Featured Application The nonlinear autoregressive with exogenous input (NARX) network model developed in this study provides an advanced solution for accurately predicting subgrade temperatures in seasonally frozen regions. This model can be directly applied to infrastructure projects, such as road and railway construction, where accurate temperature forecasting is crucial to prevent frost heave and ensure stability. Its superior predictive capability, particularly for varying subgrade depths, makes it a valuable tool for engineers and planners involved in the design and maintenance of roadways in cold climates. By integrating temperature, water content, and frost heave as inputs, this approach also holds potential for optimizing subgrade maintenance schedules and improving the durability of seasonally frozen infrastructure.Abstract Accurate prediction of subgrade temperatures in seasonally frozen regions is crucial for understanding thermal states, frost heave phenomena, stability, and other critical characteristics. This study employs a nonlinear autoregressive with exogenous input (NARX) network to predict short-term subgrade temperatures in the Golmud-Nagqu of China's National Highway 109. The methodology involves preprocessing subgrade monitoring data, including temperature, water content, and frost heave, followed by developing a temperature prediction model. This tailored NARX neural network, compared to the traditional BP neural network, integrates feedback and delay mechanisms for monitoring data, offering superior memory and dynamic response capabilities. The precision of the NARX model is assessed with the backpropagation (BP) network, indicating that the NARX neural network significantly outperforms the BP model in both precision and stability for temperature prediction in seasonally frozen subgrades. These findings suggest that the NARX model is a valuable tool for accurately predicting subgrade temperatures in seasonally frozen regions, offering significant insights for practical engineering applications.