4.7 Article

Microseismic Location in Hardrock Metal Mines by Machine Learning Models Based on Hyperparameter Optimization Using Bayesian Optimizer

Related references

Note: Only part of the references are listed.
Article Mining & Mineral Processing

Stability prediction of hard rock pillar using support vector machine optimized by three metaheuristic algorithms

Chuanqi Li et al.

Summary: This paper aims to develop hybrid support vector machine (SVM) models improved by three metaheuristic algorithms known as grey wolf optimizer (GWO), whale optimization algorithm (WOA) and sparrow search algorithm (SSA) for predicting the hard rock pillar stability. The results confirmed that the SSA-SVM model is the best prediction model with the highest values of all global indices and local indices. However, the performance of the SSA-SVM model for predicting the unstable pillar is not as good as those for stable and failed pillars.

INTERNATIONAL JOURNAL OF MINING SCIENCE AND TECHNOLOGY (2023)

Article Computer Science, Interdisciplinary Applications

Joint event location and velocity model update in real-time for downhole microseismic monitoring: A deep learning approach

Daniel Wamriew et al.

Summary: Accurate event location in downhole microseismic monitoring largely depends on the accuracy of the reconstructed velocity model. With proper inversion approach, a deep learning approach can efficiently and accurately locate microseismic events and update the velocity model in real-time.

COMPUTERS & GEOSCIENCES (2022)

Article Computer Science, Artificial Intelligence

An optimized system of GMDH-ANFIS predictive model by ICA for estimating pile bearing capacity

Danial Jahed Armaghani et al.

Summary: A new technique, ANFIS-GMDH-ICA, is proposed for predicting pile bearing capacity, with higher accuracy compared to traditional models. This technology can be utilized in the field of foundation engineering and design.

ARTIFICIAL INTELLIGENCE REVIEW (2022)

Article Construction & Building Technology

Optimization of random forest through the use of MVO, GWO and MFO in evaluating the stability of underground entry-type excavations

Jian Zhou et al.

Summary: This study investigates the application of hybrid models based on the random forest algorithm for stability evaluation in underground entry-type excavations. Three optimization strategies are employed to establish three hybrid models, and the classification ability of these models is validated using multiple measurement indexes.

TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY (2022)

Article Construction & Building Technology

Cross-correlation stacking-based microseismic source location using three metaheuristic optimization algorithms

Jian Zhou et al.

Summary: Microseismic location systems are known for their high-speed and high precision. However, the requirement of high precision can lead to slower calculation speed. This research focuses on using metaheuristic algorithms to improve the performance of cross-correlation stacking (CCS) for better location accuracy. The study shows that appropriate control parameters can greatly enhance the performance of metaheuristic algorithms, with moth flame optimization (MFO) being the most effective. CCS is found to be superior to traditional methods in terms of location efficiency, and its performance is influenced by the speed model and number of sensors.

TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY (2022)

Article Chemistry, Physical

Deep Neural Network-Evaluated Thermal Conductivity for Two-Phase WC-M (M = Ag, Co) Cemented Carbides

Shiyi Wen et al.

Summary: In this study, DNN is used to evaluate and predict the thermal conductivities of WC-M cemented carbides. The results show good agreements between the DNN-predicted thermal conductivities and the measured ones, demonstrating the effectiveness of DNN in exploring material properties. Compared to previous physical models, DNN shows similar robust predicting ability. This study highlights the efficiency of machine learning in exploring material properties in high-dimensional parameter space with less time consumption and costs.

MATERIALS (2022)

Article Computer Science, Interdisciplinary Applications

Developing a hybrid model of salp swarm algorithm-based support vector machine to predict the strength of fiber-reinforced cemented paste backfill

Enming Li et al.

Summary: This study tested the impact of different mixture ratios on backfilling strength in Fankou lead-zinc mine, and found that polypropylene fibers can improve CPB strength, while straw fibers may decrease it in some cases. Using SVM technique with three heuristic algorithms, the SSA-SVM method was recommended for modeling the complexity of interactions in fiber-reinforced CPB and predicting its strength.

ENGINEERING WITH COMPUTERS (2021)

Article Engineering, Geological

Identification of Microseismic Events in Rock Engineering by a Convolutional Neural Network Combined with an Attention Mechanism

Shibin Tang et al.

Summary: Microseismic technology is widely used in rock engineering applications to protect workers and monitor construction. This study proposes a new end-to-end training network architecture with a depthwise spatial and channel attention module to improve performance. The ResSCA network architecture, incorporating modified residual connections, achieved improved accuracy rates in microseismic event recognition.

ROCK MECHANICS AND ROCK ENGINEERING (2021)

Article Automation & Control Systems

Optimization of support vector machine through the use of metaheuristic algorithms in forecasting TBM advance rate

Jian Zhou et al.

Summary: This research aims to optimize the hyper-parameters of the support vector machine technique through the use of three optimization algorithms, namely gray wolf optimization, whale optimization algorithm, and moth flame optimization, for predicting the advance rate of a tunnel boring machine in hard rock conditions. The results indicate that the moth flame optimization algorithm can better capture the hyperparameters of the SVM model in predicting TBM AR.

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE (2021)

Article Computer Science, Interdisciplinary Applications

Bayesian topology optimization for efficient design of origami folding structures

Sourabh Shende et al.

Summary: Bayesian optimization (BO) is a popular method for solving optimization problems with expensive objective functions, although its application in structural optimization is still in early stages. By using a Gaussian process (GP) as a surrogate model, BO demonstrates the ability to efficiently solve origami-inspired design problems, showing better computational efficiency compared to traditional methods.

STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION (2021)

Review Computer Science, Artificial Intelligence

Application of deep learning algorithms in geotechnical engineering: a short critical review

Wengang Zhang et al.

Summary: With the rise of big data era, deep learning has become crucial in the field of artificial intelligence, attracting researchers globally. This study presents the state of practice of deep learning in geotechnical engineering, elaborating on four major algorithms and their applications.

ARTIFICIAL INTELLIGENCE REVIEW (2021)

Article Construction & Building Technology

On the use of acquisition function-based Bayesian optimization method to efficiently tune SVM hyperparameters for structural damage detection

Anand Kumar Agrawal et al.

Summary: This article presents a novel application of Bayesian optimization method for optimizing the hyperparameters of SVM for structural damage detection. By estimating the objective function and efficiently searching the hyperparameter space, the BO approach shows higher efficiency compared to PSO in terms of the number of function evaluations.

STRUCTURAL CONTROL & HEALTH MONITORING (2021)

Article Construction & Building Technology

Prediction of TBM performance in fresh through weathered granite using empirical and statistical approaches

Danial Jahed Armaghani et al.

Summary: This study successfully predicted the penetration rate and advance rate of tunnel boring machines in different weathering zones through the development of new equations, demonstrating the accuracy of these new models.

TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY (2021)

Article Construction & Building Technology

Real-time prediction of rockburst intensity using an integrated CNN-Adam-BO algorithm based on microseismic data and its engineering application

Xin Yin et al.

Summary: This paper presents an integrated CNN-Adam-BO algorithm based on microseismic monitoring data for real-time prediction of rockburst intensity, demonstrating superior performance compared to other machine learning models. It also illustrates a workflow for constructing a field rockburst risk warning system using the model, discusses the impact of data quality on model performance, and verifies the effectiveness of the proposed method through comparison with existing techniques.

TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY (2021)

Article Computer Science, Artificial Intelligence

Coverage-Based Designs Improve Sample Mining and Hyperparameter Optimization

Gowtham Muniraju et al.

Summary: Sampling effective solutions from large search spaces is a recurring idea in machine learning, and sequential optimization has become a popular approach. By proposing a coverage-based sample design method and developing algorithms for effective sample synthesis, we show that our approach consistently outperforms existing exploratory sampling methods in sample mining and hyperparameter optimization for supervised learning.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2021)

Article Physics, Multidisciplinary

Cross-related microseismic location based on improved particle swarm optimization and the double-difference location method of jointed coal rock mass

Kai-kai Wang et al.

Summary: The study introduced the double-difference (DD) location method to improve the accuracy of microseismic monitoring, and used an improved particle swarm algorithm to enhance the randomness of initial locations. Practical results demonstrated that this method significantly increased location accuracy and provided necessary theoretical and technical support for source location in jointed coal rock mass in deep mining.

WAVES IN RANDOM AND COMPLEX MEDIA (2021)

Article Engineering, Geological

Prediction of blasting mean fragment size using support vector regression combined with five optimization algorithms

Enming Li et al.

Summary: The main purpose of blasting operations is to produce desired and optimum mean size rock fragments to improve production efficiency and reduce costs. AI-based models are popular for predicting blasting fragmentation, with the Grey Wolf Optimization Support Vector Regression model showing the best comprehensive performance.

JOURNAL OF ROCK MECHANICS AND GEOTECHNICAL ENGINEERING (2021)

Article Geosciences, Multidisciplinary

Predicting rock size distribution in mine blasting using various novel soft computing models based on meta-heuristics and machine learning algorithms

Chengyu Xie et al.

Summary: Four intelligent models were proposed in this study to predict the size of rock distribution in mining blasting, with the FFA-GBM model providing the highest accuracy. The combination of nature-inspired and machine learning algorithms is effective in optimizing blasting parameters and improving blasting efficiency in open mines.

GEOSCIENCE FRONTIERS (2021)

Article Geosciences, Multidisciplinary

Predicting TBM penetration rate in hard rock condition: A comparative study among six XGB-based metaheuristic techniques

Jian Zhou et al.

Summary: This study aimed to develop hybrid models to predict TBM performance, with PSO-XGB technique identified as the best predictive model. Sensitivity analysis revealed that UCS, BTS, and TFC have the greatest impact on TBM performance.

GEOSCIENCE FRONTIERS (2021)

Article Computer Science, Artificial Intelligence

How to tune the RBF SVM hyperparameters? An empirical evaluation of 18 search algorithms

Jacques Wainer et al.

Summary: Selecting hyperparameters for SVM with RBF kernel is crucial for performance, with various algorithms available for this non-convex optimization problem. Empirical comparison shows that Parzen estimator and particle swarm optimization can find better hyperparameters with minimal increase in computation time, and excessive effort on hyperparameter search may not lead to better performance for future data.

ARTIFICIAL INTELLIGENCE REVIEW (2021)

Article Engineering, Geological

Time Series Prediction of Microseismic Multi-parameter Related to Rockburst Based on Deep Learning

Hang Zhang et al.

Summary: This study explores methods for predicting the time series evolution of microseismic parameters during rockburst development, utilizing a combination of dynamic moving-window method and improved CNN to establish various models for predicting different rockburst characteristics. The results indicate that these models can effectively predict the evolution trends of key characteristics in rockbursts, providing time labels for rockburst prediction and risk assessment, which aids in early warning of rockbursts.

ROCK MECHANICS AND ROCK ENGINEERING (2021)

Article Geosciences, Multidisciplinary

Updating the models and uncertainty of mechanical parameters for rock tunnels using Bayesian inference

Hongbo Zhao et al.

Summary: The study introduces a system of Bayesian inferences to update mechanical parameters of a rock tunnel model dynamically using monitored field data. The regular supplementation of monitoring data greatly enhances the performance of Bayesian inferences in determining the mechanical parameters of the surrounding rock mass in a tunnel model.

GEOSCIENCE FRONTIERS (2021)

Article Engineering, Civil

Estimation of the TBM advance rate under hard rock conditions using XGBoost and Bayesian optimization

Jian Zhou et al.

Summary: In this study, a hybrid model of XGBoost with BO was used to improve the accuracy of predicting TBM AR under hard rock conditions. By collecting data from an actual tunnel project in Malaysia, the proposed BO-XGBoost model demonstrated high accuracy in predicting TBM AR. The study also showed that machine parameters have the greatest impact on TBM AR compared to rock mass and material properties.

UNDERGROUND SPACE (2021)

Article Operations Research & Management Science

Comprehensive analysis of gradient-based hyperparameter optimization algorithms

O. Y. Bakhteev et al.

ANNALS OF OPERATIONS RESEARCH (2020)

Article Computer Science, Interdisciplinary Applications

Micro-seismic source location determined by a modified objective function

L. Z. Wu et al.

ENGINEERING WITH COMPUTERS (2020)

Article Environmental Sciences

Soybean yield prediction from UAV using multimodal data fusion and deep learning

Maitiniyazi Maimaitijiang et al.

REMOTE SENSING OF ENVIRONMENT (2020)

Review Geochemistry & Geophysics

Recent Advances and Challenges of Waveform-Based Seismic Location Methods at Multiple Scales

Lei Li et al.

REVIEWS OF GEOPHYSICS (2020)

Review Geosciences, Multidisciplinary

State-of-the-art review of soft computing applications in underground excavations

Wengang Zhang et al.

GEOSCIENCE FRONTIERS (2020)

Article Environmental Sciences

A remote sensing approach to mapping fire severity in south-eastern Australia using sentinel 2 and random forest

Rebecca Gibson et al.

REMOTE SENSING OF ENVIRONMENT (2020)

Article Geosciences, Multidisciplinary

Identifying Different Classes of Seismic Noise Signals Using Unsupervised Learning

Christopher W. Johnson et al.

GEOPHYSICAL RESEARCH LETTERS (2020)

Article Automation & Control Systems

Deep neural network model with Bayesian hyperparameter optimization for prediction of NOx at transient conditions in a diesel engine

Seunghyup Shin et al.

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE (2020)

Article Computer Science, Artificial Intelligence

Fast hyperparameter tuning using Bayesian optimization with directional derivatives

Tinu Theckel Joy et al.

KNOWLEDGE-BASED SYSTEMS (2020)

Review Multidisciplinary Sciences

Machine learning for data-driven discovery in solid Earth geoscience

Karianne J. Bergen et al.

SCIENCE (2019)

Article Materials Science, Multidisciplinary

Using deep neural network with small dataset to predict material defects

Shuo Feng et al.

MATERIALS & DESIGN (2019)

Article Computer Science, Information Systems

Research on Microseismic Source Locations Based on Deep Reinforcement Learning

Yangxu Wu et al.

IEEE ACCESS (2019)

Article Geosciences, Multidisciplinary

Prediction of shear strength of soft soil using machine learning methods

Binh Thai Pham et al.

CATENA (2018)

Article Engineering, Geological

Microseismic monitoring and stability analysis of the right bank slope at Dagangshan hydropower station after the initial impoundment

Xingzong Liv et al.

INTERNATIONAL JOURNAL OF ROCK MECHANICS AND MINING SCIENCES (2018)

Review Geochemistry & Geophysics

Locating Leaking Buried Pipes Based on Ground Microseismic Records in 3D Space

Fei Cheng et al.

SURVEYS IN GEOPHYSICS (2018)

Article Construction & Building Technology

Micro-seismic event detection and location in underground mines by using Convolutional Neural Networks (CNN) and deep learning

Linqi Huang et al.

TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY (2018)

Article Engineering, Geological

A zoning model for coal mining - induced strata movement based on microseismic monitoring

Guanwen Cheng et al.

INTERNATIONAL JOURNAL OF ROCK MECHANICS AND MINING SCIENCES (2017)

Article Computer Science, Artificial Intelligence

Pre-training the deep generative models with adaptive hyperparameter optimization

Chengwei Yao et al.

NEUROCOMPUTING (2017)

Article Energy & Fuels

Seismic monitoring and analysis of excessive gas emissions in heterogeneous coal seams

Guangyao Si et al.

INTERNATIONAL JOURNAL OF COAL GEOLOGY (2015)

Review Multidisciplinary Sciences

Deep learning

Yann LeCun et al.

NATURE (2015)

Article Engineering, Geological

Microseismic monitoring and numerical simulation on the stability of high-steep rock slopes in hydropower engineering

Chun'an Tang et al.

JOURNAL OF ROCK MECHANICS AND GEOTECHNICAL ENGINEERING (2015)

Article Geochemistry & Geophysics

PreSEIS:: A neural network-based approach to earthquake early warning, for finite faults

Maren Boese et al.

BULLETIN OF THE SEISMOLOGICAL SOCIETY OF AMERICA (2008)

Article Computer Science, Artificial Intelligence

Random forests

L Breiman

MACHINE LEARNING (2001)