Weather-Aware Prediction of Trail Running Finish Times Using Machine Learning
DOI:
https://doi.org/10.59395/ijadis.v7i2.1610Keywords:
Trail running, Extreme Gradient Boosting, Explainable AI, Event-based modeling, Weather ImpactAbstract
This study investigates the role of environmental variables in improving the prediction of Mean Finish Time (MFT) in trail running events. While previous approaches primarily rely on track-related features to predict individual athlete performance, the contribution of dynamic weather conditions at the event level remains insufficiently explored. This research adopts a quantitative modeling approach using Extreme Gradient Boosting (XGBoost) to analyze 36,700 race records integrated with spatio-temporal weather data. To rigorously prevent data leakage, a controlled experimental design was implemented using Group Shuffle Split based on race titles, comparing a model that incorporates environmental variables against one relying solely on track characteristics. The results show that the inclusion of weather variables significantly improves predictive reliability, reducing the Mean Absolute Percentage Error (MAPE) from 10.05% to 8.50% and increasing the coefficient of determination ( ) to 0.7836. Further analysis reveals that environmental variables, particularly temperature, interact with terrain difficulty and disproportionately influence high-effort events. In conclusion, integrating environmental variables significantly enhances predictive accuracy, offering a novel, data-driven approach for race organizers to calculate ideal Cut-Off Times (COT) and Cut-Off Points (COP) based on dynamic environmental constraints.
Downloads
References
[1] L. P. Ardigò, C. Capelli, and G. P. Millet, “Editorial: Human Ultra-Endurance Exercise,” Jun. 25, 2020, Frontiers Media S.A. doi: 10.3389/fphys.2020.00664. DOI: https://doi.org/10.3389/fphys.2020.00664
[2] P. Belinchón-Demiguel, P. Ruisoto, B. Knechtle, P. T. Nikolaidis, B. Herrera-Tapias, and V. J. Clemente-Suárez, “Predictors of athlete’s performance in ultra-endurance mountain races,” Int. J. Environ. Res. Public Health, vol. 18, no. 3, pp. 1–8, Feb. 2021, doi: 10.3390/ijerph18030956. DOI: https://doi.org/10.3390/ijerph18030956
[3] B. Knechtle et al., “The fastest 24-hour ultramarathoners are from Eastern Europe,” Sci. Rep., vol. 14, no. 1, Dec. 2024, doi: 10.1038/s41598-024-75260-0. DOI: https://doi.org/10.1038/s41598-024-75260-0
[4] J. Turnwald et al., “Analysis of the 50-mile ultramarathon distance using a predictive XGBoost model,” Sci. Rep., vol. 15, no. 1, Dec. 2025, doi: 10.1038/s41598-025-92581-w. DOI: https://doi.org/10.1038/s41598-025-92581-w
[5] G. Ke et al., “LightGBM: A Highly Efficient Gradient Boosting Decision Tree,” in Advances in Neural Information Processing Systems (NeurIPS), 2017, [Online]. Available: https://github.com/Microsoft/LightGBM.
[6] R. Shwartz-Ziv and A. Armon, “Tabular Data: Deep Learning is Not All You Need,” Information Fusion, Nov. 2021, doi: https://doi.org/10.1016/j.inffus.2021.11.013. DOI: https://doi.org/10.1016/j.inffus.2021.11.011
[7] D. Shu et al., “Prediction of half-marathon performance of male recreational marathon runners using nomogram,” BMC Sports Sci. Med. Rehabil., vol. 16, no. 1, Dec. 2024, doi: 10.1186/s13102-024-00889-3. DOI: https://doi.org/10.1186/s13102-024-00889-3
[8] N. El Helou et al., “Impact of Environmental Parameters on Marathon Running Performance,” PLoS One, vol. 7, no. 5, p. e37407, May 2012, doi: 10.1371/JOURNAL.PONE.0037407. DOI: https://doi.org/10.1371/journal.pone.0037407
[9] K. Mantzios et al., “Effects of Weather Parameters on Endurance Running Performance: Discipline-specific Analysis of 1258 Races,” Med. Sci. Sports Exerc., vol. 54, no. 1, pp. 153–161, Jan. 2022, doi: 10.1249/MSS.0000000000002769. DOI: https://doi.org/10.1249/MSS.0000000000002769
[10] D. Gregory, K. Kintziger, S. Crouter, C. Sims, M. Kellogg, and E. Fitzhugh, “Weather effects on natural surface trail use in an urban wilderness multi-use trail system,” Journal of Outdoor Recreation and Tourism, vol. 46, p. 100757, Jun. 2024, doi: 10.1016/J.JORT.2024.100757. DOI: https://doi.org/10.1016/j.jort.2024.100757
[11] T. Chen and C. Guestrin, “XGBoost: A scalable tree boosting system,” in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery, Aug. 2016, pp. 785–794. doi: 10.1145/2939672.2939785. DOI: https://doi.org/10.1145/2939672.2939785
[12] S. M. Lundberg et al., “From local explanations to global understanding with explainable AI for trees,” Nat. Mach. Intell., vol. 2, no. 1, pp. 56–67, Jan. 2020, doi: 10.1038/s42256-019-0138-9. DOI: https://doi.org/10.1038/s42256-019-0138-9
[13] W. Samek, G. Montavon, S. Lapuschkin, C. J. Anders, and K. R. Müller, “Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications,” Proceedings of the IEEE, vol. 109, no. 3, pp. 247–278, Mar. 2021, doi: 10.1109/JPROC.2021.3060483. DOI: https://doi.org/10.1109/JPROC.2021.3060483
[14] M. Kuhn and K. Johnson, Applied Predictive Modeling. Springer, 2013. doi: 10.1007/978-1-4614-6849-3. DOI: https://doi.org/10.1007/978-1-4614-6849-3
[15] “Mannasd/prediksi_mean_finish_time_trail_run: Implementasi pipeline machine learning untuk prediksi performa lari menggunakan data UTMB yang diperkaya dengan fitur cuaca dan variabel aktivitas.” Accessed: May 05, 2026. [Online]. Available: https://github.com/Mannasd/prediksi_mean_finish_time_trail_run
[16] “UTMB World Series - Meet your extraordinary!” Accessed: May 05, 2026. [Online]. Available: https://utmb.world/
[17] “ Free Open-Source Weather API | Open-Meteo.com.” Accessed: May 05, 2026. [Online]. Available: https://open-meteo.com/
[18] F. Pedregosa FABIANPEDREGOSA et al., “Scikit-learn: Machine Learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011, [Online]. Available: http://scikit-learn.sourceforge.net.
[19] “ITRA - International Trail Running Association - official world ranking of trail runners recognized by World Athletics.” Accessed: May 05, 2026. [Online]. Available: https://itra.run/
[20] H. Wang, N. Lu, T. Chen, H. He, Y. Lu, and X. M. Tu, “Log-transformation and its implications for data analysis,” Shanghai Arch. Psychiatry, vol. 26, no. 2, pp. 105–109, 2014, doi: 10.3969/j.issn.1002-0829.2014.02.009.
[21] D. Chicco, M. J. Warrens, and G. Jurman, “The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation,” PeerJ Comput. Sci., vol. 7, pp. 1–24, 2021, doi: 10.7717/PEERJ-CS.623. DOI: https://doi.org/10.7717/peerj-cs.623
[22] T. Chai and R. R. Draxler, “Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature,” Geosci. Model Dev., vol. 7, no. 3, pp. 1247–1250, Jun. 2014, doi: 10.5194/gmd-7-1247-2014. DOI: https://doi.org/10.5194/gmd-7-1247-2014
[23] L. Prokhorenkova, G. Gusev, A. Vorobev, A. V. Dorogush, and A. Gulin, “CatBoost: unbiased boosting with categorical features,” in Advances Neural Information Processing Systems (NeurIPS), Jan. 2019, [Online]. Available: http://arxiv.org/abs/1706.09516
[24] M. Thuany et al., “An analysis of the 6-h ultra-marathon race using a machine learning approach,” Front. Sports Act. Living, vol. 7, 2025, doi: 10.3389/fspor.2025.1577470. DOI: https://doi.org/10.3389/fspor.2025.1577470
[25] E. W. Solang, L. Linawati, I. B. G. Manuaba, and I. N. Setiawan, “A Systematic Literature Review of Machine Learning for Endurance Running Performance Prediction,” sinkron, vol. 10, no. 1, pp. 512–524, Jan. 2026, doi: 10.33395/sinkron.v10i1.15743. DOI: https://doi.org/10.33395/sinkron.v10i1.15743
[26] B. Knechtle et al., “Race course characteristics are the most important predictors in 48 h ultramarathon running,” Sci. Rep., vol. 15, no. 1, Dec. 2025, doi: 10.1038/s41598-025-94402-6. DOI: https://doi.org/10.1038/s41598-025-94402-6
[27] E. Y. Lee et al., “Ambient environmental conditions and active outdoor play in the context of climate change: A systematic review and meta-synthesis,” Environ. Res., vol. 283, Oct. 2025, doi: 10.1016/j.envres.2025.122146. DOI: https://doi.org/10.1016/j.envres.2025.122146
[28] B. Knechtle et al., “Change in elevation predicts 100 km ultra marathon performance,” Sci. Rep., vol. 15, no. 1, Dec. 2025, doi: 10.1038/s41598-025-09502-0. DOI: https://doi.org/10.1038/s41598-025-09502-0
[29] M. J. Joyner, “Physiological limits to endurance exercise performance: influence of sex,” May 01, 2017, Blackwell Publishing Ltd. doi: 10.1113/JP272268. DOI: https://doi.org/10.1113/JP272268
[30] S. Lazzer, D. Salvadego, E. Rejc, A. Buglione, G. Antonutto, and P. E. Di Prampero, “The energetics of ultra-endurance running,” European Journal of Applied Physiology 2011 112:5, vol. 112, no. 5, pp. 1709–1715, Sep. 2011, doi: 10.1007/S00421-011-2120-Z. DOI: https://doi.org/10.1007/s00421-011-2120-z
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Muhammad Annas darunnaja, Mokhamad Amin Hariyadi, Okta Qomaruddin Aziz, M.Kom., Johan Ericka Wahyu Prakasa, Agung Teguh Wibowo Almais
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
How to Cite
Share
Plum Analytics