High thermal loads on brake systems during extended descents followed by vehicle soak pose significant safety and durability risks. Excessive rotor or fluid temperatures can cause loss of braking efficacy, fluid degradation or evaporation, thermal fade, and accelerated component wear. This study uses time-history data of brake-disc and fluid temperatures which were collected during controlled hill-descent events with subsequent soak periods, where the vehicle is parked in a wind protected area. Besides the rotor and brake fluid temperatures, environmental conditions were recorded (ambient temperature, humidity, wind speed and direction) and the vehicle and brake specifications are known (rotor/caliper geometry, pad material, vehicle aerodynamic configuration and mass). 126 test runs from a dedicated vehicle program are used, each providing time-history records that form the basis of our analysis. From these records we extract phase-specific samples (descent and soak phase) and engineer compact descriptors — start and peak temperatures, environmental factors, rolling statistics and contextual metadata to represent each event. We develop and evaluate machine-learning regression and neural-network models to predict the disc and brake-fluid temperatures occurring during the descent and across the soak phase. Cross-validation is done to ensure generalization to unseen descent events. Models are evaluated with mean absolute error (MAE) and bias diagnostics. The predictive models enable early warning of critical temperature spikes and support design and operational decisions (cooling design, allowable profiles and optimization). By delivering fast temperature estimates, they reduce reliance on computationally expensive CFD during early design, while CFD and experiments remain for final validation. We present workflow, model performance and uncertainty characterization.