Article
Computer Science, Interdisciplinary Applications
Jing Cao, Juncheng Gao, Hima Nikafshan Rad, Ahmed Salih Mohammed, Mahdi Hasanipanah, Jian Zhou
Summary: The study aims to propose an efficient machine learning model to predict engineering properties of rock, with the XGBoost-FA model showing superior accuracy and generalization compared to other models.
ENGINEERING WITH COMPUTERS
(2022)
Article
Engineering, Environmental
Naima Rabahi-Touloum, Ahmed Brara, David Dessandier
Summary: The ancient ruins of Djemila in northeastern Algeria, listed on the UNESCO World Heritage list since 1982, have limestone with high compressive strength and low porosity, which has experienced characteristic decay patterns over centuries due to exposure to strong climatic variations.
BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT
(2021)
Article
Geosciences, Multidisciplinary
Zuguo Mo, Li Qian, Tianzhi Yao, Yunpeng Gao, Ru Zhang, Enlong Liu, Jianhai Zhang
Summary: The time-dependent deformation and long-term stability of rocks are important considerations in water conservancy and geotechnical engineering. Current theoretical criteria for predicting stability and damage considering time-dependent deformation are lacking. In this study, multi-level creep experiments were conducted on micritic bioclastic limestone obtained from a continuously deforming tunnel in Xinjiang, China. The evolution characteristics of axial crack strain and crack dissipation energy density were investigated, and an instability index based on creep crack dissipation energy density was proposed. The study also established an evolutionary model for the instability index and defined a stress threshold for creep sensitivity. The time-dependent instability index surface was divided into different zones, providing a criterion for evaluating and predicting rock instability and lifespan under specific stress conditions.
FRONTIERS IN EARTH SCIENCE
(2023)
Article
Biochemical Research Methods
Zhenxing Wu, Minfeng Zhu, Yu Kang, Elaine Lai-Han Leung, Tailong Lei, Chao Shen, Dejun Jiang, Zhe Wang, Dongsheng Cao, Tingjun Hou
Summary: A study on learning QSAR models using various ML algorithms for 14 public datasets showed that rbf-SVM, rbf-GPR, XGBoost, and DNN generally perform better than other algorithms. SVM and XGBoost are recommended for regression learning on small datasets, while XGBoost is an excellent choice for large datasets. Ensemble models integrating multiple algorithms can improve prediction accuracy.
BRIEFINGS IN BIOINFORMATICS
(2021)
Article
Environmental Sciences
Jian Peng, Haisheng Han, Yong Yi, Huimin Huang, Le Xie
Summary: This study utilized machine learning and deep learning models to predict particulate matter concentrations at two monitoring sites in central China's Hunan Province. The results showed that the XGBoost model outperformed the deep learning model in terms of prediction ability. The influential mechanism of meteorological variables on PM2.5 concentrations was analyzed.
Article
Business
Sami Ben Jabeur, Cheima Gharib, Salma Mefteh-Wali, Wissal Ben Arfi
Summary: Financial distress prediction is crucial for banks and investors to guide credit decisions. The study introduces a novel approach CatBoost, using gradient boosting decision trees to classify categorical data, showing effective improvement in classification performance compared with other advanced approaches one to three years before failure.
TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE
(2021)
Article
Chemistry, Multidisciplinary
Yu-Hung Tsai, Sheng-Kuang Wu, Shyr-Shen Yu, Meng-Hsiun Tsai
Summary: This study aims to detect stress by analyzing the electroencephalogram (EEG) of table tennis players using machine learning. The findings showed that XGBoost algorithm achieved high accuracy in three-level stress classification.
APPLIED SCIENCES-BASEL
(2022)
Article
Biotechnology & Applied Microbiology
Kangqi Lv, Dayang Chen, Dan Xiong, Huamei Tang, Tong Ou, Lijuan Kan, Xiuming Zhang
Summary: This study developed a functional deleteriousness-based model of CNV (dbCNV) to predict the pathogenicity of CNVs and provide a deeper understanding of the pathogenic mechanism.
Article
Plant Sciences
Shriprabha R. Upadhyaya, Philipp E. Bayer, Cassandria G. Tay Fernandez, Jakob Petereit, Jacqueline Batley, Mohammed Bennamoun, Farid Boussaid, David Edwards
Summary: Gene model prediction is a complex process with potential false positive results. This study developed a machine learning approach using gene and protein-based characteristics to classify potential low confidence gene models. The optimized models showed high prediction accuracy and F-1 scores, which can be useful for supporting future gene annotation processes.
Article
Medicine, Research & Experimental
Yiheng Zhang, Dayu Zhu, Tao Li, Xiaoya Wang, Lili Zhao, Xiaofei Yang, Meijuan Dang, Ye Li, Yulun Wu, Ziwei Lu, Jialiang Lu, Yating Jian, Heying Wang, Lei Zhang, Xiaoyun Lu, Ziyu Shen, Hong Fan, Wenshan Cai, Guilian Zhang
Summary: The study introduces a novel metabolites-based machine learning method that accurately screened five metabolites from serum, capable of detecting acute ischemic stroke and backtracking the onset time. Additionally, two metabolites were found to distinguish the core infarct area from the ischemic penumbra.
BIOMEDICINE & PHARMACOTHERAPY
(2022)
Article
Computer Science, Interdisciplinary Applications
Martin Gauch, Juliane Mai, Jimmy Lin
Summary: Accurate streamflow prediction relies on historical meteorological records and streamflow measurements, but data scarcity is a common issue. This study evaluates tree and LSTM models' sensitivity to limited training data, finding LSTMs outperforming with more data. The study highlights the importance of optimizing predictions by adjusting training data limitations.
ENVIRONMENTAL MODELLING & SOFTWARE
(2021)
Article
Biology
Amiel Meiseles, Denis Paley, Mira Ziv, Yarin Hadid, Lior Rokach, Tamar Tadmor
Summary: Chronic lymphocytic leukemia (CLL) is a common type of leukemia that primarily affects the elderly population. Predicting the necessity of treatment for CLL is important due to the heterogeneous behavior of the disease. This study aimed to develop a machine learning model to predict whether a patient will require treatment for CLL within two years of diagnosis based on demographic data and routine laboratory tests. The results showed that machine learning models outperformed the traditional prognostic scoring system in predicting the need for treatment.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Geosciences, Multidisciplinary
Quanping Zhang, Jianping Chen, Hua Xu, Yule Jia, Xuewei Chen, Zhen Jia, Hao Liu
Summary: This study applied the 3DMPM approach to explore the deep mineral resources of the Lannigou gold deposit in Guizhou. A prediction model based on the XGBoost algorithm was built, which outperformed traditional methods in terms of prediction accuracy.
NATURAL RESOURCES RESEARCH
(2022)
Article
Medicine, General & Internal
Alireza Farzipour, Roya Elmi, Hamid Nasiri
Summary: The researchers analyzed the relationship between symptoms and monkeypox using machine learning methods and found that the XGBoost model based on symptoms had the best accuracy. This study provides a new approach for the diagnosis of monkeypox.
Article
Agricultural Engineering
Wenli Gao, Liang Zhou, Shengquan Liu, Ying Guan, Hui Gao, Bin Hui
Summary: Based on extracted features from Raman spectra, prediction models for lignin content in poplar were developed using regularization algorithms (SVR, DT, RF, LightGBM, CatBoost, and XGBoost). The results showed that RF, LightGBM, CatBoost, and XGBoost outperformed the other algorithms, with test R-2 values >0.91, indicating close prediction to measured values.
BIORESOURCE TECHNOLOGY
(2022)
Article
Engineering, Civil
Minh-Ngoc Vu, Lina Maria Guayacan Carrillo, Gilles Armand
Summary: Continuous field monitoring during drifts excavation at the Meuse/Haute-Marne Underground Research Laboratory showed anisotropic hydromechanical responses, which can be explained by the inherent anisotropy of the Callovo-Oxfordian claystone. A combination of qualitative and quantitative analysis was used to understand the excavation induced pore pressure evolution.
EUROPEAN JOURNAL OF ENVIRONMENTAL AND CIVIL ENGINEERING
(2023)
Article
Engineering, Civil
Ever-Dennys Coarita-Tintaya, Fabrice Golfier, Mountaka Souley, Minh-Ngoc Vu
Summary: The Meuse/Haute-Marne underground research laboratory was built in France to assess the feasibility and safety of a deep geological formation for hosting an industrial radioactive waste repository. The study found that further understanding is needed for observations related to the direction of the major horizontal stress. By developing an elasto-viscoplastic model with transient creep and inherent anisotropies, the hydromechanical behavior of the COx claystone can be better understood.
EUROPEAN JOURNAL OF ENVIRONMENTAL AND CIVIL ENGINEERING
(2023)
Article
Engineering, Geological
Miguel A. Manica, Antonio Gens, Jean Vaunat, Gilles Armand, Minh-Ngoc Vu
Summary: This paper presents a numerical simulation of an underground excavation in the Callovo-Oxfordian claystone formation, focusing on the hydromechanical behavior and water pressure evolution. The simulation successfully reproduces the extent and configuration of the excavation-induced fractured zone, rock displacements, and water pressure changes by incorporating an appropriate constitutive model and parameters.
Article
Engineering, Geological
Miguel A. Manica, Antonio Gens, Jean Vaunat, Gilles Armand, Minh-ngoc Vu
Summary: This study presents a sensitivity analysis on the simulation of an underground excavation in the COx argillaceous formation. The analysis considers various parameters such as initial stress, strength and stiffness anisotropy, and hydraulic and hydromechanical parameters. The results provide a better understanding of the hydromechanical mechanisms associated with underground excavations in COx claystone and similar materials.
Article
Chemistry, Physical
Benjamin Darde, Anh Minh Tang, Jean-Michel Pereira, Patrick Dangla, Jean-Noel Roux, Baptiste Chabot, Jean Talandier, Minh Ngoc Vu
Summary: The experimental investigation focused on the hydromechanical behavior of pellet-powder mixtures used for sealing galleries in radioactive waste disposal concepts. Results showed that water vapor flux dominated hydration, with pellets and inter-pellet pores not in hydraulic equilibrium, and the material gradually lost its granular structure during hydration.
APPLIED CLAY SCIENCE
(2022)
Article
Computer Science, Interdisciplinary Applications
Hui Wang, Remi de la Vaissiere, Minh-Ngoc Vu, Christian La Borderie, Domenico Gallipoli
Summary: This paper investigates the excavation damage zone surrounding an underground tunnel/gallery and its evolution for the performance assessment of a radioactive waste underground repository. Through numerical analysis and experimental validation, the study focuses on the self-sealing mechanism and demonstrates the reliability of the proposed model in accurately describing the self-sealing of fractured COx claystone.
COMPUTERS AND GEOTECHNICS
(2022)
Article
Engineering, Geological
J. J. Zhao, W. Q. Shen, J. F. Shao, Z. B. Liu, M. N. Vu
Summary: A new constitutive model is proposed in this paper for clay-rich rocks, which takes into account the mechanical behavior dependent on water saturation degree and the structural anisotropy commonly exhibited by sedimentary rocks. Unlike most phenomenological models, this model explicitly describes the impact of micro-structural composition on macroscopic mechanical behavior. The efficiency of the proposed model is evaluated through comparisons with experimental data from laboratory tests on Callovo-Oxfordian claystone.
INTERNATIONAL JOURNAL OF ROCK MECHANICS AND MINING SCIENCES
(2022)
Article
Engineering, Geological
Philipp Braun, Pierre Delage, Siavash Ghabezloo, Baptiste Chabot, Nathalie Conil, Minh-Ngoc Vu
Summary: This study reproduces complex coupled thermo-hydromechanical (THM) loading paths in the laboratory to investigate the behavior of clay rocks under the conditions of geological radioactive waste repositories. By controlling radial and axial stresses, pore pressure, and temperature using a specially designed triaxial system, the study is able to maintain axial effective tension on the specimens. The results show that the fracture of clay rocks under effective tension occurs at an average stress of around 3.0 MPa.
ROCK MECHANICS AND ROCK ENGINEERING
(2022)
Article
Construction & Building Technology
Hoang-Quan Nguyen, Bao-Viet Tran, Thai-Son Vu
Summary: This paper develops a new numerical model for evaluating the flexural damage behavior of pervious concrete. By using the phase field method and a Monte Carlo simulation, the failure process of pervious concrete is successfully modeled, and the influence of pore structure on peak load is studied.
CASE STUDIES IN CONSTRUCTION MATERIALS
(2022)
Article
Engineering, Civil
H. T. Trieu, N. B. Nguyen, M. N. Vu, T. T. N. Nguyen, N. H. Tran, D. T. Pham, T. Nguyen-Sy
Summary: This study derives the effective poroelastic properties of N-layered composite assemblage based on the Hashin composite sphere assemblage (CSA) model and the linear elastic solution of n-layer coated inclusion-reinforced materials proposed by Herve and Zaoui. The contribution of this study lies in considering the poromechanical coupling and deriving not only the bulk and shear drained moduli but also the Biot coefficient and the solid Biot modulus. The results are validated against data collected from the open literature.
EUROPEAN JOURNAL OF ENVIRONMENTAL AND CIVIL ENGINEERING
(2023)
Article
Green & Sustainable Science & Technology
Duc-Phi Do, Ngoc-Tuyen Tran, Dashnor Hoxha, Minh-Ngoc Vu, Gilles Armand
Summary: The sustainability of geotechnical infrastructures is closely related to their long-term behavior. It is challenging to predict this behavior directly, and back analyses of observed data are often used to understand long-term response. In-situ observations of drifts constructed in COx claystone in France show a progressive convergence. These convergence measurements reveal significant uncertainty in the time-dependent behavior of this rock, which can impact the stability of the drift in the long term.
Article
Computer Science, Interdisciplinary Applications
Sophie Jung, Minh-Ngoc Vu, Amade Pouya, Siavash Ghabezloo
Summary: This paper presents a constitutive model including threefold anisotropies to describe the behavior of COx claystone, with a focus on the time-dependent behavior. The model is calibrated and adjusted based on laboratory tests and field observations, and successfully reproduces the convergence behavior of the drifts.
COMPUTERS AND GEOTECHNICS
(2022)
Article
Construction & Building Technology
Minh-Ngan Vu, Minh-Ngoc Vu, Duc-Tho Pham, Tuan Nguyen-Sy, Quoc-Bao Nguyen, Viet-Duc Dang
Summary: This paper proposes an analytical model to predict the blowout of the tunneling face in multi-layered soils. The model is validated and applied to different projects to demonstrate its applicability in various scenarios.
Article
Construction & Building Technology
Tuan Nguyen-Sy, Minh-Quan Thai, Ngoc-Minh Vu
Summary: This study developed a simple yet accurate adaptive homogenization approach to model the effective elastic properties of concrete from early age to hardened state. The simulation results were validated against experimental data and showed exceptional agreement. The model's simplicity and accuracy make it highly applicable in practical engineering scenarios.
JOURNAL OF ADVANCED CONCRETE TECHNOLOGY
(2023)
Article
Engineering, Geological
Jueliang Chen, Siyu Liu, Wanqing Shen, Jianfu Shao, Minh-Ngoc Vu
Summary: This paper introduces a novel microstructure-based constitutive model to comprehensively characterize the mechanical behavior of anisotropic clay rocks under water saturation. The model considers elastoplastic deformation, time-dependent behavior, and induced damage, as well as interfacial debonding between the matrix and inclusions. The application of the model is demonstrated through the analysis of Callovo-Oxfordian clayey rocks.
JOURNAL OF ROCK MECHANICS AND GEOTECHNICAL ENGINEERING
(2023)