Figure 3 - uploaded by Xin Yin
Content may be subject to copyright.
Source publication
Rockburst is a common dynamic geological hazard, severely restricting the development and utilization of underground space and resources. As the depth of excavation and mining increases, rockburst tends to occur frequently. Hence, it is necessary to carry out a study on rockburst prediction. Due to the nonlinear relationship between rockburst and i...
Similar publications
![Workflow for the deep ensemble based CO2\documentclass[12pt]{minimal}...](publication/384084357/figure/fig1/AS:11431281282999951@1728612192287/Workflow-for-the-deep-ensemble-based-CO2documentclass12ptminimal_Q320.jpg)
Excessive carbon dioxide (CO2\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\text {CO}_{2}$$\end{document}) emissions pose a formidable challenge, driving global clima...
Citations
... association between SC and the none rockburst in the generated data. (Pu et al., 2018); ②Decision tree (DT) (Ghasemi et al., 2020); ③ KNN (Yin et al., 2021); ④ Light gradient boosting machine (LightGBM) (Li et al., 2022); ⑤ Extreme gradient boosting (XGBoost) (Li et al., 2022); ⑥ RF (RF without optimization); ⑦ Bo-RF; ⑧ BP-SVM (Guo et al., 2022). M-P: macro-precision, M-R: macro-recall, M-F 1 : macro-F 1 . ...
To address the limitation of traditional machine learning models in explaining the rockburst intensity prediction process, this study proposes an interpretable rockburst intensity prediction model. The model was developed using 350 sets of actual rockburst sample data to explore the impact of input metrics on the final rockburst intensity level. The collected data underwent pre-processing using the isolation forest algorithm and synthetic minority oversampling technique. The random forest model was optimized through 5-fold cross-validation and the Optuna framework, resulting in the establishment of an Optuna-random forest (Op-RF) model that generates decision rules through its internal decision tree, utilizing the properties of the random forest model. The model was further interpreted using the Shapley additive explanations algorithm, both locally and globally. The results demonstrate that the proposed model achieved an area under curve score of 0.984. In comparison to eight other machine learning models, the proposed Op-RF model demonstrated superior accuracy, precision, recall, and F1 score. The model provides a transparent explanation of the prediction process, linking impact characteristics to the final output. Additionally, a cloud deployment method for the rockburst intensity prediction model is provided and its effectiveness is demonstrated through engineering verification. The proposed model offers a new approach to the application of machine learning in rockburst intensity prediction.
... The diversity and complementarity of different models can be leveraged to obtain more robust and accurate predictions. Ensemble learning allows for the integration of the "wisdom" of multiple models by combining their results through voting, weighting, or other techniques, which enhances the model's resistance to noise and its generalization ability, as concluded by numerous studies [47,48]. ...
This paper examines how smart cities can address land subsidence and liquefaction in the context of rapid urbanization in Japan. Since the 1960s, liquefaction has been an important topic in geotechnical engineering, and extensive efforts have been made to evaluate soil resistance to liquefaction. Currently, there is a lack of machine learning applications in smart cities that specifically target geological hazards. This study aims to develop a high-performance prediction model for estimating the depth of the bearing layer, thereby improving the accuracy of geotechnical investigations. The model was developed using actual survey data from 433 points in Setagaya-ku, Tokyo, by applying two machine learning techniques: artificial neural networks (ANNs) and bagging. The results indicate that machine learning offers significant advantages in predicting the depth of the bearing layer. Furthermore, the prediction performance of ensemble learning improved by about 20% compared to ANNs. Both interdisciplinary approaches contribute to risk prediction and mitigation, thereby promoting sustainable urban development and underscoring the potential of future smart cities.
... Nevertheless, these algorithms often have limitations due to the intricate nature of the rockburst occurrence mechanism. The KNN algorithm (Yin et al. 2021) requires a strong correlation within the data, yet the relationship among the rockburst data are unclear. Similarly, the SVM algorithm (Bao et al. 2023) relies on high-quality data and is less effective when the data include noise elements. ...
Rockburst prediction has important significance for individual safety in deep geologic engineering. To accurately predict the rockburst-intensity level, this paper proposes a rockburst prediction method via multiscale graph convolutional neural network. In the method, six rockburst indicators of each rockburst are utilized as a rockburst sample, and data segmentation oversampling of rockburst samples solves the unbalanced class-distribution problem of rockburst-data samples. The similarity perception for capturing similarity structure relationships of rockburst samples in Euclidean space is given, and a novel indicator correlation constraint of the similarity relationships with multiple rockburst criteria is designed, which can reduce the structure distortion of Euclidean space. By integrating the perception and the constraint, criterion-constrained graph structure data are constructed under the graph neural network framework. On the basis of the graph data, a multiscale graph convolutional neural network is further proposed, and multiscale information with the topology structure and criterion-constrained relationships can be effectively captured by the network, which can achieve the accurate prediction of the rockburst-intensity level. The effectiveness of the proposed method is demonstrated by extensive experiment analysis.
... However, ensemble learning can use the "wisdom" of multiple models to integrate the results of multiple models through voting, weighting, etc., which enhances the model's anti-noise ability and generalization ability. It can be concluded from many literatures [41,42]. Secondly, there are certain differences between individual learners, which will lead to different classification boundaries, that is, there may be errors. ...
This paper explores how smart cities can cope with land subsidence and liquefaction in the context of rapid urbanization in Japan. Since the 1960s, liquefaction has become an important topic in geotechnical engineering, and great efforts have been made to evaluate the resistance of soil to liquefaction. There is currently a lack of machine learning applications specifically for smart cities in areas such as geological hazards. This study uses two machine learning techniques, artificial neural networks and ensemble learning, to obtain a prediction model with high performance in predicting the bearing layer depth to improve the accuracy of geo-engineering surveys. The model was developed by analyzing actual survey data from 433 locations in Setegaya, Tokyo, by using artificial neural networks (ANNs) and bagging, respectively. The results show that machine learning has great advantages in predicting the bearing layer depth. In addition, compared with a single model such as artificial neural networks, the prediction performance of ensemble learning can be improved by about 20%. Both interdisciplinary approaches can help predict address risks and thus promote sustainable urban development, highlighting the potential of smart cities in the future.
... Although econometric models are straightforward, they cannot capture effectively the overall trend of prices due to assumptions and parameter tuning (Jnr et al., 2022). In recent years, DL models have obtained satisfactory output in dealing with nonlinear data (Yin et al., 2021). However, the performance of DL models may be over-fitting to decrease the level of prediction accuracy (Williams et al., 2021). ...
Iron ore has had a highly global market since setting a new pricing mechanism in 2008. With current dollar values, iron ore concentrate for sale price, which was 218 per tonne (62% Fe) in mid-2021. It is hovering around $120 in October 2023 (cf. https://tradingeconomics.com/commodity/iron-ore). The uncertainty associated with these fluctuations creates hardship for iron ore mine operators and steelmakers in planning mine development and making future sale agreements. Therefore, iron ore price forecasting is of special importance. This paper proposes a cutting-edge multi-echelon tandem learning (METL) model to forecast iron ore prices. This model comprises variational mode decomposition (VMD), multi-head convolutional neural network (MCNN), stacked long short-term-memory (SLSTM) network, and attention mechanism (AT). In the proposed METL (i.e., the combination of VMD, MCNN, SLSTM, AT) model, the VMD decomposes the time series data into sub-sequential modes for better measuring volatility. Then, the MCNN is applied as an encoder to extract spatial features from the decomposed sub-sequential modes. The SLSTM network is adopted as a decoder to extract temporal features. Finally, the AT is employed to capture spatial–temporal features to obtain the complete forecasting process. Extensive computational experiments are conducted based on daily-based and weekly-based iron ore price datasets with different time scales. It was validated that the proposed METL model outperformed its single-echelon and other categorized models by 10–65% in range. The proposed METL model can improve the prediction accuracy of iron ore prices and thus help mining and steelmaking enterprises to determine their sale or purchase strategies.
... The establishment of the indicator database is mainly based on the static and dynamic indicators obtained from global rockburst cases, rock indoor tests, numerical simulations, or field monitoring. At present, scholars have carried out the following studies to address the problems of the original database (Zhang et al. 2020b;Yin et al. 2021c;Zhou et al. 2021): ...
Rockbursts frequently occur in tunneling projects and pose a serious threat to workers and the environment. Therefore, accurate prediction of rockbursts is of great practical significance. Currently, various rockburst prediction methods exist, with static and dynamic indicators playing a key role. This paper analyzes the importance of rockburst prediction methods based on Citespace software. The results indicate that microseismic monitoring, acoustic emission, and machine learning are the most important methods. The paper focuses on four common rockburst prediction methods: empirical methods, microseismic monitoring, acoustic emission, and machine learning, from the perspective of static and dynamic indicators. The performance and application of static and dynamic indicators in the four common prediction methods in recent years are summarized, the limitations of static and dynamic indicators at this stage are discussed, and possible future development directions are proposed. This paper provides the necessary perspective and tools for better understanding the advantages and disadvantages of static and dynamic indicators in the four rockburst prediction methods.
... Researchers have made significant advancements in their understanding of methods and mechanisms by using innovative approaches in recent years. The practical relevance of the learned knowledge has been empirically proven in the fields of engineering, environment, and risk analysis [35][36][37][38]. However, our present level of scientific understanding is insufficient to create underground engineering projects that possess the essential qualities of safety, reliability, environmental sustainability, and the ability to sustain innovative solutions, especially in situations where rigorous testing is not feasible. ...
Pillar stability is of paramount importance in ensuring the safety of underground rock engineering structures. The stability of pillars directly influences the structural integrity of the mine and mitigates the risk of collapses or accidents. Therefore, assessing pillar stability is crucial for safe, productive, reliable, and profitable underground mining engineering processes. This study developed the application of decision intelligence-based predictive modelling of hard rock pillar stability in underground engineering structures using K-Nearest Neighbour coupled with the grey wolf optimization algorithm (KNN-GWO). Initially, a substantial dataset consisting of 236 different pillar cases was collected from seven underground hard rock mining engineering projects. This dataset was gathered by considering five significant input variables, namely pillar width, pillar height, pillar width/height ratio, uniaxial compressive strength, and average pillar stress. Secondly, the original hard rock pillar stability level has been classified into three types: failed, unstable, and stable, based on the pillar's instability mechanism and failure process. Thirdly, several visual relationships were established in order to ascertain the correlation between input variables and the corresponding pillar stability level. Fourthly, the entire pillar database was randomly divided into a training da-taset and testing dataset with a 70:30 sampling method. Moreover, the (KNN-GWO) model was developed to predict the stability of pillars in hard rock mining. Lastly, the performance of the suggested predictive model was evaluated using accuracy, precision, recall, F1-score, and a confusion matrix. The findings of the proposed model offer a superior benchmark for accurately predicting the stability of hard rock pillars. Therefore, it is recommended to employ decision intelligence models in mining engineering in order to effectively prioritise safety measures and improve the efficiency of operational processes, risk management, and decision-making related to underground engineering structures.
... On the other hand, the Stacking Ensemble method combines multiple machine learning models [31], allowing us to leverage the strengths and unique capabilities of each model. This approach improves overall performance and mitigates the weaknesses of individual models [32]. Based on the findings of Ramachandran et al. [23], we employ the TF-IDF technique for feature extraction. ...
Dynamic pricing of airline tickets in competitive markets requires innovation that responds to market changes. Dynamic pricing is also influenced by public events, such as sporting events, music concerts, and more. This study aims to increase airline ticket revenue by optimizing flight occupancy during events. The data used is obtained from social media platform Twitter (X), with eight event classifications: soccer events, music concerts, volcanic eruptions, earthquakes, riots, floods, motorcycle racing, and others (non-events). We used a stacking ensemble method for data labeling and fine-tuned the BERT model for event detection. The stacking ensemble method achieved an accuracy rate of 0.99, while the fine-tuned BERT model produced an accuracy rate of 0.94. These results show a significant contribution to improving the accuracy and effectiveness of dynamic pricing. These findings not only offer a solution to the dynamic pricing challenge but also open opportunities to increase revenue by understanding event sentiment, providing competitiveness and flexibility in a dynamic market. With a focus on accurate event detection, this research paves the way for the development of more intelligent and adaptive dynamic pricing models by combining the strengths of the Stacking Ensemble labeling technique and BERT model fine-tuning to improve model accuracy.
... Machine learning tools such as artificial neural networks (Nguyen et al., 2020;Armaghani et al., 2021), random forests (Matin et al., 2018), support vector machines (Armaghani et al., 2020), and others have been increasingly integrated into the fields of mining and rock engineering. Numerous applications have consistently demonstrated the robust predictive capabilities of machine learning techniques across various domains, including blasting vibration prediction (Nguyen and Bui, 2022;Armaghani et al., 2023), fly rock prediction (Jamei et al., 2021), microseismic location (Zhai et al., 2022c), rockburst prediction (Yin et al., 2021), and more. While there have been numerous successful instances of rock strength prediction using machine-learning techniques, the majority of these have primarily focused on static compressive strength (Lei et al., 2022;Li et al., 2022a). ...
In cold regions, the dynamic compressive strength (DCS) of rock damaged by freeze-thaw weathering significantly influences the stability of rock engineering. Nevertheless, testing the dynamic strength under freeze-thaw weathering conditions is often both time-consuming and expensive. Therefore, this study considers the effect of characteristic impedance on DCS and aims to quickly determine the DCS of frozen-thawed rocks through the application of machine-learning techniques. Initially, a database of DCS for frozen-thawed rocks, comprising 216 rock specimens, was compiled. Three external load parameters (freeze-thaw cycle number, confining pressure, and impact pressure) and two rock parameters (characteristic impedance and porosity) were selected as input variables, with DCS as the predicted target. This research optimized the kernel scale, penalty factor, and insensitive loss coefficient of the support vector regression (SVR) model using five swarm intelligent optimization algorithms, leading to the development of five hybrid models. In addition, a statistical DCS prediction equation using multiple linear regression techniques was developed. The performance of the prediction models was comprehensively evaluated using two error indexes and two trend indexes. A sensitivity analysis based on the cosine amplitude method has also been conducted. The results demonstrate that the proposed hybrid SVR-based models consistently provided accurate DCS predictions. Among these models, the SVR model optimized with the chameleon swarm algorithm exhibited the best performance, with metrics indicating its effectiveness, including root mean square error (RMSE) = 3.9675, mean absolute error (MAE) = 2.9673, coefficient of determination (R2) = 0.98631, and variance accounted for (VAF) = 98.634. This suggests that the chameleon swarm algorithm yielded the most optimal results for enhancing SVR models. Notably, impact pressure and characteristic impedance emerged as the two most influential parameters in DCS prediction. This research is anticipated to serve as a reliable reference for estimating the DCS of rocks subjected to freeze-thaw weathering.
... performed using linear discriminant analysis as a noise reduction technique 72 with 97% accuracy. By stratifying sampling 73 , the input data are divided between training (75%) and testing (25%) to account for the problem of data imbalance. Thus, both sets have a proportional representation of class. ...
The lithology log, an integral component of the master log, graphically portrays the encountered lithological sequence during drilling operations. In addition to offering real-time cross-sectional insights, lithology logs greatly aid in correlating and evaluating multiple sections efficiently. This paper introduces a novel workflow reliant on an enhanced weighted average ensemble approach for producing high-resolution lithology logs. The research contends with a challenging multiclass imbalanced lithofacies distribution emerging from substantial heterogeneities within subsurface geological structures. Typically, methods to handle imbalanced data, e.g., cost-sensitive learning (CSL), are tailored for issues encountered in binary classification. Error correcting output code (ECOC) originates from decomposition strategies, effectively breaking down multiclass problems into numerous binary subproblems. The database comprises conventional well logs and lithology logs obtained from five proximate wells within a Middle Eastern oilfield. Utilizing well-known machine learning (ML) algorithms, such as support vector machine (SVM), random forest (RF), decision tree (DT), logistic regression (LR), and extreme gradient boosting (XGBoost), as baseline classifiers, this study aims to enhance the accurate prediction of underground lithofacies. Upon recognizing a blind well, the data from the remaining four wells are utilized to train the ML algorithms. After integrating ECOC and CSL techniques with the baseline classifiers, they undergo evaluation. In the initial assessment, both RF and SVM demonstrated superior performance, prompting the development of an enhanced weighted average ensemble based on them. The comprehensive numerical and visual analysis corroborates the outstanding performance of the developed ensemble. The average Kappa statistic of 84.50%, signifying almost-perfect agreement, and mean F-measures of 91.04% emphasize the robustness of the designed ensemble-based workflow during the evaluation of blind well data.
