A geological monitoring and early warning method and system for geological survey

Abstract

The present invention relates to the field of geological monitoring technology, and specifically to a geological monitoring and early warning method and system for geological survey, comprising the following steps: deploying acoustic sensors in the geological survey area, recording the acoustic wave signals generated by crustal movement and fault activity, capturing the acoustic waves within the target frequency range in real time, and simultaneously obtaining groundwater level, ground temperature and terrain deformation data through satellite scanning of the surface, integrating with the acoustic data, and generating a preliminary data set of geological activities. In the present invention, the accuracy of geological anomaly pattern recognition is significantly improved by extracting key acoustic wave data and calculating the correlation between acoustic data and surface changes, introducing nonlinear time series analysis to further analyze the trends and seasonal fluctuations in the data, and performing cascade analysis based on the analysis results, so that the scientific nature of predicting the future direction of geological changes is strengthened, and the automatic comparison of real-time risk assessment with preset thresholds and triggering of alarm mechanisms greatly improves the initiative and timeliness of disaster prevention.

Description

Technical Field

[0001] The present invention relates to the field of geological monitoring technology, and in particular to a geological monitoring and early warning method and system for geological survey. Background Art

[0002] The field of geological monitoring technology mainly involves continuous or regular detection of physical, chemical and biological parameters on the surface or deep layers of the earth to predict and prevent natural disasters and environmental problems, including earthquake monitoring, volcano monitoring, landslide monitoring, and monitoring of groundwater and soil pollution. Through various sensors and monitoring equipment, such as seismometers, inclinometers, GPS and remote sensing technology, data can be obtained in real time and analyzed using models and software tools to predict potential geological activities and disasters.

[0003] Among them, the geological monitoring and early warning method used in geological surveys is mainly used to issue early warning information in a timely manner by monitoring relevant indicators of geological activities, such as ground displacement, seismic activity and other geological changes, so as to reduce the impact of natural disasters such as earthquakes and landslides on human activities. It uses advanced sensing technology and data analysis technology to ensure that it can respond quickly and accurately when geological activities are abnormal, so as to protect the safety of life and property and guide the implementation of relevant safety measures.

[0004] Existing geological monitoring technologies mainly rely on a single type of sensor data, such as seismometers or GPS, and show obvious limitations in data integration and multi-dimensional analysis of the complexity of geological activities. A single data source leads to delayed identification of key indicators such as crustal deformation, affecting the timeliness of disaster warnings. In addition, most existing methods rely on post-analysis for data processing and lack a rapid response mechanism for real-time data streams. In an emergency, warnings may not be issued in a timely manner, thereby increasing the risk of disasters and potential losses. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a geological monitoring and early warning method for geological survey.

[0006] In order to achieve the above object, the present invention adopts the following technical scheme: a geological monitoring and early warning method for geological survey, comprising the following steps:

[0007] S1: Deploy acoustic sensors in the geological survey area to record the acoustic signals generated by crustal movement and fault activity, capture the sound waves within the target frequency range in real time, and obtain groundwater level, ground temperature and terrain deformation data through satellite scanning of the surface, and integrate them with the acoustic data to generate a preliminary data set of geological activities;

[0008] S2: Based on the preliminary data set of geological activities, outliers are screened and excluded, key acoustic wave data of frequency and amplitude are extracted, the correlation between acoustic data and surface changes is calculated, statistical analysis is performed based on the correlation calculation results, abnormal change points are marked, abnormal geological activity trends are identified, and geological anomaly pattern recognition results are generated;

[0009] S3: Based on the preliminary data set of geological activities, extract satellite data, perform nonlinear time series analysis on the data, decompose and extract data trends and seasonal fluctuations, decompose and extract results according to data trends and seasonal fluctuations, perform cascade analysis, predict the direction of potential future geological changes, and obtain geological prediction analysis results;

[0010] S4: Based on the geological anomaly pattern recognition results and the geological prediction analysis results, real-time risk assessment is performed and the risk value is calculated. The risk value is compared with the set warning threshold. When the risk value exceeds the threshold, an alarm is automatically triggered, and the warning information is transmitted to the monitoring station in real time, and the warning notification process is started, and the geological activity monitoring warning record is output.

[0011] As a further solution of the present invention, the steps for obtaining the preliminary data set of geological activities are:

[0012] S111: Deploy broadband acoustic sensors in geological survey areas to capture acoustic signals of crustal movement and fault activity, screen the frequency range associated with crustal activity, and generate raw acoustic monitoring data;

[0013] S112: Simultaneously monitor the same area through satellites, record groundwater level data, use multi-band scanning to obtain surface temperature gradient and terrain deformation data, and generate surface monitoring data;

[0014] S113: Perform comprehensive analysis on the acoustic monitoring raw data and the surface monitoring data, perform data fusion, evaluate the correlation between the two, and generate a preliminary data set of geological activities.

[0015] As a further solution of the present invention, the calculation steps of the correlation between the acoustic data and the surface change are:

[0016] S211: Based on the preliminary data set of geological activities, high-pass filtering is performed to eliminate noise outliers in the data, extract effective sound wave information associated with the geological activities, and generate purified data;

[0017] S212: extracting key sound wave data based on the purified data, recording actual frequency and amplitude values, and generating key sound wave characteristic data;

[0018] S213: Perform regression analysis based on the key acoustic wave feature data, using the formula:

[0019] ;

[0020] Calculate the correlation coefficient between data and surface changes , generate the results of the correlation analysis between acoustic data and surface changes, where Represents the frequency or amplitude data of a sound wave, Represents the corresponding surface change data, and are the means of x and y respectively.

[0021] As a further solution of the present invention, the steps for obtaining the geological anomaly pattern recognition result are:

[0022] S221: performing statistical analysis based on the results of the correlation analysis between the acoustic data and the surface changes, identifying and separating statistically significant outliers, and generating outlier point statistics;

[0023] S222: using the statistical results of the abnormal points, determining data points of potential geological activity anomalies, marking the data points, and generating an abnormal change point data set;

[0024] S223: Combine the abnormal change point data set, analyze the pattern in the data set, and use the formula:

[0025] ;

[0026] Calculate the anomaly score for each point , generate geological anomaly pattern recognition results, where is the jth eigenvalue of the ith data point in the outlier dataset, and are the mean and standard deviation of the jth feature, respectively, and n represents the total number of feature values.

[0027] As a further solution of the present invention, the steps of decomposing and extracting the data trend and seasonal fluctuation are:

[0028] S311: querying the geographical location according to the preliminary data set of geological activities, extracting satellite images of the corresponding time period, and generating preliminary satellite data;

[0029] S312: Based on the preliminary satellite data, nonlinear time series analysis is performed to separate the trend and seasonal components in the data using the formula:

[0030] ;

[0031] Calculate the combined value of seasonal fluctuations and trend changes , generate trend and seasonal analysis results, where A represents the initial amplitude of seasonal fluctuations in the data set, and B represents the baseline value of the trend line. represents the frequency of periodic changes, represents the starting phase of the periodic fluctuation, and t represents the number of days;

[0032] S313: Utilizing the trend and seasonal analysis results, extract key geological activity data, reveal the periodicity and long-term trends of geological changes, and obtain data trend and seasonal fluctuation information.

[0033] As a further solution of the present invention, the steps for obtaining the geological prediction analysis results are:

[0034] S321: Utilizing the data trend and seasonal fluctuation information, combined with geological activity records, to perform layered analysis, overlay time series data layers, optimize data pattern recognition capabilities, and generate layered analysis data;

[0035] S322: Based on the stack analysis data, predict the future geological change trend using the formula:

[0036] ;

[0037] Calculating geological change rates , analyze the potential change direction of future geological activities and generate prediction results, among which, Represents the rate of change of trend data, represents the time interval, p represents the average change determined by historical data, and t represents the number of days;

[0038] S323: Based on the prediction results, key information is extracted and compared with the existing geological monitoring data to verify the accuracy and reliability of the prediction and obtain geological prediction analysis results.

[0039] As a further solution of the present invention, the steps for obtaining the geological activity monitoring and early warning records are:

[0040] S411: Combining the geological anomaly pattern recognition result with the geological prediction analysis result, extracting features through deep learning, and performing pattern recognition to generate a comprehensive analysis result;

[0041] S412: Based on the comprehensive analysis results, the formula is used:

[0042] ;

[0043] Calculate and obtain real-time risk value ,in, represents the standard deviation of the geological dataset, Represents the historical comparison difference value;

[0044] S413: Compare the real-time risk value with a preset threshold value. If the threshold value is exceeded, start the early warning process, send the early warning information to the monitoring station, and establish a geological activity monitoring early warning record.

[0045] A geological monitoring and early warning system for geological survey, comprising:

[0046] The sensor deployment module deploys acoustic sensors in the geological survey area to capture the acoustic signals of crustal movement and fault activity, uses satellites to monitor groundwater level data, surface temperature gradient and terrain deformation data in the same area, performs data fusion, and generates a preliminary data set of geological activities;

[0047] The data analysis module excludes noise anomalies in the data based on the preliminary data set of geological activities, records actual frequency and amplitude values, calculates the correlation coefficient between the data and surface changes, and generates the analysis results of the correlation between acoustic data and surface changes;

[0048] The anomaly recognition module identifies and separates significant anomalies based on the results of the correlation analysis between the acoustic data and the surface changes, determines the data points with potential geological activity anomalies and performs marking processing, and calculates the anomaly score of each point to generate a geological anomaly pattern recognition result;

[0049] The trend analysis module extracts satellite images of the corresponding time period based on the preliminary data set of geological activities, performs nonlinear time series analysis, calculates the comprehensive value of seasonal fluctuations and trend changes, reveals the periodicity and long-term trends of geological changes, and obtains data trends and seasonal fluctuation information;

[0050] The prediction module predicts future geological change trends, analyzes the potential change direction of future geological activities, verifies the accuracy and reliability of the prediction, and obtains geological prediction analysis results based on the data trend and seasonal fluctuation information, combined with geological activity records, and superimposed time series data layers;

[0051] The early warning module combines the geological anomaly pattern recognition results with the geological prediction analysis results, performs feature extraction and pattern recognition, calculates the real-time risk value, and compares it with the preset threshold. If the threshold is exceeded, the early warning process is initiated and the early warning information is sent to the monitoring station to establish a geological activity monitoring and early warning record.

[0052] Compared with the prior art, the advantages and positive effects of the present invention are:

[0053] In the present invention, the accuracy of geological anomaly pattern recognition is significantly improved by extracting key acoustic wave data and calculating the correlation between acoustic data and surface changes. Nonlinear time series analysis is introduced to further analyze trends and seasonal fluctuations in the data. A cascade analysis is performed based on the analysis results to enhance the scientific nature of predicting future geological change directions. The automatic comparison of real-time risk assessment with preset thresholds and the triggering of an alarm mechanism greatly improve the initiative and timeliness of disaster prevention. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a main step flow chart of the present invention;

[0055] Figure 2 A flowchart for obtaining a preliminary data set of geological activities according to the present invention;

[0056] Figure 3 The flowchart of the calculation of the correlation between acoustic data and ground surface changes of the present invention;

[0057] Figure 4 The flowchart of obtaining the geological anomaly pattern recognition result of the present invention;

[0058] Figure 5 A flow chart for extracting the decomposition of data trends and seasonal fluctuations of the present invention;

[0059] Figure 6 A flowchart for obtaining geological prediction analysis results of the present invention;

[0060] Figure 7 The present invention is a flowchart for obtaining geological activity monitoring and early warning records. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0062] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0063] See also Figure 1, a geological monitoring and early warning method for geological exploration, comprising the following steps:

[0064] S1: Deploy acoustic sensors in the geological survey area to record the acoustic signals generated by crustal movement and fault activity, capture the sound waves within the target frequency range in real time, and obtain groundwater level, ground temperature and terrain deformation data through satellite scanning of the surface, and integrate them with the acoustic data to generate a preliminary data set of geological activities;

[0065] S2: Based on the preliminary data set of geological activities, outliers are screened and excluded, key acoustic wave data of frequency and amplitude are extracted, the correlation between acoustic data and surface changes is calculated, statistical analysis is performed based on the correlation calculation results, abnormal change points are marked, abnormal geological activity trends are identified, and geological anomaly pattern recognition results are generated;

[0066] S3: Based on the preliminary data set of geological activities, satellite data are extracted, nonlinear time series analysis is performed on the data, data trends and seasonal fluctuations are decomposed and extracted, and the extraction results are decomposed according to data trends and seasonal fluctuations. Overlay analysis is performed to predict the direction of potential future geological changes and obtain geological prediction analysis results;

[0067] S4: Based on the results of geological anomaly pattern recognition and geological prediction analysis, real-time risk assessment is performed and risk values ​​are calculated. The risk values ​​are compared with the set warning thresholds. When the risk values ​​exceed the thresholds, an alarm is automatically triggered. The warning information is transmitted to the monitoring station in real time, the warning notification process is started, and the geological activity monitoring warning records are output.

[0068] The preliminary data set of geological activities includes acoustic wave data, temperature data and terrain deformation data; the results of geological anomaly pattern recognition include anomaly frequency indicators, anomaly amplitude indicators, correlation scores and anomaly point marking results; the results of geological prediction analysis include baseline trends, seasonal fluctuations and predicted change indicators; the geological activity monitoring and early warning records include risk assessment reports, risk calculation values, early warning thresholds and transmission records.

[0069] See also Figure 2 , the steps to obtain the preliminary data set of geological activities are:

[0070] S111: Deploy broadband acoustic sensors in geological survey areas to capture acoustic signals of crustal movement and fault activity, screen the frequency range associated with crustal activity, and generate raw acoustic monitoring data;

[0071] Based on wide-band acoustic sensors, real-time signal processing technology is used to screen the frequency range related to crustal activity. Acoustic data is captured through the sound wave signals of crustal movement and fault activity, and key geological dynamic signals are recorded. Data is collected synchronously at different depths and locations through multi-channel recording equipment to ensure that each captured data has high reliability and representativeness. Preliminary frequency analysis is performed on the data to identify specific patterns of corresponding geological activities. The process involves complex signal separation and noise elimination technology to ensure that effective information on crustal dynamics is accurately extracted from multi-source signals and that acoustic monitoring raw data is effectively generated.

[0072] S112: Simultaneously monitor the same area through satellites, record groundwater level data, use multi-band scanning to obtain surface temperature gradient and terrain deformation data, and generate surface monitoring data;

[0073] Satellite remote sensing technology is used to synchronously monitor the geological survey area. It has high-resolution scanning capabilities and can carefully record changes in groundwater levels, ground temperatures and terrain deformation. The data obtained by multi-band scanning include infrared, thermal infrared and visible light bands. The data is analyzed in space and time through the geographic information system (GIS) to accurately map the seasonal changes in groundwater levels and daily changes in ground temperature. At the same time, the tiny deformation of the terrain is quantified and its possible impact on the geological structure is analyzed, thereby providing multi-dimensional monitoring data, providing a basis for subsequent geological analysis, and ensuring that the generated surface monitoring data has a high degree of accuracy and application value.

[0074] S113: Combine the original acoustic monitoring data with the surface monitoring data for comprehensive analysis, perform data fusion, evaluate the correlation between the two, and generate a preliminary data set of geological activities;

[0075] First, the format of acoustic data and surface data are unified and time-synchronized to ensure that all data have consistent standards before analysis. Then, statistical methods are used to evaluate the correlation between the two. Through advanced data matching techniques, such as cluster analysis and principal component analysis (PCA), key features of geological activities are extracted from large amounts of data, providing a preliminary theoretical basis for geological analysis and generating a preliminary data set of geological activities, which will directly affect the accuracy of subsequent geological prediction and evaluation work.

[0076] See also Figure 3 , the calculation steps of the correlation between acoustic data and surface changes are:

[0077] S211: Based on the preliminary data set of geological activities, high-pass filtering is performed to eliminate noise outliers in the data, extract effective sound wave information associated with geological activities, and generate purified data;

[0078] A high-pass filtering algorithm is used to exclude noise outliers from the preliminary data set of geological activities and remove the low-frequency part of the signal, thereby retaining the high-frequency data related to the geological activities. In actual operation, the algorithm first defines a frequency cutoff point, and the frequency signals above this point are retained, while those below this point are filtered out. The setting of this cutoff point is determined empirically based on the frequency characteristics of geological sound waves. Usually in the processing of sound wave signals, the high-frequency part contains key information on changes in crustal stress. This is implemented through software such as MATLAB or Python, and its built-in high-pass filtering function can effectively reduce the interference introduced by equipment or environmental factors. The processed data is saved as purified data.

[0079] S212: extracting key sound wave data based on the purified data, recording actual frequency and amplitude values, and generating key sound wave feature data;

[0080] Extract key acoustic wave data from the purified data, including precise values ​​of frequency and amplitude. This tool is specially designed for acoustic wave frequencies that are sensitive to surface changes, and can identify and analyze key features of acoustic wave data. During implementation, the tool screens out key data by setting a specific frequency range. For example, only analyzing sound waves between 500Hz and 2000Hz. This frequency range is usually the most consistent with sound waves generated by geological activities. The extraction of amplitude depends on the intensity of the sound waves. Higher amplitudes indicate possible geological activities. The key is to use technical means to screen and confirm the acoustic wave data that is most likely to represent geological changes, providing a data basis for further correlation analysis and prediction of geological activities. The entire process plays a decisive role in ensuring data accuracy and reliability.

[0081] S213: Perform regression analysis based on key acoustic wave feature data using the formula:

[0082] ;

[0083] Calculate the correlation coefficient between data and surface changes , generate the results of the correlation analysis between acoustic data and surface changes, where Represents the frequency or amplitude data of a sound wave, Represents the corresponding surface change data, and are the average values ​​of x and y respectively;

[0084] Consider a simplified data sample: sound wave amplitude data value x=[2, 3, 4, 5, 6], surface change data value y=[1, 2, 3, 4, 5].

[0085] Calculate the mean of x and y:

[0086]

[0087] Compute the sum of the products of the differences and the sum of the squares of the differences:

[0088]

[0089] Calculate the correlation coefficient :

[0090]

[0091] This result =0.6 indicates that there is a moderately strong positive correlation between the acoustic wave amplitude and the surface change index. This means that as the acoustic wave amplitude increases, the surface change index also tends to increase. In the geological monitoring and early warning system, it is revealed that by monitoring the changes in the acoustic wave amplitude of a specific frequency, the trend of surface changes can be indirectly predicted and monitored, which has practical application value for predicting natural disasters such as earthquakes.

[0092] See also Figure 4 , the steps to obtain the geological anomaly pattern recognition results are:

[0093] S221: Perform statistical analysis based on the results of the correlation analysis between acoustic data and surface changes, identify and separate statistically significant outliers, and generate outlier point statistics;

[0094] When performing statistical analysis to identify outliers, we first use the Z score, which is a standardized method for measuring how far a single data point deviates from the population mean. The Z score is calculated for each data point using the formula: , where x represents the data point value, and are the mean and standard deviation of the data set, respectively. For example, assuming that the mean of a set of data is 50 and the standard deviation is 10, and the value of a data point is 70, then its Z score is 2, indicating that the data point is two standard deviations above the mean. Usually, a Z score greater than 2 is considered an anomaly, which can quickly and accurately identify data points that may represent potential geological anomalies, thus providing a basis for further geological analysis.

[0095] S222: using the statistical results of abnormal points, determining data points of potential geological activity anomalies, marking the data points, and generating an abnormal change point data set;

[0096] The outlier dataset obtained from the statistical analysis is applied to further mark potential abnormal change points of geological activity. In this process, a script is used to automatically mark data points with Z scores exceeding a predetermined threshold (e.g., Z score>2) as abnormal. Each marked abnormal data point is recorded in detail and summarized into an abnormal change point dataset, which is then used for pattern recognition and trend analysis. In this way, it can be ensured that all potentially important abnormal geological activities are effectively captured and included in further analysis, thereby improving the accuracy and efficiency of geological prediction.

[0097] S223: Combine the abnormal change point data set and analyze the pattern in the data set, using the formula:

[0098] ;

[0099] Calculate the anomaly score for each point , generate geological anomaly pattern recognition results, where is the jth eigenvalue of the ith data point in the outlier dataset, and are the mean and standard deviation of the jth feature, respectively, and n represents the total number of feature values;

[0100] The data points of a feature are d=[3, 5, 8, 6, 7], and the average =5.8, standard deviation =1.92. Select data point d=8 and calculate its anomaly score:

[0101] ;

[0102] This value indicates that the data point d=8 has a high degree of anomaly. When such calculations are performed for all data points, points with high anomaly scores can be identified. These points may represent key areas of abnormal patterns of geological activity, helping to better understand and predict potential geological changes.

[0103] See also Figure 5 , the steps for decomposing and extracting data trends and seasonal fluctuations are:

[0104] S311: querying the geographical location based on the preliminary data set of geological activities, extracting satellite images of the corresponding time period, and generating preliminary satellite data;

[0105] Based on the preliminary data set of geological activities, query the satellite images of the geographical location and time period related to this data, search in the observation satellite database, and use time tags and geographic coding systems to locate specific satellite data sets. In this process, refine the geological activity characteristics corresponding to each geographical location, so as to accurately match the satellite data in the relevant time period. Use high-resolution satellite imaging technology to ensure that the collected image data is clear and can effectively reflect the slight changes in geological activities. The data is preliminarily analyzed through the geographic information system, combining geographic and time information with satellite image data to provide necessary input for the next step of in-depth analysis and generate preliminary satellite data.

[0106] S312: Based on preliminary satellite data, nonlinear time series analysis is performed to separate the trend and seasonal components in the data using the formula:

[0107] ;

[0108] Calculate the combined value of seasonal fluctuations and trend changes , generate trend and seasonal analysis results, where A represents the initial amplitude of seasonal fluctuations in the data set, and B represents the baseline value of the trend line. represents the frequency of periodic changes, represents the starting phase of the periodic fluctuation, and t represents the number of days;

[0109] Parameter A represents the initial amplitude of seasonal fluctuations in the data set, which is usually obtained by comparing the maximum and minimum values ​​in a specific time period. Assume that A=5; B represents the baseline value of the trend line, which is obtained by performing linear regression analysis on long time series data. Assume that B=0.3; is the frequency of periodic changes, which can be determined by spectrum analysis, assuming , representing a one-year cycle; is the starting phase of the periodic fluctuation, usually set to the phase of the data starting point. Assume =0; time t represents the number of days since the start of the project. If we calculate the 100th day , substituting t=100 into the formula, the calculation process is:

[0110] ;

[0111] The results show that on the 100th day, the comprehensive value of seasonal fluctuations and trend changes extracted through analysis was 0.354, which reflects the intensity and characteristics of geological activities at a specific point in time and provides an important numerical basis for further geological analysis and prediction model construction.

[0112] S313: Using trend and seasonal analysis results, extract key geological activity data, reveal the periodicity and long-term trends of geological changes, and obtain data trend and seasonal fluctuation information;

[0113] Using the trend and seasonal analysis results obtained from the analysis, we further refine the extraction of key geological activity data to ensure that the data obtained accurately reflects the periodicity and long-term trends of geological changes. The results of time series analysis are used for model training, and the model parameters are optimized through machine learning algorithms. Various geological activity factors, such as the speed of crustal movement and the frequency of seismic activity, are comprehensively considered. Parameters and variables are input into the prediction model, and statistical analysis methods are used to verify and correct the trends. The final model can provide a scientific basis for the prediction of future geological activities and obtain the final data trend and seasonal fluctuation information.

[0114] See also Figure 6 , the steps to obtain geological prediction analysis results are:

[0115] S321: Using data trend and seasonal fluctuation information, combined with geological activity records, to conduct layered analysis, superimpose time series data layers, optimize the ability to identify data patterns, and generate layered analysis data;

[0116] During the cascade analysis process, data sets obtained from different satellite sensors and time points are used to integrate the characteristics of each time series through a multi-layer perceptron network model. The model training uses the gradient descent method to adjust the weights and biases to ensure that the high-dimensional features of the data are effectively identified and used for trend prediction, thereby improving the model's recognition accuracy for complex patterns of geological activities. The cascade analysis data not only contains geological activity information at a single time point, but also integrates long-term data trends, providing a more accurate and comprehensive analysis method for predicting future geological activity trends.

[0117] S322: Based on the cascade analysis data, predict the future geological change trend using the formula:

[0118] ;

[0119] Calculating geological change rates , analyze the potential change direction of future geological activities and generate prediction results, among which, Represents the rate of change of trend data, represents the time interval, p represents the average change determined by historical data, and t represents the number of days;

[0120] Assuming that from time arrive The geological activity index changes from 3.5 to 5.0 with a time interval of 2 years. , p is the average rate of change obtained from historical data analysis, assumed to be 0.5. Substitute the value into the formula for calculation:

[0121] ;

[0122] The results show that the prediction model estimates the cubic root of the future annual geological change rate to be approximately 0.96, which reflects the growth trend of geological activities and the possible rate of change.

[0123] S323: extract key information based on the prediction results, and compare the key information with the existing geological monitoring data to verify the accuracy and reliability of the prediction, and obtain the geological prediction analysis results;

[0124] Key information is extracted from the prediction results and compared with the existing geological monitoring data. A multivariate linear regression model is used to combine historical data of geological activities with newly acquired satellite data for trend comparative analysis. The model takes into account the influence of multiple variables such as geological structure changes, climate change and human activities to ensure the accuracy and reliability of the prediction. The final geological prediction analysis results reflect the potential direction of geological changes in the future. The results provide a scientific basis for regional geological safety monitoring and help decision makers formulate more effective response measures.

[0125] See also Figure 7 , the steps to obtain geological activity monitoring and early warning records are:

[0126] S411: Integrate geological anomaly pattern recognition results and geological prediction analysis results, extract features through deep learning, and perform pattern recognition to generate comprehensive analysis results;

[0127] Collect and integrate the generated comprehensive geological anomaly pattern recognition results and geological prediction analysis results, and perform feature extraction and pattern recognition through a deep learning model. The deep learning model uses a multi-layer perceptron to analyze different levels of geological data. The process includes an input layer receiving geological anomaly data and a hidden layer processing data through an activation function. The training process of the model includes forward propagation and back propagation, where forward propagation is used to predict output results and back propagation is used to optimize network weights to reduce prediction errors. Through this model, geological anomaly patterns can be more accurately identified and possible future changes can be predicted, thereby generating comprehensive analysis results.

[0128] S412: Based on the comprehensive analysis results, the formula is used:

[0129] ;

[0130] Calculate and obtain real-time risk value ,in, represents the standard deviation of the geological dataset, Represents the historical comparison difference value;

[0131] Represents the strength of geological anomaly indicators, which is obtained by calculating the standard deviation of current and historical geological data. For example, if the standard deviation of the current geological data set is 3.5, this can be regarded as =3.5; Represents the historical comparison difference, which is obtained by calculating the difference between the current geological data and the historical average data. Assuming that the historical data average is 2.0 and the current observation value is 4.5, then =4.5-2.0=2.5; Substitute the specific value into the formula, and the calculation process is as follows:

[0132] ;

[0133] The results show that the current geological risk assessment value is -3.30, which means that the geological conditions are relatively stable and do not exceed the preset risk threshold.

[0134] S413: Compare the real-time risk value with the preset threshold value. If the threshold value is exceeded, the early warning process is initiated, and the early warning information is sent to the monitoring station to establish a geological activity monitoring and early warning record;

[0135] Compare the real-time risk value with the preset threshold, and determine whether to activate the early warning system through comparative analysis. If the real-time risk value calculation result exceeds the preset risk threshold, the system will automatically activate the alarm and send the early warning information to the monitoring station through an encrypted secure communication protocol. This process involves the selection of encryption mechanism, encryption processing of data, transmission of encrypted data, and decryption process of the receiving station to ensure the security and timeliness of information. At the same time, the system will record related events in the geological activity monitoring and early warning system, provide real-time monitoring and rapid response for possible geological activities, and establish geological activity monitoring and early warning records.

[0136] A geological monitoring and early warning system for geological survey, comprising:

[0137] The sensor deployment module deploys acoustic sensors in the geological survey area to capture the acoustic signals of crustal movement and fault activity, uses satellites to monitor groundwater level data, surface temperature gradient and terrain deformation data in the same area, performs data fusion, and generates a preliminary data set of geological activities;

[0138] The data analysis module is based on the preliminary data set of geological activities, excludes noise anomalies in the data, records the actual frequency and amplitude values, calculates the correlation coefficient between the data and the surface changes, and generates the correlation analysis results between the acoustic data and the surface changes;

[0139] The anomaly recognition module identifies and separates significant anomalies based on the correlation analysis results between acoustic data and surface changes, determines data points with potential geological activity anomalies and marks them, and calculates the anomaly score of each point to generate geological anomaly pattern recognition results;

[0140] The trend analysis module extracts satellite images of the corresponding time period based on the preliminary data set of geological activities, performs nonlinear time series analysis, calculates the comprehensive value of seasonal fluctuations and trend changes, reveals the periodicity and long-term trends of geological changes, and obtains data trends and seasonal fluctuation information;

[0141] The prediction module predicts future geological change trends based on data trends and seasonal fluctuation information, combines geological activity records, and superimposes time series data layers to analyze the potential change direction of future geological activities, verify the accuracy and reliability of the prediction, and obtain geological prediction analysis results;

[0142] The early warning module integrates the results of geological anomaly pattern recognition and geological prediction analysis, performs feature extraction and pattern recognition, calculates the real-time risk value, and compares it with the preset threshold. If the threshold is exceeded, the early warning process is initiated and the early warning information is sent to the monitoring station to establish a geological activity monitoring and early warning record.

[0143] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A geological monitoring and early warning method for geological exploration, characterized in that: The following steps are involved: S1: Deploy acoustic sensors in the geological survey area to record the acoustic signals generated by crustal movement and fault activity, capture the sound waves within the target frequency range in real time, and obtain groundwater level, ground temperature and terrain deformation data through satellite scanning of the surface, and integrate them with the acoustic data to generate a preliminary data set of geological activities; S2: Based on the preliminary data set of geological activities, outliers are screened and excluded, key acoustic wave data of frequency and amplitude are extracted, the correlation between acoustic data and surface changes is calculated, statistical analysis is performed based on the correlation calculation results, abnormal change points are marked, abnormal geological activity trends are identified, and geological anomaly pattern recognition results are generated; S3: Based on the preliminary data set of geological activities, extract satellite data, perform nonlinear time series analysis on the data, decompose and extract data trends and seasonal fluctuations, decompose and extract results according to data trends and seasonal fluctuations, perform cascade analysis, predict the direction of potential future geological changes, and obtain geological prediction analysis results; S4: Combining the geological anomaly pattern recognition results and the geological prediction analysis results, real-time risk assessment is performed and risk values ​​are calculated, which are compared with the set warning thresholds. When the risk value exceeds the threshold, an alarm is automatically triggered, and the warning information is transmitted to the monitoring station in real time, and the warning notification process is started, and the geological activity monitoring warning record is output; The steps for decomposing and extracting the data trend and seasonal fluctuation are as follows: S311: querying the geographical location according to the preliminary data set of geological activities, extracting satellite images of the corresponding time period, and generating preliminary satellite data; S312: Based on the preliminary satellite data, nonlinear time series analysis is performed to separate the trend and seasonal components in the data using the formula: ； Calculate the combined value of seasonal fluctuations and trend changes , generate trend and seasonality analysis results, where represents the initial amplitude of seasonal fluctuations in the dataset, Represents the baseline value of the trend line, represents the frequency of periodic changes, represents the starting phase of the periodic fluctuation, Indicates the number of days; S313: extract key geological activity data using the trend and seasonal analysis results, reveal the periodicity and long-term trend of geological changes, and obtain data trend and seasonal fluctuation information; The steps for obtaining the geological prediction analysis results are as follows: S321: Utilizing the data trend and seasonal fluctuation information, combined with geological activity records, to perform layered analysis, overlay time series data layers, optimize data pattern recognition capabilities, and generate layered analysis data; S322: Based on the stack analysis data, predict the future geological change trend using the formula: ； Calculating geological change rates , analyze the potential change direction of future geological activities and generate prediction results, among which, Represents the rate of change of trend data, represents the time interval, represents the average change determined by historical data, Indicates the number of days; S323: Based on the prediction results, key information is extracted and compared with the existing geological monitoring data to verify the accuracy and reliability of the prediction and obtain geological prediction analysis results.

2. The geological monitoring and early warning method for geological exploration according to claim 1, characterized in that: The steps for obtaining the preliminary data set of geological activities are as follows: S111: Deploy broadband acoustic sensors in geological survey areas to capture acoustic signals of crustal movement and fault activity, screen the frequency range associated with crustal activity, and generate raw acoustic monitoring data; S112: Simultaneously monitor the same area through satellites, record groundwater level data, use multi-band scanning to obtain surface temperature gradient and terrain deformation data, and generate surface monitoring data; S113: Perform comprehensive analysis on the acoustic monitoring raw data and the surface monitoring data, perform data fusion, evaluate the correlation between the two, and generate a preliminary data set of geological activities.

3. The geological monitoring and early warning method for geological exploration according to claim 2, characterized in that: The calculation steps of the correlation between the acoustic data and the surface changes are: S211: Based on the preliminary data set of geological activities, high-pass filtering is performed to eliminate noise outliers in the data, extract effective sound wave information associated with the geological activities, and generate purified data; S212: extracting key sound wave data based on the purified data, recording actual frequency and amplitude values, and generating key sound wave characteristic data; S213: Perform regression analysis based on the key acoustic wave feature data, using the formula: ； Calculate the correlation coefficient between data and surface changes , generate the results of the correlation analysis between acoustic data and surface changes, where Represents the frequency or amplitude data of a sound wave, Represents the corresponding surface change data, and They are and The average value of .

4. The geological monitoring and early warning method for geological exploration according to claim 3 is characterized in that: The steps for obtaining the geological anomaly pattern recognition result are as follows: S221: performing statistical analysis based on the results of the correlation analysis between the acoustic data and the surface changes, identifying and separating statistically significant outliers, and generating outlier point statistics; S221: using the statistical results of the abnormal points, determining data points of potential geological activity anomalies, marking the data points, and generating an abnormal change point data set; S223: Combine the abnormal change point data set, analyze the pattern in the data set, and use the formula: ； Calculate the anomaly score for each point , generate geological anomaly pattern recognition results, where It is the first The data point eigenvalues, and They are The mean and standard deviation of the features, Represents the total number of eigenvalues.

5. The geological monitoring and early warning method for geological exploration according to claim 1, characterized in that: The steps for obtaining the geological activity monitoring and early warning records are as follows: S411: Combining the geological anomaly pattern recognition result with the geological prediction analysis result, extracting features through deep learning, and performing pattern recognition to generate a comprehensive analysis result; S412: Based on the comprehensive analysis results, the formula is used: ； Calculate and obtain real-time risk value ,in, represents the standard deviation of the geological dataset, Represents the historical comparison difference value; S413: Compare the real-time risk value with a preset threshold value. If the threshold value is exceeded, start the early warning process, send the early warning information to the monitoring station, and establish a geological activity monitoring early warning record.

6. A geological monitoring and early warning system for geological survey, characterized in that: The system is used to execute the geological monitoring and early warning method for geological survey according to any one of claims 1 to 5, comprising: The sensor deployment module deploys acoustic sensors in the geological survey area to capture the acoustic signals of crustal movement and fault activity, uses satellites to monitor groundwater level data, surface temperature gradient and terrain deformation data in the same area, performs data fusion, and generates a preliminary data set of geological activities; The data analysis module excludes noise anomalies in the data based on the preliminary data set of geological activities, records actual frequency and amplitude values, calculates the correlation coefficient between the data and surface changes, and generates the analysis results of the correlation between acoustic data and surface changes; The anomaly recognition module identifies and separates significant anomalies based on the results of the correlation analysis between the acoustic data and the surface changes, determines the data points with potential geological activity anomalies and performs marking processing, and calculates the anomaly score of each point to generate a geological anomaly pattern recognition result; The trend analysis module extracts satellite images of the corresponding time period based on the preliminary data set of geological activities, performs nonlinear time series analysis, calculates the comprehensive value of seasonal fluctuations and trend changes, reveals the periodicity and long-term trends of geological changes, and obtains data trends and seasonal fluctuation information; The prediction module predicts future geological change trends, analyzes the potential change direction of future geological activities, verifies the accuracy and reliability of the prediction, and obtains geological prediction analysis results based on the data trend and seasonal fluctuation information, combined with geological activity records, and superimposed time series data layers; The early warning module combines the geological anomaly pattern recognition results with the geological prediction analysis results, performs feature extraction and pattern recognition, calculates the real-time risk value, and compares it with the preset threshold. If the threshold is exceeded, the early warning process is initiated and the early warning information is sent to the monitoring station to establish a geological activity monitoring and early warning record.

Images