Interpretable ensemble machine-learning models for strength activity index prediction of iron ore tailings
Source abstract
Abstract
When iron ore tailings (IOTs) are used as supplementary cementitious materials, their strength activity index is an important factor affecting the mechanical properties of IOTs-cement composites. In this study, four ensemble machine learning (ML) models, including Gradient Boosting Regression Tree (GBRT), EXtreme Gradient Boosting (XGBoost), Adaptive Boosting (Adaboost), and Categorical Boosting (Catboost), were used to predict the strength activity index of IOTs. Shapley additive explanations (SHAP) were also utilized to measure the impact of influencing elements in the strength activity index of IOTs. Results showed that the R2 values of all four models were above 0.83 on the testing set. Dosage, water-solid ratio, and D0.5 particle size were found to be the most important factors affecting the strength activity index of IOTs. For high-silica IOTs, the strength activity index increased with the increase of dosage when the dosage was less than 10%, while when the dosage was higher than 10%, the opposite situation occurred. However, for low-silica IOTs, the strength activity index decreased continuously with the increase of dosage. This research developed a new approach for predicting the strength activity index of IOTs and provided some suggestions for the application of IOTs in cement-based materials.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Tailings Management and Properties · Infrastructure Maintenance and Monitoring · Non-Destructive Testing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (75)
Show source-provided references
1. Cementitious activity of iron ore tailing and its utilization in cementitious materials, bricks and concrete10.1016/j.conbuildmat.2021.123022 ↗
2. An evaluation of iron ore tailings characteristics and iron ore tailings concrete properties10.1016/j.conbuildmat.2021.122968 ↗
3. Preparation of micro-iron ore tailings by wet-grinding and its application in sulphoaluminate cement10.32604/jrm.2022.017372 ↗
4. Activation of hydration properties of iron ore tailings and their application as supplementary cementitious materials in cement10.1016/j.powtec.2019.11.002 ↗
5. Test research on the effects of mechanochemically activated iron tailings on the compressive strength of concrete10.1016/j.conbuildmat.2016.05.020 ↗
6. Different effects of wet and dry grinding on the activation of iron ore tailings10.32604/jrm.2021.015793 ↗
7. Mechanical activation as an innovative approach for the preparation of pozzolan from iron ore tailings10.1016/j.mineng.2019.106068 ↗
8. Cementitious activity optimization studies of iron tailings powder as a concrete admixture10.1016/j.conbuildmat.2020.120760 ↗
9. M. Chen, B. Li, W. Wei, Z.J.M.M. Zhu, Reactive Activity of Iron Tailings Powder and its Enhancement Effect upon Concrete, 2013.
10. Analyzing the compressive strength of green fly ash based geopolymer concrete using experiment and machine learning approaches10.1016/j.conbuildmat.2020.118581 ↗
11. Machine learning to predict properties of fresh and hardened alkali-activated concrete10.1016/j.cemconcomp.2020.103863 ↗
12. Prediction of the sulfate resistance for recycled aggregate concrete based on ensemble learning algorithms10.1016/j.conbuildmat.2021.125917 ↗
13. Modeling of compressive strength of self-compacting rubberized concrete using machine learning10.3390/ma14154346 ↗
14. Machine learning-based compressive strength prediction for concrete: an adaptive boosting approach10.1016/j.conbuildmat.2019.117000 ↗
15. Prediction of surface chloride concentration of marine concrete using ensemble machine learning10.1016/j.cemconres.2020.106164 ↗
16. Machine learning based prediction model for thermal conductivity of concrete
17. Toward intelligent construction: prediction of mechanical properties of manufactured-sand concrete using tree-based models10.1016/j.jclepro.2020.120665 ↗
18. =cmarkid_boolean AND{11502}}"Designing sustainable concrete mixture by developing a new machine learning technique10.1016/j.jclepro.2020.120578 ↗
19. Prediction of concrete coefficient of thermal expansion and other properties using machine learning10.1016/j.conbuildmat.2019.05.006 ↗
20. Prediction of failure modes, strength, and deformation capacity of RC shear walls through machine learning
21. Data-driven machine-learning-based seismic failure mode identification of reinforced concrete shear walls10.1016/j.engstruct.2020.110331 ↗
22. Explaining prediction models and individual predictions with feature contributions10.1007/s10115-013-0679-x ↗
23. Using machine learning techniques for predicting autogenous shrinkage of concrete incorporating superabsorbent polymers and supplementary cementitious materials
24. Interpretable XGBoost-SHAP Machine-Learning Model for Shear Strength Prediction of Squat RC Walls10.1061/(ASCE)ST.1943-541X.0003115 ↗
25. Machine learning approach for investigating chloride diffusion coefficient of concrete containing supplementary cementitious materials
26. Hybrid machine learning model and Shapley additive explanations for compressive strength of sustainable concrete10.1016/j.conbuildmat.2022.127298 ↗
27. Interpretable ensemble-machine-Learning models for predicting creep behavior of concrete10.1016/j.cemconcomp.2021.104295 ↗
28. Prediction of failure modes, strength, and deformation capacity of RC shear walls through machine learning
29. Application of machine learning in prediction of shear capacity of headed steel studs in steel-concrete composite structures10.1007/s13296-022-00589-z ↗
30. Analyzing the compressive strength of ceramic waste-based concrete using experiment and Artificial Neural Network (ANN) approach10.3390/ma14164518 ↗
31. V. Quan Tran , V. Quoc Dang , L. Si Ho , Evaluating compressive strength of concrete made with recycled concrete aggregates using machine learning approach, Construction and Building Materials 323, 2022. https://doi.org/10.1016/j.conbuildmat.2022.126578.10.1016/j.conbuildmat.2022.126578 ↗
32. Machine learning-based compressive strength modelling of concrete incorporating waste marble powder10.1016/j.conbuildmat.2022.126592 ↗
33. Improved estimation of coalbed methane content using the revised estimate of depth and CatBoost algorithm: a case study from southern Sichuan Basin, China10.1016/j.cageo.2021.104973 ↗
34. Explainable extreme gradient boosting tree-based prediction of load-carrying capacity of FRP-RC columns10.1016/j.engstruct.2021.112836 ↗
35. Machine learning-based prediction for compressive and flexural strengths of steel fiber-reinforced concrete10.1016/j.conbuildmat.2020.121117 ↗
36. A decision-theoretic generalization of on-line learning and an application to boosting10.1006/jcss.1997.1504 ↗
37. Greedy function approximation: a gradient boosting machine10.1214/aos/1013203451 ↗
38. T. Chen, C. Guestrin, XGBoost: A Scalable Tree Boosting System, Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery, San Francisco, California, USA, 2016, pp. 785–794.10.1145/2939672.2939785 ↗
39. L. Prokhorenkova, G. Gusev, A. Vorobev, A.V. Dorogush, A. Gulin, CatBoost: unbiased boosting with categorical features, Proceedings of the 32nd International Conference on Neural Information Processing Systems, Curran Associates Inc., Montréal, Canada, 2018, pp. 6639–6649.
40. Strength prediction of concrete-filled steel tubular columns using Categorical Gradient Boosting algorithm10.1016/j.engstruct.2021.112109 ↗
41. Modeling slump of ready mix concrete using genetic algorithms assisted training of Artificial Neural Networks10.1016/j.eswa.2014.08.048 ↗
42. Predicting the compressive strength of normal and high-performance concretes using ANN and ANFIS hybridized with Grey Wolf Optimizer10.1016/j.conbuildmat.2019.117266 ↗
43. Error metrics and performance fitness indicators for artificial intelligence and machine learning in engineering and sciences
44. Schaffer, C.J.M. Learning, Selecting a classification method by cross-validation, 13(1) ,1993, pp. 135–143.10.1007/BF00993106 ↗
45. M.T. Ribeiro, S. Singh, C. Guestrin, "Why Should I Trust You?": Explaining the Predictions of Any Classifier, Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery, San Francisco, California, USA, 2016, pp. 1135–1144.10.1145/2939672.2939778 ↗
46. F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, A. Müller, J. Nothman, G. Louppe, Scikit-learn: Machine Learning in Python, (2012).
47. Prediction of compressive strength of concrete: critical comparison of performance of a hybrid machine learning model with standalone models10.1061/(ASCE)MT.1943-5533.0002902 ↗
48. J. Thongkam, G.D. Xu, Y.C. Zhang, Ieee, AdaBoost Algorithm with Random Forests for Predicting Breast Cancer Survivability, 2008 IEEE International joint conference on neural networks, vols 1–8, 2008, pp. 3062–3069.10.1109/IJCNN.2008.4634231 ↗
49. L. Nan, D. Noe, X. He, Tree-Based Methods and Their Applications, Tree-Based Methods and Their Applications 2006.
50. Almost-everywhere algorithmic stability and generalization error
51. N. Ueda, R. Nakano, Generalization error of ensemble estimators, IEEE International Conference on Neural Networks, 2002.
52. G. Zenobi, P. Cunningham, Using Diversity in Preparing Ensembles of Classifiers Based on Different Feature Subsets to Minimize Generalization Error, European Conference on Machine Learning, 2001.10.1007/3-540-44795-4_49 ↗
53. Efficient estimating compressive strength of ultra-high performance concrete using XGBoost model10.1016/j.jobe.2022.104302 ↗
54. Hybrid machine learning model and Shapley additive explanations for compressive strength of sustainable concrete10.1016/j.conbuildmat.2022.127298 ↗
55. Investigation on factors affecting early strength of high-performance concrete by Gaussian Process Regression10.1371/journal.pone.0262930 ↗
56. Modeling of bentonite/sepiolite plastic concrete compressive strength using artificial neural network and support vector machine10.1007/s11709-018-0489-z ↗
57. Compressive strength prediction of fly ash-based geopolymer concrete via advanced machine learning techniques
58. Prediction of concrete strengths enabled by missing data imputation and interpretable machine learning10.1016/j.cemconcomp.2022.104414 ↗
59. Predicting the mechanical properties of RCA-based concrete using supervised machine learning algorithms10.3390/ma15020647 ↗
60. StructuresNet and FireNet: benchmarking databases and machine learning algorithms in structural and fire engineering domains
61. I. Yeh, UCI Machine Learning Repository: Concrete Compressive Strength Data Set, 2021. https://doi.org/http://archive.ics.uci.edu/ML/datasets/concrete+compressive+strength.
62. V. Degtyarev, Elastic Buckling and Post-buckling Strength of CFS Decks in Bending: FE Simulation Results, 2020. https://doi.org/ttps://doi.org/10.17632/3KM4B3SFCW.2.
63. Guidelines for mix proportioning of fly ash/GGBS based alkali activated concretes10.1016/j.conbuildmat.2017.04.036 ↗
64. Modeling of bentonite/sepiolite plastic concrete compressive strength using artificial neural network and support vector machine10.1007/s11709-018-0489-z ↗
65. Early-age hydration characteristics of composite binder containing iron tailing powder10.1016/j.powtec.2017.04.022 ↗
66. Characterization of mortars with iron ore tailings using destructive and nondestructive tests10.1016/j.conbuildmat.2016.11.065 ↗
67. Reconstruction of broken Si-O-Si bonds in iron ore tailings (IOTs) in concrete10.1007/s12613-019-1811-z ↗
68. W.J.M.M. Liu, Experimental Research on Preparation of Cementing Materials with Iron Tailings, 2010.
69. Fresh properties, compressive strength and microstructure of fly ash geopolymer paste blended with iron ore tailing under thermal cycle10.1016/j.conbuildmat.2016.05.059 ↗
70. Iron ore tailing-based geopolymer containing glass wool residue: a study of mechanical and microstructural properties10.1016/j.conbuildmat.2019.05.181 ↗
71. Assessment of mine tailings as precursors for alkali-activated materials for on-site applications10.1016/j.conbuildmat.2020.118470 ↗
72. Importance of W/C ratio on compressive strength of concrete in hot climate conditions10.1016/j.buildenv.2006.05.003 ↗
73. Influence of water-cement ratio and type of mixing water on the early hydration performance of calcium sulphoaluminate (CSA) cement10.1155/2021/5557763 ↗
74. Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis10.1016/j.aap.2019.105405 ↗
75. Different effects of wet and dry grinding on the activation of iron ore tailings10.32604/jrm.2021.015793 ↗