A systematic review and meta-analysis of artificial neural network application in geotechnical engineering: theory and applications

Assessment of the Undrained Shear Strength and Settlement of Organic Soils under Embankment Loading Using Artificial Neural Networks

In engineering practice, due to the high compressibility and very low shear strength of organic soils, it is difficult to construct an embankment on organic subsoil. High variability and significant change in geotechnical parameters cause difficulties in predicting the behavior of organic soils under embankment loading. The aim of the paper was to develop empirical relationships used in the preliminary design for evaluating the settlement and undrained shear strength of organic subsoil loaded by embankment based on data obtained from four test sites. Statistical multiple regression models were developed for evaluating the settlement in time and undrained shear strength in time individually for peat and gyttja. Neural networks to predict the settlement and undrained shear strength in time for peat and gyttja simultaneously as double-layer subsoils as well as a separate neural network for peat and a separate neural network for gyttja as single-layer subsoils were also developed. The vertical stress, thickness, water content, initial undrained shear strength of peat and gyttja, and time were used as the independent variables. Artificial neural networks are characterized by greater prediction accuracy than statistical multiple regression models. Multiple regression models predict dependent variables with maximum relative errors of about 35% to about 60%, and neural networks predict output variables with maximum relative errors of about 25% to about 30%.

Analysis of Unconfined Compressive Strength of Rammed Earth Mixes Based on Artificial Neural Network and Statistical Analysis

Earth materials have been used in construction as safe, healthy and environmentally sustainable. It is often challenging to develop an optimum soil mix because of the significant variations in soil properties from one soil to another. The current study analyzed the soil properties, including the grain size distribution, Atterberg limits, compaction characteristics, etc., using multilinear regression (MLR) and artificial neural networks (ANN). Data collected from previous studies (i.e., 488 cases) for stabilized (with either cement or lime) and unstabilized soils were considered and analyzed. Missing data were estimated by correlations reported in previous studies. Then, different ANNs were designed (trained and validated) using Levenberg-Marquardt (L-M) algorithms. Using the MLR, several models were developed to estimate the compressive strength of both unstabilized and stabilized soils with a Pearson Coefficient of Correlation (R²) equal to 0.2227 and 0.766, respectively. On the other hand, developed ANNs gave a higher value for R² than MLR (with the highest value achieved at 0.9883). Thereafter, an experimental program was carried out to validate the results achieved in this study. Finally, a sensitivity analysis was carried out using the resulting networks to assess the effect of different soil properties on the unconfined compressive strength (UCS). Moreover, suitable recommendations for earth materials mixes were presented.

Application of Artificial Neural Networks in Construction Management: A Scientometric Review

As a powerful artificial intelligence tool, the Artificial Neural Network (ANN) has been increasingly applied in the field of construction management (CM) during the last few decades. However, few papers have attempted to draw up a systematic commentary to appraise the state-of-the-art research on ANNs in CM except the one published in 2000. In the present study, a scientometric analysis was conducted to comprehensively analyze 112 related articles retrieved from seven selected authoritative journals published between 2000 and 2020. The analysis identified co-authorship networks, collaboration networks of countries/regions, co-occurrence networks of keywords, and timeline visualization of keywords, together with the strongest citation burst, the active research authors, countries/regions, and main research interests, as well as their evolution trends and collaborative relationships in the past 20 years. This paper finds that there is still a lack of systematic research and sufficient attention to the application of ANNs in CM. Furthermore, ANN applications still face many challenges such as data collection, cleaning and storage, the collaboration of different stakeholders, researchers and countries/regions, as well as the systematic design for the needed platforms. The findings are valuable to both the researchers and industry practitioners who are committed to ANNs in CM.

A Deep Convolutional Generative Adversarial Networks-Based Method for Defect Detection in Small Sample Industrial Parts Images

Online defect detection in small industrial parts is of paramount importance for building closed loop intelligent manufacturing systems. However, high-efficiency and high-precision detection of surface defects in these manufacturing systems is a difficult task and poses a major research challenge. The small sample size of industrial parts available for training machine learning algorithms and the low accuracy of computer vision-based inspection algorithms are the bottlenecks that restrict the development of efficient online defect detection technology. To address these issues, we propose a small sample gear face defect detection method based on a Deep Convolutional Generative Adversarial Network (DCGAN) and a lightweight Convolutional Neural Network (CNN) in this paper. Initially, we perform data augmentation by using DCGAN and traditional data enhancement methods which effectively increase the size of the training data. In the next stage, we perform defect classification by using a lightweight CNN model which is based on the state-of-the-art Vgg11 network. We introduce the Leaky ReLU activation function and a dropout layer in the proposed CNN. In the experimental evaluation, the proposed framework achieves a high score of 98.40%, which is better than that of the classic Vgg11 network model. The method proposed in this paper is helpful for the detection of defects in industrial parts when the available sample size for training is small.

Neural Network-Based Dynamic Segmentation and Weighted Integrated Matching of Cross-Media Piano Performance Audio Recognition and Retrieval Algorithm

This paper presents a dynamic segmentation and weighted comprehensive matching algorithm based on neural networks for cross-media piano performance audio recognition and retrieval. The 3D convolutional neural network process is separated to compress the network parameters and improve the computational speed. Skip connection and layer-wise learning rate solve the problem that the separated network is challenging to train. The piano performance audio recognition is facilitated by shuffle operation. In pattern recognition, music retrieval algorithms are gaining more and more attention due to their ease of implementation and efficiency. However, the problems of imprecise dynamic note segmentation and inconsistent matching templates directly affect the accuracy of the MIR algorithm. We propose a dynamic threshold-based segmentation and weighted comprehensive matching algorithm to solve these problems. The amplitude difference step is dynamically set, and the notes are segmented according to the changing threshold to improve the accuracy of note segmentation. A standard score frequency is used to transform the pitch template to achieve input normalization to enhance the accuracy of matching. Direct matching and DTW matching are fused to improve the adaptability and robustness of the algorithm. Finally, the effectiveness of the method is experimentally demonstrated. This paper implements the data collection and processing, audio recognition, and retrieval algorithm for cross-media piano performance big data through three main modules: the collection, processing, and storage module of cross-media piano performance big data, the building module of audio recognition of cross-media piano performance big data, and the dynamic precision module of cross-media piano performance big data.

A Comprehensive Comparison of the Performance of Metaheuristic Algorithms in Neural Network Training for Nonlinear System Identification

Many problems in daily life exhibit nonlinear behavior. Therefore, it is important to solve nonlinear problems. These problems are complex and difficult due to their nonlinear nature. It is seen in the literature that different artificial intelligence techniques are used to solve these problems. One of the most important of these techniques is artificial neural networks. Obtaining successful results with an artificial neural network depends on its training process. In other words, it should be trained with a good training algorithm. Especially, metaheuristic algorithms are frequently used in artificial neural network training due to their advantages. In this study, for the first time, the performance of sixteen metaheuristic algorithms in artificial neural network training for the identification of nonlinear systems is analyzed. It is aimed to determine the most effective metaheuristic neural network training algorithms. The metaheuristic algorithms are examined in terms of solution quality and convergence speed. In the applications, six nonlinear systems are used. The mean-squared error (MSE) is utilized as the error metric. The best mean training error values obtained for six nonlinear systems were 3.5×10−4, 4.7×10−4, 5.6×10−5, 4.8×10−4, 5.2×10−4, and 2.4×10−3, respectively. In addition, the best mean test error values found for all systems were successful. When the results were examined, it was observed that biogeography-based optimization, moth–flame optimization, the artificial bee colony algorithm, teaching–learning-based optimization, and the multi-verse optimizer were generally more effective than other metaheuristic algorithms in the identification of nonlinear systems.

Design of a Comprehensive Assessment Model for the Stability and Engineering Geology of Slope Based on Improved Convolutional Neural Network

The geological mechanics, geotechnical characteristics, and hydrogeological conditions of slopes are complex and changeable, so their stability assessment is a complicated system; their traditional engineering geological assessment does not consider the opposition of the system, the uncertainty of performance indicators, and the ambiguity of index classification, being easy to distort results due to the ambiguity. Improved convolutional neural network (CNN) has outstanding advantages in analyzing problems with randomness and fuzziness. It can perform unified numerical processing on slope assessment indicators with precise values, interval values, and qualitative judgment values, making the traditional qualitative description is transformed into quantitative calculation. Therefore, on the basis of summarizing and analyzing previous research works, this paper expounded the research status and significance of the comprehensive assessment model for slope stability and engineering geology; elaborated the development background, current status, and future challenges of the improved CNN; introduced the methods and principles of the model structure, convolutional layer design, and data flow optimization of the improved CNN; performed the assessment index system establishment and index weight determination; established the mathematical assessment model for slope stability; conducted the assessment module design for slope stability based on the improved CNN; analysed the importance of individual factors to the comprehensive engineering geological characteristics; discussed the determination of assessment value of comprehensive unit engineering geological characteristics; explored the assessment module design for slope engineering geology based on the improved CNN; and finally carried out an engineering application and its result analysis. The study results show that the improved CNN can select some universal and objective factors according to the actual conditions of slopes, including topography, stratum lithology, geological structure, atmospheric rainfall, groundwater, engineering activities, setting up factor sets and judgment sets, and making fuzzy inferences. The comprehensive assessment model can use appropriate mathematical methods to judge the pros and cons of slope's stability and engineering geology according to certain principles and standards, and grade the results and identify the most important geological problems. The results of this paper provide a reference for further researches on the design of a comprehensive assessment model for slope stability and engineering geology based on the improved CNN.

Fast Seismic Assessment of Built Urban Areas with the Accuracy of Mechanical Methods Using a Feedforward Neural Network

Capacity curves obtained from nonlinear static analyses are widely used to perform seismic assessments of structures as an alternative to dynamic analysis. This paper presents a novel ‘en masse’ method to assess the seismic vulnerability of urban areas swiftly and with the accuracy of mechanical methods. At the core of this methodology is the calculation of the capacity curves of low-rise reinforced concrete buildings using neural networks, where no modeling of the building is required. The curves are predicted with minimal error, needing only basic geometric and material parameters of the structures to be specified. As a first implementation, a typology of prismatic buildings is defined and a training set of more than 7000 structures generated. The capacity curves are calculated through push-over analysis using SAP2000. The results feature the prediction of 100-point curves in a single run of the network while maintaining a very low mean absolute error. This paper proposes a method that improves current seismic assessment tools by providing a fast and accurate calculation of the vulnerability of large sets of buildings in urban environments.

Automatic Surgery and Anesthesia Emergence Duration Prediction Using Artificial Neural Networks

Cost control is becoming increasingly important in hospital management. Hospital operating rooms have high resource consumption because they are a major part of a hospital. Thus, the optimal use of operating rooms can lead to high resource savings. However, because of the uncertainty of the operation procedures, it is difficult to arrange for the use of operating rooms in advance. In general, the durations of both surgery and anesthesia emergence determine the time requirements of operating rooms, and these durations are difficult to predict. In this study, we used an artificial neural network to construct a surgery and anesthesia emergence duration-prediction system. We propose an intelligent data preprocessing algorithm to balance and enhance the training dataset automatically. The experimental results indicate that the prediction accuracies of the proposed serial prediction systems are acceptable in comparison to separate systems.

Evaluation of Creep Behavior of Soft Soils by Utilizing Multisensor Data Combined with Machine Learning

To identify the unknown values of the parameters of Burger’s constitutive law, commonly used for the evaluation of the creep behavior of the soft soils, this paper demonstrates a procedure relying on the data obtained from multiple sensors, where each sensor is used to its best advantage. The geophysical, geotechnical, and unmanned aerial vehicle data are used for the development of a numerical model whose results feed into the custom-architecture neural network, which then provides information about on the complex relationships between the creep characteristics and soil displacements. By utilizing InSAR and GPS monitoring data, particle swarm algorithm identifies the most probable set of Burger’s creep parameters, eventually providing a reliable estimation of the long-term behavior of soft soils. The validation of methodology is conducted for the Oostmolendijk embankment in the Netherlands, constructed on the soft clay and peat layers. The validation results show that the application of the proposed methodology, which relies on multisensor data, can overcome the high cost and long duration issues of laboratory tests for the determination of the creep parameters and can provide reliable estimates of the long-term behavior of geotechnical structures constructed on soft soils.

Novel ensemble intelligence methodologies for rockburst assessment in complex and variable environments

Rockburst is a severe geological hazard that restricts deep mine operations and tunnel constructions. To overcome the shortcomings of widely used algorithms in rockburst prediction, this study investigates the ensemble trees, i.e., random forest (RF), extremely randomized tree (ET), adaptive boosting machine (AdaBoost), gradient boosting machine, extreme gradient boosting machine (XGBoost), light gradient boosting machine, and category gradient boosting machine, for rockburst estimation based on 314 real rockburst cases. Additionally, Bayesian optimization is utilized to optimize these ensemble trees. To improve performance, three combination strategies, voting, bagging, and stacking, are adopted to combine multiple models according to training accuracy. ET and XGBoost receive the best capabilities (85.71% testing accuracy) in single models, and except for AdaBoost, six ensemble trees have high accuracy and can effectively foretell strong rockburst to prevent large-scale underground disasters. The combination models generated by voting, bagging, and stacking perform better than single models, and the voting 2 model that combines XGBoost, ET, and RF with simple soft voting, is the most outstanding (88.89% testing accuracy). The performed sensitivity analysis confirms that the voting 2 model has better robustness than single models and has remarkable adaptation and superiority when input parameters vary or miss, and it has more power to deal with complex and variable engineering environments. Eventually, the rockburst cases in Sanshandao Gold Mine, China, were investigated, and these data verify the practicability of voting 2 in field rockburst prediction.

A deep artificial neural network architecture for mesh free solutions of nonlinear boundary value problems

Seeking efficient solutions to nonlinear boundary value problems is a crucial challenge in the mathematical modelling of many physical phenomena. A well-known example of this is solving the Biharmonic equation relating to numerous problems in fluid and solid mechanics. One must note that, in general, it is challenging to solve such boundary value problems due to the higher-order partial derivatives in the differential operators. An artificial neural network is thought to be an intelligent system that learns by example. Therefore, a well-posed mathematical problem can be solved using such a system. This paper describes a mesh free method based on a suitably crafted deep neural network architecture to solve a class of well-posed nonlinear boundary value problems. We show how a suitable deep neural network architecture can be constructed and trained to satisfy the associated differential operators and the boundary conditions of the nonlinear problem. To show the accuracy of our method, we have tested the solutions arising from our method against known solutions of selected boundary value problems, e.g., comparison of the solution of Biharmonic equation arising from our convolutional neural network subject to the chosen boundary conditions with the corresponding analytical/numerical solutions. Furthermore, we demonstrate the accuracy, efficiency, and applicability of our method by solving the well known thin plate problem and the Navier-Stokes equation.

Entropy Optimized Second Grade Fluid with MHD and Marangoni Convection Impacts: An Intelligent Neuro-Computing Paradigm

Artificial intelligence applications based on soft computing and machine learning algorithms have recently become the focus of researchers’ attention due to their robustness, precise modeling, simulation, and efficient assessment. The presented work aims to provide an innovative application of Levenberg Marquardt Technique with Artificial Back Propagated Neural Networks (LMT-ABPNN) to examine the entropy generation in Marangoni convection Magnetohydrodynamic Second Grade Fluidic flow model (MHD-SGFM) with Joule heating and dissipation impact. The PDEs describing MHD-SGFM are reduced into ODEs by appropriate transformation. The dataset is determined through Homotopy Analysis Method by the variation of physical parameters for all scenarios of proposed LMT-ABPNN. The reference data samples for training/validation/testing processes are utilized as targets to determine the approximated solution of proposed LMT-ABPNN. The performance of LMT-ABPNN is validated by MSE based fitness, error histogram scrutiny, and regression analysis. Furthermore, the influence of pertinent parameters on temperature, concentration, velocity, entropy generation, and Bejan number is also deliberated. The study reveals that the larger β and Ma, the higher f′(η) while M has the reverse influence on f′(η). For higher values of β, M, Ma, and Ec, θ(η) boosts. The concentration ϕ(η) drops as Ma and Sc grow. An augmentation is noticed for NG for higher estimations of β,M, and Br. Larger β,M and Br decays the Bejan number.

GAN inversion method of an initial in situ stress field based on the lateral stress coefficient

The initial in situ stress field influences underground engineering design and construction. Since the limited measured data, it is necessary to obtain an optimized stress field. Although the present stress field can be obtained by valley evolution simulation, the accuracy of the ancient stress field has a remarkable influence. This paper proposed a method using the generative adversarial network (GAN) to obtain optimized lateral stress coefficients of the ancient stress field. A numerical model with flat ancient terrain surfaces is established. Utilizing the nonlinear relationship between measured stress components and present burial depth, lateral stress coefficients of ancient times are estimated to obtain the approximate ancient stress field. Uniform designed numerical tests are carried out to simulate the valley evolution by excavation. Coordinates, present burial depth, present lateral stress coefficients and ancient regression factors of lateral stress coefficients are input to GAN as real samples for training, and optimized ancient regression factors can be predicted. The present stress field is obtained by excavating strata layers. Numerical results show the magnitude and distribution law of the present stress field match well with measured points, thus the proposed method for the stress field inversion is effective.

Landslide Susceptibility Mapping in Brazil: A Review

Landslide susceptibility studies are a common type of landslide assessment. Landslides are one of the most frequent hazards in Brazil, resulting in significant economic and social losses (e.g., deaths, injuries, and property destruction). This paper presents a literature review of susceptibility mapping studies in Brazil and analyzes the methods and input data commonly used. The publications used in this analysis were extracted from the Web of Science platform. We considered the following aspects: location of study areas, year and where the study was published, methods, thematic variables, source of the landslide inventory, and validation methods. The susceptibility studies are concentrated in Brazil’s south and southeast region, with the number of publications increasing since 2015. The methods commonly used are slope stability and statistical models. Validation was performed based on receiver operating characteristic (ROC) curves and area under the curve (AUC). Even though landslide inventories constitute the most critical input data for susceptibility mapping, the criteria used for the creation of landslide inventories are not evident in most cases. The included studies apply various validation techniques, but evaluations with potential users and information on the practical applicability of the results are largely missing.

A New Approach of Hybrid Bee Colony Optimized Neural Computing to Estimate the Soil Compression Coefficient for a Housing Construction Project

In the design phase of housing projects, predicting the settlement of soil layers beneath the buildings requires the estimation of the coefficient of soil compression. This study proposes a low-cost, fast, and reliable alternative for estimating this soil parameter utilizing a hybrid metaheuristic optimized neural network (NN). An integrated method of artificial bee colony (ABC) and the Levenberg–Marquardt (LM) algorithm is put forward to train the NN inference model. The model is capable of delivering the response variable of soil compression coefficient a set of physical properties of soil. A large-scale real-life urban project at Hai Phong city (Vietnam) was selected as a case study. Accordingly, a dataset of 441 samples with their corresponding testing values of the compression coefficient has been collected and prepared during the construction phase. Experimental outcomes confirm that the proposed NN model with the hybrid ABC-LM training algorithm has attained the highly accurate estimation of the soil compression coefficient with root mean square error (RMSE) = 0.008, mean absolute percentage error (MAPE) = 10.180%, and coefficient of determination (R2) = 0.864. Thus, the proposed machine learning method can be a promising tool for geotechnical engineers in the design phase of housing projects.

Predicting Slope Stability Failure through Machine Learning Paradigms

In this study, we employed various machine learning-based techniques in predicting factor of safety against slope failures. Different regression methods namely, multi-layer perceptron (MLP), Gaussian process regression (GPR), multiple linear regression (MLR), simple linear regression (SLR), support vector regression (SVR) were used. Traditional methods of slope analysis (e.g., first established in the first half of the twentieth century) used widely as engineering design tools. Offering more progressive design tools, such as machine learning-based predictive algorithms, they draw the attention of many researchers. The main objective of the current study is to evaluate and optimize various machine learning-based and multilinear regression models predicting the safety factor. To prepare training and testing datasets for the predictive models, 630 finite limit equilibrium analysis modelling (i.e., a database including 504 training datasets and 126 testing datasets) were employed on a single-layered cohesive soil layer. The estimated results for the presented database from GPR, MLR, MLP, SLR, and SVR were assessed by various methods. Firstly, the efficiency of applied models was calculated employing various statistical indices. As a result, obtained total scores 20, 35, 50, 10, and 35, respectively for GPR, MLR, MLP, SLR, and SVR, revealed that the MLP outperformed other machine learning-based models. In addition, SVR and MLR presented an almost equal accuracy in estimation, for both training and testing phases. Note that, an acceptable degree of efficiency was obtained for GPR and SLR models. However, GPR showed more precision. Following this, the equation of applied MLP and MLR models (i.e., in their optimal condition) was derived, due to the reliability of their results, to be used in similar slope stability problems.

The Feasibility of Three Prediction Techniques of the Artificial Neural Network, Adaptive Neuro-Fuzzy Inference System, and Hybrid Particle Swarm Optimization for Assessing the Safety Factor of Cohesive Slopes

In this paper, a neuro particle-based optimization of the artificial neural network (ANN) is investigated for slope stability calculation. The results are also compared to another artificial intelligence technique of a conventional ANN and adaptive neuro-fuzzy inference system (ANFIS) training solutions. The database used with 504 training datasets (e.g., a range of 80%) and testing dataset consists of 126 items (e.g., 20% of the whole dataset). Moreover, variables of the ANN method (for example, nodes number for each hidden layer) and the algorithm of PSO-like swarm size and inertia weight are improved by utilizing a total of 28 (i.e., for the PSO-ANN) trial and error approaches. The key properties were fed as input, which were utilized via the analysis of OptumG2 finite element modelling (FEM), containing undrained cohesion stability of the baseline soil (Cu), angle of the original slope (β), and setback distance ratio (b/B) where the target is selected factor of safety. The estimated data for datasets of ANN, ANFIS, and PSO-ANN models were examined based on three determined statistical indexes. Namely, root mean square error (RMSE) and the coefficient of determination (R2). After accomplishing the analysis of sensitivity, considering 72 trials and errors of the neurons number, the optimized architecture of 4 × 6 × 1 was determined to the structure of the ANN model. As an outcome, the employed methods presented excellent efficiency, but based on the ranking method, the PSO-ANN approach might have slightly better efficiency in comparison to the algorithms of ANN and ANFIS. According to statistics, for the proper structure of PSO-ANN, the indexes of R2 and RMSE values of 0.9996, and 0.0123, as well as 0.9994 and 0.0157, were calculated for the training and testing networks. Nevertheless, having the ANN model with six neurons for each hidden layer was formulized for further practical use. This study demonstrates the efficiency of the proposed neuro model of PSO-ANN in estimating the factor of safety compared to other conventional techniques.