Underground water environment monitoring method and system based on big data

Abstract

The invention relates to the field of intelligent monitoring, and particularly discloses an underground water environment monitoring method and system based on big data, and the method comprises the steps: firstly, decomposing complex water quality time sequence data into three components, namely a trend component, a season component and a residual error component through an STL decomposition technology, thereby effectively separating an inherent periodic rule of an underground water system from random disturbance; on this basis, trend and seasonal components are innovatively used as dynamic macroscopic backgrounds for interpreting the real meaning of residual components, then a normal disturbance mode under a specific background is deeply learned in combination with an LSTM auto-encoder, and finally early warning judgment is made by an SVM model. Through the mode, the method can effectively adapt to the periodic change of the groundwater environment, and accurately recognize the normal water quality fluctuation caused by natural factors, thereby remarkably reducing the false alarm rate, improving the monitoring sensitivity of real pollution events, and finally realizing the accurate dynamic evaluation and reliable early warning of the groundwater environment state.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent monitoring, and more specifically, to a groundwater environment monitoring method and system based on big data. BACKGROUND

[0002] Due to the characteristics of slow, hidden and difficult to repair of groundwater pollution, if it cannot be discovered and controlled in time, it will cause serious consequences to the sustainable use of water resources and human health. Therefore, building an intelligent monitoring system that can monitor the dynamic of groundwater environment in real time and accurately, and can timely warn potential pollution risks, has strategic significance for protecting water resources safety and effectively managing and protecting water environment.

[0003] To meet this monitoring demand, a variety of groundwater environment monitoring technologies based on time series data analysis have been developed. These technologies usually analyze the water quality data collected by sensors to identify abnormal fluctuations to determine whether a pollution event has occurred. However, the existing monitoring methods have technical limitations in dealing with complex groundwater environment data. The core problem is that they mostly define normal water quality state as a relatively stable or slowly changing baseline, without fully considering the inherent strong nonlinearity and periodicity of the groundwater system. In fact, groundwater quality will show significant periodic fluctuations with seasonal changes, rainfall recharge and other natural factors, and these fluctuations are part of the normal operation of the system. Due to the lack of effective modeling of this temporal context and periodic pattern, traditional models cannot establish a dynamic baseline that can adapt to different hydrological backgrounds. This makes it difficult for the model to distinguish between mutations caused by real pollution events and normal large fluctuations caused by natural factors (such as systematic differences between wet and dry seasons), resulting in a large number of false positives, which seriously restricts the accuracy and reliability of the monitoring system.

[0004] Therefore, an optimized groundwater environment monitoring method based on big data is expected. SUMMARY

[0005] In order to solve the above technical problems, the present application is proposed. Embodiments of the present application provide a groundwater environment monitoring method and system based on big data, which first decomposes complex water quality time series data into trend, season and residual components by STL decomposition technology, so as to effectively separate the inherent periodicity of the groundwater system and random disturbance, and on this basis, innovatively uses the trend and season components as a dynamic macro background to interpret the true meaning of the residual component, and further combines the normal disturbance mode of the LSTM autoencoder deep learning in a specific background, and finally makes a warning judgment by the SVM model. In this way, the periodic changes of the groundwater environment can be effectively adapted, the normal water quality fluctuations caused by natural factors can be accurately identified, the false positive rate can be significantly reduced, the monitoring sensitivity to real pollution events can be improved, and finally the precise dynamic evaluation and reliable warning of the groundwater environment state can be realized.

[0006] According to one aspect of the present application, a groundwater environment monitoring method based on big data is provided, which comprises: obtaining water quality time series data from a specific monitoring well; inputting the water quality time series data into an STL decomposition module to obtain trend components, season components and residual components; extracting a water quality residual feature vector sequence from the residual components with the trend components and the season components as background information; performing abnormal score calculation on the water quality residual feature vector sequence based on an LSTM autoencoder to obtain an abnormal score value sequence; inputting the abnormal score value sequence into a warning analysis engine based on an SVM model to obtain a warning analysis result.

[0007] According to another aspect of the present application, a groundwater environment monitoring system based on big data is provided, which comprises: a data acquisition module for acquiring water quality time series data from a specific monitoring well; an STL decomposition module for inputting the water quality time series data into the STL decomposition module to obtain trend components, season components and residual components; a water quality residual feature extraction module for extracting a water quality residual feature vector sequence from the residual components with the trend components and the season components as background information; an abnormal score calculation module for performing abnormal score calculation on the water quality residual feature vector sequence based on an LSTM autoencoder to obtain an abnormal score value sequence; a warning analysis module for inputting the abnormal score value sequence into a warning analysis engine based on an SVM model to obtain a warning analysis result.

[0008] Compared with the prior art, the groundwater environment monitoring method and system based on big data provided by the application firstly decomposes complex water quality time series data into three components of trend, season and residual through STL decomposition technology, so as to effectively separate the inherent periodicity of the groundwater system and random disturbance, on this basis, the trend and season components are innovatively used as a dynamic macro background for interpreting the real meaning of the residual component, and then combined with the normal disturbance mode of the LSTM self-encoder deep learning in a specific background, and finally a warning judgment is made by the SVM model. In this way, the periodic change of the groundwater environment can be effectively adapted, the normal water quality fluctuation caused by natural factors can be accurately identified, the false positive rate can be significantly reduced, the monitoring sensitivity to real pollution events can be improved, and finally the accurate dynamic evaluation and reliable warning of the groundwater environment state can be realized. BRIEF DESCRIPTION OF DRAWINGS

[0009] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description of embodiments of the present application taken in conjunction with the accompanying drawings. The drawings provided in the present application are used to provide further understanding of the embodiments of the present application, and constitute a part of the specification, and are used to explain the present application together with the embodiments of the present application, and do not constitute a limitation of the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0010] Figure 1 a flowchart of the groundwater environment monitoring method based on big data according to the embodiments of the present application; Figure 2 a data flow schematic diagram of the groundwater environment monitoring method based on big data according to the embodiments of the present application; Figure 3 a block diagram of the groundwater environment monitoring system based on big data according to the embodiments of the present application. DETAILED DESCRIPTION

[0011] Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, and not all the embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein.

[0012] As shown in the present application and claims, unless the context clearly indicates otherwise, "one", "a", "an" and / or "the" do not refer to the singular, but can also include the plural. Generally, the terms "comprise" and "include" only indicate the inclusion of the steps and elements explicitly identified, and these steps and elements do not constitute an exclusive list, and the method or device can also include other steps or elements.

[0013] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or server. The modules are merely illustrative, and different aspects of the system and method can use different modules.

[0014] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in sequence. On the contrary, various steps can be processed in reverse order or simultaneously as needed. Meanwhile, other operations can be added to these processes, or one or more steps of operation can be removed from these processes.

[0015] In the following, the example embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, and not all embodiments of the present application, and it should be understood that the present application is not limited to the example embodiments described herein.

[0016] In the technical solution of the present application, a groundwater environment monitoring method based on big data is proposed. Figure 1 A flowchart of the groundwater environment monitoring method based on big data according to the embodiments of the present application. Figure 2 A data flow diagram of the groundwater environment monitoring method based on big data according to the embodiments of the present application. As Figure 1 and Figure 2 As shown in the groundwater environment monitoring method based on big data according to the embodiments of the present application, the method comprises the steps of: S1, obtaining water quality time series data from a specific monitoring well; S2, inputting the water quality time series data into an STL decomposition module to obtain a trend component, a seasonal component and a residual component; S3, extracting a water quality residual feature vector sequence from the residual component with the trend component and the seasonal component as background information; S4, performing abnormal score calculation based on an LSTM autoencoder on the water quality residual feature vector sequence to obtain an abnormal score value sequence; and S5, inputting the abnormal score value sequence into a warning analysis engine based on an SVM model to obtain a warning analysis result.

[0017] In particular, the S1 obtains water quality time series data from a specific monitoring well. By systematically and continuously collecting objective physicochemical indicators of the groundwater environment, real, effective and high-density raw data input can be provided for subsequent data decomposition, feature extraction, anomaly detection and warning analysis, and data support can be provided for subsequent models to accurately analyze the dynamic evolution of the groundwater environment, thereby realizing timely discovery and reliable warning of potential pollution events.

[0018] Among them, the specific monitoring well refers to a special observation well laid in a representative geographical location or a key hydraulic connection node according to the hydrogeological exploration results. These monitoring wells are equipped with professional water quality sensing equipment as the front end of long-term and fixed-point groundwater quality data collection. The water quality time series data refers to a series of water quality parameter measurement values collected from a single or multiple specific monitoring wells at a preset and fixed time interval (such as every hour, every minute). Each data point in the data set contains an accurate time stamp and multiple water quality parameter values such as pH value, conductivity, turbidity, dissolved oxygen, and specific pollutant concentration, thereby forming a structured data stream that can reflect the dynamic changes of water quality over time.

[0019] In specific implementation, first, one or more multi-parameter water quality monitoring probes or sensor arrays are deployed in the specific monitoring well, which can measure the preset water quality indicators in real time. Subsequently, the measurement values of all sensors are automatically read at a determined sampling frequency (for example, every 30 minutes) through an embedded data acquisition unit. The collected raw data is preliminarily formatted and encapsulated into a data frame containing the unique identifier of the monitoring well, the acquisition time stamp, and the key-value pairs of various water quality parameters; then, the encapsulated data frame is remotely sent to the central data server in a safe and reliable manner using a wireless data transmission module (Data Transmission Unit), such as through GPRS, 4G / 5G, or NB-IoT Internet of Things communication technology. After receiving the data, the central server will parse and verify it, and store the valid data into a database dedicated to processing time series data (such as time series database InfluxDB or HBase), thereby forming a structured water quality time series data set that can be called by subsequent analysis modules.

[0020] In particular, the S2, the water quality time series data is input into the STL decomposition module to obtain the trend component, the seasonal component and the residual component. It should be understood that the original water quality time series data is a mixed signal formed under the joint action of multiple complex factors, which contains not only slow changes (trend) driven by long-term evolution or persistent influence of groundwater system, but also periodic fluctuations (seasonality) caused by natural laws such as seasonal change and rainfall cycle, and also random disturbances (residual) caused by sudden and accidental events. If the mixed signal is not distinguished for abnormal detection, normal seasonal fluctuations will be greatly misjudged as pollution events, resulting in high false alarm rate of the system. Therefore, in the technical solution of the present application, the water quality time series data is input into the STL decomposition module to structurally deconstruct the mixed signal and accurately separate each component, so as to strip the real random abnormal signal that needs to be focused on for the subsequent analysis module, and lay a solid data foundation for realizing high-precision abnormal event recognition and early warning.

[0021] Among them, the STL decomposition module is a functional unit specially used for time series decomposition, and its name is the abbreviation of "Seasonal and Trend decomposition using Loess", which means using local weighted regression scatter smoothing method for seasonal and trend decomposition. It is a powerful and robust time series decomposition algorithm that can effectively process various types of time series data. The trend component output refers to the overall trend and internal law of water quality data in a long time span, which is continuously rising, falling or remaining stable; the seasonal component is the regular fluctuation pattern that appears repeatedly in a fixed time period (for example, one year or one day); the residual component is the part left after the trend component and the seasonal component are removed from the original time series, which represents random noise, measurement error and potential abnormal signals caused by sudden events that cannot be explained by trend and seasonal patterns.

[0022] In specific implementation, the STL decomposition module receives the water quality time series data obtained in the previous step as input and processes the sequence according to a specific mathematical model; specifically, the STL decomposition module processes the water quality time series data to obtain the trend component, the seasonal component and the residual component according to the following formula: , Among them, is the trend component, is the seasonal component, is the residual component. In this process, the STL decomposition module first smooths the water quality time series data to preliminarily estimate the trend component, and then subtracts the trend from the water quality time series to obtain a detrended sequence; then the detrended sequence is smoothed to estimate the seasonal component. Subtract the seasonal component from the water quality time series to obtain a seasonally adjusted sequence, and smooth the sequence to update the trend component. This process is repeated iteratively until the estimates of the trend component and the seasonal component converge stably, and finally the water quality time series data is decomposed into three independent components.

[0023] In particular, the S3 extracts the water quality residual feature vector sequence from the residual component with the trend component and the seasonal component as background information. It should be understood that the traditional mechanism often only retains the residual component for analysis after decomposing the original time series data, and completely discards the trend component and the seasonal component which contain the system macro state. The fundamental defect of this processing method is that it staticizes and isolates the meaning of the residual. In the real groundwater environment, a residual disturbance with the same value has a high dependence on the system background in which it is located. For example, in the flood season, a larger residual value may belong to the normal category because the flow is abundant and the hydrological conditions are volatile; however, in the dry season, a residual of the same size is most likely to be a significant abnormal signal because the hydrological activity is flat. Therefore, in the technical solution of the present application, the trend and seasonal information representing the macro state of the system are used as the dynamic background for interpreting the residual signal, that is, the data sequence formed by combining the trend component and the seasonal component together represents the predictable and regular macro state of the groundwater system at any time. Further, through a deep interaction mechanism, a residual feature is generated which can contain context information and has stronger expression ability, so that the subsequent anomaly detection model can make more accurate and more realistic judgments.

[0024] In implementation, first, the trend component and the seasonal component are spliced to obtain a background component; then, the background component and the residual component are interacted to obtain a water quality residual feature vector sequence. Here, it should be understood that the groundwater system itself is jointly affected by natural periods and long-term trends, and although the residual component has been stripped of the main trend and seasonal factors, it still may implicitly contain structural information related to the background state. If the original residual is directly used for anomaly detection, it may fail to fully consider the internal relationship between the residual and the current hydrological background (trend and season), resulting in misjudgment of normal fluctuations or missed reports of real anomalies. Therefore, in the technical solution of the present application, through manifold transmission modulation, the residual feature and the background feature are deeply fused at the structural level, so that the generated water quality residual feature vector sequence not only contains the original abnormal signal of the residual, but also encodes the deviation degree and nature of the abnormal signal relative to the current system expected state (defined by the trend and seasonal components). In this way, the system can better distinguish between normal water quality fluctuations caused by rainfall recharge and abnormal mutations caused by pollutant leakage, thereby reducing the false positive rate at the root and improving the accuracy and reliability of the early warning results, providing core technical support for building a truly intelligent groundwater environment monitoring system.

[0025] Specifically, first, local time sequence feature extraction is performed on the background component and the residual component to obtain a sequence of background component local time sequence feature encoding vectors and a sequence of residual component local time sequence feature encoding vectors. It should be understood that each component obtained by STL decomposition is a macroscopic time sequence structure, and direct interaction may ignore its internal fine-grained and dynamically changing local patterns. The trend of the groundwater system is not a straight line that remains unchanged, and its change rate may fluctuate due to long-term climate or human activities; the seasonal component is also not a perfect sine wave, and its amplitude and shape may have slight differences in different periods. The residual component is a complex sequence that contains rich short-term fluctuation information. Traditional global feature representation cannot capture the details of the evolution of these components over time, and interacting these components as smooth wholes will lose important local context information for anomaly detection, making it difficult to accurately quantify the deviation of the residual anomaly from the current background state at a specific time point. Therefore, in the technical solution of the present application, local time sequence feature extraction can be used to convert the macroscopic background and residual sequences into a series of feature encoding vector sequences rich in local context information. In this way, the subsequent manifold alignment and anomaly detection process greatly enhances the perception of complex hydrological dynamics, thereby providing a key technical guarantee for precise early warning. In a specific example of the present application, one-dimensional convolutional neural network-based local time sequence feature extraction can be used to obtain a sequence of background component local time sequence feature encoding vectors and a sequence of residual component local time sequence feature encoding vectors.

[0026] Specifically, the background component and the residual component are locally time-series feature extracted to obtain a sequence of background component local time-series feature encoding vectors and a sequence of residual component local time-series feature encoding vectors by using the following formula: , , wherein, is the background component, is the residual component, represents one-dimensional convolution encoding, and are the i-th background component local time-series feature encoding vector and the i-th residual component local time-series feature encoding vector in the sequence of background component local time-series feature encoding vectors and the sequence of residual component local time-series feature encoding vectors, respectively, is the sequence of background component local time-series feature encoding vectors, is the sequence of residual component local time-series feature encoding vectors.

[0027] Then, the manifold transport modulation matrix of the sequence of background component local time-series feature encoding vectors relative to the sequence of residual component local time-series feature encoding vectors is calculated. It should be understood that the background component carries the long-term evolution rule and periodic pattern of the groundwater system, and the essence of the residual component is the abnormal signal that the system deviates from the expected normal behavior under a specific background state. The traditional method of directly calculating the similarity or distance between the two often only scratches the surface and cannot capture the deep and structured dependence relationship between them. Therefore, in the technical solution of the present application, an optimal transport theory is used to construct a globally optimal and structured alignment scheme for the two feature manifolds of background and residual to obtain the manifold transport modulation matrix. Through the matrix, the system can penetrate the manifold structure information of the background feature into the explanation of the residual anomaly in a globally optimal way, which lays a solid foundation for the final accurate judgment of the nature of the anomaly and greatly improves the ability of the system to distinguish natural fluctuations from pollution events, and essentially reduces the false positive rate of monitoring and early warning.

[0028] Specifically, in the technical solution of the present application, the specific process of calculating the manifold transport modulation matrix of the sequence of background component local time-series feature encoding vectors relative to the sequence of residual component local time-series feature encoding vectors includes: First, the weighted cross-covariance matrix between the sequence of background component local time-series feature encoding vectors and the sequence of residual component local time-series feature encoding vectors is calculated, which is represented by the formula as follows: , , wherein, ​is a time weight, is a weighted cross-covariance matrix, is a transpose vector of the residual component local temporal feature encoding vector, is a background component local temporal feature encoding vector; Further, singular value decomposition and modulation matrix extraction are performed on the weighted cross-covariance matrix to obtain a manifold transmission modulation matrix, which is expressed by the formula as follows: , , wherein, is the manifold transmission modulation matrix.

[0029] Further, based on the manifold transmission modulation matrix, the sequence of the background component local temporal feature encoding vector is feature-aligned to obtain a sequence of the background component remodeled local temporal feature encoding vector. It can be understood that although the background component describes the long-term trend and periodic law of the system, its original feature representation is not adaptively adjusted for the current specific residual anomaly pattern. Under different hydrological conditions, the same background state has different explanatory power for residual anomalies. For example, in the dry season stable period, the background feature indicates that the system is in a low activity state, and at this time a small residual anomaly may be of great significance; while in the active period of the rainy season, the same residual anomaly may belong to the normal fluctuation range. If the background feature is not calibrated specifically, direct fusion will not accurately reflect this dynamic and context-dependent correlation, resulting in inaccurate anomaly judgment. Therefore, in the technical solution of the present application, the optimal transmission mapping relationship is calculated to intelligently remodel the background feature sequence in a situational manner, so that the manifold structure of the background feature is distorted in a globally optimal manner to the most matching form of the current residual anomaly feature manifold, so that the remodeled background feature can maximize the absorption and reflection of the abnormal pattern information contained in the current residual sequence. Based on this, the system can more sensitively identify residual anomalies that still have significant structural deviations from the remodeled background feature in the subsequent fusion stage, thereby greatly improving the ability of the monitoring system to distinguish true and false anomalies in complex hydrological environments, and achieving accurate early warning.

[0030] Specifically, based on the manifold transmission modulation matrix, the sequence of the background component local temporal feature encoding vector is feature-aligned to obtain a sequence of the background component remodeled local temporal feature encoding vector, by the formula as follows: , wherein, is a transpose vector of the sequence of the background component local temporal feature encoding vector, is a sequence of the background component remodeled local temporal feature encoding vector.

[0031] Subsequently, each group of the background component reshaped local timing feature encoding vector and the residual component local timing feature encoding vector in the sequence of the background component reshaped local timing feature encoding vector and the sequence of the residual component local timing feature encoding vector is subjected to feature fusion to obtain the water quality residual feature vector sequence. It can be understood that the reshaped background feature has already contained the context information for the current residual anomaly pattern, but it is still two independent signal streams with the residual feature, and the system is still difficult to capture the subtle and dynamic difference pattern between the expected background state and the observed abnormal signal, and the difference is the key to distinguish the real pollution event from the natural fluctuation. Therefore, in the technical solution of the present application, a refined feature fusion operation is performed to highlight the residual anomaly that does not conform to the expectation under a specific background environment, thereby providing the most discriminative information for the final anomaly score. This enables the subsequent LSTM autoencoder to learn a more accurate normal pattern representation, thereby being more sensitive to anomalies that are significantly inconsistent with the background environment, greatly improving the accuracy of the system in identifying real pollution events under complex hydrological conditions, while effectively reducing false positives caused by natural fluctuations, and finally achieving the core goal of the intelligent monitoring system.

[0032] Specifically, each group of the background component reshaped local timing feature encoding vector and the residual component local timing feature encoding vector in the sequence of the background component reshaped local timing feature encoding vector and the sequence of the residual component local timing feature encoding vector is subjected to feature fusion to obtain the water quality residual feature vector sequence, and the formula is as follows: , wherein, is the residual component local timing feature encoding vector, is the background component reshaped local timing feature encoding vector at the corresponding position, represents and the water quality residual feature vector.

[0033] In particular, S4, the water quality residual feature vector sequence is subjected to anomaly score calculation based on the LSTM autoencoder to obtain the anomaly score value sequence. It can be understood that the water quality residual feature vector sequence generated in the previous step contains context information, but it is still high-dimensional and complex data, which is difficult to directly use for early warning judgment. In the technical solution of the present application, a deep learning model with strong modeling capability for time series data is introduced to convert this high-dimensional and complex feature expression into an intuitive and quantifiable scalar score, which directly reflects the degree of deviation of the current water quality state from its normal behavior pattern, and provides a direct, clear and reliable basis for subsequent early warning decision-making.

[0034] wherein the LSTM autoencoder is an unsupervised neural network model, which consists of two main parts: an encoder based on LSTM units and a decoder also based on LSTM units. The encoder is responsible for reading the input sequence of feature vectors and compressing it into a fixed-length internal representation (or latent vector) that contains the core information of the entire sequence; the decoder then attempts to reconstruct the original input sequence as accurately as possible from this internal representation. The core idea of this model is to train it on a large amount of normal data so that it becomes proficient in compressing and reconstructing normal patterns. The anomaly score measures the degree of difference between the reconstructed sequence and the sequence of water quality residual feature vectors. In an example, if the sequence of water quality residual feature vectors conforms to the normal patterns learned by the model during the training phase, the reconstruction error will be small; on the contrary, if the sequence of water quality residual feature vectors presents an abnormal pattern that the model has never seen before, the model will not be able to effectively reconstruct it, resulting in a huge reconstruction error.

[0035] In implementation, first, the sequence of water quality residual feature vectors is input into the trained LSTM autoencoder to obtain the reconstructed sequence of water quality residual feature vectors. That is, during real-time monitoring, the sequence of water quality residual feature vectors generated in the previous step is input into the trained LSTM autoencoder model as a complete input. The encoder part reads each feature vector in the sequence by time step and updates its internal state step by step, finally generating a latent vector that can summarize the information of the entire input sequence. Then, the decoder part receives this latent vector and starts to generate a new sequence, i.e., the reconstructed sequence of water quality residual feature vectors, by time step; if the sequence of water quality residual feature vectors is normal, the reconstructed sequence of water quality residual feature vectors should be highly similar in value to the original input sequence.

[0036] Further, the reconstruction error between each corresponding pair of water quality residual feature vectors and reconstructed water quality residual feature vectors in the sequence of water quality residual feature vectors and the reconstructed sequence of water quality residual feature vectors is calculated to obtain the sequence of anomaly score values. In this process, the system compares the original sequence and the reconstructed sequence one by one at each time point. The mean square error between each corresponding pair of water quality residual feature vectors and reconstructed water quality residual feature vectors is calculated as the reconstruction error. Specifically, assuming that at time point , the original water quality residual feature vector is , the reconstructed vector is , and the dimension of the vector is , the calculation formula of the anomaly score at this time point can be represented as: , wherein is and The corresponding abnormal score value.

[0037] In particular, S5 inputs the anomaly score sequence into an early warning analysis engine based on an SVM model to obtain an early warning analysis result. It should be understood that relying solely on a static anomaly score threshold (e.g., an alarm is triggered when the score is greater than a certain constant) is often too rigid and unable to adapt to the complex dynamic characteristics of abnormal events as they develop. It can easily generate false alarms for brief, harmless noise spikes or be unresponsive to slowly developing but persistent potential threats. Therefore, the technical solution of this application introduces a specialized classification model trained through supervised learning to learn and distinguish the subtle differences between score fluctuations under normal conditions and score patterns caused by true abnormal events, thereby providing a more reliable, accurate, and business-logical final early warning judgment, ensuring the timeliness and accuracy of the warning. It is worth noting that SVM is a highly recognized and high-performance supervised learning classifier in the field of machine learning. It excels at finding an optimal decision hyperplane in high-dimensional space that can separate data points of different categories with the maximum margin. In this application, the SVM model is configured as a binary or multi-class classification model to determine the current water quality status. The warning analysis result is a discrete, qualitative status label, rather than a continuous numerical value. For example, the result can be a clear level such as "normal," "level one warning," or "level two warning," which directly corresponds to different emergency response levels.

[0038] In practice, this step consists of two core phases: offline model training and online inference. During the offline training phase, a high-quality, labeled training dataset is prepared for the SVM model. This dataset is constructed as follows: First, a sufficiently long series of historical anomaly score values ​​is collected, encompassing a variety of known normal operating conditions and at least one or more types of real-world abnormal events (e.g., historical pollution incidents). This series is then annotated, with each time point or time period clearly labeled as "normal" or "abnormal." Next, to enable the SVM model to capture dynamic trends in anomaly scores, rather than just instantaneous values, the system employs a sliding window technique to perform feature engineering on this labeled anomaly score sequence. For example, for each time point t, the anomaly scores for that time point and the N-1 previous time points are used to form a window, and a feature vector is extracted from this window. This vector can include multiple statistics, such as the current anomaly score, the average score within the window, the maximum score, the score variance, and the slope of the score series growth. Finally, these feature vectors and their corresponding "normal" / "abnormal" labels serve as training samples and are input into the SVM model training algorithm. The training algorithm will automatically learn an optimal decision hyperplane that can best distinguish normal samples from abnormal samples in the feature space; In the online inference (i.e. real-time monitoring) stage, the execution flow of this step is as follows: first, the early warning analysis engine receives the abnormal score values calculated by the LSTM autoencoder module in real time, one by one. Whenever a new abnormal score value arrives, the engine immediately adopts the same sliding window and feature engineering method as in the training stage to construct the feature vector at the current time. Subsequently, the feature vector is input into the already trained SVM model. The SVM model will determine which side of its internal decision hyperplane the feature vector is located on. Finally, the model outputs a pre-defined class label, i.e. the early warning analysis result, according to the determination result. In response to the output label being "abnormal" or a certain early warning level, the system triggers the corresponding alarm mechanism, such as sending an alarm message to the management personnel, highlighting on the monitoring large screen or starting the emergency plan.

[0039] In summary, the groundwater environment monitoring method based on big data according to the embodiments of the present application is illustrated, which first decomposes the complex water quality time series data into three components of trend, season and residual by the STL decomposition technology, so as to effectively separate the inherent periodicity of the groundwater system and the random disturbance. On this basis, the trend and season components are innovatively used as a dynamic macro background to interpret the true meaning of the residual component, combined with the normal disturbance pattern of the LSTM autoencoder deep learning in a specific background, and finally the SVM model makes a warning judgment. In this way, it can effectively adapt to the periodic changes of the groundwater environment, accurately identify the normal water quality fluctuations caused by natural factors, thereby significantly reducing the false positive rate and improving the monitoring sensitivity of real pollution events, and finally achieving accurate dynamic evaluation and reliable warning of the groundwater environment state.

[0040] Further, a groundwater environment monitoring system based on big data is also provided.

[0041] Figure 3 A block diagram of the groundwater environment monitoring system based on big data according to the embodiments of the present application is shown. As shown in Figure 3 The groundwater environment monitoring system based on big data 300 according to the embodiments of the present application includes: a data acquisition module 310 for acquiring water quality time series data from a specific monitoring well; an STL decomposition module 320 for inputting the water quality time series data into the STL decomposition module to obtain trend components, season components and residual components; a water quality residual feature extraction module 330 for extracting a water quality residual feature vector sequence from the residual components with the trend components and season components as background information; an abnormal score calculation module 340 for performing abnormal score calculation based on the LSTM autoencoder on the water quality residual feature vector sequence to obtain an abnormal score value sequence; and an early warning analysis module 350 for inputting the abnormal score value sequence into an early warning analysis engine based on the SVM model to obtain an early warning analysis result.

[0042] As described above, the big data based groundwater environment monitoring system 300 according to the embodiments of the present application can be implemented in various wireless terminals, such as a server with a big data based groundwater environment monitoring algorithm, etc. In one possible implementation, the big data based groundwater environment monitoring system 300 according to the embodiments of the present application can be integrated into a wireless terminal as a software module and / or a hardware module. For example, the big data based groundwater environment monitoring system 300 can be a software module in the operating system of the wireless terminal, or can be an application program developed for the wireless terminal; of course, the big data based groundwater environment monitoring system 300 can also be one of the many hardware modules of the wireless terminal.

[0043] Alternatively, in another example, the big data based groundwater environment monitoring system 300 and the wireless terminal can also be separate devices, and the big data based groundwater environment monitoring system 300 can be connected to the wireless terminal through a wired and / or wireless network, and transmit interactive information in an agreed data format.

[0044] The above has described the embodiments of the present disclosure, the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes are obvious to those skilled in the art without departing from the scope and spirit of the described embodiments. The choice of terms used herein is intended to best explain the principles of the embodiments, practical application or improvement of the technology in the market, or to enable other ordinary skilled in the art to understand the embodiments disclosed herein.

Claims

1. A groundwater environment monitoring method based on big data, characterized in that: include: Obtain water quality time series data from specific monitoring wells; The water quality time series data were input into the STL decomposition module to obtain the trend component, seasonal component and residual component; Taking the trend component and seasonal component as background information, the water quality residual feature vector sequence is extracted from the residual component; The abnormal score of the water quality residual feature vector sequence is calculated based on the LSTM autoencoder to obtain the abnormal score value sequence; The abnormal score value sequence is input into the early warning analysis engine based on the SVM model to obtain the early warning analysis results.

2. The groundwater environment monitoring method based on big data according to claim 1, characterized in that: Inputting the water quality time series data into an STL decomposition module to obtain a trend component, a seasonal component, and a residual component, comprising: the STL decomposition module processes the water quality time series data using the following formula to obtain a trend component, a seasonal component, and a residual component, wherein the formula is: in, is the trend component, For seasonal components, is the residual component.

3. The groundwater environment monitoring method based on big data according to claim 2, characterized in that: Taking the trend component and seasonal component as background information, the water quality residual feature vector sequence is extracted from the residual component, including: The trend component and the seasonal component are concatenated to obtain the background component; The background component and the residual component are implicitly interacted to obtain the water quality residual feature vector sequence.

4. The groundwater environment monitoring method based on big data according to claim 3 is characterized in that: The background component and the residual component are implicitly interacted to obtain the water quality residual feature vector sequence, including: Performing local temporal feature extraction on the background component and the residual component to obtain a sequence of local temporal feature coding vectors of the background component and a sequence of local temporal feature coding vectors of the residual component; Calculate the manifold transmission modulation matrix of the sequence of local temporal feature coding vectors of the background component relative to the sequence of local temporal feature coding vectors of the residual component; Based on the manifold transmission modulation matrix, feature alignment is performed on the sequence of local temporal feature coding vectors of the background component to obtain a sequence of local temporal feature coding vectors after the background component is reshaped; Feature fusion is performed on each group of background component reshaped local time series feature coding vectors and residual component local time series feature coding vectors in the sequence of background component reshaped local time series feature coding vectors and the sequence of residual component local time series feature coding vectors to obtain the water quality residual feature vector sequence.

5. The groundwater environment monitoring method based on big data according to claim 1, characterized in that: The water quality residual feature vector sequence is subjected to anomaly score calculation based on the LSTM autoencoder to obtain an anomaly score value sequence, including: The water quality residual feature vector sequence is input into the trained LSTM autoencoder to obtain the reconstructed water quality residual feature vector sequence; The reconstruction error between each group of corresponding water quality residual feature vectors and the reconstructed water quality residual feature vector in the water quality residual feature vector sequence and the reconstructed water quality residual feature vector sequence is calculated to obtain the abnormal score value sequence.

6. The groundwater environment monitoring method based on big data according to claim 5, characterized in that: Calculating the reconstruction error between each group of corresponding water quality residual feature vectors and the reconstructed water quality residual feature vector in the water quality residual feature vector sequence and the reconstructed water quality residual feature vector sequence, including: calculating the mean square error between each group of corresponding water quality residual feature vectors and the reconstructed water quality residual feature vector as the reconstruction error.

7. A groundwater environment monitoring system based on big data, characterized in that: include: A data acquisition module is used to obtain water quality time series data from a specific monitoring well; STL decomposition module, used to input water quality time series data into the STL decomposition module to obtain trend component, seasonal component and residual component; The water quality residual feature extraction module is used to extract the water quality residual feature vector sequence from the residual component with the trend component and the seasonal component as background information; Anomaly score calculation module, used to calculate the anomaly score of the water quality residual feature vector sequence based on the LSTM autoencoder to obtain an anomaly score value sequence; The early warning analysis module is used to input the abnormal score value sequence into the early warning analysis engine based on the SVM model to obtain the early warning analysis results.

Images