency data;

[0080] Step S56: Based on the preset water circulation model, water mixing efficiency data is used to analyze the water circulation characteristics of the dynamic water temperature and thermal layer monitoring data to generate water circulation pattern data.

[0081] The present invention utilizes the corrected water temperature field data to accurately reconstruct the water temperature distribution through appropriate algorithms and models, so that the water temperature profile data is closer to the actual situation. Thermal layer stratification is performed based on the reconstructed water temperature profile data, in order to identify the distribution of different temperature layers in the water body and identify the location and characteristics of the thermal layer. Continuous dynamic monitoring of the thermal layer based on the water body thermal layer stratification data is performed to monitor the changes in the water body thermal layer in real time and capture the dynamic changes in the temperature stratification. The rate of change of temperature between different depths of the water body is analyzed to reveal the vertical gradient of the water temperature and further understand the circulation characteristics of the water body. The water mixing efficiency is evaluated on the water temperature gradient data to understand the uniformity of the temperature distribution inside the water body. Combined with the results of the water mixing efficiency evaluation, the circulation characteristics and patterns of the water body are analyzed through the water body circulation model, providing an in-depth understanding of the laws of water body circulation and providing a scientific basis for water environment management and protection.

[0082] The present invention also provides a water temperature information monitoring system, which executes the water temperature information monitoring method as described above, and the water temperature information monitoring system comprises:

[0083] The intelligent device deployment module is used to analyze the water environment function of the target monitoring water area and obtain water environment characteristic data; based on the water environment characteristic data, the intelligent water temperature monitoring device is used to deploy the best monitoring device for the target monitoring water area and obtain a water temperature monitoring network;

[0084] The real-time water level estimation module is used to perform periodic water depth estimation processing based on the water temperature monitoring network to generate spatial water depth interpolation fusion data; perform monitoring device water level correction processing based on the spatial water depth interpolation fusion data to generate real-time water level correction data;

[0085] The adaptive sampling module is used to analyze the monitored water layer according to the real-time water level correction data to generate the target monitored water layer data; perform water temperature layer sampling operations based on the target monitored water layer data to generate initial water temperature layer sampling data; adjust the adaptive sampling strategy according to the initial water temperature layer sampling data to obtain adaptive water temperature sampling data;

[0086] The water temperature compensation correction module is used to perform temperature tensor standardization processing on the adaptive water temperature sampling data to generate standard water temperature sampling data; perform outlier masking based on the standard water temperature sampling data to obtain purified temperature cube data; perform environmental compensation correction processing based on the purified temperature cube data to generate corrected water temperature field data;

[0087] The water temperature circulation analysis module is used to reconstruct the three-dimensional water temperature profile based on the corrected water temperature field data to generate reconstructed water temperature profile data; to dynamically monitor the thermal layer based on the reconstructed water temperature profile data to generate dynamic water temperature thermal layer monitoring data; to analyze the water body circulation characteristics of the dynamic water temperature thermal layer monitoring data to generate water body circulation pattern data. BRIEF DESCRIPTION OF THE DRAWINGS

[0088] Figure 1 A schematic diagram of the steps of a water temperature information monitoring method of the present invention;

[0089] Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart;

[0090] Figure 3 for Figure 1 Detailed implementation steps of step S5;

[0091] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0092] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0093] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0094] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0095] To achieve this, please refer to Figures 1 to 3 The present invention provides a water temperature information monitoring method, comprising the following steps:

[0096] Step S1: Performing water environment function analysis on the target monitoring water area to obtain water environment characteristic data; deploying the best monitoring device for the target monitoring water area using the intelligent water temperature monitoring device based on the water environment characteristic data to obtain a water temperature monitoring network;

[0097] Step S2: Perform periodic water depth estimation processing according to the water temperature monitoring network to generate spatial water depth interpolation fusion data; perform monitoring device water level correction processing according to the spatial water depth interpolation fusion data to generate real-time water level correction data;

[0098] Step S3: Perform monitoring water layer analysis based on the real-time water level correction data to generate target monitoring water layer data; perform water temperature layer sampling based on the target monitoring water layer data to generate initial water temperature layer sampling data; perform adaptive sampling strategy adjustment based on the initial water temperature layer sampling data to obtain adaptive water temperature sampling data;

[0099] Step S4: performing temperature tensor normalization processing on the adaptive water temperature sampling data to generate standard water temperature sampling data; performing outlier masking based on the standard water temperature sampling data to obtain purified temperature cube data; performing environmental compensation correction processing based on the purified temperature cube data to generate corrected water temperature field data;

[0100] Step S5: Reconstruct the three-dimensional water temperature profile based on the corrected water temperature field data to generate reconstructed water temperature profile data; dynamically monitor the thermal layer based on the reconstructed water temperature profile data to generate dynamic water temperature thermal layer monitoring data; perform water body circulation characteristic analysis on the dynamic water temperature thermal layer monitoring data to generate water body circulation pattern data.

[0101] The present invention performs water environment function analysis on the target monitoring water area, and can deeply understand various environmental characteristics of the target monitoring water area, including but not limited to information such as water quality, water flow, and biological community. This helps to accurately evaluate the overall environmental status of the water area. By using an intelligent water temperature monitoring device to analyze the water environment characteristic data, the layout of the monitoring network can be effectively optimized to ensure that the coverage and density of the monitoring device can reflect the actual situation of the water area to the greatest extent, thereby improving the monitoring efficiency and accuracy. According to the water temperature monitoring network, periodic water depth estimation processing can be performed to calculate the water depth of the detection device in different time periods. According to the water depth data, the water level measured by the monitoring device is corrected to eliminate the error caused by the change of water depth and generate more accurate real-time water level correction data. The real-time water level correction data is used to analyze the monitored water layer, determine the different water layer structures and characteristics of the water body, and deeply understand the water body movement and distribution inside the water area. According to the target water layer data, water temperature sampling is carried out in a targeted manner to obtain water temperature data of different water layers. Through such operations, the water temperature conditions of different depths in the water area can be obtained. The sampling strategy is adjusted according to the initial sampling data to make the sampling more efficient and accurate. By adjusting the adaptive strategy, the selection of sampling points, the arrangement of frequency and sampling time can be optimized, and the representativeness and reliability of the sampling data can be improved. The sampling data is standardized so that the temperature data of different sampling points are comparable. The outliers in the sampling data can be effectively identified and eliminated by masking the outliers according to the standard water temperature sampling data. The temperature data can be corrected according to the environmental conditions, and the influence of the specific environmental factors of the water area on the temperature can be considered to more accurately reflect the actual temperature distribution of the water area. Using the corrected water temperature field data and combining it with the three-dimensional space reconstruction technology, we can deeply understand the spatial distribution of the temperature inside the water area. Through real-time monitoring and analysis of water temperature profile data, we can track the temperature changes inside the water area and identify and analyze the dynamic change characteristics of the thermal layer. This helps to gain a deeper understanding of the temperature stratification of the water body and the formation and evolution mechanism of the thermal layer. Through the comprehensive analysis of the monitoring data, the circulation characteristics of the water body can be revealed, including information such as the flow direction, speed, and circulation pattern of the water body. Therefore, a water temperature information monitoring method of the present invention analyzes the environmental characteristics of the target monitored water area, intelligently deploys water temperature monitoring devices, considers the real-time water level data of the monitoring device, and adaptively collects the original stratified water temperature data to make sampling more efficient and accurate; the sampled water temperature data is compensated and corrected for environmental factors to eliminate the influence of environmental factors on water temperature stratification measurement; the monitored water temperature stratification data is used to perform time-series water body circulation characteristic analysis to realize the analysis of the hydrological environment characteristics within the water area; the edge terminal nodes and the intelligent monitoring device are deployed to process the data in real time to improve the monitoring response capability, and at the same time realize the water temperature remote monitoring function.

[0102] In the embodiment of the present invention, reference Figure 1The above is a schematic flow chart of the steps of a water temperature information monitoring method of the present invention. In this embodiment, the water temperature information monitoring method includes the following steps:

[0103] Step S1: Performing water environment function analysis on the target monitoring water area to obtain water environment characteristic data; deploying the best monitoring device for the target monitoring water area using the intelligent water temperature monitoring device based on the water environment characteristic data to obtain a water temperature monitoring network;

[0104] In an embodiment of the present invention, water environment characteristic data is obtained through functional analysis of the target water environment. Image data is collected using a remote sensing platform to interpret deep water areas, shallows, and aquatic plant coverage areas. Depth analysis, shallow area measurement, and aquatic plant coverage statistics are performed using GIS tools to obtain characteristic data. Determine monitoring needs and select a distributed sensor network. Install sensors at different depths and locations with high water flow velocities, as well as around aquatic plant coverage areas to ensure comprehensive monitoring. Deploy intelligent water temperature monitoring devices, and have ships and divers accurately install sensors and buoys at predetermined locations. The monitoring device is connected to the monitoring center via a wireless network to achieve real-time data transmission.

[0105] Step S2: Perform periodic water depth estimation processing according to the water temperature monitoring network to generate spatial water depth interpolation fusion data; perform monitoring device water level correction processing according to the spatial water depth interpolation fusion data to generate real-time water level correction data;

[0106] In an embodiment of the present invention, a pressure sensor installed at the bottom of the intelligent water temperature monitoring device is used to regularly collect water pressure data and transmit it to a microprocessor for processing. The water depth information is calculated using a physical formula, and the processed data is transmitted to the water temperature monitoring network. A wireless communication module is set up to transmit the water depth estimation data to the edge computing terminal node for spatial interpolation and fusion processing. A water depth distribution map is generated, and outliers are cleaned, denoised, and processed. The water level gradient is calculated using the numerical differential method to generate monitoring water level estimation data. Multiple water level reference points are selected, water level data is extracted, and water level deviation analysis is performed. A linear regression model is designed to perform water level correction processing and generate real-time water level correction data.

[0107] Step S3: Perform monitoring water layer analysis based on the real-time water level correction data to generate target monitoring water layer data; perform water temperature layer sampling based on the target monitoring water layer data to generate initial water temperature layer sampling data; perform adaptive sampling strategy adjustment based on the initial water temperature layer sampling data to obtain adaptive water temperature sampling data;

[0108] In an embodiment of the present invention, the monitored water layer analysis is performed based on the real-time water level correction data, and the temperature sensor of the intelligent water temperature monitoring device is marked as the target monitored water layer. A suitable temperature sampling instruction processing method is selected to generate temperature sampling instruction data, including determining the sampling point and setting the sampling depth. The instructions are transmitted to the monitoring device via a wireless network, and the microprocessor parses the instructions and controls the sensor to perform sampling operations. The collected data is processed to generate initial water temperature layer sampling data, and then data preprocessing is performed, including outlier correction, missing value filling and data smoothing. According to the adaptive sampling strategy adjustment, targeted water temperature sampling is achieved to obtain adaptive water temperature sampling data.

[0109] Step S4: performing temperature tensor normalization processing on the adaptive water temperature sampling data to generate standard water temperature sampling data; performing outlier masking based on the standard water temperature sampling data to obtain purified temperature cube data; performing environmental compensation correction processing based on the purified temperature cube data to generate corrected water temperature field data;

[0110] In an embodiment of the present invention, first, the geographic coordinate information of the monitoring point is obtained through an intelligent water temperature monitoring device, and it is bound to the adaptive water temperature sampling data to ensure data relevance. Then, the bound data is transmitted to the edge computing terminal node. At the node, the temperature part is standardized to conform to the standard normal distribution, and a hierarchical water temperature matrix is ​​constructed. According to the preset confidence temperature interval, outliers are marked and removed. Next, the purification temperature cube data is corrected using environmental parameters to generate corrected water temperature field data to eliminate temperature deviations caused by environmental factors.

[0111] Step S5: Reconstruct the three-dimensional water temperature profile based on the corrected water temperature field data to generate reconstructed water temperature profile data; dynamically monitor the thermal layer based on the reconstructed water temperature profile data to generate dynamic water temperature thermal layer monitoring data; perform water body circulation characteristic analysis on the dynamic water temperature thermal layer monitoring data to generate water body circulation pattern data.

[0112] In an embodiment of the present invention, first, a three-dimensional spatial grid is constructed to represent the water temperature data at different locations in the water area, and interpolation processing of missing data is performed. Then, based on the corrected water temperature field data, the water temperature profile data is reconstructed, and smoothing and noise filtering are performed on it. Next, the selected thermal layer identification algorithm is used to determine the existence and location of the thermal layer, and the thermal layer is classified. The water body thermal layer stratification data is continuously acquired, the dynamic changes of the thermal layer are detected, and dynamic water temperature thermal layer monitoring data is generated. The water temperature gradient is calculated to evaluate the water mixing efficiency, and the characteristic analysis is performed according to the water body circulation model to generate water body circulation pattern data.

[0113] Preferably, step S1 comprises the following steps:

[0114] Step S11: collecting water area remote sensing images of the target monitoring water area to generate remote sensing impact data of the target water area;

[0115] Step S12: Performing water environment function analysis based on the remote sensing impact data of the target water area to obtain water environment characteristic data, wherein the water environment characteristic data includes a deep water measurement area, a shallow beach measurement area, and a waterweed measurement area;

[0116] Step S13: performing optimal monitoring device deployment strategy processing based on the water environment characteristic data to obtain the optimal monitoring device deployment strategy;

[0117] Step S14: deploy the intelligent water temperature monitoring device in the target monitoring water area through the optimal monitoring device deployment strategy, so as to build a water temperature monitoring network.

[0118] In an embodiment of the present invention, the water area to be monitored may be a lake, a river or an ocean area. According to the characteristics and requirements of the monitored water area, a suitable remote sensing platform is selected, which may be a satellite, an airplane or a drone. The selected remote sensing platform is used to collect images of the monitored water area. This may involve setting acquisition parameters, such as resolution, band, etc., to ensure that high-quality image data is obtained. For example, multiple image acquisitions are performed in a suitable time period, covering the entire lake and surrounding areas. The previously acquired remote sensing images are interpreted to identify deep water areas, shallows and aquatic grass covered areas in the water area. Then, a GIS tool is used to perform a depth analysis of the deep water area to determine the distribution of different depth ranges; the shallows area is measured and the position is calibrated; the aquatic grass covered area is calculated and the coverage rate is counted. Finally, the water environment characteristic data is obtained, including relevant information of the deep water measurement area, the shallows measurement area and the aquatic grass covered area. For example, it is found that a certain lake has large water flow and water depth changes, as well as areas with more aquatic grass coverage. In the monitoring demand determination stage, it is determined that the water temperature and water quality need to be monitored. Based on this information, during the deployment strategy development phase, it was decided to use a distributed sensor network, installing sensors at different depths of the lake and locations with high water flow speeds, as well as around areas covered by aquatic plants. This can cover different terrains and water quality conditions in the lake, ensuring the comprehensiveness and accuracy of monitoring data. The intelligent water temperature monitoring device was installed in the lake according to a pre-established plan. The deployment of the device involved boats and divers, who accurately installed sensors and buoys in the lake according to pre-determined locations. After installation, the monitoring device was connected to the monitoring center via a wireless network, ensuring real-time data transmission.

[0119] Preferably, step S14 comprises the following steps:

[0120] Step S141: constructing water area environment characteristic indexes according to the water area environment characteristic data to obtain environment characteristic index system data, wherein the environment characteristic index system data includes a water depth index, a water area bottom hardness index, and aquatic plant growth density index;

[0121] Step S142: Performing water area level environmental sensitivity assessment processing based on the environmental characteristic index system data to obtain water area level environmental characteristic assessment data;

[0122] Step S143: quantifying the performance of the intelligent water temperature monitoring device through the water environment characteristic data to generate quantified performance data of the monitoring device;

[0123] Step S144: using the water area level environmental characteristic assessment data to perform monitoring demand weighting processing on the monitoring device performance quantification data to obtain water area monitoring demand weight data;

[0124] Step S145: Optimize the monitoring node density according to the water area monitoring demand weight data to obtain monitoring node density data;

[0125] Step S146: performing deployment connectivity analysis on the water environment characteristic data by monitoring node density data to obtain monitoring node topology data;

[0126] Step S147: Optimize the minimum number of nodes according to the monitoring node topology data to generate the best monitoring device deployment strategy.

[0127] In an embodiment of the present invention, specific indicators required for constructing an environmental characteristic index system are determined, such as a water depth index, a water bottom hardness index, and a waterweed growth density index. For example, the water depth distribution, bottom hardness, and waterweed growth density of a lake are calculated. For example, the water depth can be obtained by sampling and measurement, and then the water depth index is constructed according to the distribution of different depths; the bottom hardness can be measured by sonar and other equipment, and then the bottom hardness index is constructed according to the measurement results; the waterweed growth density can be obtained by remote sensing images or field surveys, and then the waterweed growth density index is constructed according to the distribution of waterweeds in the water area. For example, for an intelligent water temperature monitoring device, the performance parameters include temperature measurement accuracy, data transmission stability, and coverage. By testing in a laboratory or in the field, the specific values ​​of each performance parameter can be obtained, such as a measurement accuracy of ±0.1°C, a data transmission stability of 99%, and a coverage range of the entire water area. These data constitute the performance quantification data of the monitoring device. For example, the water depth index has the highest weight in the assessment of water environment sensitivity, followed by the water bottom hardness index, and the waterweed growth density index is the lowest. The temperature measurement accuracy in the performance quantification data of the monitoring device is greatly affected by the water depth, the data transmission stability is greatly affected by the bottom hardness, and the coverage is greatly affected by the density of aquatic plants. In the weighted processing, the temperature measurement accuracy is weighted by the water depth weight, the data transmission stability is weighted by the bottom hardness weight, and the coverage is weighted by the density of aquatic plants growth, so as to obtain the weighted monitoring demand weight data. For example, the water depth in the northern area of ​​a lake is large. According to the water depth index weight, the density of monitoring nodes will be increased in this area; while the aquatic plants growth density in the southern area is high, and the monitoring node density will also be increased according to the aquatic plants growth density index weight. In the northern area with large water depth, the density of monitoring nodes needs to be increased to ensure coverage and connectivity; while in the southern area with high aquatic plants growth density, the node layout position needs to be adjusted according to the aquatic plants coverage to ensure connectivity between nodes. According to the topological structure data of the lake monitoring nodes, the minimum number of monitoring nodes required is analyzed and determined, and the corresponding monitoring device deployment strategy is formulated. For example, by reasonably adjusting the node position and coverage, the number of nodes can be reduced as much as possible, while ensuring that the monitoring needs of various areas of the lake are met.

[0128] Preferably, step S2 comprises the following steps:

[0129] Step S21: using a pressure sensor to collect water body pressure factors based on a preset pressure collection cycle to generate water body static pressure collection data;

[0130] Step S22: using a microprocessor to perform reverse fluid water depth estimation on the water body pressure factor collection data to generate water depth estimation data;

[0131] Step S23: using the water temperature monitoring network to transmit the water depth estimation data to the edge computing terminal node through the wireless communication module, and performing spatial interpolation fusion processing to obtain spatial water depth interpolation fusion data;

[0132] Step S24: performing water depth distribution analysis based on the spatial water depth interpolation fusion data to obtain water depth distribution map data;

[0133] Step S25: estimating the water level gradient according to the water depth distribution map data to obtain monitoring water level estimation data;

[0134] Step S26: selecting multiple water level reference points for the monitored water level estimation data to generate reference point water level estimation data;

[0135] Step S27: performing water level deviation analysis on the monitoring water level estimation data by using the reference point water level estimation data to generate water level deviation analysis data;

[0136] Step S28: Performing monitoring device water level correction processing on the water level deviation analysis data through a preset linear regression model to generate real-time water level correction data.

[0137] As an example of the present invention, refer to Figure 2 As shown, Figure 1 Detailed implementation steps of step S2 in the embodiment are shown in the flowchart. In this embodiment, step S2 includes:

[0138] Step S21: using a pressure sensor to collect water body pressure factors based on a preset pressure collection cycle to generate water body static pressure collection data;

[0139] In an embodiment of the present invention, according to a preset pressure collection cycle, the intelligent monitoring device begins to use the pressure sensor installed at the bottom to regularly collect water pressure data. The collected data usually includes the static pressure of the water body, which can reflect the water depth. According to a preset pressure collection cycle, the intelligent monitoring device begins to use the pressure sensor installed at the bottom to regularly collect water pressure data. The collected data usually includes the static pressure of the water body, which can reflect the water depth.

[0140] Step S22: using a microprocessor to perform reverse fluid water depth estimation on the water body pressure factor collection data to generate water depth estimation data;

[0141] In an embodiment of the present invention, the collected water body pressure factor data is transmitted to a microprocessor for processing. This can be achieved by wired or wireless means to ensure timely transmission and integrity of the data. The data processing process required for water depth estimation is performed in the microprocessor. The collected pressure factor data is parsed and converted so as to be applied to the selected physical formula calculation. The physical formula is calculated as P=ρgh, where P represents the pressure of water, ρ represents the density of water, g represents the acceleration of gravity, and h represents the height of water. The pressure factor data is reversely calculated to derive the depth information of the water body.

[0142] Step S23: using the water temperature monitoring network to transmit the water depth estimation data to the edge computing terminal node through the wireless communication module, and performing spatial interpolation fusion processing to obtain spatial water depth interpolation fusion data;

[0143] In an embodiment of the present invention, a wireless communication module in a water temperature monitoring network is set to ensure that it can receive and process transmission requests from water depth estimation data. The settings include parameters such as network connection, data reception and storage. Using the wireless communication module of the water temperature monitoring network, the water depth estimation data is transmitted from the collection point to the edge computing terminal node. The data needs to be relayed through multiple monitoring nodes until it reaches the edge computing terminal node. For example, after the water depth estimation data is calculated by a microprocessor, it is transmitted to a monitoring node in the water temperature monitoring network through a wireless communication module. After receiving the data, the node forwards it to the adjacent node until it is transmitted to the edge computing terminal node. Spatial interpolation and fusion processing is performed at the edge computing terminal node, and the water depth distribution of the entire lake water area is obtained by combining the surrounding water depth data using the inverse distance weighted interpolation method. Finally, the processed spatial water depth interpolation and fusion data can be sent to the monitoring center through the wireless communication module.

[0144] Step S24: performing water depth distribution analysis based on the spatial water depth interpolation fusion data to obtain water depth distribution map data;

[0145] In an embodiment of the present invention, the water depth interpolation fusion data is preprocessed, including data cleaning, denoising, outlier processing, etc. to ensure the quality and accuracy of the data. After preprocessing these data, a water depth distribution analysis is performed using a statistical analysis method. The analysis results show that the water depth in the central area of ​​the lake is deeper, while the water depth in the lakeshore edge area is shallower. Based on the results of the water depth distribution analysis, water depth distribution map data is generated. The water depth distribution map is usually displayed in the form of a graph or a heat map, which intuitively shows the distribution of water depth in space. Professional geographic information system (GIS) software or data visualization tools can be used to generate a water depth distribution map.

[0146] Step S25: estimating the water level gradient according to the water depth distribution map data to obtain monitoring water level estimation data;

[0147] In an embodiment of the present invention, for example, in a lake water depth monitoring project, water depth distribution map data has been generated, and water level gradient estimation is ready. According to project requirements and data characteristics, numerical differentiation is selected as a method for estimating water level gradients. Water level gradient values ​​at different positions are obtained by numerically differentiating the water depth distribution map data. Based on the calculated water level gradient values, combined with known reference water level information, monitoring water level estimation data is generated. These data can be water level changes relative to the reference water level, or absolute water level height data. For example, combined with known reference water level information, water level estimation data for each monitoring point is calculated. For example, the reference water level of the monitoring center is 100 meters above sea level. Through water level gradient estimation, the water level estimation data of a certain monitoring point is calculated to be 98.5 meters above sea level.

[0148] Step S26: selecting multiple water level reference points for the monitored water level estimation data to generate reference point water level estimation data;

[0149] In an embodiment of the present invention, for example, in a lake water level monitoring project, monitoring water level estimation data has been generated, and multiple water level reference points are ready to be selected. According to the requirements of the project, the following selection criteria are formulated: high frequency of water level changes, wide geographical distribution, and strong representativeness. According to these criteria, multiple water level reference points located in different geographical locations such as the center of the lake, the edge of the lake shore, and the entrance of the lake are selected from the monitoring water level estimation data. For example, a water level reference point in the center of the lake, located far away from the edge of the lake shore, and a water level reference point at the entrance of the lake are selected to represent the situation where the lake water level change is affected by the river entrance. Then, for each selected water level reference point, the corresponding water level data is extracted from the monitoring water level estimation data, and the reference point water level estimation data is generated.

[0150] Step S27: performing water level deviation analysis on the monitoring water level estimation data by using the reference point water level estimation data to generate water level deviation analysis data;

[0151] In an embodiment of the present invention, for example, in a lake water level monitoring project, reference point water level estimation data has been generated, and water level deviation analysis is ready. According to project requirements, the root mean square error (RMSE) is selected as a method for water level deviation analysis. By comparing the monitored water level estimation data with the corresponding reference point water level estimation data point by point, the water level deviation value of each monitoring point is calculated. For example, the water level deviation value of a certain monitoring point is 0.2 meters, indicating that the average deviation of the water level estimation data of the monitoring point relative to the reference point water level estimation data is 0.2 meters. Then, water level deviation analysis data is generated based on the calculation results.

[0152] Step S28: Performing monitoring device water level correction processing on the water level deviation analysis data through a preset linear regression model to generate real-time water level correction data.

[0153] In an embodiment of the present invention, for example, in a river water level monitoring project, water level deviation analysis data has been generated and is ready for water level correction processing. Based on historical data and actual measurements, a linear regression model is pre-designed for water level correction. For example, the input features of the linear regression model include factors such as flow, rainfall, and season, and the output is a water level correction. By inputting the water level deviation analysis data into the linear regression model, the water level correction of each monitoring point is calculated. For example, the water level correction of a certain monitoring point is 0.1 meters, indicating that the water level data of the monitoring point needs to be corrected upward by 0.1 meters. Then, the correction is applied to the original monitored water level data to generate real-time water level correction data.

[0154] Preferably, step S3 comprises the following steps:

[0155] Step S31: Perform monitoring water layer analysis based on real-time water level correction data to generate target monitoring water layer data;

[0156] Step S32: Processing the temperature sampling instruction according to the target monitored water layer data to generate temperature sampling instruction data;

[0157] Step S33: transmitting the temperature sampling instruction data to the matching intelligent water temperature monitoring device, using a microprocessor to perform instruction parsing on the temperature sampling instruction data, and controlling the temperature sensor of the monitoring water layer to perform water temperature layer sampling operation, thereby generating initial water temperature layer sampling data;

[0158] Step S34: using a microprocessor to perform data preprocessing on the initial water temperature level sampling data to generate cleaning initial water temperature sampling data;

[0159] Step S35: performing adaptive water temperature sampling strategy processing according to the initial water temperature sampling data of cleaning to generate an adaptive water temperature sampling strategy;

[0160] Step S36: adjusting the sampling strategy based on the adaptive water temperature sampling strategy, and performing stratified water temperature sampling processing to obtain adaptive water temperature sampling data.

[0161] In the embodiment of the present invention, the actual measured water layer analysis is performed according to the real-time water level correction data, and the temperature sensor that can monitor the water body in the intelligent water temperature monitoring device is marked as the target monitoring water layer. According to the monitoring requirements and the characteristics of the target monitoring water layer data, a suitable temperature sampling instruction processing method is selected. Common methods include determining the sampling points and setting the sampling depth according to the water temperature distribution. According to the target monitoring water layer data and the selected processing method, the temperature sampling instruction data is generated. These instructions include the determination of the temperature sampling points at each depth in the monitoring water layer and the setting of the sampling depth. The temperature sampling instruction data is transmitted to the intelligent water temperature monitoring device via a wireless network. After the built-in microprocessor of the device receives the instruction data, the microprocessor parses the instruction data into corresponding control commands according to the instruction format and protocol, controls the temperature sensor to perform sampling operations according to the parsing results, and performs temperature sampling at the specified depth. The sensor records the water temperature data at each depth, which is transmitted back to the microprocessor and integrated to generate the initial water temperature layer sampling data. The initial water temperature layer sampling data is preprocessed by the microprocessor. According to the pre-set threshold, outliers are detected and corrected, missing values ​​are filled according to the data at the adjacent depth, and a low-pass filter is applied for data smoothing. Adaptive adjustments are made according to the adaptive sampling strategy, and water temperature sampling operations are performed according to the adjusted strategy to achieve targeted water temperature sampling.

[0162] Preferably, step S35 includes the following steps:

[0163] Step S351: using a preset time window to perform sampling data division processing on the initial water temperature sampling data of the cleaning, and generating time series window water temperature sampling data;

[0164] Step S352: Process the temperature variation according to the water temperature sampling data in the time series window to generate temperature difference data;

[0165] Step S353: calculating the water temperature change rate of the temperature difference data through a preset time window to obtain water temperature change rate data;

[0166] Step S354: Processing the water temperature fluctuation degree according to the water temperature change rate data to generate water temperature fluctuation degree data;

[0167] Step S355: performing temperature change trend analysis based on the water temperature change rate data to generate temperature change trend data;

[0168] Step S356: performing time series temperature change pattern analysis on the temperature change trend data to generate water temperature change pattern data;

[0169] Step S356: evaluating the sampling adjustment trigger condition based on the water temperature fluctuation degree data and the temperature change trend data, and generating adjustment condition trigger result data;

[0170] Step S357: When the adjustment condition trigger result data is failure, the current water temperature sampling strategy is maintained; when the adjustment condition trigger result data is success, step S38 is executed;

[0171] Step S358: determining the sampling frequency adjustment direction according to the water temperature conversion mode data, and generating sampling frequency adjustment direction data; performing comprehensive sampling adjustment weight calculation according to the water temperature fluctuation degree data and the water temperature change rate data, and generating comprehensive sampling adjustment weight data;

[0172] Step S359: Calculate the sampling adjustment amplitude based on the comprehensive sampling adjustment weight data and the sampling frequency adjustment direction data, and optimize the sampling adjustment amplitude through a preset adjustment amplitude limiting strategy, so as to obtain an adaptive water temperature sampling strategy.

[0173] In the embodiment of the present invention, according to the monitoring requirements and data characteristics, an appropriate time window size is set for dividing the sampled data. The initial water temperature sampled data for cleaning is divided according to the preset time window to obtain the water temperature sampled data in different time periods. Generally, the time window can be a time period of fixed length, such as every hour, every day or every week. For the water temperature sampled data in each time window, the temperature change between adjacent time points is calculated. This can be achieved by calculating the water temperature difference between adjacent time points, that is, the water temperature at the current time point minus the water temperature at the previous time point. For the temperature difference data in each time window, the temperature change rate is calculated according to the preset time window. Generally, the water temperature change rate can be calculated by dividing the temperature difference by the length of the time window. The result obtained in this way represents the degree of change of the water temperature in a unit time. For the case where the water temperature change rate is large in a certain time period, a higher fluctuation degree value can be obtained, reflecting the violent fluctuation of the water temperature. In the case where the water temperature change rate is small, the fluctuation degree value is low, indicating that the water temperature change is relatively stable. The water temperature change rate data is trend analyzed using a linear regression method. For example, if the slope of the linear regression is positive, it means that the water temperature is on an upward trend; if the slope is negative, it means that the water temperature is on a downward trend; if the slope is close to zero, it means that the water temperature remains stable. For the temperature change trend data, the selected pattern analysis method is applied for analysis. This can help identify the change patterns of water temperature in different time periods, such as periodic changes, sudden changes, etc. According to the degree of water temperature fluctuation and the temperature change trend data, the evaluation criteria for the trigger conditions are set. These criteria can be based on experience or theoretical models to determine whether sampling adjustment is required. According to the adjustment condition trigger result data, it is determined whether the conditions for sampling adjustment are met. If the trigger result is failure, the current water temperature sampling strategy is maintained; if the trigger result is successful, according to the water temperature conversion mode data, the change trend and periodicity of the water temperature are analyzed to determine whether the sampling frequency needs to be adjusted and the direction of adjustment (increase or decrease the sampling frequency). For example, according to the analysis of the water temperature conversion mode data, it is found that the current water temperature shows periodic changes, and the change rate is large, and the sampling frequency needs to be increased. At the same time, the comprehensive sampling adjustment weight calculated based on the water temperature fluctuation degree data and the water temperature change rate data shows that the change rate has a greater impact and needs to be given priority. The amplitude of the sampling adjustment is calculated based on the comprehensive sampling adjustment weight data and the sampling frequency adjustment direction data. The size of the sampling adjustment can be determined based on the weight and direction, so that the adjustment amplitude can fully consider the dynamic changes in water temperature. The sampling adjustment amplitude calculated based on the comprehensive sampling adjustment weight data and the adjustment direction data is to increase the sampling frequency once every 30 minutes, and the maximum adjustment amplitude is limited to no more than ten samples per hour according to the preset adjustment amplitude limit strategy.

[0174] Preferably, step S4 comprises the following steps:

[0175] Step S41: using the intelligent water temperature monitoring device to obtain position information and obtain monitoring position data;

[0176] Step S42: Binding the monitoring position data with the adaptive water temperature sampling data, and transmitting them to the edge computing terminal node to generate position-water temperature sampling data;

[0177] Step S43: performing temperature tensor normalization processing on the orientation-water temperature sampling data to generate standard water temperature sampling data; constructing a stratified water temperature matrix based on the standard water temperature sampling data to generate original stratified water temperature matrix data;

[0178] Step S44: performing outlier mask identification on the original stratified water temperature matrix data through a preset confidence temperature interval to generate outlier mask tensor data;

[0179] Step S45: performing data elimination processing on the abnormal mask tensor data through the original layered water temperature matrix data to obtain purified temperature cube data;

[0180] Step S46: Perform environmental compensation correction processing according to the purification temperature cube data to generate corrected water temperature field data.

[0181] In an embodiment of the present invention, the intelligent water temperature monitoring device obtains the precise location information of the current monitoring point through a built-in location information system (such as GPS). This information includes geographic coordinate data such as longitude and latitude. The acquired monitoring azimuth data is bound to the adaptive water temperature sampling data generated previously. This ensures that each sampling data is associated with the corresponding monitoring location. The bound azimuth-water temperature sampling data is transmitted to the edge computing terminal node through a communication network. This node is usually located at the edge of the water area or a ground station nearby. For the azimuth-water temperature sampling data obtained from different monitoring points, the temperature part is first standardized so that the data conforms to the standard normal distribution. Then, according to the standardized data, a layered water temperature matrix is ​​constructed according to dimensions such as water depth and time. According to previous water temperature observation data and domain knowledge, a confidence temperature range is preset, usually a temperature range within the range of the average temperature plus or minus a standard deviation, to determine the normal water temperature fluctuation range. The temperature value of the original layered water temperature matrix data is detected. If a temperature value exceeds the preset confidence temperature range, it is marked as an abnormal value, otherwise it is marked as a normal value. According to the abnormal mask tensor data, the abnormal values ​​at the corresponding positions in the original stratified water temperature matrix data are removed, that is, the temperature value at the location of the abnormal value is set as a missing value or filled with the mean of the surrounding normal values. The purified temperature cube data is corrected using environmental parameters (such as depth, time, location, etc.) to eliminate the temperature deviation caused by environmental factors. Based on the corrected purified temperature cube data, the corrected water temperature field data is generated, that is, the water temperature distribution after considering the environmental impact.

[0182] Preferably, step S46 includes the following steps:

[0183] Step S461: acquiring real-time external environment data, wherein the real-time external environment data includes water flow velocity data, external environment temperature data, and external weather data;

[0184] Step S462: Perform environmental factor impact analysis based on real-time external environmental data to generate environmental factor impact assessment data;

[0185] Step S463: performing overall environmental disturbance calculation according to the environmental factor impact analysis data to generate an overall environmental disturbance value;

[0186] Step S464: performing real-time disturbance compensation calculation on the overall environmental disturbance value through the real-time external environmental data to obtain real-time disturbance compensation data;

[0187] Step S465: performing spatiotemporal water temperature related hypersurface segmentation on the purified temperature cube data to obtain spatiotemporal water temperature related hypersurface data;

[0188] Step S466: using the real-time disturbance compensation data to perform environmental disturbance elimination processing on the spatiotemporal related water temperature hypersurface data to generate environmental disturbance elimination field data;

[0189] Step S467: performing sensor confidence vector processing according to the purified temperature cube data to generate sensor confidence vector data;

[0190] Step S468: Perform temperature field fusion correction processing on the environmental disturbance elimination field data using the sensor confidence vector data to obtain corrected water temperature field data.

[0191] In the embodiment of the present invention, a water flow velocity sensor or a water flow velocity measuring instrument is used to collect water flow velocity data in the monitored water area in real time. For example, the water flow is measured by a laser Doppler current meter or other equipment. The external environmental temperature data around the monitored water area is collected in real time by a temperature sensor or a weather station or other equipment. For example, a temperature sensor is installed on an underwater buoy or a weather station or other equipment on the shore. External weather data around the monitored water area is obtained in real time by using channels such as a weather station or a weather forecast, including information such as air temperature, wind speed, and rainfall. The influence of real-time water flow velocity data on water temperature distribution is analyzed, including the degree of influence of water flow velocity on water temperature propagation. For example, the diffusion of water temperature in the water area is evaluated based on the magnitude and direction of water flow velocity. The influence of external environmental temperature data on water temperature is analyzed, including the degree of influence of ambient temperature on water temperature. For example, based on the difference between external temperature and water temperature, the influence of external temperature change on water temperature is evaluated. The influence of external weather data on water temperature is analyzed, including the influence of factors such as air temperature, wind speed, and rainfall on water temperature distribution. For example, the influence of future meteorological changes on water temperature is analyzed based on weather forecast data. According to the environmental factor impact analysis data, the influence weights of each environmental factor on the water temperature are determined, for example, the influence weights of water flow velocity, external ambient temperature and external weather. According to the environmental factor weights and real-time external environmental data, the overall environmental disturbance value is calculated, that is, the comprehensive influence degree of each environmental factor on the water temperature. Each environmental factor data is multiplied by its corresponding weight, and then the results are added to obtain the overall disturbance value. For example, the influence weights of water flow velocity, external temperature and weather conditions on water temperature are 0.4, 0.3 and 0.3 respectively, then the overall environmental disturbance value can be calculated by the following formula: Overall environmental disturbance value = (0.4 × water flow velocity) + (0.3 × external temperature) + (0.3 × weather conditions). For example, the real-time disturbance compensation amount can be calculated by a linear or nonlinear method according to the size and direction of the overall environmental disturbance value. The calculated real-time disturbance compensation amount is applied to the original water temperature data to generate real-time disturbance compensation data. The purified temperature cube data is processed by the spatiotemporal correlation analysis algorithm and divided into spatiotemporal related water temperature hypersurfaces. These hypersurfaces represent the variation law of water temperature in time and space. Such as Kriging interpolation method, these data are processed to generate time-space related water temperature hypersurface. Real-time disturbance compensation data is applied to time-space related water temperature hypersurface data, and the water temperature data is corrected through mathematical models or machine learning algorithms to eliminate the impact of environmental disturbances on water temperature data, and generate environmental disturbance elimination field data. For each time point and spatial position in the purified temperature cube data, the data quality of each sensor at that point is analyzed. This can be achieved by statistically analyzing indicators such as data deviation, variance, and continuity of each sensor. A confidence value is assigned to each sensor based on the characteristics of the sensor and data quality assessment.This can be a value ranging from 0 to 1, indicating the degree of credibility of the sensor data, where 1 means completely credible and 0 means completely untrustworthy. The water temperature field is corrected in combination with the environmental disturbance elimination field data. Areas with high sensor confidence will affect the correction results more, while areas with low confidence will have less impact. According to the sensor confidence vector data, the water temperature data at each time point and spatial position is fused and corrected. In this process, the confidence of the sensor is taken into account, and the data of high-confidence sensors is given a higher weight, and the data of low-confidence sensors is given a lower weight. After the temperature field fusion correction processing, the corrected water temperature field data is obtained. These data comprehensively consider the credibility of the sensor, and through fusion correction processing, the data is made more accurate and reliable.

[0192] Preferably, step S5 comprises the following steps:

[0193] Step S51: performing three-dimensional water temperature profile reconstruction processing according to the corrected water temperature field data to generate reconstructed water temperature profile data;

[0194] Step S52: performing thermal layer stratification identification according to the reconstructed water temperature profile data to obtain water body thermal layer stratification data;

[0195] Step S53: Perform continuous dynamic monitoring of the thermal layer based on the water body thermal layer stratification data to generate dynamic water temperature thermal layer monitoring data;

[0196] Step S54: Calculate the vertical gradient of water temperature according to the dynamic water temperature thermal layer monitoring data to generate water temperature gradient data;

[0197] Step S55: evaluating the water mixing efficiency of the water temperature gradient data to obtain water mixing efficiency data;

[0198] Step S56: Based on the preset water circulation model, water mixing efficiency data is used to analyze the water circulation characteristics of the dynamic water temperature and thermal layer monitoring data to generate water circulation pattern data.

[0199] As an example of the present invention, refer to Figure 3 As shown, Figure 1 Detailed implementation steps of step S5 in the flowchart, in this example, step S5 includes:

[0200] Step S51: performing three-dimensional water temperature profile reconstruction processing according to the corrected water temperature field data to generate reconstructed water temperature profile data;

[0201] In an embodiment of the present invention, a three-dimensional spatial grid is constructed according to the corrected water temperature field data to represent the water temperature data at different positions in the water area. This grid can be a regular cubic grid or an irregular grid optimized according to the actual morphology of the water area. For the missing positions or time points in the corrected water temperature field data, interpolation processing is required to fill the missing data. Common interpolation methods include linear interpolation, spline interpolation, Kriging interpolation, etc. According to the corrected water temperature field data and the three-dimensional spatial grid, each profile is reconstructed. This includes determining the water temperature value of each position according to the water temperature data and filling it in the corresponding position in the spatial grid. The generated three-dimensional water temperature profile data is further processed, such as smoothing, noise filtering, etc., to ensure the accuracy and reliability of the data. The generated three-dimensional water temperature profile data is visualized to facilitate analysis and understanding of the distribution of water temperature in the water area. This can be achieved through three-dimensional graphics display software or a professional geographic information system (GIS).

[0202] Step S52: performing thermal layer stratification identification according to the reconstructed water temperature profile data to obtain water body thermal layer stratification data;

[0203] In an embodiment of the present invention, a sign of the existence of a thermal layer is determined. Generally, the determination index of the thermal layer can be the temperature gradient of the water temperature, the rate of change of the vertical distribution of the water temperature, etc. According to the thermal layer determination index, a suitable algorithm is selected to perform thermal layer stratification identification. Commonly used algorithms include temperature gradient method, density gradient method, potential temperature method, etc. For each water temperature profile data, the selected thermal layer identification algorithm is used for processing to determine the existence and position of the thermal layer. For example, for the temperature gradient method, it can be determined whether a thermal layer exists based on the temperature change rate of the water temperature profile, and then the position of the thermal layer is determined. According to the characteristics of the thermal layer, it is classified, for example, into a warm layer, a mixed layer, a cold layer, etc. This helps to better understand the thermal layer structure and changes of the water body.

[0204] Step S53: Perform continuous dynamic monitoring of the thermal layer based on the water body thermal layer stratification data to generate dynamic water temperature thermal layer monitoring data;

[0205] In an embodiment of the present invention, water body thermal layer stratification data is continuously acquired, and the collected water temperature data is compared and analyzed with the previously generated water body thermal layer stratification data to detect the dynamic changes of the thermal layer. This involves processing such as cleaning, correction and interpolation of the data to ensure the accuracy and reliability of the data. Using the results of data processing and analysis, the dynamic changes of the thermal layer are detected, including the rise, sinking, thickening, thinning and other conditions of the thermal layer. This can be achieved by comparing water temperature profile data at different time points. Based on the dynamic changes of the thermal layer, dynamic water temperature thermal layer monitoring data is generated. These data may include information such as the location, thickness, temperature distribution and other information of the thermal layer, as well as characteristics such as the trend and periodicity of thermal layer changes.

[0206] Step S54: Calculate the vertical gradient of water temperature according to the dynamic water temperature thermal layer monitoring data to generate water temperature gradient data;

[0207] In an embodiment of the present invention, dynamic water temperature and thermal layer monitoring data are prepared, and these data include vertical profiles of water temperature, usually including temperature data of different depths or different water layers. For each monitoring point, the vertical gradient of water temperature is calculated according to the water temperature data of different depths or water layers. The commonly used calculation method is to calculate the water temperature gradient by dividing the water temperature difference of adjacent depths or water layers by the depth difference. For example, assuming that the water temperature data collected at the monitoring points at a water depth of 0 meters and a water depth of 10 meters are 20°C and 15°C respectively, then the water temperature gradient between these two depths can be calculated by the following formula: Water temperature gradient = (15°C-20°C) / (10 meters-0 meters) = -0.5°C / m. Water temperature gradient data is generated based on the water temperature gradient calculated at each monitoring point. These data can be the water temperature gradient value of each monitoring point, or a curve graph of the water temperature gradient changing with depth.

[0208] Step S55: evaluating the water mixing efficiency of the water temperature gradient data to obtain water mixing efficiency data;

[0209] In an embodiment of the present invention, a suitable method for evaluating the mixing efficiency of a water body is selected according to the research object and the actual situation. Common evaluation methods include using water temperature gradient data to calculate the depth of the water mixing layer, the mixing rate, the mixing coefficient, etc. According to the selected evaluation method, the water temperature gradient data is processed and calculated accordingly to evaluate the mixing efficiency of the water body. This involves complex mathematical models and algorithms. For example, a commonly used method is to use water temperature gradient data to calculate the mixing rate of the water body. This can be achieved by analyzing the trend of the change of the water temperature gradient with depth, and combining the theory of fluid dynamics to calculate the distance or speed of the water mixing in unit time. Based on the evaluation results, water mixing efficiency data is generated. These data can be the mixing efficiency value of each monitoring point, or a curve graph of the water mixing efficiency changing with time or depth.

[0210] Step S56: Based on the preset water circulation model, water mixing efficiency data is used to analyze the water circulation characteristics of the dynamic water temperature and thermal layer monitoring data to generate water circulation pattern data.

[0211] In an embodiment of the present invention, first, a preset water body circulation model is prepared. This model can be a mathematical model established based on hydrological principles, fluid dynamics theory, meteorological factors, etc., which is used to describe the movement and circulation characteristics of water bodies under specific conditions. According to the water body circulation model and water body mixing efficiency data, the dynamic water temperature and thermal layer monitoring data are characteristically analyzed. This includes analyzing the flow of water bodies in time and space, as well as the propagation and change law of water temperature in the water body. For example, according to the water body mixing efficiency data, the mixing degree and mixing rate of the water body can be evaluated. Combined with the water body circulation model, the flow path, flow rate and circulation pattern of the water body can be inferred. By analyzing the dynamic water temperature and thermal layer monitoring data, the water body circulation characteristics can be determined, including the change law of water temperature and the periodicity of water body circulation. According to the results of the water body circulation characteristic analysis, water body circulation pattern data are generated. These data may include water body circulation path diagrams, circulation period diagrams, water temperature change diagrams, etc., which are used to describe the movement and circulation laws of water bodies.

[0212] The present invention also provides a water temperature information monitoring system, which executes the water temperature information monitoring method as described above, and the water temperature information monitoring system comprises:

[0213] The intelligent device deployment module is used to analyze the water environment function of the target monitoring water area and obtain water environment characteristic data; based on the water environment characteristic data, the intelligent water temperature monitoring device is used to deploy the best monitoring device for the target monitoring water area and obtain a water temperature monitoring network;

[0214] The real-time water level estimation module is used to perform periodic water depth estimation processing based on the water temperature monitoring network to generate spatial water depth interpolation fusion data; perform monitoring device water level correction processing based on the spatial water depth interpolation fusion data to generate real-time water level correction data;

[0215] The adaptive sampling module is used to analyze the monitored water layer according to the real-time water level correction data to generate the target monitored water layer data; perform water temperature layer sampling operations based on the target monitored water layer data to generate initial water temperature layer sampling data; adjust the adaptive sampling strategy according to the initial water temperature layer sampling data to obtain adaptive water temperature sampling data;

[0216] The water temperature compensation correction module is used to perform temperature tensor standardization processing on the adaptive water temperature sampling data to generate standard water temperature sampling data; perform outlier masking based on the standard water temperature sampling data to obtain purified temperature cube data; perform environmental compensation correction processing based on the purified temperature cube data to generate corrected water temperature field data;

[0217] The water temperature circulation analysis module is used to reconstruct the three-dimensional water temperature profile based on the corrected water temperature field data to generate reconstructed water temperature profile data; to dynamically monitor the thermal layer based on the reconstructed water temperature profile data to generate dynamic water temperature thermal layer monitoring data; to analyze the water body circulation characteristics of the dynamic water temperature thermal layer monitoring data to generate water body circulation pattern data.

[0218] The beneficial effect of the present application is that the application of the intelligent water temperature monitoring device optimizes the layout of the monitoring network, improves the coverage and density, and can more accurately reflect the actual situation of the water area. The intelligent monitoring device can realize real-time monitoring and ensure the continuity and real-time nature of the data. The water temperature data obtained by the intelligent water temperature monitoring device can be used for periodic water depth estimation processing, and then the water level measured by the monitoring device can be corrected, the error caused by the change of water depth can be eliminated, and more accurate real-time water level correction data can be generated. In this way, the water level data measured by the monitoring device is more reliable, which helps to accurately assess the overall environmental conditions of the water area. By standardizing the water temperature data and removing the outlier mask, the comparability and accuracy of the data can be improved. Traditional water temperature monitoring methods are easily affected by environmental factors, resulting in inaccurate measurement results, while the data obtained by the intelligent monitoring device can obtain more reliable results through methods such as standardization and outlier removal. Using the corrected water temperature field data and three-dimensional space reconstruction technology, the spatial distribution of the temperature inside the water area can be deeply understood, the temperature changes inside the water area can be tracked, and the dynamic change characteristics of the thermal layer can be identified and analyzed. This helps to gain a deep understanding of the temperature stratification and circulation characteristics of the water body, and provides a scientific basis for water area management and protection.

[0219] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0220] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A water temperature information monitoring method, characterized in that: Applied to an intelligent water temperature monitoring device, the intelligent water temperature monitoring device includes a water gauge main structure, a temperature sensor, a pressure sensor, a wireless communication module and a microprocessor, the temperature sensor, the pressure sensor, the wireless communication module and the microprocessor are electrically connected, and the water temperature information monitoring method includes the following steps: Step S1: Performing water environment function analysis on the target monitoring water area to obtain water environment characteristic data; deploying the best monitoring device for the target monitoring water area using the intelligent water temperature monitoring device based on the water environment characteristic data to obtain a water temperature monitoring network; Step S2: Perform periodic water depth estimation processing according to the water temperature monitoring network to generate spatial water depth interpolation fusion data; perform monitoring device water level correction processing according to the spatial water depth interpolation fusion data to generate real-time water level correction data; Step S3: Perform monitoring water layer analysis based on real-time water level correction data to generate target monitoring water layer data; perform water temperature layer sampling based on the target monitoring water layer data to generate initial water temperature layer sampling data; perform adaptive sampling strategy adjustment based on the initial water temperature layer sampling data to obtain adaptive water temperature sampling data; wherein, step S3 is specifically as follows: Step S31: Perform monitoring water layer analysis based on real-time water level correction data to generate target monitoring water layer data; Step S32: Processing the temperature sampling instruction according to the target monitored water layer data to generate temperature sampling instruction data; Step S33: transmitting the temperature sampling instruction data to the matching intelligent water temperature monitoring device, using a microprocessor to parse the temperature sampling instruction data, and controlling the temperature sensor of the monitoring water layer to perform water temperature layer sampling operations to generate initial water temperature layer sampling data; Step S34: using a microprocessor to perform data preprocessing on the initial water temperature level sampling data to generate cleaning initial water temperature sampling data; Step S35: Performing adaptive water temperature sampling strategy processing according to the initial water temperature sampling data of cleaning to generate an adaptive water temperature sampling strategy; wherein step S35 is specifically as follows: Step S351: using a preset time window to perform sampling data division processing on the initial water temperature sampling data of the cleaning, and generating time series window water temperature sampling data; Step S352: Process the temperature variation according to the water temperature sampling data in the time series window to generate temperature difference data; Step S353: calculating the water temperature change rate of the temperature difference data through a preset time window to obtain water temperature change rate data; Step S354: Processing the water temperature fluctuation degree according to the water temperature change rate data to generate water temperature fluctuation degree data; Step S355: performing temperature change trend analysis based on the water temperature change rate data to generate temperature change trend data; Step S356: performing time series temperature change pattern analysis on the temperature change trend data to generate water temperature change pattern data; Step S356: evaluating the sampling adjustment trigger condition based on the water temperature fluctuation degree data and the temperature change trend data, and generating adjustment condition trigger result data; Step S357: when the adjustment condition trigger result data is failure, the current water temperature sampling strategy is maintained; when the adjustment condition trigger result data is success, step S358 is executed; Step S358: determining the sampling frequency adjustment direction according to the water temperature conversion mode data, and generating sampling frequency adjustment direction data; performing comprehensive sampling adjustment weight calculation according to the water temperature fluctuation degree data and the water temperature change rate data, and generating comprehensive sampling adjustment weight data; Step S359: Calculate the sampling adjustment amplitude based on the comprehensive sampling adjustment weight data and the sampling frequency adjustment direction data, and optimize the sampling adjustment amplitude through a preset adjustment amplitude limiting strategy, thereby obtaining an adaptive water temperature sampling strategy; Step S36: adjusting the sampling strategy based on the adaptive water temperature sampling strategy, and performing stratified water temperature sampling processing to obtain adaptive water temperature sampling data; Step S4: performing temperature tensor normalization processing on the adaptive water temperature sampling data to generate standard water temperature sampling data; performing outlier masking based on the standard water temperature sampling data to obtain purified temperature cube data; performing environmental compensation correction processing based on the purified temperature cube data to generate corrected water temperature field data; Step S5: Reconstruct the three-dimensional water temperature profile based on the corrected water temperature field data to generate reconstructed water temperature profile data; dynamically monitor the thermal layer based on the reconstructed water temperature profile data to generate dynamic water temperature thermal layer monitoring data; perform water body circulation characteristic analysis on the dynamic water temperature thermal layer monitoring data to generate water body circulation pattern data.

2. The water temperature information monitoring method according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: collecting water area remote sensing images of the target monitoring water area to generate remote sensing impact data of the target water area; Step S12: Performing water environment function analysis based on the remote sensing impact data of the target water area to obtain water environment characteristic data, wherein the water environment characteristic data includes a deep water measurement area, a shallow beach measurement area, and a waterweed measurement area; Step S13: performing optimal monitoring device deployment strategy processing based on the water environment characteristic data to obtain the optimal monitoring device deployment strategy; Step S14: deploy the intelligent water temperature monitoring device in the target monitoring water area through the optimal monitoring device deployment strategy, so as to build a water temperature monitoring network.

3. The water temperature information monitoring method according to claim 2, characterized in that: Step S14 includes the following steps: Step S141: constructing water area environment characteristic indexes according to the water area environment characteristic data to obtain environment characteristic index system data, wherein the environment characteristic index system data includes a water depth index, a water area bottom hardness index, and aquatic plant growth density index; Step S142: Performing water area level environmental sensitivity assessment processing based on the environmental characteristic index system data to obtain water area level environmental characteristic assessment data; Step S143: quantifying the performance of the intelligent water temperature monitoring device through the water environment characteristic data to generate quantified performance data of the monitoring device; Step S144: using the water area level environmental characteristic assessment data to perform monitoring demand weighting processing on the monitoring device performance quantification data to obtain water area monitoring demand weight data; Step S145: Optimize the monitoring node density according to the water area monitoring demand weight data to obtain monitoring node density data; Step S146: performing deployment connectivity analysis on the water environment characteristic data by monitoring node density data to obtain monitoring node topology data; Step S147: Optimize the minimum number of nodes according to the monitoring node topology data to generate the best monitoring device deployment strategy.

4. The water temperature information monitoring method according to claim 1, characterized in that: The pressure sensor is installed at the bottom of the water gauge main structure, and step S2 includes the following steps: Step S21: using a pressure sensor to collect water body pressure factors based on a preset pressure collection cycle to generate water body static pressure collection data; Step S22: using a microprocessor to perform reverse fluid water depth estimation on the water body pressure factor collection data to generate water depth estimation data; Step S23: using the water temperature monitoring network to transmit the water depth estimation data to the edge computing terminal node through the wireless communication module, and performing spatial interpolation fusion processing to obtain spatial water depth interpolation fusion data; Step S24: performing water depth distribution analysis based on the spatial water depth interpolation fusion data to obtain water depth distribution map data; Step S25: estimating the water level gradient according to the water depth distribution map data to obtain monitoring water level estimation data; Step S26: selecting multiple water level reference points for the monitored water level estimation data to generate reference point water level estimation data; Step S27: performing water level deviation analysis on the monitoring water level estimation data by using the reference point water level estimation data to generate water level deviation analysis data; Step S28: Performing monitoring device water level correction processing on the water level deviation analysis data through a preset linear regression model to generate real-time water level correction data.

5. The water temperature information monitoring method according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: using the intelligent water temperature monitoring device to obtain position information and obtain monitoring position data; Step S42: Binding the monitoring position data with the adaptive water temperature sampling data, and transmitting them to the edge computing terminal node to generate position-water temperature sampling data; Step S43: performing temperature tensor normalization processing on the orientation-water temperature sampling data to generate standard water temperature sampling data; constructing a stratified water temperature matrix based on the standard water temperature sampling data to generate original stratified water temperature matrix data; Step S44: performing outlier mask identification on the original stratified water temperature matrix data through a preset confidence temperature interval to generate outlier mask tensor data; Step S45: performing data elimination processing on the abnormal mask tensor data through the original layered water temperature matrix data to obtain purified temperature cube data; Step S46: Perform environmental compensation correction processing according to the purification temperature cube data to generate corrected water temperature field data.

6. The water temperature information monitoring method according to claim 5, characterized in that: Step S46 includes the following steps: Step S461: acquiring real-time external environment data, wherein the real-time external environment data includes water flow velocity data, external environment temperature data, and external weather data; Step S462: Perform environmental factor impact analysis based on real-time external environmental data to generate environmental factor impact assessment data; Step S463: performing overall environmental disturbance calculation according to the environmental factor impact analysis data to generate an overall environmental disturbance value; Step S464: performing real-time disturbance compensation calculation on the overall environmental disturbance value through the real-time external environmental data to obtain real-time disturbance compensation data; Step S465: performing spatiotemporal water temperature related hypersurface segmentation on the purified temperature cube data to obtain spatiotemporal water temperature related hypersurface data; Step S466: using the real-time disturbance compensation data to perform environmental disturbance elimination processing on the spatiotemporal related water temperature hypersurface data to generate environmental disturbance elimination field data; Step S467: performing sensor confidence vector processing according to the purified temperature cube data to generate sensor confidence vector data; Step S468: Perform temperature field fusion correction processing on the environmental disturbance elimination field data using the sensor confidence vector data to obtain corrected water temperature field data.

7. The water temperature information monitoring method according to claim 1, characterized in that: Step S5 includes the following steps: Step S51: performing three-dimensional water temperature profile reconstruction processing according to the corrected water temperature field data to generate reconstructed water temperature profile data; Step S52: performing thermal layer stratification identification according to the reconstructed water temperature profile data to obtain water body thermal layer stratification data; Step S53: Perform continuous dynamic monitoring of the thermal layer based on the water body thermal layer stratification data to generate dynamic water temperature thermal layer monitoring data; Step S54: Calculate the vertical gradient of water temperature according to the dynamic water temperature thermal layer monitoring data to generate water temperature gradient data; Step S55: evaluating the water mixing efficiency of the water temperature gradient data to obtain water mixing efficiency data; Step S56: Based on the preset water circulation model, water mixing efficiency data is used to analyze the water circulation characteristics of the dynamic water temperature and thermal layer monitoring data to generate water circulation pattern data.

8. A water temperature information monitoring system, characterized in that: Used to execute the water temperature information monitoring method according to claim 1, the water temperature information monitoring system comprises: The intelligent device deployment module is used to analyze the water environment function of the target monitoring water area and obtain water environment characteristic data; based on the water environment characteristic data, the intelligent water temperature monitoring device is used to deploy the best monitoring device for the target monitoring water area and obtain a water temperature monitoring network; The real-time water level estimation module is used to perform periodic water depth estimation processing based on the water temperature monitoring network to generate spatial water depth interpolation fusion data; perform monitoring device water level correction processing based on the spatial water depth interpolation fusion data to generate real-time water level correction data; The adaptive sampling module is used to analyze the monitored water layer according to the real-time water level correction data to generate the target monitored water layer data; perform water temperature layer sampling operations based on the target monitored water layer data to generate initial water temperature layer sampling data; adjust the adaptive sampling strategy according to the initial water temperature layer sampling data to obtain adaptive water temperature sampling data; The water temperature compensation correction module is used to perform temperature tensor standardization processing on the adaptive water temperature sampling data to generate standard water temperature sampling data; perform outlier masking based on the standard water temperature sampling data to obtain purified temperature cube data; perform environmental compensation correction processing based on the purified temperature cube data to generate corrected water temperature field data; The water temperature circulation analysis module is used to reconstruct the three-dimensional water temperature profile based on the corrected water temperature field data to generate reconstructed water temperature profile data; to dynamically monitor the thermal layer based on the reconstructed water temperature profile data to generate dynamic water temperature thermal layer monitoring data; to analyze the water body circulation characteristics of the dynamic water temperature thermal layer monitoring data to generate water body circulation pattern data.

Images