Advanced Geological Prediction Research Articles

GeoPredict-LLM: Intelligent Tunnel Advanced Geological Prediction by Reprogramming Large Language Models

GeoPredict-LLM: Intelligent Tunnel Advanced Geological Prediction by Reprogramming Large Language Models

GeoPredict-LLM: Intelligent Tunnel Advanced Geological Prediction by Reprogramming Large Language Models

GeoPredict-LLM: Intelligent Tunnel Advanced Geological Prediction by Reprogramming Large Language Models

Reliable simulation analysis for high-temperature inrush water hazard based on the digital twin model of tunnel geological environment

In complex mountainous terrains, tunnel construction faces unique challenges from high-temperature water inrush hazards, a systemic risk arising from the interplay of stress, seepage, and temperature fields. Traditional simulation methods, focusing on isolated disaster scenarios, fall short in addressing the multifaceted nature of these risks due to geological ambiguity and data incompleteness. Digital twin technology presents an effective solution to these challenges; however, its core challenge lies in how to utilize digital twin technology for data-model-co-driven simulation analysis of coupled multi-physical fields in situations of incomplete data. This paper introduces a digital twin paradigm for the simulation analysis of water inrush, which significantly enhances efficiency and accuracy through the integration of advanced machine learning and finite element analysis techniques. Specifically, this is achieved by combining a high-precision geological modeling method based on Gaussian Processes (GP) with a parameter calibration method through Gaussian Process-Differential Evolution (GP-DE) back-analysis. Firstly, a voxel structure is utilized to integrate the multi-field attribute features of the tunnel environment. Secondly, through the integration of multi-source advanced geological prediction data, we construct a dynamic digital twin model of the tunnel environment leveraging machine learning techniques. To overcome the issue of low modeling accuracy, the GP is employed, enhancing the exploitation of latent information within multi-source geophysical data. Lastly, we utilize the GP-DE back-analysis method to calibrate the parameters of the tunnel environment, thereby enhancing the precision and reliability of water inrush simulations. The method has been validated through application to a section of an ultra-high-temperature water inrush tunnel in China, featuring a burial depth of 230 meters. The accuracy of the method is corroborated by the monitoring data from the tunnel, supporting dynamic optimization design and safety prevention measures during construction.

Study on InSAR deformation information extraction and stress state assessment in a railway tunnel in a plateau area

Introduction: The study proposes a method for evaluating stress distribution in high-altitude Tibetan Plateau railway tunnels using high-precision radar satellite time-series interferometric synthetic aperture radar technology.Methods: To effectively monitor and prevent geological hazards during the construction process, this method i employed, as it serves as a component of advanced geological prediction and surrounding rock deformation monitoring technology for high-altitude tunnels, particularly in the Dongelu Tunnel of the China–Tibet Railway. The study utilizes time-series interferometric synthetic aperture radar to obtain deformation information for Dongelu Tunnel area between 2022 and 2023 from Sentinel- 1A orbit images. This quantitatively investigates the upper mountain body and line-of-sight direction along the tunnel. The deformation characteristics are correlated with high-frequency and high-precision automated vertical displacement monitoring results, determining the spatiotemporal distribution of tunnel deformation. In this study, a model that determines the vertical stress state of the Dongelu Tunnel under loading near the entrance and evaluates its health status was established.Results: The results show that the surface deformation of the mountain above the tunnel axis develops slowly and is relatively small, with a maximum vertical deformation rate of 1–3 mm/year. The average stress on the tunnel arch is 5.54 MPa, with a fluctuation range of 0.01 MPa. Temporal Q9 changes in various parts of the tunnel are periodic, with maximum fluctuations observed in December 2022. The study reveals inconsistent surface settlement of the tunnel arch and mountain above it, causing minor vertical stress changes. As the tunnel construction progresses, vertical stress variation shows periodicity because of an initial imbalance in internal stress within the mountain. Stress fluctuations near the tunnel entrance occur during the initial excavation phase, gradually diminishing as the project progresses and internal stress stabilizes.Discussion: The proposed tunnel monitoring and stability assessment method can reduce its impact on engineering construction and provide guidance for advanced geological prediction.

Seismic resolution improving by a sequential convolutional neural network.

Thin-bed soft rock is one of the main factors causing large deformations of tunnels. In addition to relying on some innovative construction techniques, detecting thin beds early during surface geological exploration and advanced geological prediction can provide a basis for planning and implementing effective coping measures. The commonly used seismic methods cannot meet the requirement for thin beds detection accuracy. A high-resolution (HR) seismic signal processing method is proposed by introducing a sequential convolutional neural network (SCNN). The deep learning dataset including low-resolution (LR) and HR seismic is firstly prepared through forward modeling. Then, a one-dimension (1D) SCNN architecture is proposed to establish the mapping relationship between LR and HR sequences. Training on the prepared dataset, the HR seismic processing model with high accuracy is achieved and applied to some practical seismic data. The applications on both poststack and prestack seismic data demonstrate that the trained HR processing model can effectively improve the seismic resolution and restore the high-frequency seismic energy so that to recognize the thin-bed rocks.

Exploration of Advanced Geological Prediction for the Double-arch Highway Tunnel in Karst Area

Combined with the construction method of a highway double-arch tunnel in the karst area, a comprehensive advanced geological prediction method combining geological radar and advanced horizontal drilling is proposed, and the comprehensive advanced geological pre- diction method is successfully applied to the construction of a highway double-arch tunnel in a karst area of Guangxi. The result of site con- struction proves that the method has a satisfactory forecasting effect.

Comprehensive Application of Borehole Fine Detection Methods: A Case Study in Shantou Bay Subsea Tunnel

Water inrush disaster is one of the most severe problems during the construction of sea tunnels, primarily due to faults, karst, and weathered zones. Once a water inrush disaster occurs, it can lead to construction delays, traffic disruptions, and major economic losses, as well as potential consequences such as seawater intrusion, casualties, project suspension, and tunnel closure. Thus, advanced geological prediction is indispensable. During the construction of the Shantou Bay subsea tunnel, a sudden water inrush accident occurred in the sea–land transition section. To prevent such incidents and ensure safety, an integrated approach was employed. Firstly, the cross‐hole resistivity method was used to predict water content in front of the tunnel, as it is highly sensitive to water. Subsequently, borehole ground‐penetrating radar was applied to finely characterize the geological structure. By combining these two methods, the size, scale, location, water content, and spatial distribution of water‐bearing structures in front of the tunnel were identified. With the above measures, the Shantou Bay subsea tunnel passed through the detection section successfully. Herein, we present a case study and offer a valuable reference for similar projects concerning subsea tunnel construction.

Deformation and failure characteristics of high-speed tunnels in complex karst areas: a case at the Qilinguan tunnel

The construction of expressway tunnels in karst areas faces many challenges under complex geological conditions. It is of great scientific and engineering significance to study the deformation and failure laws of tunnels and surfaces. Taking the Qilinguan tunnel of the Hubei Expressway as an example, the deformation and failure laws of the tunnel are analyzed when the tunnel passes through the complex karst area. The composition of karst water and surrounding rock was analyzed by inductively coupled plasma mass spectrometry and XRD, and the compression-shear failure model of tunnels in karst areas was proposed according to the regional hydrological and geological conditions. It was found that the thickness of the protective layer and the water pressure were the main factors affecting the deformation and failure of the surrounding rock in this area, and the treatment scheme of this project was put forward accordingly. The geological characteristics of karst areas were explored by advanced geological prediction and advanced geological drilling. The primary support is provided by a steel arch and advanced small pipe grouting. The composite lining is composed of shotcrete as the primary support and molded concrete as the secondary lining. The primary support structure of the flexible support system is adopted in the design to give full play to the bearing capacity of the surrounding rock. After the support measures were adopted, the trend of settlement change gradually slowed down, indicating that the support measures were effective.

Research on the Application of Ground Penetrating Radar in Advanced Geological Prediction of Deep Buried Tunnels

With the development of the social economy and the emergence of a large number of tunneling projects, the importance of over-advance geological forecasting in the safe construction of tunnels has become increasingly obvious, and it has also attracted a lot of attention from the academic community. In this paper, the measured radar data are analyzed to verify the feasibility of ground-penetrating radar in the overtopping geological prediction of deep-buried tunnels and the validity of data characteristics. By analyzing the overtopping geological data of ground-penetrating radar and verifying the results by excavation, the following conclusions can be obtained: in the process of overtopping geological forecasting, ground-penetrating radar has the characteristics of simplicity, convenience, and high accuracy, and the method can make anomalies in advance for the abnormalities in front of the tunnel's palm face, and it can provide accurate and reliable geological information to ensure that the tunnel project can be constructed safely.

Application Comparison of Different Transient Electromagnetic Devices in Water Exploration of Tunnel Advanced Geological Prediction

Detecting the possibility of water inrush in front of tunnel face is always the key of tunnel advanced geological prediction. Because of its sensitivity to groundwater, transient electromagnetic method is gradually being used in water exploration of tunnel advanced geological prediction. However, the current transient electromagnetic theory is established based on the half-space environment. In order to adapt to the detection work in the full-space environment such as tunnels, different transient electromagnetic devices have been improved. The effectiveness of these improved devices still need to be tested in actual engineering projects. In this paper, a tunnel under construction is used as the engineering background, and different transient electromagnetic devices are placed in front of the same tunnel face for detection. The detection results are compared and analyzed with the actual situation of tunnel excavation, which can provide reference for water exploration of tunnel advanced geological prediction.

Excavation and Construction Technology of Diversion Tunnel under Complex Geological Conditions

During the construction of a diversion tunnel, geological problems often include faults, fragile strata, hard rock formations, karst landforms, etc., which may have adverse effects on the excavation and construction of the diversion tunnel. Based on the analysis of the engineering overview, this study designed a new construction technology for the excavation of water diversion tunnels in hard rock layers and high-karst areas. Based on tunnel seismic prediction (TSP) technology to achieve advanced geological prediction, combined with actual geological conditions, construction difficulties are analyzed. Then, detection technology is used to collect two-way travel time, amplitude, and waveform data. By processing and analyzing the detection image, the spatial orientation and length of the main tunnel during the construction of the diversion tunnel are calculated. After completing the construction ventilation and wind, water, and electricity layout, the excavation construction procedure is designed. In the specific excavation design, the tunnel curtain excavation technology, tunnel body excavation and support technology, excavation grouting technology, important unfavorable geological tunnel section excavation technology, upper/lower flat section excavation technology, upper/lower curved section excavation technology, and vertical shaft section excavation technology were elaborated. Finally, a plan was made for the reuse process of slag material and a construction quality control system was established. During the testing process, it was found that the antidamage coefficient of the side wall was above 0.9 after using the technology described in this article. Therefore, it indicates that the excavation construction technology designed in this article can ensure the support capacity of the side wall of the diversion tunnel, which is suitable for the excavation of the main tunnel during the construction of the diversion tunnel.

Evolution mechanism of tunnel water and sand inrush considering water-rich sandy dolomite hazard-causing structures

Water-rich sandy dolomite stratum is prone to water and sand inrush disasters during tunnel construction. It is of great significance to explore its hazard-causing structure and water inrush mechanism for disaster control. The physical and mechanical properties of dolomite samples are tested to reveal the difference between unsanded dolomite and sandy dolomite. Based on the advanced geological prediction and geological sketching, three types of water and sand inrush hazard-causing structures are identified. Furthermore, three types of water and sand inrush mechanisms under different hazard-causing structures are explored by using fluid–solid coupling model test. One is the progressive failure type of water and sand inrush caused by crack coalescence for the broken unsanded dolomite outburst prevention structure, another is the failure type in which the seepage failure of sandy dolomite strips promotes the crack coalescence of unsanded dolomite, and the other is seepage failure type for the overall sandy dolomite outburst prevention structure. Finally, fluid–solid coupling simulation is used to discuss the failure characteristics of outburst prevention structure with different factors. The results show that the critical sandy dolomite area ratio of the three types is 25 % and 75 %. The factors affecting the inrush disaster are ranked as follows: sandy dolomite area ratio > unsanded dolomite fragmentation degree > buried depth > water storage structure pore pressure > water storage structure size. The findings provide valuable reference for disaster control in water-rich sandy dolomite area.

Applied research of comprehensive advance geological prediction in Daluoshan water diversion tunnel

In order to study the accuracy of comprehensive advanced geological prediction methods in tunnel construction projects, this paper takes the Daluoshan Water Diversion Tunnel Project in Wenzhou, Zhejiang Province as the basis of the project, selects a typical section of the water diversion tunnel, and uses Tunnel Seismic Tomography and Ground Penetrating Radar to transmit seismic and electromagnetic waves to the surrounding rock face of the tunnel, and process and interpret the collected signal information. Advanced borehole and drilling techniques are used for verification. The results show that the geological prediction results are consistent with the actual revealed conditions, and the advantages of various technologies can be exerted and mutually verified through advanced geological prediction, which can significantly improve the accuracy of advanced geological prediction in the application of water diversion tunnels and provide reference and basis for later construction, and provide safety assurance.

BIM-based digital platform and risk management system for mountain tunnel construction

During the construction of mountain tunnels, there are often various intricate and mutable potential hazards, the management and control of which are crucial to ensuring the safety of such construction. With the rapid advancement of engineering information technologies, including Building Information Model (BIM), the internet, big data, and cloud computing, dynamic management of mountain tunnel construction will inevitably become a prevailing trend. This paper proposes a new digital approach to realize the informatization and visualization of risk management in mountain tunnel construction, by combining monitoring measurement with advanced geological prediction based on BIM technology. The proposed approach suggests a BIM-based digital platform architecture for mountain tunnel construction, which is comprised of five layers—basic, model, data, application, and user. The integration of these five layers can realize risk management information during the construction of mountain tunnels. In addition, a set of dynamic risk management systems, including risk monitoring, identification, and assessment, can be established based on the digital platform. The digital platform and dynamic risk management system proposed in this paper have certain advantages in the construction of mountain tunnels, providing a new and significant way for the management of safety risks in such construction projects.

A technical study of advanced geological prediction of tunnels under complex geological conditions

Advanced geological prediction, as an indispensable step in tunnel construction, is an essential measure for reducing the occurrence of geological disasters in tunnel construction and disaster losses. To solve intractable technical issues relating to advanced geological prediction of tunnels under complex geological conditions, this research explores construction methods of advanced geological prediction of tunnels under complex geological conditions and relevant specific implementation process by taking tunnels in Maanshan as engineering objects. Furthermore, construction methods applicable to complex geological conditions were proposed to investigate key construction processes of advanced geological prediction. The research can provide reference for similar engineering practices and technology.

Depth Effect of Rock-Breaking Seismic Source by Drilling Jumbo in Subsea Tunnel with the Drill and Blast Method and Its Application Prospects

The drilling source of a drilling jumbo contains a great amount of noise in the construction of a subsea tunnel, which leads to a large prediction error for the conventional source selection method. To address this problem, this paper proposes an optimization method for the source selection of a drilling jumbo. The optimal truth element is selected for the advanced prediction of a subsea tunnel to ensure the safety of the subsea tunnel construction. First, a spectrum analysis of borehole seismic sources with different drilling depths is carried out, the noise interference contained in the seismic source signal at different drilling depths is analyzed, and the propagation law of a borehole seismic wave field at different depths is studied. Second, the deconvolution-cross-correlation method is used to denoise and reconstruct the seismic records of borehole sources at different depths, and a clutter and signal-to-noise ratio analysis of the reconstructed seismic records is carried out. The principle of optimal selection of the pilot signal time window is established to suppress random noise and surface wave interference. Finally, based on the actual project, the proposed method is evaluated. The results show that when using the optimization method of drilling source interception proposed in this paper, when the drilling jumbo is drilled to the deepest place, the selection of the source signal stationary section for advanced geological prediction is the best. The prediction results are basically consistent with the actual excavation situation, verifying the feasibility and effectiveness of the method.

Data-driven real-time advanced geological prediction in tunnel construction using a hybrid deep learning approach

This paper investigates the prediction of geological conditions ahead of tunnel boring machines (TBM) using a hybrid deep learning approach. By integrating graph convolutional network (GCN) and long short-term memory (LSTM) networks, the spatial and temporal features from TBM parameters and geological information are extracted for accurate prediction. The results from the case study indicate that (1) The proposed approach provides estimation with a high accuracy of 0.9986; (2) The past geological information has a significant contribution to the model; (3) The proposed approach outperforms several state-of-the-art methods including support vector machine (SVM), extreme gradient boosting (XGBoost) and LSTM method. The proposed hybrid deep learning approach can be a useful tool that provides reliable estimation of the advanced geological conditions in real-time.

Water Inrush Mechanism of Fault Zone in Karst Tunnel under Fluid-Solid Coupling Field considering Effective Stress

At present, the tunnel construction engineering is increasingly transferring to southwest mountainous areas with complex terrain and geological conditions in China and presents a trend of “large buried depth, long tunnel line, high stress, strong karst, high water pressure, complex structure and frequent disasters.” Taking water inrush disaster of karst tunnel fault zone as the research object, an evolutionary mechanical model of rock damage under the coupling action of stress-seepage is proposed in this paper. Besides, based on Comsol Multiphysics numerical software, the tunnel excavation is simulated, and the stress field, seepage field, and rock damage during the excavation are analyzed; thus, the mechanical mechanism of water inrush disaster from tunnel fault in karst area is obtained. The research results indicate that the tunnel excavation is a dynamic construction process, and the construction disturbance redistributes the original rock stress field and changes the state of seepage field. With the increase of excavation steps, the contour distribution of vertical stress ratio near the tunnel face is a circle shape, indicating that the rock mass is obviously disturbed by excavation, and the ratio of principal stress difference of rock mass at arch crown and bottom plate is large. Besides, the fault fissures expand and penetrate under the influence of tunnel excavation disturbance, increasing the permeability of fault zone in karst tunnel. In addition, the water seepage erosion takes away the granular rock mass, and the lithology becomes more weaker, which makes it possible for the occurrence of water inrush disaster in karst tunnel. Therefore, the advanced geological prediction is important in tunnel construction in karst area. The research results can be treated as an important theoretical basis for the prevention and treatment for water inrush disaster of fault zone in karst tunnel.

Three-Dimensional Quantitative Recognition of Filler Materials Ahead of a Tunnel Face via Time-Energy Density Analysis of Wavelet Transforms

Advanced geological prediction of tunnels has become an indispensable task to ensure the safety and effectiveness of tunnel construction before excavation in karst areas. Geological disasters caused by unfavorable geological conditions, such as karst caves, faults, and broken zones ahead of a tunnel face, are highly sudden and destructive. Determining how to predict the spatial location and geometric size of unfavorable geological bodies accurately is a challenging problem. In order to facilitate a three-dimensional quantitative analysis of the filler material ahead of the tunnel face, a biorthogonal wavelet with short support, linear phase, and highly matching waveform of ground penetrating radar (GPR) wavelet is constructed by lifting a simple and general initial filter on the basis of lifting wavelet theory. A method for a time-energy density analysis of wavelet transforms (TEDAWT) is proposed in accordance with the biorthogonal wavelet. Fifteen longitudinal and horizontal survey lines are used to detect void fillers of different heights. Then, static correction, DC bias, gain, band-pass filtering, and offset processing are performed in the original GPR profile to enhance reflected signals and converge diffraction signals. A slice map of GPR profile is generated in accordance with the relative position of longitudinal and horizontal survey lines in space. The wavelet transform analysis of a single-channel signal of each survey line is performed by adopting the TEDAWT method because of the similar rule of the single-channel signal of GPR on the waveform overlay and the ability of the constructed wavelet basis to highlight the time-frequency characteristics of GPR signals. The characteristic value points of the first and second interfaces of the void fillers can be clearly determined, and the three-dimensional spatial position and geometric sizes of different void fillers can be obtained. Therefore, the three-dimensional visualization of GPR data is realized. Results show that the TEDAWT method has a good practical application effect in the quantitative identification of void fillers, which provides a basis for the interpretation of advanced geological prediction data of tunnels and for the construction decision.

Dynamic Risk Assessment of Karst Tunnel Collapse Based on Fuzzy‐AHP: A Case Study of the LianHuaShan Tunnel, China

Tunnel collapse in the karst tunnel occurs suddenly. Dynamic risk assessment for tunnel collapse is more accurate than static analysis, which is not enough at the stage. The study designs a new questionnaire to establish dynamic risk assessment for karst tunnels collapse, by a fuzzy analytic hierarchy process (F‐AHP) method. The characteristics of the cave, dynamic monitoring, and prediction are fully considered in the assessment to strengthen the karst and dynamic characters: (1) the factors of dynamic risk assessment are selected based on advanced geological prediction, collapse investigation, and theoretical analysis as dynamic and static factors. Dynamic factors are classified as the rationality of advanced geological prediction method, reliability of data, the accuracy of data analysis, and timeliness and effectiveness of forecast information transmission. Karst cave characteristic factors are composed of cave scales, locations, and thickness of rock plate, based on collapse investigation and theoretical analysis to strengthen the character of karst. (2) A new questionnaire is designed in the consulting process to express the relative importance of factors by combining a Saaty scale method and a designed three‐scale method. The judgment matrix by the new questionnaire can satisfy the consistency requirement, which is hard to satisfy in the traditional F‐AHP method. (3) The dynamic risk assessment is carried out on different samples in the Lianhuashan tunnel. By comparing the dynamic assessment results with the occurrence of disasters, the rationality of the assessment is verified.