Estimating the Speed of Ice-Going Ships by Integrating SAR Imagery and Ship Data from an Automatic Identification System

Abstract

The automatic identification system (AIS) was developed to support the safety of marine traffic. In ice-covered seas, the ship speeds extracted from AIS data vary with ice conditions that are simultaneously reflected by features in synthetic aperture radar (SAR) images. In this study, the speed variation was related to the SAR features and the results were applied to generate a chart of expected speeds from the SAR image. The study was done in the Gulf of Bothnia in March 2013 for ships with ice class IA Super that are able to navigate without icebreaker assistance. The speeds were normalized to dimensionless units ranging from 0 to 10 for each ship. As the matching between AIS and SAR was complicated by ice drift during the time gap (from hours to two days), we calculated a set of local statistical SAR features over several scales. Random forest tree regression was used to estimate the speed. The accuracy was quantified by mean squared error and by the fraction of estimates close to the actual speeds. These depended strongly on the route and the day. The error varied from 0.4 to 2.7 units 2 for daily routes. Sixty-five percent of the estimates deviated by less than one speed unit and 82% by less than 1.5 speed units from the AIS speeds. The estimated daily mean speeds were close to the observations. The largest speed decreases were provided by the estimator in a dampened form or not at all. This improved when the ice chart thickness was included as a predictor.

Satellite SAR Data-based Sea Ice Classification: An Overview

“…This technology has been developed for the Baltic Sea and is currently being developed for the Kara and Barents Seas. In addition, it will be extended to the other arctic seas [13].…”

A Data-Driven Approach to Trip Generation Modeling for Urban Residents and Non-local Travelers

“…In order to identify the ordinary least squares (OLS) models that best explain the relationship between the trips and the features of the 10 different POI categories, all possible combinations of the 10 candidate explanatory variables were compared in an exploratory approach, the form of the OLS model is [28]:…”

“…(c) Model Bias VIF: The variance inflation factor (VIF) measures multicollinearity among explanatory variables in an ordinary least squares regression model [28]. It provides an index that measures how much the variance (the square of the estimate's standard deviation) of a regression coefficient is inflated due to collinearity.…”

A machine learning-based method for simulation of ship speed profile in a complex ice field

“…Li et al (2017) used Bayesian networks on full-scale data to develop a model which yields the probability of certain ship speed under given ice conditions. Similä and Lensu (2018) used regression to estimate ship speed from SAR imagery and ship data. Finally, Montewka et al (2019) developed a hybrid model for estimating ship performance in ice combining traditional engineering and data-driven approaches.…”