Vessel Traffic Flow Prediction on Sparse Data via Spatio-Temporal Graph Neural Networks with a Learnable Tweedie Head

• URL: http://arxiv.org/abs/2606.07694v1
• Date: Fri, 05 Jun 2026 07:31:07 GMT
• Title: Vessel Traffic Flow Prediction on Sparse Data via Spatio-Temporal Graph Neural Networks with a Learnable Tweedie Head
• Abstract summary: Maritime traffic flow data are often sparse with intermittent bursts, making robust forecasting challenging.<n>We propose a model-agnostic learnable Tweedie head that can be attached as a plug-and-play output module to arbitrary ST-GNN backbones.
• Score: 9.797319790710711
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate vessel traffic flow prediction is crucial for smart port operations and navigational safety. However, maritime traffic flow data are often highly sparse with intermittent bursts, making robust forecasting challenging. Under such conditions, conventional spatio-temporal graph neural networks (ST-GNNs) can degrade toward conservative near-zero predictions and fail to capture non-zero activity. Although zero-inflated negative binomial (ZINB) models partially address excess zeros, their two-part formulation can still remain conservative around abrupt transitions. To address these issues, we propose a model-agnostic learnable Tweedie head that can be attached as a plug-and-play output module to arbitrary ST-GNN backbones. Instead of likelihood-based Tweedie training, which typically requires surrogate objectives, our approach optimizes the closed-form Tweedie unit deviance and predicts the mean for point forecasting while learning a node-level variance power to capture heterogeneous variability across port areas. Experiments on a maritime traffic graph constructed from real-world AIS data in the Port of Los Angeles and Long Beach show that the proposed head consistently improves RMSE across multiple ST-GNN backbones, especially on non-zero events, leading to more reliable forecasts for practical maritime traffic control.

Related papers

• MobiWave: Dispatch-Oriented Graph Wavelets and Drift-Guided Selective Optimization for Autonomous Fleet Rebalancing [17.05150937022831]
  name is a framework that connects a dispatch-oriented multi-scale graph wavelet module with Drift-Guided Layer-Selective Optimization (DGLS)<n> DGLS addresses the adaptation challenge by measuring Dispatch-weighted Spectral Drift.<n>Experiments on both real-world datasets and simluated environments demonstrate the effectiveness of name in comparing with state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-07-27T12:39:04Z)
• Adaptive Graph Pruning with Sudden-Events Evaluation for Traffic Prediction using Online Semi-Decentralized ST-GNNs [0.07456526005219317]
  We propose an adaptive pruning algorithm that filters redundant neighbour features while preserving the most informative spatial context for prediction.<n>The algorithm adjusts pruning rates based on recent model performance, allowing each cloudlet to focus on regions experiencing traffic changes without compromising accuracy.<n>We evaluate our approach in an online semi-decentralized setting with traditional FL, server-free FL, and Gossip Learning on two large-scale traffic datasets.
  arXiv  Detail & Related papers  (2025-12-19T08:48:36Z)
• ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving [64.42138266293202]
  ResAD is a Normalized Residual Trajectory Modeling framework.<n>It reframes the learning task to predict the residual deviation from an inertial reference.<n>On the NAVSIM benchmark, ResAD achieves a state-of-the-art PDMS of 88.6 using a vanilla diffusion policy.
  arXiv  Detail & Related papers  (2025-10-09T17:59:36Z)
• Physics-guided Active Sample Reweighting for Urban Flow Prediction [75.24539704456791]
  Urban flow prediction is a nuanced-temporal modeling that estimates the throughput of transportation services like buses, taxis and ride-driven models. Some recent prediction solutions bring remedies with the notion of physics-guided machine learning (PGML) We develop a atized physics-guided network (PN), and propose a data-aware framework Physics-guided Active Sample Reweighting (P-GASR)
  arXiv  Detail & Related papers  (2024-07-18T15:44:23Z)
• Unveiling Delay Effects in Traffic Forecasting: A Perspective from Spatial-Temporal Delay Differential Equations [20.174094418301245]
  Traffic flow forecasting is a fundamental research issue for transportation planning and management. In recent years, Graph Neural Networks (GNNs) and Recurrent Neural Networks (RNNs) have achieved great success in capturing spatial-temporal correlations for traffic flow forecasting. However, two non-ignorable issues haven't been well solved: 1) The message passing in GNNs is immediate, while in reality the spatial message interactions among neighboring nodes can be delayed.
  arXiv  Detail & Related papers  (2024-02-02T08:55:23Z)
• Streaming Motion Forecasting for Autonomous Driving [71.7468645504988]
  We introduce a benchmark that queries future trajectories on streaming data and we refer to it as "streaming forecasting" Our benchmark inherently captures the disappearance and re-appearance of agents, which is a safety-critical problem yet overlooked by snapshot-based benchmarks. We propose a plug-and-play meta-algorithm called "Predictive Streamer" that can adapt any snapshot-based forecaster into a streaming forecaster.
  arXiv  Detail & Related papers  (2023-10-02T17:13:16Z)
• Newell's theory based feature transformations for spatio-temporal traffic prediction [0.0]
  We propose a traffic flow physics-based transformation feature for Deep learning (DL) models for traffic flow forecasting. This transformation incorporates Newell's uncongested and congested filters of traffic flows at the target locations, enabling the models to learn broader dynamics of the system. An important advantage of our framework is its ability to be transferred to new locations where data is unavailable.
  arXiv  Detail & Related papers  (2023-07-12T06:31:43Z)
• Deep Learning for Day Forecasts from Sparse Observations [60.041805328514876]
  Deep neural networks offer an alternative paradigm for modeling weather conditions. MetNet-3 learns from both dense and sparse data sensors and makes predictions up to 24 hours ahead for precipitation, wind, temperature and dew point. MetNet-3 has a high temporal and spatial resolution, respectively, up to 2 minutes and 1 km as well as a low operational latency.
  arXiv  Detail & Related papers  (2023-06-06T07:07:54Z)
• Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction [60.60223171143206]
  Trajectory prediction is a crucial undertaking in understanding entity movement or human behavior from observed sequences. Current methods often assume that the observed sequences are complete while ignoring the potential for missing values. This paper presents a unified framework, the Graph-based Conditional Variational Recurrent Neural Network (GC-VRNN), which can perform trajectory imputation and prediction simultaneously.
  arXiv  Detail & Related papers  (2023-03-28T14:27:27Z)
• STG-GAN: A spatiotemporal graph generative adversarial networks for short-term passenger flow prediction in urban rail transit systems [11.167132464665578]
  Short-term passenger flow prediction is an important but challenging task for better managing urban rail transit systems. We propose a novel deep learning-basedtemporal graph generative adversarial network (STG-GAN) model with higher prediction accuracy, higher efficiency, and lower memory occupancy. This study can provide critical experience in conducting short-term passenger flow predictions, especially from the perspective of real-world applications.
  arXiv  Detail & Related papers  (2022-02-10T13:18:11Z)
• Spatial-Temporal Tensor Graph Convolutional Network for Traffic Prediction [46.762437988118386]
  We propose a factorized Spatial-Temporal Graph Convolutional Network to deal with traffic speed prediction. To reduce the computational burden, we take Tucker tensor decomposition and derive factorized a tensor convolution. Experiments on two real-world traffic speed datasets demonstrate our method is more effective than those traditional traffic prediction methods.
  arXiv  Detail & Related papers  (2021-03-10T15:28:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.