Reliable characterization of the wellbore temperature field is essential for ensuring drilling safety and optimizing operational parameters in shale oil horizontal wells. To address the limitations of conventional models that assume constant thermophysical properties and neglect interactions among multiple heat sources, a transient heat transfer model featuring one-dimensional heat transfer in the wellbore and two-dimensional heat transfer in the formation is developed. The model uniquely accounts for variable thermophysical properties along with three internal heat sources: bit–rock interaction heat (BRIH), viscous dissipation heat (VDH), and drillpipe–formation friction heat (DFFH). The governing equations are implemented numerically using a fully implicit finite-difference approach and verified against field measurements from 10 wells in the Shengli Oilfield. The model demonstrates high predictive accuracy, with an average relative error of 1.58%. VDH contributes significantly to wellbore temperature elevation (≈3.33 °C), whereas BRIH and DFFH exert comparatively minor effects (≈0.34 °C). Sensitivity analysis shows that geothermal gradient is the dominant factor controlling BHCT (correlation coefficients: 0.74 for OBDF; 0.65 for WBDF), followed by drilling fluid density, with all parameters exhibiting weak intercorrelations. Furthermore, a PSO-RBF optimization framework is developed, reducing computation time from 48.34 min per evaluation to an average of 9.0 min per well (81.4% efficiency improvement) while maintaining high prediction accuracy. Overall, this study contributes theoretical understanding and practical value to temperature prediction and parameter optimization in shale oil horizontal well drilling.

In ultra-deep well drilling, directly measuring the static formation temperature (SFT) is highly time-consuming, as it requires extended shut-in periods for the wellbore to reach full thermal equilibrium, making it impractical for routine engineering operations. To overcome this challenge, this paper establishes a wellbore–formation transient temperature model (WFTM) and proposes an SFT inversion method based on the Improved Grey Wolf Optimizer (IGWO) and Radial Basis Function (RBF) neural network. The RBF network serves as a surrogate model to replace the WFTM during iterative optimization, avoiding the prohibitive computational cost of repeated WFTM evaluations and enabling rapid prediction of the transient wellbore temperature field. Meanwhile, the IGWO algorithm uses the measured bottomhole circulating temperature (BHCT) as a constraint to optimize the geothermal gradient in SFT inversion. Multi-well validation shows that the RBF surrogate predicts BHCT with relative errors consistently below 1%, demonstrating its effectiveness as a substitute for the WFTM. Compared with the direct iterative approach (IGWO-WFTM), the IGWO-RBF method yields slightly lower SFT inversion accuracy, but this deviation remains within engineering tolerances, and the computational time is reduced by approximately 18 times. Requiring only surface temperature and routinely measured BHCT, the proposed approach offers a practical and efficient pathway for real-time assessment of formation temperature during ultra-deep oil well drilling.