{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T21:40:00Z","timestamp":1766439600257,"version":"3.48.0"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T00:00:00Z","timestamp":1763596800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T00:00:00Z","timestamp":1763596800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Union","doi-asserted-by":"crossref","award":["958410"],"award-info":[{"award-number":["958410"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000780","name":"European Union","doi-asserted-by":"crossref","award":["958410"],"award-info":[{"award-number":["958410"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100020468","name":"Flanders Make","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100020468","id-type":"DOI","asserted-by":"publisher"}]},{"name":"KU Leuven Research Fund"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s10994-025-06933-8","type":"journal-article","created":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T19:59:08Z","timestamp":1763668748000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Limits: Enhancing the Extrapolation Performance of Regression Models by Leaving the Boundary Out"],"prefix":"10.1007","volume":"114","author":[{"given":"Francisco","family":"Ambrosio Garcia","sequence":"first","affiliation":[]},{"given":"Frank","family":"Naets","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,20]]},"reference":[{"issue":"1","key":"6933_CR1","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1186\/2193-9772-3-8","volume":"3","author":"A Agrawal","year":"2014","unstructured":"Agrawal, A., Deshpande, P. D., Cecen, A., Basavarsu, G. P., Choudhary, A. N., & Kalidindi, S. R. (2014). Exploration of data science techniques to predict fatigue strength of steel from composition and processing parameters. Integrating Materials and Manufacturing Innovation, 3(1), 90\u2013108.","journal-title":"Integrating Materials and Manufacturing Innovation"},{"key":"6933_CR2","doi-asserted-by":"crossref","unstructured":"Akiba, T., Sano, S., Yanase, T., Ohta, T., & Koyama, M. (2019). Optuna: A next-generation hyperparameter optimization framework. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining (pp. 2623\u20132631).","DOI":"10.1145\/3292500.3330701"},{"key":"6933_CR3","unstructured":"Balestriero, R., Pesenti, J., LeCun, Y. (2021). Learning in high dimension always amounts to extrapolation. arXiv preprint arXiv:2110.09485."},{"key":"6933_CR4","unstructured":"Bergstra, J., Bardenet, R., Bengio, Y., & K\u00e9gl, B. (2011). Algorithms for hyper-parameter optimization. Advances in Neural Information Processing Systems 24."},{"key":"6933_CR5","unstructured":"Bergstra, J., Yamins, D., & Cox, D. (2013). Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures. In International conference on machine learning (pp. 115\u2013123). PMLR."},{"issue":"7","key":"6933_CR6","doi-asserted-by":"publisher","first-page":"6585","DOI":"10.1007\/s11071-022-08178-9","volume":"111","author":"D Bertsimas","year":"2023","unstructured":"Bertsimas, D., & Gurnee, W. (2023). Learning sparse nonlinear dynamics via mixed-integer optimization. Nonlinear Dynamics, 111(7), 6585\u20136604.","journal-title":"Nonlinear Dynamics"},{"issue":"8","key":"6933_CR7","doi-asserted-by":"publisher","first-page":"1883","DOI":"10.3390\/ma14081883","volume":"14","author":"FE Bock","year":"2021","unstructured":"Bock, F. E., Keller, S., Huber, N., & Klusemann, B. (2021). Hybrid modelling by machine learning corrections of analytical model predictions towards high-fidelity simulation solutions. Materials, 14(8), 1883.","journal-title":"Materials"},{"key":"6933_CR8","unstructured":"Bonnasse-Gahot, L. (2022). Interpolation, extrapolation, and local generalization in common neural networks. arXiv preprint arXiv:2207.08648."},{"key":"6933_CR9","unstructured":"Buritic\u00e1, G., & Engelke, S. (2024). Progression: An extrapolation principle for regression. arXiv preprint arXiv:2410.23246."},{"key":"6933_CR10","unstructured":"daalgi, Fem simulations: Data to build a regression surrogate model of a complex numerical model. (2025). https:\/\/www.kaggle.com\/datasets\/daalgi\/fem-simulations"},{"key":"6933_CR11","doi-asserted-by":"crossref","unstructured":"de\u00a0Silva, B.\u00a0M., Champion, K., Quade, M., Loiseau, J.-C., Kutz, J.\u00a0N., & Brunton, S.\u00a0L. (2020). Pysindy: A python package for the sparse identification of nonlinear dynamics from data. arXiv preprint arXiv:2004.08424.","DOI":"10.21105\/joss.02104"},{"issue":"6","key":"6933_CR12","doi-asserted-by":"publisher","first-page":"763","DOI":"10.1039\/D2DD00039C","volume":"1","author":"S Durdy","year":"2022","unstructured":"Durdy, S., Gaultois, M. W., Gusev, V. V., Bollegala, D., & Rosseinsky, M. J. (2022). Random projections and Kernelised leave one cluster out cross validation: Universal baselines and evaluation tools for supervised machine learning of material properties. Digital Discovery, 1(6), 763\u2013778.","journal-title":"Digital Discovery"},{"issue":"4","key":"6933_CR13","doi-asserted-by":"publisher","first-page":"695","DOI":"10.1007\/s10462-012-9348-9","volume":"42","author":"MO Elish","year":"2014","unstructured":"Elish, M. O. (2014). A comparative study of fault density prediction in aspect-oriented systems using MLP, RBF, KNN, RT, DENFIS and SVR models. Artificial Intelligence Review, 42(4), 695\u2013703. https:\/\/doi.org\/10.1007\/s10462-012-9348-9","journal-title":"Artificial Intelligence Review"},{"key":"6933_CR14","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/s00158-024-03828-5","volume":"67","author":"P Eremeev","year":"2024","unstructured":"Eremeev, P., Cock, A. D., Devriendt, H., & Naets, F. (2024). Product family design optimization considering manufacturing and assembly process costs. Structural and Multidisciplinary Optimization, 67, 115. https:\/\/doi.org\/10.1007\/s00158-024-03828-5","journal-title":"Structural and Multidisciplinary Optimization"},{"key":"6933_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.compind.2025.104267","volume":"168","author":"FA Garcia","year":"2025","unstructured":"Garcia, F. A., Devriendt, H., Metin, H., \u00d6zer, M., & Naets, F. (2025). Physics-informed digital twin design for supporting the selection of process settings in continuous manufacturing, with a focus in fiberboard production. Computers in Industry, 168, Article 104267. https:\/\/doi.org\/10.1016\/j.compind.2025.104267https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0166361525000326.","journal-title":"Computers in Industry"},{"key":"6933_CR16","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.5518","volume":"6","author":"T Hengl","year":"2018","unstructured":"Hengl, T., Nussbaum, M., Wright, M. N., Heuvelink, G. B., & Gr\u00e4ler, B. (2018). Random forest as a generic framework for predictive modeling of spatial and spatio-temporal variables. PeerJ, 6, Article e5518.","journal-title":"PeerJ"},{"issue":"8045","key":"6933_CR17","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1038\/s41586-024-08328-6","volume":"637","author":"N Hollmann","year":"2025","unstructured":"Hollmann, N., M\u00fcller, S., Purucker, L., Krishnakumar, A., K\u00f6rfer, M., Hoo, S. B., Schirrmeister, R. T., & Hutter, F. (2025). Accurate predictions on small data with a tabular foundation model. Nature, 637(8045), 319\u2013326.","journal-title":"Nature"},{"key":"6933_CR18","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1023\/A:1022631118932","volume":"11","author":"RC Holte","year":"1993","unstructured":"Holte, R. C. (1993). Very simple classification rules perform well on most commonly used datasets. Machine Learning, 11, 63\u201390.","journal-title":"Machine Learning"},{"key":"6933_CR19","doi-asserted-by":"publisher","first-page":"1378","DOI":"10.1038\/s42256-025-01109-4","volume":"7","author":"F Ilievski","year":"2025","unstructured":"Ilievski, F., Hammer, B., van Harmelen, F., Paassen, B., Saralajew, S., Schmid, U., Biehl, M., Bolognesi, M., Dong, X. L., Gashteovski, K., Hitzler, P., Marra, G., Minervini, P., Mundt, M., Ngonga Ngomo, A.-C., Oltramari, A., Pasi, G., Saribatur, Z. G., Serafini, L., \u2026 Villmann, T. (2025). Aligning generalization between humans and machines. Nature Machine Intelligence, 7, 1378\u20131389. https:\/\/doi.org\/10.1038\/s42256-025-01109-4","journal-title":"Nature Machine Intelligence"},{"issue":"7","key":"6933_CR20","doi-asserted-by":"publisher","first-page":"1477","DOI":"10.1007\/s00521-013-1439-2","volume":"24","author":"H Jia","year":"2014","unstructured":"Jia, H., Ding, S., Xu, X., & Nie, R. (2014). The latest research progress on spectral clustering. Neural Computing and Applications, 24(7), 1477\u20131486.","journal-title":"Neural Computing and Applications"},{"key":"6933_CR21","unstructured":"Kang, K., Setlur, A., Tomlin, C., & Levine, S. (2023). Deep neural networks tend to extrapolate predictably. arXiv preprint arXiv:2310.00873."},{"issue":"6","key":"6933_CR22","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1038\/s42254-021-00314-5","volume":"3","author":"GE Karniadakis","year":"2021","unstructured":"Karniadakis, G. E., Kevrekidis, I. G., Lu, L., Perdikaris, P., Wang, S., & Yang, L. (2021). Physics-informed machine learning. Nature Reviews Physics, 3(6), 422\u2013440.","journal-title":"Nature Reviews Physics"},{"key":"6933_CR23","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al. (2009). Learning multiple layers of features from tiny images."},{"issue":"11","key":"6933_CR24","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), 2278\u20132324.","journal-title":"Proceedings of the IEEE"},{"issue":"5","key":"6933_CR25","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1007\/s12289-023-01770-3","volume":"16","author":"T Lehrer","year":"2023","unstructured":"Lehrer, T., Kaps, A., Lepenies, I., Duddeck, F., & Wagner, M. (2023). 2s-ml: A simulation-based classification and regression approach for drawability assessment in deep drawing. International Journal of Material Forming, 16(5), 56.","journal-title":"International Journal of Material Forming"},{"issue":"54","key":"6933_CR26","first-page":"1","volume":"25","author":"D LeJeune","year":"2024","unstructured":"LeJeune, D., Liu, J., & Heckel, R. (2024). Monotonic risk relationships under distribution shifts for regularized risk minimization. Journal of Machine Learning Research, 25(54), 1\u201337. http:\/\/jmlr.org\/papers\/v25\/22-1197.html.","journal-title":"Journal of Machine Learning Research"},{"issue":"11","key":"6933_CR27","doi-asserted-by":"publisher","first-page":"4597","DOI":"10.1007\/s10994-023-06386-x","volume":"112","author":"M Luca","year":"2023","unstructured":"Luca, M., Pappalardo, L., Lepri, B., & Barlacchi, G. (2023). Trajectory test-train overlap in next-location prediction datasets. Machine Learning, 112(11), 4597\u20134634.","journal-title":"Machine Learning"},{"key":"6933_CR28","unstructured":"Martius, G., & Lampert, C.\u00a0H. (2016). Extrapolation and learning equations. arXiv preprint arXiv:1610.02995."},{"issue":"3","key":"6933_CR29","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1002\/cite.201800091","volume":"91","author":"K McBride","year":"2019","unstructured":"McBride, K., & Sundmacher, K. (2019). Overview of surrogate modeling in chemical process engineering. Chemie Ingenieur Technik, 91(3), 228\u2013239. https:\/\/doi.org\/10.1002\/cite.201800091","journal-title":"Chemie Ingenieur Technik"},{"issue":"5","key":"6933_CR30","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1039\/C8ME00012C","volume":"3","author":"B Meredig","year":"2018","unstructured":"Meredig, B., Antono, E., Church, C., Hutchinson, M., Ling, J., Paradiso, S., Blaiszik, B., Foster, I., Gibbons, B., Hattrick-Simpers, J., et al. (2018). Can machine learning identify the next high-temperature superconductor? Examining extrapolation performance for materials discovery. Molecular Systems Design & Engineering, 3(5), 819\u2013825.","journal-title":"Molecular Systems Design & Engineering"},{"issue":"5","key":"6933_CR31","doi-asserted-by":"publisher","first-page":"1425","DOI":"10.1039\/D3DD00082F","volume":"2","author":"ES Muckley","year":"2023","unstructured":"Muckley, E. S., Saal, J. E., Meredig, B., Roper, C. S., & Martin, J. H. (2023). Interpretable models for extrapolation in scientific machine learning. Digital Discovery, 2(5), 1425\u20131435.","journal-title":"Digital Discovery"},{"key":"6933_CR32","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, 2825\u20132830.","journal-title":"Journal of Machine Learning Research"},{"key":"6933_CR33","doi-asserted-by":"crossref","unstructured":"Qu, Y., William, J., Saxena, A., Eklund, N., & Clements, S. (2023). An introduction to 2023 phm data challenge: The elephant in the room and an analysis of competition results. In Annual Conference of the PHM Society (Vol. 15).","DOI":"10.36001\/phmconf.2023.v15i1.3814"},{"issue":"8","key":"6933_CR34","doi-asserted-by":"publisher","first-page":"913","DOI":"10.1111\/ecog.02881","volume":"40","author":"DR Roberts","year":"2017","unstructured":"Roberts, D. R., Bahn, V., Ciuti, S., Boyce, M. S., Elith, J., Guillera-Arroita, G., Hauenstein, S., Lahoz-Monfort, J. J., Schr\u00f6der, B., Thuiller, W., et al. (2017). Cross-validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure. Ecography, 40(8), 913\u2013929.","journal-title":"Ecography"},{"issue":"12","key":"6933_CR35","doi-asserted-by":"publisher","first-page":"3464","DOI":"10.1016\/j.csda.2005.07.015","volume":"50","author":"W Sauerbrei","year":"2006","unstructured":"Sauerbrei, W., Meier-Hirmer, C., Benner, A., & Royston, P. (2006). Multivariable regression model building by using fractional polynomials: Description of SAS, STATA and R programs. Computational Statistics & Data Analysis, 50(12), 3464\u20133485. https:\/\/doi.org\/10.1016\/j.csda.2005.07.015https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0167947305001623.","journal-title":"Computational Statistics & Data Analysis"},{"key":"6933_CR36","doi-asserted-by":"crossref","unstructured":"Singh, H.\u00a0V., Girdhar, A., & Dahiya, S. (2022). A literature survey based on dbscan algorithms. In 2022 6th international conference on intelligent computing and control systems (ICICCS) (pp. 751\u2013758). IEEE.","DOI":"10.1109\/ICICCS53718.2022.9788440"},{"key":"6933_CR37","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.75485","volume":"11","author":"H Tiedemann","year":"2022","unstructured":"Tiedemann, H., Morgenstern, Y., Schmidt, F., & Fleming, R. W. (2022). One-shot generalization in humans revealed through a drawing task. eLife, 11, Article e75485. https:\/\/doi.org\/10.7554\/eLife.75485","journal-title":"eLife"},{"key":"6933_CR38","doi-asserted-by":"crossref","unstructured":"Ubbink, J., Viljoen, R., Aertbeli\u00ebn, E., Decr\u00e9, W., & De Schutter, J. (2024). Contactless surface following with acceleration limits: Enhancing robot manipulator performance through model predictive control. In European Control Conference (ECC) (pp. 3594\u20133599). IEEE.","DOI":"10.23919\/ECC64448.2024.10591035"},{"key":"6933_CR39","unstructured":"Vanwinckelen, G., & Blockeel, H. (2012). On estimating model accuracy with repeated cross-validation. In BeneLearn 2012: Proceedings of the 21st Belgian-Dutch conference on machine learning (pp. 39\u201344)."},{"key":"6933_CR40","unstructured":"Vapnik, V., Golowich, S., & Smola, A. (1996). Support vector method for function approximation, regression estimation and signal processing. Advances in Neural Information Processing Systems 9."},{"key":"6933_CR41","unstructured":"Wang, R., Maddix, D., Faloutsos, C., Wang, Y., Yu, R. (2021). Bridging physics-based and data-driven modeling for learning dynamical systems, In: Learning for dynamics and control, PMLR, pp. 385\u2013398."},{"key":"6933_CR42","unstructured":"Watanabe, S. (2023). Tree-structured parzen estimator: Understanding its algorithm components and their roles for better empirical performance. arXiv preprint arXiv:2304.11127."},{"key":"6933_CR43","doi-asserted-by":"publisher","DOI":"10.1016\/j.commatsci.2019.109203","volume":"171","author":"Z Xiong","year":"2020","unstructured":"Xiong, Z., Cui, Y., Liu, Z., Zhao, Y., Hu, M., & Hu, J. (2020). Evaluating explorative prediction power of machine learning algorithms for materials discovery using k-fold forward cross-validation. Computational Materials Science, 171, Article 109203.","journal-title":"Computational Materials Science"},{"key":"6933_CR44","unstructured":"Xu, K., Zhang, M., Li, J., Du, S.\u00a0S., Kawarabayashi, K.-I., & Jegelka, S. (2020). How neural networks extrapolate: From feedforward to graph neural networks. arXiv preprint arXiv:2009.11848."},{"key":"6933_CR45","doi-asserted-by":"publisher","unstructured":"Yadav, S., & Shukla, S. (2016). Analysis of k-fold cross-validation over hold-out validation on colossal datasets for quality classification. In 2016 IEEE 6th international conference on advanced computing (IACC) (pp. 78\u201383). https:\/\/doi.org\/10.1109\/IACC.2016.25","DOI":"10.1109\/IACC.2016.25"},{"key":"6933_CR46","doi-asserted-by":"publisher","DOI":"10.24432\/C5PK67","author":"I.-C. Yeh","year":"1998","unstructured":"Yeh, I. .-C. . (1998). Concrete compressive strength. UCI Machine Learning Repository. https:\/\/doi.org\/10.24432\/C5PK67","journal-title":"UCI Machine Learning Repository"},{"issue":"5","key":"6933_CR47","doi-asserted-by":"publisher","first-page":"1058","DOI":"10.1039\/D3DD00256J","volume":"3","author":"M Yu","year":"2024","unstructured":"Yu, M., Zhou, Y.-N., Wang, Q., & Yan, F. (2024). Extrapolation validation (EV): a universal validation method for mitigating machine learning extrapolation risk. Digital Discovery, 3(5), 1058\u20131067.","journal-title":"Digital Discovery"},{"key":"6933_CR48","unstructured":"Zhuang, C. (2025). Steel fatigue strength prediction. https:\/\/www.kaggle.com\/datasets\/chaozhuang\/steel-fatigue-strength-prediction"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06933-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-025-06933-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06933-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T21:29:19Z","timestamp":1766438959000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-025-06933-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,20]]},"references-count":48,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["6933"],"URL":"https:\/\/doi.org\/10.1007\/s10994-025-06933-8","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"type":"print","value":"0885-6125"},{"type":"electronic","value":"1573-0565"}],"subject":[],"published":{"date-parts":[[2025,11,20]]},"assertion":[{"value":"30 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 October 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 November 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 November 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"285"}}