Prediction of compaction parameters for fine-grained soil: Critical comparison of the deep learning and standalone models

Khatti, Jitendra; Grover, Kamaldeep Singh

doi:10.1016/j.jrmge.2022.12.034

Cited by 41 publications

(7 citation statements)

References 90 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Building upon these traditional approaches, advanced AI methodologies have brought significant advancements in the fields of geotechnical characterization in cohesive soils. Comparative analyses have been conducted on various machine learning models and soft computing techniques to predict key soil properties such as soil compaction parameters [60]- [62], shear strength properties [63]- [67] and the suitable percentage of waste materials for soil improvement [68]. In these studies, the proposed models showed superior performance with high prediction accuracy.…”

Section: F Research Frontier Identificationmentioning

confidence: 99%

Global Research Trends in Soft Soil Management for Infrastructure Development: Opportunities and Challenges

Sim,

Katman,

Baharuddin

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Soft soils present significant challenges to infrastructure development worldwide due to high compressibility, low shear strength and low permeability. Bibliometric analysis remains scarce in the soft soil management field, making it difficult to grasp global trends and contributions. This research addresses this gap by providing a novel and comprehensive bibliometric analysis of soft soil management literature to investigate the trend, opportunities and challenges. The analysis predominantly examines ground improvement methods based on 2,260 journal articles and proceeding papers from WOS core collection between 2013 and 2023 using CiteSpace. The analysis encompasses country distribution, authorship and cocited authors, cited journals, reference co-citations and identification of research hotspots and frontiers. Findings show a growing interest and increased research focus in soft soil management, with China emerging as a prominent contributor. Reference co-citation clustering analysis reveals two dominant research themes: ground improvement methods (geosynthetic-reinforced embankments and stone columns) and sustainable practices (reuse of waste materials). The emerging word analysis reveals an evolutionary trend from investigating innovative and sustainable techniques to shear strength and failure mechanisms. Recent studies focus on the use of vertical drains, deep mixing columns, chemical stabilization, and sustainable ground improvement strategies. Opportunities lie in sustainable ground improvement methods and novel sensing technologies. Key challenges include bearing capacity, settlement, and slope stability. The study highlights the need for more research into two other key areas such as geotechnical characterization and foundation design. Overall, this bibliometric review contributes to a more thorough understanding of soft soil management studies for researchers and practitioners.

show abstract

Section: F Research Frontier Identificationmentioning

confidence: 99%

Global Research Trends in Soft Soil Management for Infrastructure Development: Opportunities and Challenges

Sim,

Katman,

Baharuddin

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Using the Pearson product-moment correlation coefficient, this relationship is identified. The two databases' correlation coefficients range (between ±) from 0.0 to 0.20, 0.21 to 0.40, 0.60 to 0.80, and 0.81 to 1.0, respectively, show extremely strong, strong, moderate, weak, and no association 49 . Figure 5 illustrates the relationship between variables present in the database in terms of the correlation coefficient.…”

Section: Data Analysis and Soft Computing Approachesmentioning

confidence: 99%

“…Several researchers have suggested different multicollinearity levels in terms of variance inflation factor (VIF = ). Khatti and Grover 49 have proposed different multicollinearity levels. In the present research, the variance inflation factor (VIF) has been calculated for the input variables, i.e., number of drilling holes, burden-to-diameter ratio, stiffness ratio, burden, spacing, explosive weight, scaling distance, and peak particle velocity (ground vibrations), as mentioned in Table 2 .…”

Section: Data Analysis and Soft Computing Approachesmentioning

confidence: 99%

Assessment of the ground vibration during blasting in mining projects using different computational approaches

Hosseini,

Khatti,

Taiwo

et al. 2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

The investigation compares the conventional, advanced machine, deep, and hybrid learning models to introduce an optimum computational model to assess the ground vibrations during blasting in mining projects. The long short-term memory (LSTM), artificial neural network (ANN), least square support vector machine (LSSVM), ensemble tree (ET), decision tree (DT), Gaussian process regression (GPR), support vector machine (SVM), and multilinear regression (MLR) models are employed using 162 data points. For the first time, the blackhole-optimized LSTM model has been used to predict the ground vibrations during blasting. Fifteen performance metrics have been implemented to measure the prediction capabilities of computational models. The study concludes that the blackhole optimized-LSTM model PPV11 is highly capable of predicting ground vibration. Model PPV11 has assessed ground vibrations with RMSE = 0.0181 mm/s, MAE = 0.0067 mm/s, R = 0.9951, a20 = 96.88, IOA = 0.9719, IOS = 0.0356 in testing. Furthermore, this study reveals that the prediction accuracy of hybrid models is less affected by multicollinearity because of the optimization algorithm. The external cross-validation and literature validation confirm the prediction capabilities of model PPV11. The ANOVA and Z tests reject the null hypothesis for actual ground vibration, and the Anderson–Darling test rejects the null hypothesis for predicted ground vibration. This study also concludes that the GPR and LSSVM models overfit because of moderate to problematic multicollinearity in assessing ground vibration during blasting.

show abstract

“…Following the processing of the incomplete data, the 682 stratified data points were partitioned into a test set and a training set with the 10-fold cross-validation method [38], [39]. The soil category of the center borehole was used as the dependent variable, and the other data from the center borehole and the eight surrounding boreholes were used as the independent variables.…”

Section: B Three-dimensional Information Model For Anchor Engineering...mentioning

confidence: 99%

Three-Dimensional Information Modeling Based on Incomplete Data for Anchor Engineering

Songan,

Wei,

Liang

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Intelligent design is a trend in geotechnical engineering. However, a middle link between demand identification and intelligent design is missing in anchor engineering, resulting in lower efficiency in terms of the interaction between the anchor components, geological body and modeling information. To address this challenge, this paper proposes a method for modeling a three-dimensional anchor engineering information model based on sparse boreholes. This method includes three parts: modeling the geological body, integrated modeling of the anchor components and the geological body, and multiple information assignments based on the anchor model. The feasibility was validated in actual engineering scenarios by using neural networks and rendering engines. The results showed that the prediction accuracy of the strata improved by 17.69%, the modeling efficiency increased by double, and engineering information was fit to the model well. This paper has the application potential to achieve intelligent design in anchor engineering.

show abstract

Prediction of compaction parameters for fine-grained soil: Critical comparison of the deep learning and standalone models

Cited by 41 publications

References 90 publications

Global Research Trends in Soft Soil Management for Infrastructure Development: Opportunities and Challenges

Global Research Trends in Soft Soil Management for Infrastructure Development: Opportunities and Challenges

Assessment of the ground vibration during blasting in mining projects using different computational approaches

Three-Dimensional Information Modeling Based on Incomplete Data for Anchor Engineering

Contact Info

Product

Resources

About