Guleryuz, DidemYildirim, UmitGuler, Cuneyt2026-09-012026-09-0120260177-798X1434-4483http://dx.doi.org/10.1007/s00704-026-06433-2https://hdl.handle.net/20.500.12403/8564Soil-temperature predictability is inherently depth-dependent because atmospheric forcing is progressively attenuated and transformed into smoother, lower-frequency thermal dynamics with increasing depth. Under Mediterranean climatic conditions, where pronounced seasonality and strong surface forcing coexist, this depth-dependent transformation provides an informative basis for evaluating model behaviour. This study examines soil-temperature prediction at depths of 5, 10, 20, 50, and 100 cm using a multivariate dataset comprising 5,285 retained daily observations from the Mersin meteorological station on T & uuml;rkiye's eastern Mediterranean coast. Precipitation, air temperature, relative humidity, wind speed, and evaporation were used as predictors. Support vector regression, random forest, and LightGBM were evaluated using R & sup2;, RMSE, and MAE. All three models performed strongly in the near-surface layers, with test R & sup2; values ranging from 0.948 to 0.954 at depths of 5-20 cm. Predictive performance declined with increasing depth as short-period variability weakened and the thermal signal became smoother and more seasonally structured. RF and LightGBM showed a greater numerical decline at 50-100 cm, whereas SVR achieved test R & sup2; values of 0.923 at 50 cm and 0.847 at 100 cm; however, inter-model differences remained modest and were interpreted descriptively. Lomb-Scargle spectral analysis, applied using the actual observation dates, indicated that short-period variability became relatively less pronounced with depth while seasonal-scale and low-frequency components remained prominent. Overall, the findings suggest that soil-temperature prediction should be interpreted in relation to depth-dependent temporal signal characteristics rather than as a search for a universally superior algorithm.eninfo:eu-repo/semantics/closedAccess[Keyword Not Available]Article157810.1007/s00704-026-06433-22-s2.0-105045230083Q2WOS:001826896800002Q3