AI Insight
DG-LLM is a novel deep learning framework for traffic forecasting that combines signal decomposition, dynamic graph construction, and large language models to capture complex spatiotemporal dependencies in traffic data. The model decomposes traffic signals into intrinsic modes, builds adaptive spatial graphs for each mode, and integrates these representations into pre-trained large language models to handle long-range temporal patterns. Evaluated on six real-world traffic datasets, the framework achieves 13 to 19 percent improvement in mean absolute error and 19 to 25 percent improvement in root mean square error compared to state-of-the-art baseline methods, while also demonstrating robustness to missing data and cross-dataset generalization through zero-shot evaluation.
Why it matters
Improved traffic forecasting accuracy directly supports more efficient urban planning, congestion management, and transportation policy decisions. The model's ability to generalize across datasets and handle data gaps suggests practical deployment potential in real-world intelligent transportation systems.
by Sadia Tabassum, Naushin Nower
Traffic forecasting plays a critical role in the field of urban planning. Yet, existing methods struggle with modeling complicated spatiotemporal dependencies and capturing long-term patterns due to their multiscale nature. In this paper, we present a novel framework named DG-LLM that leverages the advantages of decomposed temporal representations and adaptive spatial connectivity to model spatiotemporal dependencies. In this framework, traffic signals are decomposed into intrinsic modes, and dynamic graphs are learned for each mode to represent the spatial dependencies. These representations are then incorporated with pre-trained Large Language Models for effective long-range temporal dependency modeling. We conducted comprehensive experiments across six real-world traffic datasets spanning urban mobility systems and highway traffic networks and evaluated short- and long-term forecasting. Experimental results demonstrate that our framework provides significant improvements over state-of-the-art approaches, including benchmark graph- and LLM-based spatiotemporal forecasting models, even in long-term forecasting scenarios with severe temporal instability. Our model outperforms other methods by achieving 13−19% improvements in MAE and 19−25% in RMSE across all six benchmarks compared with baseline approaches. Additional analyses, including ablation studies, robustness to missing data, and zero-shot cross-dataset evaluation, further validate the effectiveness and generalization capability of the proposed framework.