Intelligent buoy dynamic early warning method and platform for environmental monitoring

Abstract

The present application provides a smart buoy dynamic early warning method and platform for environmental monitoring, which relates to the field of environmental monitoring and early warning technology. The method generates a multi-source prediction data distribution by reading the real-time position coordinates of the buoy and multi-source monitoring data for interpolation prediction; records the multi-source prediction data distribution under P consecutive monitoring points to construct a multi-source prediction data distribution sequence, performs water quality pollution analysis of the target water area in the future time zone, and generates multiple water quality pollution probabilities; obtains the maximum pollution probability and the mean pollution probability based on the multiple water quality pollution probabilities; if the maximum pollution probability is greater than the first probability threshold and / or the mean pollution probability is greater than the second probability threshold, a water quality pollution early warning is issued for the target water area. The present application solves the technical problem in the prior art that the buoy is easily affected by environmental factors and the position fluctuates, making it difficult to accurately obtain monitoring data, thereby affecting the accuracy of the early warning, thereby improving the accuracy of environmental monitoring and water quality early warning.

Description

Technical Field

[0001] The present application relates to the field of environmental monitoring and early warning technology, and specifically to an intelligent buoy dynamic early warning method and platform for environmental monitoring. Background Art

[0002] Buoys, as important tools for environmental monitoring, are widely used in water quality monitoring, meteorological data collection, and ecological and environmental assessments. Traditional buoy-based environmental monitoring and early warning methods primarily rely on sensors mounted on fixed buoys to collect real-time water quality parameters and issue warnings based on preset thresholds.

[0003] However, due to the complex water environment, buoys are easily disturbed by environmental factors such as water flow and wind during actual operation. Their positions may fluctuate, making it difficult to maintain them at the predetermined position for a long time. This positional deviation will reduce the spatial consistency of the collected data, thereby affecting the accuracy and completeness of environmental monitoring data. In addition, most methods rely heavily on a single monitoring data set and fail to fully integrate multi-source data for comprehensive analysis. This limitation leads to insufficient spatial distribution accuracy of monitoring data. In complex water environments, early warning results may be distorted or delayed, reducing the reliability of water pollution monitoring and early warning. Summary of the Invention

[0004] This application provides a dynamic early warning method and platform for intelligent buoys for environmental monitoring, which solves the technical problem in the existing technology that the buoys are easily affected by environmental factors and have position fluctuations, making it difficult to accurately obtain monitoring data at the predetermined position, thereby affecting the accuracy of the early warning, and achieves the technical effect of improving the accuracy of environmental monitoring and water quality early warning.

[0005] In view of the above problems, on the one hand, the present application provides an intelligent buoy dynamic early warning method for environmental monitoring, which includes: fixed-point reading of the real-time position coordinates and multi-source monitoring data of several buoys in the target water area, performing interpolation prediction based on the real-time position coordinates and multi-source monitoring data, obtaining multi-source prediction data of the calibrated position coordinates of several buoys, and generating a multi-source prediction data distribution; recording the multi-source prediction data distribution under P consecutive monitoring points to construct a multi-source prediction data distribution sequence, performing water quality pollution analysis of the target water area in the future time zone based on the multi-source prediction data distribution sequence, and generating multiple water quality pollution probabilities; performing maximum probability extraction and probability mean calculation based on the multiple water quality pollution probabilities, respectively, to obtain the maximum pollution probability and the pollution probability mean; if the maximum pollution probability is greater than the first probability threshold and / or the pollution probability mean is greater than the second probability threshold, a water quality pollution early warning is issued for the target water area.

[0006] On the other hand, the present application also provides an intelligent buoy dynamic warning platform for environmental monitoring, which includes: an interpolation prediction module, which is used to read the real-time position coordinates and multi-source monitoring data of several buoys in the target water area at a fixed point, perform interpolation prediction based on the real-time position coordinates and multi-source monitoring data, obtain multi-source prediction data of the calibrated position coordinates of several buoys, and generate a multi-source prediction data distribution; a water quality pollution analysis module, which is used to record the multi-source prediction data distribution under P consecutive monitoring points to construct a multi-source prediction data distribution sequence, and perform water quality pollution analysis of the target water area in the future time zone based on the multi-source prediction data distribution sequence to generate multiple water quality pollution probabilities; a probability extraction and calculation module, which is used to perform maximum probability extraction and probability mean calculation based on the multiple water quality pollution probabilities, respectively, to obtain the maximum pollution probability and the pollution probability mean; a pollution warning module, which is used to issue a water quality pollution warning for the target water area if the maximum pollution probability is greater than the first probability threshold and / or the pollution probability mean is greater than the second probability threshold.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] By accurately reading the real-time position coordinates of several buoys within the target waters and multi-source monitoring data, the actual position of the buoys can be accurately determined despite fluctuations due to factors such as waves, wind speed, and current velocity. Multi-source monitoring data provides more comprehensive environmental information and serves as the raw data for subsequent analysis, avoiding data collection errors caused by buoy position fluctuations and improving data timeliness and accuracy. By interpolating and predicting the buoy's calibrated position coordinates based on the real-time position coordinates and multi-source monitoring data, multi-source prediction data can be obtained. Uncollected data can be extrapolated based on the buoy's position fluctuations to estimate the buoy's intended calibrated position data, ensuring spatial consistency. By recording the distribution of multi-source prediction data at P consecutive monitoring points and constructing a multi-source prediction data distribution sequence, it is possible to better capture environmental trends, analyze the temporal characteristics of water quality changes, and improve the accuracy of pollution warnings. By analyzing the multi-source prediction data distribution sequence, future water pollution risks can be predicted and multiple water pollution probabilities generated. This provides multi-dimensional information for decision-making, helping to analyze the likelihood of water quality changes and prepare for emergency responses in advance. Based on multiple water pollution probabilities, the system extracts the maximum probability and calculates the mean probability, quantifying water pollution from multiple dimensions and reducing the errors caused by single probability judgments, making the warning results more reliable. When the pollution probability exceeds the set threshold, a water pollution warning is issued. By setting two probability thresholds, a water pollution warning is issued when the pollution probability exceeds the set threshold. This ensures that an alarm is issued promptly when the water pollution risk reaches a certain level, providing timely information support for environmental protection and governance.

[0009] In summary, this application effectively solves the problem of insufficient data accuracy caused by buoy position fluctuations in buoy monitoring, improves the accuracy of environmental monitoring and water pollution warning, and provides more accurate decision-making support for water pollution prevention and control and emergency response.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A flow chart of the intelligent buoy dynamic warning method for environmental monitoring provided in an embodiment of the present application.

[0012] Figure 2 A schematic diagram of a process for interpolating and predicting multiple unlabeled calibrated position coordinates based on real-time position coordinates and multi-source monitoring data in the intelligent buoy dynamic warning method for environmental monitoring provided in an embodiment of the present application.

[0013] Figure 3 A schematic diagram of the structure of the intelligent buoy dynamic warning platform for environmental monitoring provided in an embodiment of the present application.

[0014] Description of the accompanying symbols: interpolation prediction module 10, water quality pollution analysis module 20, probability extraction and calculation module 30, pollution warning module 40. DETAILED DESCRIPTION

[0015] The embodiments of the present application provide a dynamic early warning method and platform for intelligent buoys for environmental monitoring, thereby solving the technical problem in the prior art that the buoys are easily affected by environmental factors and experience position fluctuations, making it difficult to accurately obtain monitoring data at predetermined positions, thereby affecting the accuracy of early warnings. This achieves the technical effect of improving the accuracy of environmental monitoring and water quality early warnings.

[0016] Example 1, as Figure 1 As shown, the embodiment of the present application provides a smart buoy dynamic early warning method for environmental monitoring, the method comprising:

[0017] Step S1: Read the real-time position coordinates and multi-source monitoring data of several buoys in the target waters at a fixed point, perform interpolation prediction based on the real-time position coordinates and multi-source monitoring data, obtain multi-source prediction data of the calibrated position coordinates of several buoys, and generate a multi-source prediction data distribution.

[0018] Specifically, the buoy is equipped with a variety of sensors, such as water temperature sensors, pH sensors, dissolved oxygen sensors, salinity sensors, turbidity sensors, etc., which are used to monitor water environment parameters in real time. The real-time position coordinates of several buoys in the target water area are read at a fixed point through a positioning system (such as GPS), and multi-source monitoring data are obtained by using various sensors on the buoy. These multi-source monitoring data are data obtained by multiple different types of sensors on the buoy. Using interpolation prediction methods (such as linear interpolation or spline interpolation), data prediction is performed for unobserved positions based on real-time position coordinates and multi-source monitoring data. Through interpolation prediction, multi-source prediction data of multiple buoys can be obtained, and these multi-source prediction data are integrated according to spatial distribution to generate a multi-source prediction data distribution. The multi-source prediction data distribution includes multi-source prediction data at different locations at the same time, reflecting the spatial distribution of water environment data.

[0019] By dynamically reading the buoy position and monitoring data, and using interpolation prediction methods to correct data errors caused by buoy position fluctuations, the accuracy of the data can be improved, ensuring that the generated environmental data distribution is more reliable, and providing basic data for subsequent pollution analysis.

[0020] Step S2: Record the distribution of multi-source prediction data at P consecutive monitoring points to construct a multi-source prediction data distribution sequence, perform water quality pollution analysis on the target water area in the future time zone based on the multi-source prediction data distribution sequence, and generate multiple water quality pollution probabilities.

[0021] Specifically, record the multi-source prediction data distribution of P monitoring points. These monitoring points are specific time points for data collection in the target waters. The time intervals between two adjacent monitoring points are the same. For example, starting from the time point when monitoring begins, a monitoring point is set every two hours, and a total of P monitoring points are set, wherein P is a positive integer representing the number of monitoring points, which can be adjusted according to specific monitoring needs. Arrange the multi-source prediction data distribution of each monitoring point according to the time sequence of P monitoring points to generate a multi-source prediction data distribution sequence. Then, utilize a model (such as a regression analysis model based on statistical principles or a model based on machine learning) to perform water pollution analysis of the target waters in the future time zone according to the multi-source prediction data distribution sequence, and generate a water pollution probability for each monitoring indicator to obtain multiple water pollution probabilities. These water pollution probabilities are the probability values ​​of the water pollution risks of each position in the target waters at a certain moment in the future that are predicted.

[0022] By constructing a multi-source forecast data distribution sequence, we can understand the water quality of target water bodies from a dynamic and holistic perspective, overcoming the limitations of single-point-in-time and single-location data. Water pollution analysis based on this sequence can more accurately predict water pollution conditions in future time zones, providing forward-looking data for water quality management and pollution warnings.

[0023] Step S3: performing maximum probability extraction and probability mean calculation according to the multiple water pollution probabilities to obtain the maximum pollution probability and the pollution probability mean.

[0024] Specifically, the multiple water pollution probabilities generated in step S2 are obtained. A comparison algorithm is used to find the maximum probability, which is recorded as the maximum pollution probability. The mean of all probabilities is calculated by adding all the water pollution probabilities and dividing them by the number of water pollution probabilities to obtain the mean pollution probability. By extracting the maximum probability and calculating the mean, pollution warnings are provided with two different dimensions of information: the maximum pollution risk under the worst-case scenario and the overall pollution trend, allowing for a more comprehensive assessment of the potential risk of water pollution.

[0025] Step S4: If the maximum pollution probability is greater than the first probability threshold and / or the mean pollution probability is greater than the second probability threshold, a water pollution warning is issued for the target water area.

[0026] Specifically, the first probability threshold and the second probability threshold are pre-set pollution warning thresholds used to determine whether an early warning is needed. The maximum pollution probability is compared with the first probability threshold, and the mean pollution probability is compared with the second probability threshold. If the maximum pollution probability is greater than the first probability threshold or the mean pollution probability is greater than the second probability threshold, a water pollution early warning for the target waters is triggered. By setting two probability thresholds for double judgment, the accuracy and reliability of water pollution early warnings are improved. It takes into account both the possibility of the most serious pollution situation (maximum pollution probability) and the overall pollution situation (mean pollution probability), and can more reasonably judge whether it is necessary to issue an early warning for the target waters, avoiding the misjudgment or missed judgment that may be caused by a single threshold judgment, and improving the accuracy and rationality of water pollution early warnings.

[0027] Furthermore, step S1 includes:

[0028] Step S11: Obtain several calibrated position coordinates of several buoys in the target waters, and calculate the relative distances between the several calibrated position coordinates and the nearest real-time position coordinates respectively. If the relative distance is less than a predetermined distance threshold, the multi-source monitoring data corresponding to the real-time position coordinates is set as the multi-source prediction data corresponding to the calibrated position coordinates.

[0029] Step S12: Filter and obtain multiple unlabeled calibrated position coordinates, and perform interpolation prediction on the multiple unlabeled calibrated position coordinates according to the real-time position coordinates and multi-source monitoring data to obtain multiple multi-source prediction data of the multiple unlabeled calibrated position coordinates.

[0030] Step S13: Arrange the plurality of multi-source prediction data of the plurality of calibrated position coordinates according to the positions to generate the multi-source prediction data distribution.

[0031] Specifically, the calibrated position coordinates of multiple buoys in the target waters are obtained. These positions are where the buoys should be in the absence of interference. The relative distance between the actual position (real-time position coordinates) and the calibrated position coordinates of each buoy is calculated, which can be calculated using the Euclidean distance formula. Comparing the relative distance with the predetermined distance threshold, if the calculated relative distance is less than the predetermined distance threshold, it means that the actual position of the buoy is close to the calibrated position, and the multi-source monitoring data corresponding to the real-time position coordinates can be directly regarded as the multi-source prediction data of the buoy at the calibrated position. Among them, the predetermined distance threshold is a pre-set value used to determine whether the calibrated position coordinates are close enough to the real-time position coordinates.

[0032] All buoy locations whose relative distances are less than a predetermined distance threshold are marked, and the coordinates of all unmarked buoys in the target waters that have experienced significant position changes are identified. For these unmarked buoy coordinates, interpolation predictions are performed based on the real-time position coordinates of nearby buoys and existing multi-source monitoring data. This interpolation method allows the water quality data for these unmarked locations to be predicted. This interpolation prediction method fills in the missing data for these unmarked locations, ensuring that water quality monitoring data for all buoys in the target waters is effectively supplemented, providing complete monitoring data for subsequent pollution analysis.

[0033] The calibrated position coordinates of multiple buoys are arranged with their corresponding multi-source prediction data. This involves spatially sorting the calibrated position coordinates (e.g., longitude and latitude) of each buoy within the water area to generate a multi-source prediction data distribution for the current moment within the target water area. For example, each buoy position and its monitoring data within the water area can form a dataset of coordinate points, forming a complete spatial data map showing the spatial distribution of water quality changes. This spatial arrangement forms a complete multi-source prediction data distribution, which accurately reflects the environmental monitoring status of each point within the target water area, ensuring the spatial accuracy and timeliness of the data and providing accurate spatial data support for subsequent water pollution analysis and early warning.

[0034] Further, such as Figure 2 As shown, step S12 includes:

[0035] Step S121: Randomly select a first unmarked calibrated position coordinate, use the first unmarked calibrated position coordinate as a reference, search within a predetermined distance range, obtain multiple first adjacent real-time position coordinates, and analyze to obtain multiple position association information, wherein the position association information includes an associated distance and an associated direction.

[0036] Step S122: Obtain multi-source monitoring indicators, and perform distance and azimuth correlation analysis on the multi-source monitoring indicators to establish a multi-source position mapping association between distance, azimuth and monitoring indicators, wherein the multi-source monitoring indicators include at least dissolved oxygen, pH value, turbidity, conductivity, temperature, heavy metal concentration, chemical oxygen demand and ammonia nitrogen.

[0037] Step S123: Based on the multi-source position mapping association, a plurality of association coefficient sets are obtained according to the matching of the plurality of position association information, and a plurality of association weight sets are determined by analysis.

[0038] Step S124: Acquire a plurality of first multi-source monitoring data of a plurality of first adjacent real-time position coordinates, perform weighted interpolation prediction on the plurality of first multi-source monitoring data according to the plurality of association weight sets, and output first multi-source prediction data.

[0039] Specifically, the specific process of interpolating and predicting multiple unlabeled calibrated position coordinates based on real-time position coordinates and multi-source monitoring data includes the following: First, randomly select one of all unlabeled calibrated position coordinates as the first unlabeled calibrated position coordinate. Then, using this coordinate as a reference, a coordinate calculation and search algorithm is used to search for buoys within a predetermined distance range to obtain the real-time position coordinates of these buoys, i.e., multiple first adjacent real-time position coordinates. The predetermined distance range is a pre-set distance range of a circular or square area centered at a certain point. For example, it can be set as a circular area with a radius of 100 meters centered at a certain coordinate. After determining the multiple first adjacent real-time position coordinates, the position association information of the multiple first adjacent real-time position coordinates and the first unlabeled calibrated position coordinate is analyzed. The position association information describes the relationship between the two positions, including the associated distance and associated bearing. The associated distance can be calculated using a coordinate calculation tool to calculate the straight-line distance between the two positions, and the associated bearing can be determined by azimuth calculation. By determining the adjacent real-time position coordinates of the first unmarked calibrated position coordinates and their position association information, the positional relationship of the relevant monitoring points around the target position is clarified, which helps to more accurately perform position-based monitoring indicator analysis and interpolation prediction.

[0040] Obtain multi-source monitoring indicators of the buoy. These multi-source monitoring indicators are different indicators collected by various sensors on the buoy to reflect the environmental conditions of the target waters, including at least dissolved oxygen, pH value, turbidity, conductivity, temperature, heavy metal concentration, chemical oxygen demand, and ammonia nitrogen. For each monitoring indicator, perform correlation analysis based on the aforementioned position correlation information (distance and orientation). For example, analyze the variation pattern of dissolved oxygen content at different distances and orientations, establish the relationship between distance, orientation, and dissolved oxygen content, and so on to establish a multi-source position mapping association between the distance, orientation, and monitoring indicators of all monitoring indicators.

[0041] Based on the established multi-source location mapping association, matching is performed according to multiple location association information, and the location association information corresponding to each first adjacent real-time location coordinate is substituted into the corresponding multi-source location mapping association to obtain the correlation coefficients corresponding to multiple monitoring indicators of each first adjacent real-time location coordinate. The correlation coefficients of multiple monitoring indicators corresponding to the same first adjacent real-time location coordinate are integrated to obtain multiple association weight sets.

[0042] Obtain multi-source monitoring data corresponding to multiple first adjacent real-time location coordinates, i.e., multiple first multi-source monitoring data, and the actual monitoring value of each monitoring indicator monitored by each first adjacent real-time location coordinate in the first multi-source monitoring data. Then, based on the determined multiple association weight sets, perform weighted interpolation prediction on the first multi-source monitoring data and output first multi-source prediction data. Formaldehyde interpolation can be calculated using the following formula: Where D is the first multi-source prediction data, ω i is position P i The association weight corresponding to the i-th monitoring indicator, D ( P i) is the i-th monitoring indicator at position P i The actual monitoring value.

[0043] The system randomly selects another unmarked calibrated location from all the unmarked calibrated locations and repeats the interpolation prediction steps to obtain the multi-source prediction data corresponding to that unmarked calibrated location. The coordinate extraction and interpolation prediction steps are repeated continuously to obtain multiple multi-source prediction data for multiple unmarked calibrated locations. Through weighted interpolation prediction, the target water area can be more accurately predicted based on the data from adjacent buoys, ensuring the accuracy and credibility of the data prediction, effectively improving the precision and reliability of the buoy environmental monitoring system, and providing accurate and reliable data for subsequent pollution warnings.

[0044] Furthermore, step S122 includes:

[0045] Step S122-1: randomly select a first monitoring indicator from the multi-source monitoring indicators, search the water quality pollution monitoring log of the target water area according to the first monitoring indicator, and obtain a sample initial monitoring data set, a sample relative distance set, a sample relative orientation set, and a sample associated monitoring data set.

[0046] Step S122 - 2 : Based on the sample initial monitoring data set and the sample associated monitoring data set, correlation analysis is performed on the sample initial monitoring data and the sample associated monitoring data respectively to obtain a sample correlation coefficient set.

[0047] Step S122 - 3 : constructing a first position mapping association according to the sample relative distance set, the sample relative orientation set and the sample correlation coefficient set, and adding the first position mapping association to the multi-source position mapping association.

[0048] Specifically, one of the multi-source monitoring indicators is randomly selected as the first monitoring indicator. Then, based on the first monitoring indicator, a database query tool or data retrieval algorithm is used to search the water quality pollution monitoring log of the target water area, and all monitoring data related to the indicator are queried as sample data, including a sample initial monitoring data set, a sample relative distance set, a sample relative orientation set, and a sample associated monitoring data set. Among them, the sample initial monitoring data set refers to the monitoring value of the first monitoring indicator directly collected by the sensor on the buoy during the historical monitoring process; the sample relative distance set is the distance between multiple adjacent real-time position coordinates and the initial measurement point obtained by searching within a predetermined distance range; the sample relative orientation set is the orientation of multiple adjacent real-time position coordinates and the initial measurement point obtained by searching within a predetermined distance range, and there is a one-to-one correspondence between the sample relative distance set and the sample relative orientation set; the sample associated monitoring data set is the monitoring value of the first monitoring indicator corresponding to multiple adjacent real-time position coordinates.

[0049] The sample initial monitoring data set and the sample associated monitoring data set are analyzed using a correlation analysis method to obtain the correlation coefficient between each sample associated monitoring data and the sample initial monitoring data, thereby forming a sample correlation coefficient set. Correlation analysis can use correlation coefficient calculation methods in statistics, such as the Pearson correlation coefficient method. The sample correlation coefficient set quantifies the degree of correlation between the sample initial monitoring data and the sample associated monitoring data, helping to more accurately understand the relationship between different monitoring data. It provides an important data basis for the subsequent construction of location mapping associations and can more scientifically integrate the relationship between location information and monitoring data.

[0050] Obtain a set of sample relative distances, a set of sample relative orientations, and a set of sample correlation coefficients. Then, construct a first location mapping association based on this data. Relative distances, relative orientations, and correlation coefficients can be linked by establishing a functional relationship or in the form of a data table. For example, using relative distances and relative orientations as independent variables and the correlation coefficient as the dependent variable, a functional relationship can be constructed. This functional relationship is the first location mapping association, which is then added to the multi-source location mapping association.

[0051] For other multi-source monitoring indicators, the same method is used to construct corresponding location mapping associations, thereby obtaining a complete multi-source location mapping association. By constructing a multi-source location mapping association, the association between different monitoring indicators under different location relationships can be more comprehensively reflected. This provides a more detailed and accurate basis for subsequent data matching and interpolation prediction based on location association information, helping to improve the accuracy of predictions of the target water environment.

[0052] Furthermore, step S2 includes:

[0053] Step S21: randomly selecting a first prediction data distribution sequence of a first monitoring indicator from the multi-source prediction data distribution sequence, and matching a first analysis plug-in in a water pollution analysis channel according to the first monitoring indicator.

[0054] Step S22: Performing water pollution analysis on the first predicted data distribution sequence in a future time zone through the first analysis plug-in, outputting a first water pollution probability, and adding it to the multiple water pollution probabilities.

[0055] Specifically, a monitoring indicator is randomly selected from the multi-source predicted data distribution sequence as the first monitoring indicator. Then, data related to the first monitoring indicator is extracted from the multi-source predicted data distribution sequence to form a first predicted data distribution sequence. Next, based on the first monitoring indicator, a matching operation is performed within the water pollution analysis channel to find a first analysis plug-in suitable for analyzing the first monitoring indicator. The water pollution analysis channel is a machine learning model used for water pollution analysis and contains multiple analysis plug-ins for pollution analysis based on different monitoring indicators. The first analysis plug-in is the module in the water pollution analysis channel used to analyze the first monitoring indicator data.

[0056] The algorithm and parameter settings in the first analysis plug-in are used to analyze water pollution in future time zones based on the first predicted data distribution sequence. For example, if the first analysis plug-in is based on a machine learning algorithm, it will use the historical data in the first predicted data distribution sequence (such as turbidity data at different times in the past) and a pre-trained model to predict water pollution in the future time zone and output a numerical value representing the likelihood of water pollution, namely, a first water pollution probability. Finally, this first water pollution probability is added to the multiple water pollution probabilities for subsequent comprehensive processing.

[0057] Randomly select another monitoring indicator from the multi-source prediction data distribution sequence, extract the data related to this monitoring indicator, and form a prediction data distribution sequence. Then, select the analysis plug-in corresponding to the new monitoring indicator from the water pollution analysis channel to predict the water pollution probability. Repeat this step, performing water pollution probability prediction for each monitoring indicator in the multi-source prediction data distribution sequence, and finally obtain multiple water pollution probabilities.

[0058] By analyzing the predicted data of various monitoring indicators and performing targeted calculations of pollution probabilities through analysis plug-ins, a scientific basis is provided for subsequent pollution warnings, ensuring that different monitoring indicators are reasonably analyzed and processed, and ultimately outputting accurate water pollution probabilities, thereby enhancing the accuracy and real-time nature of water pollution predictions.

[0059] Furthermore, the method described in the embodiment of the present application also includes constructing a water pollution analysis channel:

[0060] Step S2-1: According to the water pollution monitoring log of the target water area, with the first monitoring indicator and P monitoring points as constraints, a sample monitoring data distribution sequence set is collected.

[0061] Step S2-2: Based on a predetermined similarity tolerance interval, the water pollution frequency of different sample monitoring data distribution sequences in the historical time zone is counted and set as the sample water pollution probability to obtain a sample water pollution probability set, wherein the time intervals of the historical time zone and the future time zone are the same.

[0062] Step S2-3: Using the sample monitoring data distribution sequence set and the sample water quality pollution probability set as supervision data, train the BP neural network until convergence to obtain the first analysis plug-in, and sequentially construct multiple analysis plug-ins for multiple monitoring indicators to build the water quality pollution analysis channel.

[0063] Specifically, the process of constructing a water pollution analysis channel includes: determining a water pollution monitoring log for the target water area. The water pollution monitoring log records information such as various water quality index data at different times and different monitoring points in the target water area. Based on the first monitoring index (the same as step S21) and P monitoring points as constraints, the water pollution monitoring data of the first monitoring index at the same time in the monitoring log are retrieved and arranged in the time order of the monitoring points to form a sample monitoring data distribution sequence. All sample monitoring data distribution sequences are summarized to obtain a sample monitoring data distribution sequence set.

[0064] Obtain a pre-set similarity tolerance interval, which is the interval range used to judge data similarity. Then, for each sample monitoring data distribution sequence in the sample monitoring data distribution sequence set, perform water pollution frequency statistics in the historical time zone. The time interval of this historical time zone is the same as the aforementioned future time zone. If the future time zone is 5 to 10 days in the future, the historical time zone is 5 to 10 days after the monitoring period corresponding to the sample monitoring data. During the statistical process, if the data in different sample monitoring data distribution sequences are within the predetermined similarity tolerance interval, they are considered to be similar water pollution situations, and their frequency of occurrence is counted. For example, for a sample monitoring data distribution sequence with dissolved oxygen as the first monitoring indicator, the number of times the dissolved oxygen value occurs within a certain range (determined by the predetermined similarity tolerance interval) is the water pollution frequency. Divide this frequency by the total number of statistics to obtain the sample water pollution probability. Water pollution frequency statistics are performed on all sample monitoring data distribution sequences to obtain a sample water pollution probability set. By setting similar tolerance intervals to statistically analyze the sample water pollution probability set, the similarity of the data is taken into account, which can more reasonably evaluate the possibility of water pollution in the distribution series of different sample monitoring data in the historical time zone, providing meaningful supervision data for the subsequent training of the neural network, and helping to improve the accuracy of the constructed analysis plug-in for water pollution analysis.

[0065] The BP neural network is trained using the sample monitoring data distribution sequence set and the sample water quality pollution probability set as supervisory data. First, a deep learning framework such as TensorFlow or PyTorch is used to construct an initialized BP neural network structure, in which the number of input layer nodes is the same as the dimension of the sample monitoring data distribution sequence; the number of hidden layer nodes is determined based on experience or trial and error; and the number of output layer nodes is 1, representing the water quality pollution probability. Next, the BP neural network is trained using supervised data, and the error between the network output and the sample water quality pollution probability set is gradually reduced by continuously adjusting the network weights and biases until convergence (i.e., the error reaches an acceptable minimum value). The trained BP neural network is output as the first analysis plug-in. Following the same method, corresponding analysis plug-ins are constructed for other monitoring indicators in turn, and these analysis plug-ins are combined to form a water quality pollution analysis channel.

[0066] The above steps use the powerful nonlinear fitting ability of the BP neural network to train analysis plug-ins and build water quality pollution analysis channels. They can accurately construct analysis plug-ins suitable for different monitoring indicators based on historical data. The water quality pollution analysis channel composed of these plug-ins can conduct a comprehensive and accurate analysis of water quality pollution in the target water area, thereby improving the scientificity and reliability of water quality pollution analysis.

[0067] Furthermore, the method described in the embodiment of the present application also includes: configuring a first probability threshold and a second probability threshold, wherein the second probability threshold is smaller than the first probability threshold.

[0068] Specifically, when issuing water pollution warnings for target waters, two different probability thresholds are configured to verify the probability of water pollution, namely the first and second probability thresholds, based on the specific circumstances of the target waters (such as their function, surrounding environment, and historical water quality). The first probability threshold is used to identify serious pollution incidents, while the second probability threshold serves as a warning of potential pollution risks. The second probability threshold should be lower than the first. When the probability of water pollution reaches the second threshold, a warning or prompt is issued, but no full-scale emergency response is triggered. When the probability of pollution exceeds the first threshold, a more drastic alert and emergency measures are triggered. For example, if the target water area is a drinking water source, the first probability threshold can be set low, such as 0.3, indicating that a high level of concern and strict protective measures are required when the probability of water pollution reaches 0.3. The second probability threshold might be set at 0.1. When the probability of water pollution is between 0.1 and 0.3, relatively mild measures such as increased monitoring frequency can be implemented. The dual threshold configuration helps to stratify the severity of water pollution, enabling more targeted response strategies to protect the water quality of the target waters.

[0069] In summary, the intelligent buoy dynamic warning method for environmental monitoring provided by the embodiments of the present application has the following technical effects:

[0070] The embodiment of the present application ensures the spatial consistency and accuracy of the data by dynamically reading the real-time position of the buoy and multi-source monitoring data, and correcting the fluctuation of the buoy position in combination with interpolation prediction technology; by recording the distribution of multi-source data of multiple consecutive monitoring points and analyzing the data sequence, it effectively captures the trend of water quality changes and improves the timeliness and accuracy of pollution warnings; further, through the comprehensive calculation of the maximum pollution probability and the mean pollution probability, it provides a reliable judgment basis for water pollution warnings. The warning mechanism of the dual probability threshold further improves the scientific nature and accuracy of the warning and reduces false alarms and missed reports. Overall, the embodiment of the present application realizes dynamic monitoring and early warning of water pollution, significantly improves the accuracy of environmental monitoring and the accuracy and reliability of water pollution warnings, and provides strong technical support for the protection and management of aquatic environments.

[0071] Example 2, as Figure 3 As shown, based on the same inventive concept as the aforementioned embodiment 1, this embodiment of the present application provides an intelligent buoy dynamic warning platform for environmental monitoring, the platform comprising:

[0072] The interpolation prediction module 10 is used to read the real-time position coordinates and multi-source monitoring data of several buoys in the target water area at a fixed point, perform interpolation prediction based on the real-time position coordinates and multi-source monitoring data, obtain multi-source prediction data of the calibrated position coordinates of several buoys, and generate a multi-source prediction data distribution.

[0073] The water pollution analysis module 20 is used to record the distribution of multi-source prediction data under P consecutive monitoring points to construct a multi-source prediction data distribution sequence, perform water pollution analysis on the target water area in the future time zone based on the multi-source prediction data distribution sequence, and generate multiple water pollution probabilities.

[0074] The probability extraction and calculation module 30 is used to perform maximum probability extraction and probability mean calculation according to the multiple water pollution probabilities to obtain the maximum pollution probability and the pollution probability mean.

[0075] The pollution warning module 40 is configured to issue a water pollution warning to the target water area if the maximum pollution probability is greater than a first probability threshold and / or the mean pollution probability is greater than a second probability threshold.

[0076] Furthermore, the interpolation prediction module 10 of the embodiment of the present application is further configured to perform the following steps:

[0077] Obtain several calibrated position coordinates of several buoys in the target waters, calculate the relative distances between the several calibrated position coordinates and the nearest real-time position coordinates respectively, and if the relative distance is less than a predetermined distance threshold, set the multi-source monitoring data corresponding to the real-time position coordinates as the multi-source prediction data corresponding to the calibrated position coordinates; screen and obtain multiple unmarked calibrated position coordinates, perform interpolation prediction on the multiple unmarked calibrated position coordinates according to the real-time position coordinates and the multi-source monitoring data, and obtain multiple multi-source prediction data of the multiple unmarked calibrated position coordinates; arrange the multiple multi-source prediction data of the several calibrated position coordinates according to their positions to generate the multi-source prediction data distribution.

[0078] Furthermore, the interpolation prediction module 10 of the embodiment of the present application is further configured to perform the following steps:

[0079] Randomly select a first unmarked calibrated position coordinate, use the first unmarked calibrated position coordinate as a reference, search within a predetermined distance range, obtain multiple first adjacent real-time position coordinates, and analyze to obtain multiple position association information, wherein the position association information includes associated distance and associated azimuth; obtain multi-source monitoring indicators, and perform distance and azimuth association analysis on the multi-source monitoring indicators, establish a multi-source position mapping association between distance, azimuth and monitoring indicators, wherein the multi-source monitoring indicators include at least dissolved oxygen, pH value, turbidity, conductivity, temperature, heavy metal concentration, chemical oxygen demand and ammonia nitrogen; based on the multi-source position mapping association, obtain multiple association coefficient sets according to the matching of the multiple position association information, analyze and determine multiple association weight sets; obtain multiple first multi-source monitoring data of multiple first adjacent real-time position coordinates, perform weighted interpolation prediction on the multiple first multi-source monitoring data according to the multiple association weight sets, and output first multi-source prediction data.

[0080] Furthermore, the interpolation prediction module 10 of the embodiment of the present application is further configured to perform the following steps:

[0081] A first monitoring indicator is randomly selected from the multi-source monitoring indicators, and the water quality pollution monitoring log of the target water area is retrieved according to the first monitoring indicator to obtain a sample initial monitoring data set, a sample relative distance set, a sample relative orientation set and a sample associated monitoring data set; based on the sample initial monitoring data set and the sample associated monitoring data set, a correlation analysis is performed on the sample initial monitoring data and the sample associated monitoring data respectively to obtain a sample correlation coefficient set; a first position mapping association is constructed according to the sample relative distance set, the sample relative orientation set and the sample correlation coefficient set, and added to the multi-source position mapping association.

[0082] Furthermore, the water pollution analysis module 20 of the embodiment of the present application is further configured to perform the following steps:

[0083] A first prediction data distribution sequence for a first monitoring indicator is randomly selected from the multi-source prediction data distribution sequence, and a first analysis plug-in is matched in a water quality pollution analysis channel according to the first monitoring indicator; water quality pollution analysis of the future time zone is performed on the first prediction data distribution sequence through the first analysis plug-in, and a first water quality pollution probability is outputted and added to the multiple water quality pollution probabilities.

[0084] Furthermore, the platform described in the embodiment of the present application further includes an analysis channel construction module, and the analysis channel construction module is used to perform the following steps:

[0085] According to the water quality pollution monitoring log of the target water area, with the first monitoring indicator and P monitoring points as constraints, a sample monitoring data distribution sequence set is collected; based on a predetermined similarity tolerance interval, the water quality pollution frequency of different sample monitoring data distribution sequences in the historical time zone is statistically analyzed and set as the sample water quality pollution probability, and a sample water quality pollution probability set is obtained, wherein the time interval between the historical time zone and the future time zone is the same; using the sample monitoring data distribution sequence set and the sample water quality pollution probability set as supervision data, a BP neural network is trained until convergence to obtain a first analysis plug-in, and multiple analysis plug-ins for multiple monitoring indicators are sequentially constructed to build the water quality pollution analysis channel.

[0086] Furthermore, the platform described in the embodiment of the present application further includes a threshold configuration module, which is configured to perform the following steps:

[0087] A first probability threshold and a second probability threshold are configured, wherein the second probability threshold is smaller than the first probability threshold.

[0088] Through the detailed description of the intelligent buoy dynamic warning method for environmental monitoring in the foregoing specification, those skilled in the art can clearly understand the intelligent buoy dynamic warning platform for environmental monitoring in this embodiment. For the platform disclosed in Example 2, since it corresponds to the method disclosed in Example 1 and has corresponding functional modules and beneficial effects, the relevant details can be referred to the method section.

[0089] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one 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 application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A smart buoy dynamic early warning method for environmental monitoring, characterized in that: Methods include: Fixed-point reading of the real-time position coordinates and multi-source monitoring data of several buoys in the target waters, performing interpolation prediction based on the real-time position coordinates and multi-source monitoring data, obtaining multi-source prediction data of the calibrated position coordinates of the several buoys, and generating a multi-source prediction data distribution; Record the distribution of multi-source prediction data at P consecutive monitoring points to construct a multi-source prediction data distribution sequence, perform water quality pollution analysis on the target water area in the future time zone based on the multi-source prediction data distribution sequence, and generate multiple water quality pollution probabilities; Performing maximum probability extraction and probability mean calculation according to the multiple water pollution probabilities to obtain the maximum pollution probability and the pollution probability mean; If the maximum pollution probability is greater than the first probability threshold and / or the mean pollution probability is greater than the second probability threshold, a water pollution warning is issued for the target water area; The interpolation prediction is performed based on the real-time position coordinates and the multi-source monitoring data to obtain the multi-source prediction data of the calibrated position coordinates of several buoys and generate the multi-source prediction data distribution, including: Obtaining a plurality of calibrated position coordinates of a plurality of buoys in the target waters, calculating the relative distances between the plurality of calibrated position coordinates and the nearest real-time position coordinate, and setting the multi-source monitoring data corresponding to the real-time position coordinate as the multi-source prediction data corresponding to the calibrated position coordinate if the relative distances are less than a predetermined distance threshold; Filtering and acquiring a plurality of unlabeled calibrated position coordinates, and performing interpolation prediction on the plurality of unlabeled calibrated position coordinates according to the real-time position coordinates and the multi-source monitoring data, to obtain a plurality of multi-source prediction data of the plurality of unlabeled calibrated position coordinates; Arranging a plurality of multi-source prediction data of a plurality of calibrated position coordinates according to positions to generate the multi-source prediction data distribution; The interpolation prediction of the plurality of unlabeled calibrated position coordinates is performed respectively according to the real-time position coordinates and the multi-source monitoring data, including: Randomly selecting a first unmarked calibrated position coordinate, searching within a predetermined distance range based on the first unmarked calibrated position coordinate as a reference, obtaining a plurality of first adjacent real-time position coordinates, and analyzing to obtain a plurality of position association information, wherein the position association information includes an association distance and an association direction; Acquire multi-source monitoring indicators, perform distance and azimuth correlation analysis on the multi-source monitoring indicators, and establish a multi-source position mapping association between the distance, azimuth, and monitoring indicators, wherein the multi-source monitoring indicators include at least dissolved oxygen, pH value, turbidity, conductivity, temperature, heavy metal concentration, chemical oxygen demand, and ammonia nitrogen; Based on the multi-source position mapping association, a plurality of association coefficient sets are obtained according to the matching of the plurality of position association information, and a plurality of association weight sets are determined by analysis; A plurality of first multi-source monitoring data of a plurality of first adjacent real-time position coordinates are obtained, weighted interpolation prediction is performed on the plurality of first multi-source monitoring data according to the plurality of association weight sets, and first multi-source prediction data is output.

2. The intelligent buoy dynamic early warning method for environmental monitoring according to claim 1 is characterized in that: Performing distance and azimuth correlation analysis on the multi-source monitoring indicators, and establishing multi-source location mapping correlation between distance, azimuth and monitoring indicators, including: Randomly selecting a first monitoring indicator from the multi-source monitoring indicators, searching the water quality pollution monitoring log of the target water area according to the first monitoring indicator, and obtaining a sample initial monitoring data set, a sample relative distance set, a sample relative orientation set, and a sample associated monitoring data set; According to the sample initial monitoring data set and the sample associated monitoring data set, respectively, correlation analysis is performed on the sample initial monitoring data and the sample associated monitoring data to obtain a sample correlation coefficient set; A first position mapping association is constructed according to the sample relative distance set, the sample relative orientation set, and the sample correlation coefficient set, and is added to the multi-source position mapping association.

3. The intelligent buoy dynamic early warning method for environmental monitoring according to claim 1 is characterized in that: Water pollution analysis of target waters in future time zones is performed based on the multi-source prediction data distribution sequence to generate multiple water pollution probabilities, including: Randomly selecting a first prediction data distribution sequence of a first monitoring indicator from the multi-source prediction data distribution sequence, and matching a first analysis plug-in in a water quality pollution analysis channel according to the first monitoring indicator; The first analysis plug-in is used to perform water pollution analysis on the first predicted data distribution sequence in a future time zone, output a first water pollution probability, and add it to the multiple water pollution probabilities.

4. The intelligent buoy dynamic early warning method for environmental monitoring according to claim 3 is characterized in that: Construct a water pollution analysis channel, including: According to the water quality pollution monitoring log of the target water area, with the first monitoring indicator and P monitoring points as constraints, a sample monitoring data distribution sequence set is collected; Based on a predetermined similarity tolerance interval, the water pollution frequency of different sample monitoring data distribution sequences in the historical time zone is counted and set as the sample water pollution probability, thereby obtaining a sample water pollution probability set, wherein the time intervals of the historical time zone and the future time zone are the same; The sample monitoring data distribution sequence set and the sample water pollution probability set are used as supervision data to train the BP neural network until convergence to obtain the first analysis plug-in, and then multiple analysis plug-ins for multiple monitoring indicators are constructed in sequence to build the water pollution analysis channel.

5. The intelligent buoy dynamic early warning method for environmental monitoring according to claim 1 is characterized in that: A first probability threshold and a second probability threshold are configured, wherein the second probability threshold is smaller than the first probability threshold.

6. Intelligent buoy dynamic warning platform for environmental monitoring, characterized by: The platform is used to execute the intelligent buoy dynamic early warning method for environmental monitoring according to any one of claims 1 to 5, comprising: An interpolation prediction module is used to read the real-time position coordinates and multi-source monitoring data of several buoys in the target waters at a fixed point, perform interpolation prediction based on the real-time position coordinates and multi-source monitoring data, obtain multi-source prediction data of the calibrated position coordinates of several buoys, and generate a multi-source prediction data distribution; A water pollution analysis module is used to record the distribution of multi-source prediction data at P consecutive monitoring points to construct a multi-source prediction data distribution sequence, perform water pollution analysis on target waters in future time zones based on the multi-source prediction data distribution sequence, and generate multiple water pollution probabilities; A probability extraction and calculation module is used to perform maximum probability extraction and probability mean calculation according to the multiple water pollution probabilities to obtain the maximum pollution probability and the pollution probability mean; The pollution warning module is used to issue a water pollution warning to the target water area if the maximum pollution probability is greater than a first probability threshold and / or the mean pollution probability is greater than a second probability threshold.

Images