Technology Category
Intelligent Robots: State EstimationMachine Learning: Ensemble MethodsPlanning, Routing, and Scheduling: Activity and Plan Recognition
Predicting Barge Presence and Quantity on Inland Waterways using Vessel Tracking Data: A Machine Learning Approach
🤖 AI Summary
Fine-grained monitoring of inland waterway freight volume remains challenging due to the lack of reliable methods for detecting and quantifying barges towed by tugboats.
Method: This paper proposes a two-stage machine learning framework that jointly predicts barge presence and count. The first stage employs a binary classifier to detect barge presence; the second stage performs regression to estimate barge count. The framework innovatively integrates kinematic features (e.g., speed, heading change) from AIS trajectories, vessel intrinsic features (e.g., type, dimensions), and tug–barge interaction features. Bayesian optimization is applied to enhance generalization, and a high-quality training dataset is constructed using annotations from traffic surveillance cameras.
Contribution/Results: Experimental results show F1-scores of 0.932 for barge presence detection and 0.886 for barge count estimation—significantly outperforming baseline methods. To our knowledge, this is the first end-to-end joint modeling framework for barge presence and count, enabling practical applications in dredging scheduling, dynamic resource allocation, and multimodal freight volume assessment.
Technology Category
Application Category
📝 Abstract
This study presents a machine learning approach to predict the number of barges transported by vessels on inland waterways using tracking data from the Automatic Identification System (AIS). While AIS tracks the location of tug and tow vessels, it does not monitor the presence or number of barges transported by those vessels. Understanding the number and types of barges conveyed along river segments, between ports, and at ports is crucial for estimating the quantities of freight transported on the nation's waterways. This insight is also valuable for waterway management and infrastructure operations impacting areas such as targeted dredging operations, and data-driven resource allocation. Labeled sample data was generated using observations from traffic cameras located along key river segments and matched to AIS data records. A sample of 164 vessels representing up to 42 barge convoys per vessel was used for model development. The methodology involved first predicting barge presence and then predicting barge quantity. Features derived from the AIS data included speed measures, vessel characteristics, turning measures, and interaction terms. For predicting barge presence, the AdaBoost model achieved an F1 score of 0.932. For predicting barge quantity, the Random Forest combined with an AdaBoost ensemble model achieved an F1 score of 0.886. Bayesian optimization was used for hyperparameter tuning. By advancing predictive modeling for inland waterways, this study offers valuable insights for transportation planners and organizations, which require detailed knowledge of traffic volumes, including the flow of commodities, their destinations, and the tonnage moving in and out of ports.
Problem
Research questions and friction points this paper is trying to address.
Barge Quantity and Type Prediction
Inland Waterway Freight Assessment
Resource Allocation Optimization
Innovation
Methods, ideas, or system contributions that make the work stand out.
Machine Learning
Bayesian Optimization
AIS Data Analysis
🔎 Similar Papers
