Accurately identifying and predicting long-term deformation of tunnel surrounding rock is crucial for the stability assessment and safety control of underground engineering. However, conventional prediction approaches are often limited by idealized assumptions and single modeling frameworks, which hinders their ability to achieve high-precision forecasts. Utilizing over 8 years of deformation monitoring data collected from a drill-and-blast-excavated experimental tunnel at the Beishan exploration tunnel test platform, this study proposes a novel hybrid forecasting model ALA–BiTG by integrating the Artificial Lemming Algorithm (ALA), Bidirectional Temporal Convolutional Network (BiTCN), and Bidirectional Gated Recurrent Unit (BiGRU). In the proposed model, the BiTCN captures long-range temporal dependencies and bidirectional patterns in time-series data, the BiGRU enhances bidirectional temporal dynamics, and the ALA optimizes the hyperparameter configuration of the BiTG subnetwork. The results demonstrate that the proposed ALA–BiTG model significantly outperforms benchmark models including BiTG, CNN-LSTM-ATT, BiGRU, and LSTM on the testing set, achieving a Coefficient of Determination (R2) of 0.971 and a Root Mean Square Error (RMSE) of 0.0016. Furthermore, comparative experiments with several mainstream metaheuristic optimization algorithms reveal that ALA achieves superior performance in convergence speed, computational efficiency, and optimization accuracy, demonstrating its effectiveness and applicability in complex engineering time-series modeling. Finally, based on existing time-series data, reliable prediction of the deformation pattern of surrounding rock in the next 1000 days can be achieved.
Radionuclide pollution, driven by the rapid development of nuclear energy, has emerged as a critical environmental concern. Effectively managing radioactive nuclide pollutants to mitigate their impact on the ecological environment and human health is an urgent challenge. Bentonite, a naturally occurring mineral, is known for its strong adsorption capacity due to its unique mineral composition and structure, showing significant potential in nuclear waste management and environmental remediation. Its TOT layered structure, high ion exchange capacity, and large surface area enable effective adsorption of various radioactive nuclides, such as uranium (U), strontium-90 (90Sr), cesium-137 (137Cs), and selenium-79 (79Se), playing a vital role in water pollution remediation and nuclear waste isolation. However, its adsorption performance is influenced by inherent physical-chemical properties and environmental conditions. Radiation exposure, especially from ionizing radiation (alpha, beta, and gamma), can significantly alter bentonite's structure, reducing its adsorption capacity, swelling behavior, and long-term stability. Significant advancements have been made in modifying bentonite. Modification techniques such as acid-base treatment, composite material enhancement, surface functionalization, and the addition of radiation-shielding additives have improved bentonite's adaptability and performance. This study reviews the current state of bentonite and its modified derivatives for radionuclide adsorption, examines their adsorption mechanisms and modification strategies, analyzes influencing factors, and explores potential applications in future nuclear waste management and environmental remediation. By optimizing its adsorption behavior and modification technologies, bentonite is expected to provide safer, more efficient, and sustainable solutions for controlling radioactive pollution, contributing to global nuclear pollution governance.
As thermal infrared remote sensing advances toward higher spectral and spatial resolutions, the need for precise surface parameters is becoming increasingly important for earth observation applications. However, effective retrieval remains fundamentally challenging due to degraded spectral quality caused by narrow bandwidths of thermal infrared hyperspectral imagers, atmospheric line absorption interference, and limitations in sensor manufacturing. To address this, this study introduces a Noise-Resilient Atmospheric Compensation with Temperature and Emissivity Separation (NRAC-TES) method, where the noise-resistant capability is mainly achieved through the NRAC module during the atmospheric compensation (AC) stage. The robust retrieval strategy uses data-model correlations constrained by atmospheric parameter features, enabling adaptive adjustment of model parameters to match real-world noisy data and reducing biases caused by spectral noise in at-sensor radiance. The temperature and emissivity separation of ASTER-TES incorporates an atmospheric downwelling radiance lookup table, allowing direct retrieval of land surface temperature and emissivity without needing prior surface-atmospheric information. Ground validation experiments on Hypercam-LW demonstrate that the proposed NRAC-TES achieves an AC accuracy of 1.2 K for ground-leaving radiance, with corresponding errors of 1.2 K and 0.025 for LST and LSE, respectively. Additionally, comparison with traditional methods like MODTRAN-TES, ICCAAC-TES, and FSW-TES, based on airborne datasets from HyTES and TASI, highlights the importance and effectiveness of the noise-resilient design incorporated in our approach.
A subway station is a crucial part of a city's subway system, and its recovery following an earthquake can significantly impact the overall resilience of the entire system. However, the post-earthquake repair of underground subway stations is complex, time-consuming, and costly, and the existing seismic resilience evaluation methods based on superstructures cannot be directly applied to underground structures. Therefore, this study builds upon previous fragility research, introducing the economic loss correction factor lambda L, i under different seismic performance levels and the recovery time correction factor lambda t to account for the unique challenges of postearthquake repair in underground stations. This approach enhances the resilience evaluation method for underground station structures, analyzing the influence of recovery functions and site classifications on their resilience. The results indicated that the revised resilience evaluation method, which accounts for the particularities of economic loss and recovery time, can accurately assess the resilience loss of underground station structures. The correction factor lambda t should be determined based on the structural form, specifically, lambda t =1.7 for a one-story, two-span structure, and lambda t = 4.0 for a two-story, three-span structure. Resilience loss is highly dependent on site classification and recovery strategies, with stations located on harder sites exhibiting lower resilience loss. Additionally, stations employing a rapid recovery strategy (exponential recovery) demonstrate reduced resilience loss.
The long-term strength of rocks under high-temperature and high-pressure conditions is crucial for assessing the stability of high-level radioactive waste disposal facilities. This study investigates the thermomechanical behavior of Beishan granite, a candidate host rock for Chinese high-level radioactive waste repository, under coupled thermal-mechanical loading. A series of triaxial direct shear creep tests integrated with acoustic emission monitoring were conducted to analyze the damage evolution and failure mechanisms of the rock. Results reveal that as temperature increases from 30 degrees C to 150 degrees C, the proportion of tensile failure in the granite increases from 29.03 % to 51.36 %. A thermo-mechanically coupled viscoelastic damage constitutive model is developed to accurately capture the time-dependent mechanical response of granite under triaxial direct shear. After validation against experimental data, the model is implemented into a finite element framework via a user subroutine to predict the long-term stability of an high-level radioactive waste disposal unit. Furthermore, fuzzy set theory was applied to optimize the layout parameters of the disposal unit, leading to an enhanced safety and efficiency profile; the optimal layout is determined with a canister number (NC) to canister spacing (SC) to unit spacing (SI) ratio of 1:3:10. These results provide valuable insights into the thermo-mechanical behavior of granite and offer a practical tool supporting the design and safety evaluation of deep geological repositories, thereby facilitating the sustainable development of nuclear energy.
