{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T10:35:01Z","timestamp":1769510101304,"version":"3.49.0"},"reference-count":46,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T00:00:00Z","timestamp":1765843200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Jilin Key Research and Development Program of China","award":["20250203150SF"],"award-info":[{"award-number":["20250203150SF"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>In plateau and high-altitude areas, freeze-thaw cycles often alter the uniaxial compressive strength (UCS) of rock, thereby impacting the stability of geotechnical engineering. Acquiring rock samples in these areas for UCS testing is often time-consuming and labor-intensive. This study developed a hybrid model based on the XGBoost algorithm to predict the UCS of rock under freeze-thaw conditions. First, a database was created containing longitudinal wave velocity (Vp), rock porosity (P), rock density (D), freezing temperature (T), number of freeze-thaw cycles (FTCs), and UCS. Four swarm intelligence optimization algorithms\u2014artificial bee colony, Newton\u2013Raphson, particle swarm optimization, and dung beetle optimization\u2014were used to optimize the maximum iterations, depth, and learning rate of the XGBoost model, thereby enhancing model accuracy and developing four hybrid models. The four hybrid models were compared to a single XGBoost model and a random forest (RF) model to evaluate overall performance, and the optimal model was selected. The results demonstrate that all hybrid models outperform the single models. The XGBoost model optimized by the sparrow algorithm (R2 = 0.94, RMSE = 10.10, MAPE = 0.095, MAE = 7.22) performed best in predicting UCS. SHapley Additive exPlanations (SHAP) were used to assess the marginal contribution of each input variable to the UCS prediction of freeze-thawed rock. This study is expected to provide a reference for predicting the UCS of freeze-thawed rock using machine learning.<\/jats:p>","DOI":"10.3390\/bdcc9120323","type":"journal-article","created":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T12:47:26Z","timestamp":1765889246000},"page":"323","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Influence Mechanism of Rock Compressive Mechanical Properties Under Freeze-Thaw Cycles: Insights from Machine Learning"],"prefix":"10.3390","volume":"9","author":[{"given":"Shuai","family":"Gao","sequence":"first","affiliation":[{"name":"Jilin Emergency Management College, Changchun Institute of Technology, Changchun 130012, China"}]},{"given":"Zhongyuan","family":"Gu","sequence":"additional","affiliation":[{"name":"Jilin Emergency Management College, Changchun Institute of Technology, Changchun 130012, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6404-8247","authenticated-orcid":false,"given":"Xin","family":"Xiong","sequence":"additional","affiliation":[{"name":"School of Resources and Safety Engineering, Central South University, Changsha 410083, China"}]},{"given":"Chengnian","family":"Wang","sequence":"additional","affiliation":[{"name":"Jilin Emergency Management College, Changchun Institute of Technology, Changchun 130012, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,16]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"781","DOI":"10.1016\/j.jrmge.2021.10.005","article-title":"Experimental studies on the pore structure and mechanical properties of anhydrite rock under freeze-thaw cycles","volume":"14","author":"Hou","year":"2022","journal-title":"J. Rock Mech. Geotech. Eng."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1649","DOI":"10.1007\/s10064-015-0787-9","article-title":"The effect of freeze-thaw cycles on physical and mechanical properties of granitoid hard rocks","volume":"75","author":"Momeni","year":"2016","journal-title":"Bull. Eng. Geol. Environ."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1016\/j.ijmst.2015.12.019","article-title":"Physical and mechanical properties of sandstone containing a single fissure after exposure to high temperatures","volume":"26","author":"Zhu","year":"2016","journal-title":"Int. J. Min. Sci. Technol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"3785","DOI":"10.1109\/TSMC.2021.3074496","article-title":"Open-Set Support Vector Machines","volume":"52","author":"Mendes","year":"2022","journal-title":"IEEE Trans. Syst. Man Cybern.-Syst."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Si, K., Cui, Z.D., Peng, R.D., Zhao, L.L., and Zhao, Y. (2021). Crack Propagation Process and Seismogenic Mechanisms of Rock Due to the Influence of Freezing and Thawing. Appl. Sci., 11.","DOI":"10.3390\/app11209601"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"104100","DOI":"10.1016\/j.coldregions.2023.104100","article-title":"Mechanical properties and damage modeling of unloaded marble under freezing and thawing with different temperature ranges","volume":"218","author":"Wang","year":"2024","journal-title":"Cold Reg. Sci. Technol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1007\/s00603-021-02645-2","article-title":"Study on a Damage Model and Uniaxial Compression Simulation Method of Frozen-Thawed Rock","volume":"55","author":"Feng","year":"2022","journal-title":"Rock Mech. Rock Eng."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1186\/s40537-023-00874-6","article-title":"Data-driven multinomial random forest: A new random forest variant with strong consistency","volume":"11","author":"Chen","year":"2024","journal-title":"J. Big Data"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2591","DOI":"10.1016\/j.jrmge.2023.09.017","article-title":"Predicting dynamic compressive strength of frozen-thawed rocks by characteristic impedance and data-driven methods","volume":"16","author":"Zhou","year":"2024","journal-title":"J. Rock Mech. Geotech. Eng."},{"key":"ref_10","first-page":"5106045","article-title":"Modeling PM2.5 Urban Pollution Using Machine Learning and Selected Meteorological Parameters","volume":"2017","author":"Zalakeviciute","year":"2017","journal-title":"J. Electr. Comput. Eng."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1473","DOI":"10.1007\/s12145-023-00979-9","article-title":"Machine learning for prediction of the uniaxial compressive strength within carbonate rocks","volume":"16","author":"Abdelhedi","year":"2023","journal-title":"Earth Sci. Inform."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"112420","DOI":"10.1016\/j.jenvman.2021.112420","article-title":"Predictive modeling of swell-strength of expansive soils using artificial intelligence approaches: ANN, ANFIS and GEP","volume":"289","author":"Jalal","year":"2021","journal-title":"J. Environ. Manag."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"107186","DOI":"10.1016\/j.ress.2020.107186","article-title":"Evaluation of patient safety culture using a random forest algorithm","volume":"204","author":"Simsekler","year":"2020","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Shahani, N.M., Zheng, X.G., Guo, X.W., and Wei, X. (2022). Machine Learning-Based Intelligent Prediction of Elastic Modulus of Rocks at Thar Coalfield. Sustainability, 14.","DOI":"10.3390\/su14063689"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1016\/j.neunet.2019.04.019","article-title":"Subrecursive neural networks","volume":"116","year":"2019","journal-title":"Neural Netw."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1485","DOI":"10.1016\/j.jrmge.2021.07.011","article-title":"An intelligent procedure for updating deformation prediction of braced excavation in clay using gated recurrent unit neural networks","volume":"13","author":"Yang","year":"2021","journal-title":"J. Rock Mech. Geotech. Eng."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"100225","DOI":"10.1016\/j.qsa.2024.100225","article-title":"Prediction of UCS and BTS under freeze-thaw conditions in the NW himalayan rock mass using petrographic analysis and laboratory testing","volume":"15","author":"Jaiswal","year":"2024","journal-title":"Quat. Sci. Adv."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"119943","DOI":"10.1016\/j.renene.2024.119943","article-title":"A cohesive structure of Bi-directional long-short-term memory (BiLSTM)\u2014GRU for predicting hourly solar radiation","volume":"222","author":"Michael","year":"2024","journal-title":"Renew. Energy"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/s10462-023-10636-8","article-title":"State-of-the-art review of machine learning and optimization algorithms applications in environmental effects of blasting","volume":"57","author":"Zhou","year":"2024","journal-title":"Artif. Intell. Rev."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"288","DOI":"10.1007\/s12517-020-5273-4","article-title":"Application of soft computing methods in predicting uniaxial compressive strength of the volcanic rocks with different weathering degree","volume":"13","author":"Ceryan","year":"2020","journal-title":"Arab. J. Geosci."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"105519","DOI":"10.1016\/j.jappgeo.2024.105519","article-title":"Optimized gradient boosting models and reliability analysis for rock stiffness C13","volume":"230","year":"2024","journal-title":"J. Appl. Geophys."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"8043","DOI":"10.1007\/s00521-020-05546-7","article-title":"Unconfined compressive strength (UCS) prediction in real-time while drilling using artificial intelligence tools","volume":"33","author":"Gowida","year":"2021","journal-title":"Neural Comput. Appl."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"5617","DOI":"10.1007\/s00603-021-02575-z","article-title":"Prediction of Uniaxial Compressive Strength and Elastic Modulus of Migmatites by Microstructural Characteristics Using Artificial Neural Networks","volume":"54","author":"Saedi","year":"2021","journal-title":"Rock Mech. Rock Eng."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1007\/s00366-015-0429-7","article-title":"Rock strength assessment based on regression tree technique","volume":"32","author":"Liang","year":"2016","journal-title":"Eng. Comput."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Abdelhedi, M. (2020). Prediction of uniaxial compressive strength of carbonate rocks and cement mortar using artificial neural network and multiple linear regressions. Acta Geodyn. Et Geomater., 367\u2013377.","DOI":"10.13168\/AGG.2020.0027"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"785","DOI":"10.1016\/j.ijmst.2020.06.008","article-title":"Comparative evaluation of different statistical tools for the prediction of uniaxial compressive strength of rocks","volume":"30","author":"Teymen","year":"2020","journal-title":"Int. J. Min. Sci. Technol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"142706","DOI":"10.1016\/j.conbuildmat.2025.142706","article-title":"Pore characteristics and constitutive model of constrained granite under freeze-thaw cycles","volume":"491","author":"Gong","year":"2025","journal-title":"Constr. Build. Mater."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"104416","DOI":"10.1016\/j.coldregions.2024.104416","article-title":"Research on the predictability of rock strength under freeze-thaw cycles\u2014A hybrid model of SHAP-IPOA-XGBoost","volume":"231","author":"Liu","year":"2025","journal-title":"Cold Reg. Sci. Technol."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"390","DOI":"10.1007\/s12594-023-2322-0","article-title":"Study of Freeze-thaw Induced Damage Characteristic for Himalayan Schist","volume":"99","author":"Verma","year":"2023","journal-title":"J. Geol. Soc. India"},{"key":"ref_30","first-page":"e202411296","article-title":"Reproducing Reaction Mechanisms with Machine-Learning Models Trained on a Large-Scale Mechanistic Dataset","volume":"63","author":"Joung","year":"2024","journal-title":"Angew. Chem.-Int. Ed."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"9669","DOI":"10.1109\/TPAMI.2023.3251957","article-title":"Fast and Informative Model Selection Using Learning Curve Cross-Validation","volume":"45","author":"Mohr","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"120309","DOI":"10.1016\/j.jenvman.2024.120309","article-title":"Research on mining land subsidence by intelligent hybrid model based on gradient boosting with categorical features support algorithm","volume":"354","author":"Zhang","year":"2024","journal-title":"J. Environ. Manag."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"4741","DOI":"10.1007\/s00603-021-02497-w","article-title":"Study on the Influence of Freeze\u2013Thaw Weathering on the Mechanical Properties of Huashan Granite Strength","volume":"54","author":"Li","year":"2021","journal-title":"Rock Mech. Rock Eng."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"3690","DOI":"10.1109\/TIP.2013.2268977","article-title":"A Novel Fractal Image Compression Scheme with Block Classification and Sorting Based on Pearson\u2019s Correlation Coefficient","volume":"22","author":"Wang","year":"2013","journal-title":"IEEE Trans. Image Process."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"123856","DOI":"10.1016\/j.energy.2022.123856","article-title":"Explaining household electricity consumption using quantile regression, decision tree and artificial neural network","volume":"250","author":"Nsangou","year":"2022","journal-title":"Energy"},{"key":"ref_36","first-page":"7530759","article-title":"Comparison of Parametric and Nonparametric Methods for Analyzing the Bias of a Numerical Model","volume":"2016","author":"Mugume","year":"2016","journal-title":"Model. Simul. Eng."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"2651","DOI":"10.1007\/s10462-018-9634-2","article-title":"Recent studies on optimisation method of Grey Wolf Optimiser (GWO): A review (2014\u20132017)","volume":"52","author":"Hatta","year":"2019","journal-title":"Artif. Intell. Rev."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Chen, T.Q., and Guestrin, C. (2016, January 13\u201317). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1428","DOI":"10.1016\/j.jrmge.2021.09.003","article-title":"Data-driven estimation of joint roughness coefficient","volume":"13","year":"2021","journal-title":"J. Rock Mech. Geotech. Eng."},{"key":"ref_40","first-page":"24","article-title":"Lion Optimization Algorithm (LOA): A nature-inspired metaheuristic algorithm","volume":"3","author":"Yazdani","year":"2016","journal-title":"J. Comput. Des. Eng."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"107532","DOI":"10.1016\/j.engappai.2023.107532","article-title":"Newton-Raphson-based optimizer: A new population-based metaheuristic algorithm for continuous optimization problems","volume":"128","author":"Sowmya","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"729","DOI":"10.1007\/s10845-011-0621-6","article-title":"An upgraded artificial bee colony (ABC) algorithm for constrained optimization problems","volume":"24","author":"Brajevic","year":"2013","journal-title":"J. Intell. Manuf."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"605","DOI":"10.1007\/s40789-020-00383-4","article-title":"Relationship between rock uniaxial compressive strength and digital core drilling parameters and its forecast method","volume":"8","author":"Gao","year":"2021","journal-title":"Int. J. Coal Sci. Technol."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"2428","DOI":"10.1093\/eurheartj\/ehac544.2428","article-title":"Prediction of depression among patients with cardiovascular disease scheduled cardiac surgery using an Al-empowered pipeline","volume":"43","author":"Pezoulas","year":"2022","journal-title":"Eur. Heart J."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"141319","DOI":"10.1016\/j.conbuildmat.2025.141319","article-title":"Compressive strength prediction of sleeve grouting materials in prefabricated structures using hybrid optimized XGBoost models","volume":"476","author":"Wu","year":"2025","journal-title":"Constr. Build. Mater."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1727","DOI":"10.1007\/s11831-022-09850-4","article-title":"Efficient Initialization Methods for Population-Based Metaheuristic Algorithms: A Comparative Study","volume":"30","author":"Agushaka","year":"2023","journal-title":"Arch. Comput. Methods Eng."}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/12\/323\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T13:13:24Z","timestamp":1765890804000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/9\/12\/323"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,16]]},"references-count":46,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["bdcc9120323"],"URL":"https:\/\/doi.org\/10.3390\/bdcc9120323","relation":{},"ISSN":["2504-2289"],"issn-type":[{"value":"2504-2289","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,16]]}}}