Technology Category
Planning, Routing, and Scheduling: Model-Based ReasoningIntelligent Robots: State EstimationHumans and AI: Human-Aware Planning and Behavior Prediction
Predicting Barge Tow Size on Inland Waterways Using Vessel Trajectory Derived Features: Proof of Concept
🤖 AI Summary
To address the challenge of real-time, accurate estimation of non-self-propelled barge counts in inland waterways, this paper proposes a barge-count prediction method leveraging Automatic Identification System (AIS) trajectory data. We construct a 30-dimensional feature set—including dynamic metrics such as heading entropy and speed variability—by spatiotemporally aligning AIS trajectories with satellite imagery annotations. Recursive feature elimination identifies 12 key predictors, and a Poisson regression model is employed for count prediction. Experimental results demonstrate an average absolute error of only 1.92 barges in real-world scenarios, outperforming five alternative regression models. This work pioneers the incorporation of motion complexity indicators—particularly heading entropy—into barge fleet identification, enabling interpretable, scalable, and real-time modeling of tug-barge relationships. The approach establishes a novel paradigm for inland waterway situational awareness, navigational scheduling, and freight planning.
Technology Category
Application Category
📝 Abstract
Accurate, real-time estimation of barge quantity on inland waterways remains a critical challenge due to the non-self-propelled nature of barges and the limitations of existing monitoring systems. This study introduces a novel method to use Automatic Identification System (AIS) vessel tracking data to predict the number of barges in tow using Machine Learning (ML). To train and test the model, barge instances were manually annotated from satellite scenes across the Lower Mississippi River. Labeled images were matched to AIS vessel tracks using a spatiotemporal matching procedure. A comprehensive set of 30 AIS-derived features capturing vessel geometry, dynamic movement, and trajectory patterns were created and evaluated using Recursive Feature Elimination (RFE) to identify the most predictive variables. Six regression models, including ensemble, kernel-based, and generalized linear approaches, were trained and evaluated. The Poisson Regressor model yielded the best performance, achieving a Mean Absolute Error (MAE) of 1.92 barges using 12 of the 30 features. The feature importance analysis revealed that metrics capturing vessel maneuverability such as course entropy, speed variability and trip length were most predictive of barge count. The proposed approach provides a scalable, readily implementable method for enhancing Maritime Domain Awareness (MDA), with strong potential applications in lock scheduling, port management, and freight planning. Future work will expand the proof of concept presented here to explore model transferability to other inland rivers with differing operational and environmental conditions.
Problem
Research questions and friction points this paper is trying to address.
Predicting barge tow size using vessel trajectory features
Developing machine learning models for real-time barge quantity estimation
Enhancing maritime awareness through AIS data and feature analysis
Innovation
Methods, ideas, or system contributions that make the work stand out.
Uses AIS vessel tracking data for barge prediction
Applies machine learning with 30 AIS-derived features
Identifies vessel maneuverability metrics as key predictors
🔎 Similar Papers
No similar papers found.
