Some methods for addressing errors in static AIS data records

The Automatic Identification System (AIS) provides essential services in support of maritime domain awareness. Accurate AIS values for hull dimension and type are often critical safe efficient management ship traffic, development new artificial intelligence algorithms. variables subject to faults from multiple sources, ranging bad weather human error. New heuristic methods correcting draft, beam, class were developed evaluated, using data the vicinity large Florida ports as a test bed. Novel low order polynomials 8 broad functional vessel classes yielded predicted draft beam functions length. majority relative differences between reported <0.1. A logistic regression (LR) multiclass classification scheme residuals these polynomial predictions generally showed good agreement estimated class. LR demonstrated skill verifying AIS-transmitted classification, detecting incorrectly classified vessels, flagging those with incorrect or operating near an extreme draft. diagnostic reports whose had very high confidence suggested directions further improvement algorithm. hierarchy processed is proposed.