Open caissons are increasingly utilized for underground construction due to the increasing demand for aboveground structures, which employ the principle of submersion using the self-weight of the edge cutting face and the applied bearing pressure to mitigate the vertical soil reaction. This paper examines the bearing capacity factor of the edge cutting face in anisotropic clays, approximated using the finite element limit analysis (FELA) method and considering the average results between the upper and lower bounds. The influence of the adhesion factor at the interface of the cutting edge (alpha), the ratio between the depth of the internal embedment and the embedded width (H/B), the ratio between the radius and the embedded width (R/B), the anisotropic shear strength (re), and the cutting face angle ((1) is investigated. The results indicate a significant influence of the anisotropic shear strength on the adhesion factor at the interface of the cutting edge. An increase in re denotes a decrease in the undrained shear strength obtained from the triaxial compression test, resulting in an increase in the value of N. An increase in alpha influences (1, such that when (1 <90 degrees, the value of N remains constant when (1 = 90 degrees. In addition, a highly efficient hybrid model called DNN-PBT was established utilizing a deep neural network (DNN) and a population based training (PBT) approach, specifically for the purpose of accurately predicting the bearing capacity factor of circular open caissons positioned in undrained clay. Both computational and comparative outcomes demonstrate that the proposed DNN-PBT can precisely forecast the bearing capacity, achieving an R2 value higher than 0.999 and a mean squared error (MSE) <0.007. These findings highlight the accuracy and efficiency of the suggested approach. Furthermore, the sensitivity analysis results demonstrated that the anisotropic shear strength (re) is the most important input variable for estimating the bearing capacity factor of the edge cutting face.

Structural health monitoring (SHM) is crucial in the early stage of damage formation for the life-cycle service of offshore structures. The influence of soils on vibration-based damage detection systems in offshore structures is a critical issue but has received less attention in previous literature. Due to the complexity of offshore structures and their exposure to diverse loads, simultaneous compound damages across different components can occur, posing a significant challenge for damage detection. Existing methods often treat compound damage as a distinct type of damage, independent of corresponding single damages. Nonetheless, in cases where damages arise concurrently, the distinct characteristics of each individual damage are evident independently within the vibration signals. This study presents a new approach for detecting both single and compound damage in offshore structures considering soil interaction using vibration data. The approach combines Wavelet Transform (WT) with a Multiple Interference Deep Convolutional Neural Network (MIDCNN) to effectively learn desired features and detect damage in these structures. The MIDCNN model is trained on time-frequency data from healthy and single damage states, without incorporating time-frequency data from compound damage during training. In the testing phase, the MIDCNN model intelligently alarms healthy, single damage states, and an untrained compound damage state based on predefined probabilistic conditions derived from the MIDCNN output probabilities. The time-frequency data are generated using the WT method, which is adept at capturing the natural characteristics of the structure while minimizing the influence of noise or irrelevant components. The proposed approach is validated using measured data from a laboratory-scale offshore monopile model with soil interaction. The findings demonstrate that the proposed method is more robust than other methods in extracting features and classifying various states, including healthy, single and compound damages.

Detecting faults in solar photovoltaic modules (PVM) is crucial for enhancing their longevity, power output, and overall reliability. Visual anomalies such as soiling, partial shading, cell damage, and glass breakage pose significant challenges for fault identification, particularly in harsh environmental conditions. Therefore, it is essential to maintain healthy PV systems with extended lifecycles and optimal performance through the quick and efficient detection of faults. This work introduces a comprehensive approach that encompasses dataset creation, preprocessing, and PV fault classification utilizing the EfficientNet B0 model. Processed RGB images serve as input for the model, enabling the classification of visual faults in PVM. The performance evaluation of the proposed deep neural network model includes metrics such as classification accuracy, F1 score, specificity, and recall. The results highlight the exceptional performance of the proposed model, achieving a classification accuracy of 97.24% for visual fault identification in PV modules. Moreover, the study underscores the model's robustness and efficacy through a comparative analysis with other classification techniques reported in the literature.

The deformation characteristics and constitutive behavior of granular materials under normal forces acting on particles are dependent on the geometry of the grain structure, fabrics and the inter-particle friction. In this study, the influence of particle morphology on the friction and dilatancy of five natural sands was investigated using deep learning (DL) techniques. A Three-dimensional (3D) imaging technique using computed tomography was utilized to compute the morphology (roundness and sphericity) of collected natural sands. Triaxial tests were conducted on the five different natural sands at different densities and confinement stresses (r3). From the triaxial results, peak friction angle (up), critical state friction angle (ucs), and dilatancy angle (w) were obtained and modeled using conventional multiple linear regression (MLR) models and DL techniques. A total of 100 deep artificial neural networks (DANN) models were trained at different sizes of first and second hidden layers. The use of MLR resulted in R2 of 0.709, 0.565, and 0.795 for up, u cs and w, respectively, while the best performed DANN (30 and 50 neurons for the 1st and 2nd hidden layers, respectively) had R2 of 0.956 for all outputs (up, u cs and w) combined. Using the best-performed DANN model, the weight partitioning technique was used to compute an importance score for each parameter in predicting up, u cs and w. The r3 had the highest importance followed by relative density, roundness, and sphericity with a relative importance of more than 10%. In addition, sensitivity analysis was conducted to investigate the effect of each parameter on the shear parameters and ensure the robustness of the developed model. (c) 2024 Production and hosting by Elsevier B.V. on behalf of The Japanese Geotechnical Society. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).

This study presents a novel approach to forecasting the evolution of hysteresis stress-strain response of different types of soils under repeated loading-unloading cycles. The forecasting is made solely from the knowledge of soil properties and loading parameters. Our approach combines mathematical modeling, regression analysis, and Deep Neural Networks (DNNs) to overcome the limitations of traditional DNN training. As a novelty, we propose a hysteresis loop evolution equation and design a family of DNNs to determine the parameters of this equation. Knowing the nature of the phenomenon, we can impose certain solution types and narrow the range of values, enabling the use of a very simple and efficient DNN model. The experimental data used to develop and test the model was obtained through Torsional Shear (TS) tests on soil samples. The model demonstrated high accuracy, with an average R 2 value of 0.9788 for testing and 0.9944 for training.

Stubble burning is a conventional technique of residue management that has affected the physio-chemical properties of the soils. In soil sciences, dielectric properties of soils using radio and microwave-based remote sensing have huge applications. Thus, presented paper has studied the burning effects of stubble on soil's physical, chemical and dielectric properties ($\varepsilon {{\prime}} $epsilon ' and $\varepsilon {{\prime \prime}}$epsilon ''). Moreover, the experimentally observed soil's dielectric data has been explored with various classical Machine Learning (ML) and Neural Network (NN) based regression models. The soil samples were taken from the fields of Punjab, India, in the October-November months following a multistage soil sampling method. Then, Dak-12 open-ended coaxial probe (DOCP) has been used in alliance with a two-port Vector Network Analyzer (VNA) E5071C, Agilent Technologies, to investigate the dielectric properties of soil samples. The obtained results indicate that physio-chemical and dielectric properties have been strongly affected by burning as well as because of the presence of high concentrations of ash residues.$ \varepsilon {{\prime}} $epsilon ' and $\varepsilon {{\prime \prime}}$epsilon '' variations with depth indicate that ash residues can seep up to depths of 10 cm in a single burning process. Moreover, the continuous burning of stubble can have permanent effects on soil's properties. Among considered regression models, the Deep NN-based regression model has given the most accurate predictions of the regressor variables $\varepsilon {{\prime}} $epsilon ' and $\varepsilon {{\prime \prime}}$epsilon '', with a root-mean-square-error (RMSE) of 0.06 and 0.07, respectively. Stubble burning has visible effects on physical, chemical as well as dielectric properties of soil. The burning of stubble damages natural ecosystem and essential nutrients which decrease fertility of soil. Also, the resultant residue ash becomes permanent part of soil profile and alters basic properties of soil. Moreover, exploration of ML-based regression models suggests the tremendous applications of data-centric models in soil and material sciences.

In urban areas, backfilling voids with complex and narrow shapes necessitates alternative backfill methods and materials, such as controlled low-strength materials (CLSMs), to minimize ground subsidence caused by improper compaction of backfill soils. This study aims to propose a predictive methodology for the mechanical properties of CLSMs using regression analysis and a deep neural network (DNN). CLSM mixtures are prepared with various mixing ratios of calcium sulfoaluminate (CSA) expansive admixture, water, Portland cement, fly ash, sand, silt, and alkali-free accelerator. The flow consistency and compressive strength at 12 hrs and 7 days post-mixing are estimated. The relationships between CLSM mixing ratios and the estimated mechanical properties are established through multiple regression analysis and DNN. The DNN's performance is evaluated, with coefficients of determination being 0.0874, 0.8432, and 0.6826 for flowability, and compressive strength at 12 hrs and 7 days, respectively. To address the low performance, oversampling algorithms like the synthetic minority oversampling technique (SMOTE) and the conditional tabular generative adversarial network (CTGAN) are utilized. Analysis of the oversampled data using SMOTE indicates improved performance, with the coefficients of determination rising to 0.6818, 0.9856, and 0.983 for flowability, and compressive strength at 12 hrs and 7 days, respectively. This study illustrates that the identified correlations may be effectively used to predict flowability and compressive strength based on the mixing ratio.

In this study, the multifaceted toxicity induced by high doses of the essential trace element molybdenum in Allium cepa L. was investigated. Germination, root elongation, weight gain, mitotic index (MI), micronucleus (MN), chromosomal abnormalities (CAs), Comet assay, malondialdehyde (MDA), proline, superoxide dismutase (SOD), catalase (CAT) and anatomical parameters were used as biomarkers of toxicity. In addition, detailed correlation and PCA analyzes were performed for all parameters discussed. On the other hand, this study focused on the development of a two hidden layer deep neural network (DNN) using Matlab. Four experimental groups were designed: control group bulbs were germinated in tap water and application group bulbs were germinated with 1000, 2000 and 4000 mg/L doses of molybdenum for 72 h. After germination, root tips were collected and prepared for analysis. As a result, molybdenum exposure caused a dose-dependent decrease (p < 0.05) in the investigated physiological parameter values, and an increase (p < 0.05) in the cytogenetic (except MI) and biochemical parameter values. Molybdenum exposure induced different types of CAs and various anatomical damages in root meristem cells. Comet assay results showed that the severity of DNA damage increased depending on the increasing molybdenum dose. Detailed correlation and PCA analysis results determined significant positive and negative interactions between the investigated parameters and confirmed the relationships of these parameters with molybdenum doses. It has been found that the DNN model is in close agreement with the actual data showing the accuracy of the predictions. MAE, MAPE, RMSE and R2 were used to evaluate the effectiveness of the DNN model. Collective analysis of these metrics showed that the DNN model performed well. As a result, it has been determined once again that high doses of molybdenum cause multiple toxicity in A. cepa and the Allium test is a reliable universal test for determining this toxicity. Therefore, periodic measurement of molybdenum levels in agricultural soils should be the first priority in preventing molybdenum toxicity.

With an increase in local precipitation caused by extreme climatic phenomena, the frequency of landslides and associated damage has also increased. Therefore, compiling fine-scale landslide susceptibility assessment maps based on data from landslide-affected areas is essential. Deep neural network (DNN) and kernel-based DNN(DNNK) models were used to prepare landslide susceptibility maps of the mountainous Pyeongchang-gun region (South Korea) within a geographic information system framework. To map landslide susceptibility, datasets of landslide occurrence areas, topography, land use, forest, and soil were collected and entered into spatial databases, and 18 factors were then selected from the databases and used as model inputs. The training and test datasets consisted of 1600 and 400 landslide locations, respectively. The test accuracies of the DNN and DNNK models were 98.19% and 97.53% and 94.11% and 92.22% for the area under the receiver operating characteristic curve and the average precision value of the precision-recall curve, respectively. The location of future landslides can now be quickly and efficiently predicted using remote sensing data at a lower cost and with less labor. The landslide susceptibility maps produced in this study can play a role in sustainability and serve as references for establishing policies for landslide prevention and mitigation.