With the accelerating pace of urbanization and the growing urgency to address climate change, improving the efficiency of multimodal transport systems has become a critical focus for sustainable development. High-speed rail (HSR) stations, as major urban transportation hubs, often suffer from inefficient transfer processes, leading to increased energy consumption and elevated carbon emissions. This study proposes the application of time series models, specifically Long Short-Term Memory (LSTM) networks and the Autoregressive Integrated Moving Average (ARIMA) model, to predict passenger flow and optimize transfer coordination. By incorporating historical traffic data along with external factors such as weather conditions, holidays, and large-scale events, these models provide accurate predictions of congestion patterns. The insights derived from these forecasts enable dynamic scheduling adjustments, minimizing transfer delays and reducing reliance on high-carbon transportation modes. This study underscores the potential of data-driven decision-making in promoting low-carbon mobility and fostering the integration of sustainable transportation systems. The findings offer practical recommendations for policymakers and urban planners seeking to achieve carbon neutrality goals while enhancing urban mobility quality.