Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Truck Parking Usage Prediction with Decomposed Graph Neural Networks

Rei Tamaru, Yang Cheng, Steven Parker, Ernie Perry, Bin Ran, Soyoung Ahn

TL;DR

The paper targets the challenge of predicting truck parking occupancy across multiple sites along freight corridors, addressing safety and efficiency concerns under HOS constraints. It introduces the Regional Temporal Graph Convolutional Network (RegT-GCN) that uses Regional Decomposition to form state-level regional subgraphs, integrating a spatial GCN with a GRU-based temporal module to model spatio-temporal dependencies. Through extensive experiments on TPIMS-derived data from eight MAASO states, RegT-GCN outperforms a suite of baselines, demonstrates robustness across time horizons and weeks, and shows improved computational efficiency due to decomposed regional graphs. The study demonstrates the practical value of regional graph structures for large-scale truck parking occupancy prediction and offers insights into graph connectivity and decomposition strategies for future transport analytics.

Abstract

Truck parking on freight corridors faces the major challenge of insufficient parking spaces. This is exacerbated by the Hour-of-Service (HOS) regulations, which often result in unauthorized parking practices, causing safety concerns. It has been shown that providing accurate parking usage prediction can be a cost-effective solution to reduce unsafe parking practices. In light of this, existing studies have developed various methods to predict the usage of a truck parking site and have demonstrated satisfactory accuracy. However, these studies focused on a single parking site, and few approaches have been proposed to predict the usage of multiple truck parking sites considering spatio-temporal dependencies, due to the lack of data. This paper aims to fill this gap and presents the Regional Temporal Graph Convolutional Network (RegT-GCN) to predict parking usage across the entire state to provide more comprehensive truck parking information. The framework leverages the topological structures of truck parking site locations and historical parking data to predict the occupancy rate considering spatio-temporal dependencies across a state. To achieve this, we introduce a Regional Decomposition approach, which effectively captures the geographical characteristics of the truck parking locations and their spatial correlations. Evaluation results demonstrate that the proposed model outperforms other baseline models, showing the effectiveness of our regional decomposition. The code is available at https://github.com/raynbowy23/RegT-GCN.

Truck Parking Usage Prediction with Decomposed Graph Neural Networks

TL;DR

The paper targets the challenge of predicting truck parking occupancy across multiple sites along freight corridors, addressing safety and efficiency concerns under HOS constraints. It introduces the Regional Temporal Graph Convolutional Network (RegT-GCN) that uses Regional Decomposition to form state-level regional subgraphs, integrating a spatial GCN with a GRU-based temporal module to model spatio-temporal dependencies. Through extensive experiments on TPIMS-derived data from eight MAASO states, RegT-GCN outperforms a suite of baselines, demonstrates robustness across time horizons and weeks, and shows improved computational efficiency due to decomposed regional graphs. The study demonstrates the practical value of regional graph structures for large-scale truck parking occupancy prediction and offers insights into graph connectivity and decomposition strategies for future transport analytics.

Abstract

Truck parking on freight corridors faces the major challenge of insufficient parking spaces. This is exacerbated by the Hour-of-Service (HOS) regulations, which often result in unauthorized parking practices, causing safety concerns. It has been shown that providing accurate parking usage prediction can be a cost-effective solution to reduce unsafe parking practices. In light of this, existing studies have developed various methods to predict the usage of a truck parking site and have demonstrated satisfactory accuracy. However, these studies focused on a single parking site, and few approaches have been proposed to predict the usage of multiple truck parking sites considering spatio-temporal dependencies, due to the lack of data. This paper aims to fill this gap and presents the Regional Temporal Graph Convolutional Network (RegT-GCN) to predict parking usage across the entire state to provide more comprehensive truck parking information. The framework leverages the topological structures of truck parking site locations and historical parking data to predict the occupancy rate considering spatio-temporal dependencies across a state. To achieve this, we introduce a Regional Decomposition approach, which effectively captures the geographical characteristics of the truck parking locations and their spatial correlations. Evaluation results demonstrate that the proposed model outperforms other baseline models, showing the effectiveness of our regional decomposition. The code is available at https://github.com/raynbowy23/RegT-GCN.
Paper Structure (24 sections, 14 equations, 6 figures, 4 tables, 1 algorithm)

This paper contains 24 sections, 14 equations, 6 figures, 4 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Spatio-Temporal Prediction in Transportation
  4. Parking Usage Prediction
  5. Spatio-Temporal Representation in Parking Prediction
  6. Methodological Approach
  7. Problem Formulation
  8. Regional Temporal Graph Convolutional Network
  9. Temporal Module
  10. Model Training
  11. Experiments
  12. Data Collection and Pre-processing
  13. Evaluation Metrics
  14. Model Comparison
  15. Truck Parking Usage Prediction
  16. ...and 9 more sections

Figures (6)

  • Figure 1: The overview of Regional Temporal Graph Neural Network.
  • Figure 2: The architecture of GCN based GRU.
  • Figure 3: Spatial distribution of truck parking sites in eight states in MAASTO (left). Average hourly occupancy rate at one site in a week averaged by days of 4 weeks (right top). Monthly whiskers data visualization (right bottom) rei2023.
  • Figure 4: The results of occupancy rate prediction with RegT-GCN at one truck parking site for the time horizon of 30 minutes (above) and 360 minutes (below) and ground truth from Mar. 3rd, 2022 to Mar. 14th, 2022.
  • Figure 5: Variety of connectivity on the simple graphs (Left: connected, Middle: randomly connected, Right: regionally connected). Small ellipses represent regional classification. The same color denotes the same group constructing one graph.
  • ...and 1 more figures