Bicycle traffic, as a sustainable mode of transport, helps reduce urban emissions and promote livable cities. Accurate short-term prediction of bicycle traffic flow can support real-time and near-real-time traffic management decisions in urban cycling systems. However, this task is challenging due to limited high-quality bicycle data, sparse sensor coverage, and high sensitivity to external factors. In this work, we propose a Bicycle Spatial-Temporal Large Language Model (BiSTLLM) for bicycle traffic prediction, inspired by the strong time series modeling capabilities of large language models (LLMs). In BiSTLLM, we define the historical traffic sequence at each location as tokens, allowing the model to learn complex spatial-temporal patterns. Specifically, we first introduce a weather lagging processor using causal temporal convolution to capture the delayed effects of weather on bicycle traffic. We also incorporate semantic embeddings of Point-of-Interest (POIs) and bicycle lane accessibility to represent land use and infrastructure, enhancing the model’s ability to learn both localized activity patterns and broader spatial-temporal dynamics. We then further introduce a fine-tuning strategy to better tailor the general knowledge of a pre-trained LLM to the specific characteristics of bicycle traffic. Experiments on real-world bicycle traffic flow datasets demonstrate that BiSTLLM outperforms existing state-of-the-art models. Notably, BiSTLLM exhibits strong performance even in few-shot settings, highlighting its potential for accurate bicycle traffic prediction in data-sparse environments.

Bicycle transportation, a low-carbon option, is essential for promoting sustainable urban mobility. However, predicting bicycle traffic is challenging due to limited investments in data collection, especially in smaller cities. This paper proposes a multi-source transfer learning spatial-temporal graph neural network (Multi-TLSTGCN) for accurate bicycle traffic prediction in target cities with limited available data. This study first examines how to transfer knowledge from single source domain to the target domain while mitigating the risk of negative transfer. Following this, a multi-source adaptive transfer learning approach is developed to optimize traffic prediction in the target domain by adaptively integrating knowledge from multiple sources. Finally, the performance of the Multi-TLSTGCN model is evaluated under various levels of target data scarcity and compared with models that do not incorporate source domain knowledge. The experimental results demonstrate several key insights: 1) Models fine-tuned with a single-cluster pre-trained source model where the clusters are formed based on similar traffic patterns are more effective at minimizing negative knowledge transfer than those fine-tuned with single-city pre-trained source models. 2) The proposed Multi-TLSTGCN outperforms baseline models in bicycle traffic prediction, showing promise for accurate predictions in data-scarce environments; and 3) The Multi-TLSTGCN model remains robust across varying levels of data scarcity, exhibiting only a slight decrease in accuracy as the availability of target data decreases, in contrast to models relying solely on target domain data. These findings highlight the Multi-TLSTGCN model as an effective and promising solution for bicycle traffic prediction with limited data availability.

Accurate prediction of active mode traffic is imperative for optimizing traffic operations in Intelligent Trans-portation Systems. However, existing data-driven approaches heavily rely on extensive datasets to achieve reliable traffic prediction. This dependence poses a challenge when it comes to data sharing, particularly when collecting information from multiple local clients, such as institutions, organizations, and mobile devices, and transmitting it to a central server for model training and application. To overcome this challenge and enhance data security, we introduce the FedASTGNN model for active mode traffic prediction. This approach combines the federated averaging (FedAvg) algorithm with an attention-based spatial-temporal graph neural network (ASTGNN) model. Subsequently, we conduct an evaluation to determine the performance gap between the centralized ASTGNN model and the proposed distributed FedASTGNN model. This evaluation takes into account the model's performance across different time aggregation intervals and prediction horizons. Moreover, considering the unique attributes and intricacies of active mode data, we create three scenarios to demonstrate the influence of diverse active mode data from different local clients (subnet-works) on the FedASTGNN model. The findings of our study illustrate that the FedASTGNN model effectively preserves the advantages of the ASTGNN model while ensuring data confidentiality in active mode traffic prediction. Furthermore, we observe that the performance of the FedASTGNN model is significantly affected by the varying degrees of imbalanced data distribution among subnetworks. The insights shed light on the potential and challenges presented by the FedASTGNN model as an efficient and secure solution for predicting active mode traffic in Intelligent Transportation Systems.