Shield tunnels in operation are often affected by complex geological conditions, environmental factors, and structural aging, leading to cumulative damage in the segments and, consequently, increased deformation that compromises structural safety. To investigate the deformation behavior of tunnel linings under random damage conditions, this study integrates finite element numerical simulation with deep learning techniques to analyze and predict the deformation of shield tunnel segments. First, a refined three-dimensional finite element model was established, and a random damage modeling method was developed to simulate the deformation evolution of tunnel segments under different damage ratios. Additionally, a statistical analysis was conducted to assess the uncertainty in deformation caused by random damage. Furthermore, this study introduces a convolutional neural network (CNN) surrogate model to enable the rapid prediction of shield tunnel deformation under random damage conditions. The results indicate that as the damage ratio increases, both the mean deformation and its variability progressively rise, leading to increased deformation instability, demonstrating the cumulative effect of damage on segment deformation. Moreover, the 1D-CNN surrogate model was trained using finite element computation results, and predictions on the test dataset showed excellent agreement with FEM calculations. The surrogate model achieved a correlation coefficient (R2) exceeding 0.95 and an RMSE below 0.016 mm, confirming its ability to accurately predict the deformation of tunnel segments across different damage conditions. To the best of our knowledge, the finite-element-deep-learning hybrid approach proposed in this study provides a valuable theoretical foundation for predicting the deformation of in-service shield tunnels and assessing structural safety, offering scientific guidance for tunnel safety evaluation and damage repair strategies.

Land subsidence (LS) and pipe collapse (PC) as the major types of geomorphologic hazards lead to noticeable changes in landscape alterations, land damage, loss of soil and water, surface erosion, and sediment buildup in affected areas. To overcome this, the susceptibility to LS and CP was investigated using three deep learning convolutional neural network (DL-CNN) architectures, including Res-Net, AlexNet, and VGG-Network. We used various predictor variables, and then, trained and tested our DL-CNN models using ReLu, Cross-Entropy, and Adam as activation, loss, and optimization functions, respectively. Our findings showed that DL-CNN models achieved an overall accuracy of 0.9836, 0.9721, and 0.9642 for the Res-Net, AlexNet, and VGG-Network, respectively, for CP sensitivity detection. In addition, the Res-Net, AlexNet, and VGG-Network with an overall accuracy of 0.9698, 0.9654, and 0.9519, respectively, showed satisfying performances for LS detection. We also applied univariate summary statistics, including L(r), the pair correlation function (g(r)), and the O-ring function (O(r)), to investigate the spatial pattern and distribution of CP and LS. The L(r) function graph showed that the spatial patterns of CP and LS were clustered across all the investigated distance scales. The value of this function fell outside the Monte Carlo range, indicating that the accumulation of CP and LS at the mentioned distance scale was statistically significant. The results of the O(r) function for the distribution pattern of CP in the study area indicated that this phenomenon was mostly distributed next to each other, implying the facilitating effect of CP on the creation and expansion of each other across all the investigated distance scales. Similarly, the univariate function g(r) also showed the dispersed distribution of subsidence LS at all distances next to each other. In summary, the results of this research revealed that much of the study area was susceptible to CP and LS. The proposed methodology and findings of this study would be useful for land managers, stakeholders, and researchers.

Geomechanical assessment using coupled reservoir-geomechanical simulation is becoming increasingly important for analyzing the potential geomechanical risks in subsurface geological developments. However, a robust and efficient geomechanical upscaling technique for heterogeneous geological reservoirs is lacking to advance the applications of three-dimensional (3D) reservoir-scale geomechanical simulation considering detailed geological heterogeneities. Here, we develop convolutional neural network (CNN) proxies that reproduce the anisotropic nonlinear geomechanical response caused by lithological heterogeneity, and compute upscaled geomechanical properties from CNN proxies. The CNN proxies are trained using a large dataset of randomly generated spatially correlated sand-shale realizations as inputs and simulation results of their macroscopic geomechanical response as outputs. The trained CNN models can provide the upscaled shear strength (R-2 > 0.949), stress-strain behavior (R-2 > 0.925), and volumetric strain changes (R-2 > 0.958) that highly agree with the numerical simulation results while saving over two orders of magnitude of computational time. This is a major advantage in computing the upscaled geomechanical properties directly from geological realizations without the need to perform local numerical simulations to obtain the geomechanical response. The proposed CNN proxy-based upscaling technique has the ability to (1) bridge the gap between the fine-scale geocellular models considering geological uncertainties and computationally efficient geomechanical models used to assess the geomechanical risks of large-scale subsurface development, and (2) improve the efficiency of numerical upscaling techniques that rely on local numerical simulations, leading to significantly increased computational time for uncertainty quantification using numerous geological realizations. (c) 2024 Institute of Rock and Soil Mechanics, Chinese Academy of Sciences. Production and hosting by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/ licenses/by-nc-nd/4.0/).

Landslides are a prevalent natural hazard in West Bengal, India, particularly in Darjeeling and Kurseong, resulting in substantial socio-economic and physical consequences. This study aims to develop a hybrid model, integrating a Genetic-based Random Forest (GA-RF) and a novel Self-Attention based Convolutional Neural Network and Long Short-term Memory (SA-CNN-LSTM), for accurate landslide susceptibility mapping (LSM) and generate landslide vulnerability-building map in these regions. To achieve this, we compiled a database with 1830 historical data points, incorporating a landslide inventory as the dependent variable and 32 geoenvironmental parameters from Remote Sensing (RS) and Geographic Information Systems (GIS) layers as independent variables. These parameters include features like topography, climate, hydrology, soil properties, terrain distribution, radar features, and anthropogenic influences. Our hybrid model exhibited superior performance with an AUC of 0.92 and RMSE of 0.28, outperforming standalone SA-CNN-LSTM, GA-RF, RF, MLP, and TreeBagger models. Notably, slope, Global Human Modification (gHM), Combined Polarization Index (CPI), distances to streams and roads, and soil erosion emerged as key layers for LSM in the region. Our findings identified around 30% of the study area as having high to very high landslide susceptibility, 20% as moderate, and 50% as low to very low. The vulnerability-building map for 244,552 building footprints indicated varying landslide risk levels, with a significant proportion (27.74%) at high to very high risk. Our model highlighted high-risk zones along roads in the northeastern and southern areas. These insights can enhance landslide risk management in Darjeeling and Kurseong, guiding sustainable strategies for future damage qualification.

Machine learning (ML) algorithms are increasingly applied to structure health monitoring (SHM) problems. However, their application to pile damage detection (PDD) is hindered by the complexity of the problem. A novel multi-sensor pile damage detection (MSPDD) method is proposed in this paper to extend the application of ML algorithms in the automatic identification of PDD. The time-series signals collected by multiple sensors during the pile integrity test are first processed by the traveling wave decomposition (TWD) theory and are then input into a hybrid one-dimensional (1D) convolutional and recurrent neural network. The hybrid neural network can achieve the automatic multi-task identification of pile damage detection based on the time series of MSPDD results. Finally, the analytical solution-based sample set is utilized to evaluate the performance of the proposed hybrid model. The outputs of the multi-task learning framework can provide a detailed description of the actual pile quality and provide strong support for the classification of pile quality as well.

This study introduces a cutting-edge, high-resolution tool leveraging the predictive prowess of convolutional neural networks to advance the field of hazard assessment in urban pluvial flooding scenarios. The tool uniquely accounts for the high heterogeneity of urban space and the potential impact of complex climate scenarios, which are often underestimated by traditional data-reliant methods. Employing Shenzhen as a case study, the model showcased superior accuracy, resilience, and interpretability, illuminating potential flood hazards. The performance analysis shows that the model can accurately predict the vast majority of urban flood depths, but has errors in extreme flood predictions (depths greater than 35 cm). Findings underscore escalating flood impacts under enhanced scenario loads, with western and central Shenzhen-regions rife with construction-highlighted as particularly vulnerable. Under the most severe matrix scenario (Scenario 25), economic losses are estimated to be about $25,484 million. These commercial and residential hotspots are anticipated to suffer maximum economic loss, with these two areas accounting for 39.6% and 25.1% of the total losses, necessitating reinforced mitigation efforts, especially during extreme rainfall events and high soil saturation levels. In addition, the flooding control strategies should prioritize the reduction of flood inundation areas and integrate functionally oriented land use characteristics in their development. By aiding in the precise identification of flood-prone areas, this research expedites the development of efficient evacuation plans, bolsters urban sustainability, and augments climate resilience, ultimately mitigating flood-induced economic tolls.

This study presents a deep learning model created for enabling comprehensive wildfire control by seamlessly combining satellite images, weather data and terrain details. Current systems face challenges in comprehensively analyzing these factors due to limitations in data integration, dynamic fire behavior prediction, and post-fire ecological impact evaluation. By improving detection and accurate assessment of impact, the system addresses all aspects of wildfire management from forecasting to post event analysis. The model integrates soil quality examination and vegetation regrowth simulation Using image analysis and state of the art deep learning methods. This holistic approach of Image analysis employs Convolutional Neural Networks (CNN) for predicting wildfire risk and Recurrent Neural Networks (RNN) for assessing soil and hydrological effects. This adaptable approach, which aims to transform the way fire control is done, can be readily adjusted to changing conditions and takes correlations between different aspects into account. It surpasses conventional techniques by including soil quality analysis, vegetation regrowth modeling, and vegetation damage evaluation. The adaptable nature of this method proves invaluable, in lessening the impact of wildfires with a focus, on evaluating vegetation damage and promoting restoration.

Aviation emissions are the only direct source of anthropogenic particulate pollution at high altitudes, which can form con-trails and contrail-induced clouds, with consequent effects upon global radiative forcing. In this study, we develop a pre-dictive model, called APMEP-CNN, for aviation non-volatile particulate matter (nvPM) emissions using a convolutional neural network (CNN) technique. The model is established with data sets from the newly published aviation emission databank and measurement results from several field studies on the ground and during cruise operation. The model also takes the influence of sustainable aviation fuels (SAFs) on nvPM emissions into account by considering fuel properties. This study demonstrates that the APMEP-CNN can predict nvPM emission index in mass (EIm) and number (EIn) for a number of high-bypass turbofan engines. The accuracy of predicting EIm and EIn at ground level is significantly improved (R2 = 0.96 and 0.96) compared to the published models. We verify the suitability and the applicability of the APMEP-CNN model for estimating nvPM emissions at cruise and burning SAFs and blend fuels, and find that our predictions for EIm are within & PLUSMN;36.4 % of the measurements at cruise and within & PLUSMN;33.0 % of the measurements burning SAFs in av-erage. In the worst case, the APMEP-CNN prediction is different by -69.2 % from the measurements at cruise for the JT3D-3B engine. Thus, the APMEP-CNN model can provide new data for establishing accurate emission inventories of global aviation and help assess the impact of aviation emissions on human health, environment and climate.Synopsis: The results of this paper provide accurate predictions of nvPM emissions from in-use aircraft engines, which im-pact airport local air quality and global radiative forcing.