19 January 2024 in Transportation Research Part D: Transport and Environment
15 November 2024 in International Journal of Modern Physics C
1 February 2021 in Journal of Transportation Engineering, Part A: Systems
Snowplow trucks serve a crucial role in winter maintenance activities by removing, loading, and disposing of snow. A performance-monitoring and analysis process can assist transportation agencies in effectively managing snowplow trucks and maintaining the normal functioning of roadways. Previous literature suggests that most snowplow truck performance analysis is done through life-cycle cost assessment at the macro level to determine the optimal life cycle for the entire truck fleet. However, this can lead to a waste of resources and may incur bias due to ignorance of performance variations resulting from endogenous and exogenous features. More important, such analysis fails to identify the factors that contribute to performance deterioration. With the proliferation of operational data on snowplow operations, these concerns can be addressed through predictive machine-learning (ML) techniques in a data-driven fashion. In this study, we applied a popular ML technique, random forest (RF), to predict the performance of snowplow trucks, which was quantified via the rank of major repair times. Another ML technique, linear support vector machine (SVM), was also applied for benchmarking and comparison. Using the snowplow truck fleet managed by the Utah Department of Transportation (UDOT), both models were implemented and it was demonstrated that RF outperforms linear SVM with regard to prediction accuracy. Further, a feature importance analysis from the RF model can help transportation agencies to improve truck replacement strategies by identifying crucial performance factors. Lastly, a sample application of the developed prediction model using RF suggests the threshold of work intensity for preventing the rapid deterioration of truck performance in various working environments. Compared with the life-cycle cost analyses used in previous studies, the prediction model proposed here can help transportation agencies to better prioritize fleet replacement.
28 February 2026 in SSRN Electronic Journal
Evaluating parking difficulty is critical for urban planning and policy, including parking pricing, demand management, parking facility allocation, and curb space regulation. Reliable estimates of parking difficulty are also essential for commercial applications such as routing and navigation systems. However, accurately estimating parking difficulty at large scale remains challenging for several reasons. First, large-scale parking data are difficult to collect or are commercially restricted. Uncovering parking patterns requires extensive historical data with rich spatial and temporal coverage. Second, parking behavior exhibits substantial spatial heterogeneity due to the combined effects of road characteristics and the surrounding built environment. In this paper, we quantify parking difficulty with parking search time (PST) and propose a multimodal framework - PaSTNet - for estimating PST for each road segment at city scale. PaSTNet integrates a Graph Neural Network (GNN) to capture spatial dependencies in parking behavior. Visual features reflecting curbside and roadway conditions are extracted from satellite imagery using a large-scale pre-trained visual foundation model DINO-v2. A cross-attention module is then employed to fuse visual embeddings with trajectory-based features and road characteristics, enabling the model to jointly learn from network structure and visual context. Experimental results demonstrate that PaSTNet consistently outperforms baseline methods. In addition, this study provides insights into the spatiotemporal distribution of parking difficulty across urban areas.