{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T16:25:24Z","timestamp":1787847924184,"version":"build-2784847793"},"reference-count":25,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T00:00:00Z","timestamp":1787788800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Curve squeal is a loud tonal noise from railway traffic that contributes to environmental noise pollution. Squealing arises from friction-induced vibrations in the wheel-rail contact during vehicle curving under specific friction conditions. Environmental factors are known to influence these friction conditions and, consequently, the tendency of squeal occurrence. This study investigates whether environmental variables measured from the wayside of the track can be used to predict curve squeal using machine learning models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Separate prediction models were developed for low-rail and high-rail squeal using a labeled dataset collected during a 19-month measurement campaign at a commuter railway curve in Sweden. Multiple machine learning algorithms were evaluated, and feature importance analysis was used to investigate the environmental predictors associated with low-rail and high-rail squeal. The practical usefulness of the prediction models was further assessed for adaptive top-of-rail friction modifier (TOR-FM) application.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Environmental variables contained useful predictive information regarding curve squeal occurrence, although the overall predictive performance remained limited. The tree-based ensemble models generally achieved the highest performance, while the feature importance analysis indicated that low-rail and high-rail squeal relied on different feature patterns. The operational assessment demonstrated that the prediction models could reduce unnecessary TOR-FM triggering while maintaining high squeal detection rates.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The results demonstrate the potential of combining environmental monitoring with machine learning to support site-specific predictive railway noise mitigation and maintenance decision-making. The differences between low-rail and high-rail prediction further indicate the value of treating the two squeal types as separate prediction tasks.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1887534","type":"journal-article","created":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T16:03:36Z","timestamp":1787846616000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Railway curve squeal prediction using environmental variables"],"prefix":"10.3389","volume":"9","author":[{"given":"Leevi","family":"Toratti","sequence":"first","affiliation":[{"name":"Division of Operation, Maintenance and Acoustics, Lule\u00e5 University of Technology","place":["Lule\u00e5, Sweden"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Praneeth","family":"Chandran","sequence":"additional","affiliation":[{"name":"Division of Operation, Maintenance and Acoustics, Lule\u00e5 University of Technology","place":["Lule\u00e5, Sweden"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Florian","family":"Thiery","sequence":"additional","affiliation":[{"name":"Division of Operation, Maintenance and Acoustics, Lule\u00e5 University of Technology","place":["Lule\u00e5, Sweden"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matti","family":"Rantatalo","sequence":"additional","affiliation":[{"name":"Division of Operation, Maintenance and Acoustics, Lule\u00e5 University of Technology","place":["Lule\u00e5, Sweden"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,27]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn"},{"key":"B2","doi-asserted-by":"publisher","first-page":"4018","DOI":"10.3390\/app11094018","article-title":"Supervised machine learning approach for detecting missing clamps in rail fastening system from differential eddy current measurements","volume":"11","author":"Chandran","year":"2021","journal-title":"Appl. Sci"},{"key":"B3","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1145\/2939672.2939785","article-title":"\u201cXGBoost: a scalable tree boosting system,\u201d","author":"Chen","year":"2016","journal-title":"Proceedings of the 22nd ACM sigkdd international conference on knowledge discovery and data mining, KDD '16"},{"key":"B4","doi-asserted-by":"publisher","first-page":"5739","DOI":"10.3390\/s21175739","article-title":"A survey on data-driven predictive maintenance for the railway industry","volume":"21","author":"Davari","year":"2021","journal-title":"Sensors"},{"key":"B5","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1016\/j.jsv.2005.12.007","article-title":"Top-of-rail friction control for curve noise mitigation and corrugation rate reduction","volume":"293","author":"Eadie","year":"2006","journal-title":"J. Sound Vib"},{"key":"B6","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/978-981-99-7852-6_45","article-title":"\u201cSurvey of curve squeal occurrence for an entire metro system,\u201d","author":"Eriksson","year":"2024","journal-title":"Noise and vibration mitigation for rail transportation systems"},{"key":"B7","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1186\/s44147-025-00842-2","article-title":"Predictive maintenance of railway tracks using sparse time-series and health state-based RUL modeling","volume":"72","author":"Fernandes","year":"2025","journal-title":"J. Eng. Appl. Sci"},{"key":"B8","doi-asserted-by":"publisher","first-page":"106521","DOI":"10.1016\/j.triboint.2020.106521","article-title":"The low adhesion problem: the effect of environmental conditions on adhesion in rolling-sliding contact","volume":"151","author":"Galas","year":"2020","journal-title":"Tribol. Int"},{"key":"B9","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1016\/S0261-3794(99)00028-1","article-title":"Loess: a nonparametric, graphical tool for depicting relationships between variables","volume":"19","author":"Jacoby","year":"2000","journal-title":"Elect. Stud"},{"key":"B10","doi-asserted-by":"publisher","first-page":"118510","DOI":"10.1016\/j.measurement.2025.118510","article-title":"Towards railways safety: a systematic review on predictive diagnostics for axle bearings","volume":"257","author":"Konecny","year":"2026","journal-title":"Measurement"},{"key":"B11","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.wear.2013.11.045","article-title":"Investigation of the effect of relative humidity on lateral force in rolling contact and curve squeal","volume":"310","author":"Liu","year":"2014","journal-title":"Wear"},{"key":"B12","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat. Mach. Intell"},{"key":"B13","article-title":"\u201cA unified approach to interpreting model predictions,\u201d","volume-title":"Advances in Neural Information Processing Systems","author":"Lundberg","year":"2017"},{"key":"B14","article-title":"\u201cProbabilistic prediction of wheel squeal under field humidity variation,\u201d","author":"Meehan","year":"2010","journal-title":"20th International congress on acoustics 2010, ICA 2010"},{"key":"B15","volume-title":"Noise Prediction of Trains in Curves","author":"Ostermann","year":"2021"},{"key":"B16","volume-title":"NASA TN D-840: Equations for the Determination of Humidity from Dewpoint and Psychometric Data","author":"Parish","year":"1977"},{"key":"B17","doi-asserted-by":"publisher","first-page":"2825","DOI":"10.48550\/arXiv.1201.0490","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res"},{"key":"B18","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1016\/0022-460X(76)90862-2","article-title":"Wheel\/rail noise\u2014Part II: wheel squeal","volume":"46","author":"Rudd","year":"1976","journal-title":"J. Sound Vib"},{"key":"B19","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1016\/j.ipm.2009.03.002","article-title":"A systematic analysis of performance measures for classification tasks","volume":"45","author":"Sokolova","year":"2009","journal-title":"Inform. Process. Manag"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-08-045147-3.00009-8","author":"Thompson","year":"2009","journal-title":"Railway Noise and Vibration: Mechanisms, Modelling and Means of Control"},{"key":"B21","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-319-73411-8_1","article-title":"\u201cA state-of-the-art review of curve squeal noise: phenomena, mechanisms, modelling and mitigation,\u201d","volume-title":"Noise and Vibration Mitigation for Rail Transportation Systems. Notes on Numerical Fluid Mechanics and Multidisciplinary Design","author":"Thompson","year":"2018"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1007\/s40534-026-00432-9","article-title":"Statistical analysis of railway curve squeal occurrence on the low and high rails in relation to environmental conditions","author":"Toratti","year":"2026","journal-title":"Railway Eng. Sci"},{"key":"B23","doi-asserted-by":"publisher","first-page":"695","DOI":"10.24874\/ti.1728.07.24.10","article-title":"Case study: correlations between curve squeal, weather conditions, and traction in a tram loop","volume":"46","author":"Valena","year":"2024","journal-title":"Tribol. Industry"},{"key":"B24","article-title":"\u201cThe impact of weather conditions on the noise radiation level of curve squeal,\u201d","volume-title":"Proceedings IWRN13. 13th international workshop on railway noise","author":"Venghaus","year":"2019"},{"key":"B25","year":"2023","journal-title":"Guide to Meteorological Instruments and Methods of Observation. Volume I"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1887534\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T16:03:38Z","timestamp":1787846618000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1887534\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,27]]},"references-count":25,"alternative-id":["10.3389\/frai.2026.1887534"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1887534","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,27]]},"article-number":"1887534"}}