Accuracy of Sea Ice Data from Remote Sensing Methods, its Impact on Safe Speed Determination and Planning of Voyage in Ice-Covered Areas

Pastusiak, Tadeusz

doi:10.12716/1001.10.02.06

Cited by 6 publications

(5 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering the practical requirements of fast processing for near-real-time ice charting services, the RF can be a reasonable solution. We use the RF with the Python Scikit-Learn implementation (Pedregosa et al, 2011). We split the RF classifier into several binary classifiers using a one-vs.-all scheme (Anand et al, 1995).…”

Section: Machine Learning Classifiermentioning

confidence: 99%

“…Wide swath SAR observation from several spaceborne SAR missions (RADARSAT-1, 1995(RADARSAT-1, -2013Envisat ASAR, 2002-2012ALOS-1 PALSAR, 2006-2011RADARSAT-2, 2007present;Sentinel-1, 2014-present) played an important role in studying global ocean and ice-covered polar regions. The Sentinel-1 constellation (1A and 1B) is producing dualpolarization observation data with the largest Arctic coverage and the highest temporal resolution ever.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Classification of sea ice types in Sentinel-1 synthetic aperture radar images

Park

Korosov²,

Babiker³

et al. 2020

The Cryosphere

View full text Add to dashboard Cite

Abstract. A new Sentinel-1 image-based sea ice classification algorithm using a machine-learning-based model trained in a semi-automated manner is proposed to support daily ice charting. Previous studies mostly rely on manual work in selecting training and validation data. We show that the readily available ice charts from the operational ice services can reduce the amount of manual work in preparation of large amounts of training/testing data. Furthermore, they can feed highly reliable data to the trainer by indirectly exploiting the best ability of the sea ice experts working at the operational ice services. The proposed scheme has two phases: training and operational. Both phases start from the removal of thermal, scalloping, and textural noise from Sentinel-1 data and calculation of grey level co-occurrence matrix and Haralick texture features in a sliding window. In the training phase, the weekly ice charts are reprojected into the SAR image geometry. A random forest classifier is trained with the texture features on input and labels from the rasterized ice charts on output. Then, the trained classifier is directly applied to the texture features from Sentinel-1 images operationally. Test results from the two datasets spanning winter (January–March) and summer (June–August) seasons acquired over the Fram Strait and the Barents Sea showed that the classifier is capable of retrieving three generalized cover types (open water, mixed first-year ice, old ice) with overall accuracies of 87 % and 67 % in winter and summer seasons, respectively. For the summer season, the classifier failed in distinguishing mixed first-year ice from old ice with accuracy of only 12 %; however, it performed rather like an ice–water discriminator with high accuracy of 98 % as the misclassification between the mixed first-year ice and old ice was between them. The accuracy for five cover types (open water, new ice, young ice, first-year ice, old ice) in the winter season was 60 %. The errors are attributed both to incorrect manual classification on the ice charts and to the semi-automated algorithm. Finally, we demonstrate the potential for near-real-time service of the ice map using daily mosaicked Sentinel-1 images.

show abstract

Section: Machine Learning Classifiermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Classification of sea ice types in Sentinel-1 synthetic aperture radar images

Park

Korosov²,

Babiker³

et al. 2020

The Cryosphere

View full text Add to dashboard Cite

show abstract

“…There are two ice services that publish weekly ice charts with Pan-Arctic coverage: National Ice Center (NIC) of the United States of America, and Arctic and Antarctic Research Institute (AARI) of Russia. Although the accuracies are known to be comparable (Pastusiak, 2016) to each other, there is no partial ice concentration information in the AARI ice chart. In this study, we use the ice charts downloaded from the NIC website (https://www.natice.noaa.gov/Main_Products.htm).…”

Section: Study Area and Used Datamentioning

confidence: 99%

Classification of Sea Ice Types in Sentinel-1 SAR images

Park¹,

Korosov²,

Babiker³

et al. 2019

Preprint

View full text Add to dashboard Cite

Abstract. A new Sentinel-1 image-based sea ice classification algorithm is proposed to support automated ice charting. Previous studies mostly rely on manual work in selecting training and validation data. We show that the use of readily available ice charts from an operational ice services allow to automate selection of large amount of training/testing data void of biased, subjective decisions. The proposed scheme has two phases: training and operational. Both phases start from removal of thermal, scalloping and textural noise from Sentinel-1 data and calculation of gray level co-occurrence matrix and Haralick texture features in a sliding window. In the training phase, the weekly ice charts are reprojected into the SAR image geometry. A random forest classifier is trained with the texture features on input and labels from the rasterized ice charts on output. Then the trained classifier is directly applied to the texture features from Sentinel-1 images in operational manner. Test results from two winter season dataset acquired over the Fram Strait and Barents Sea area showed that the classifier is capable of retrieving 3 generalized cover types (ice free, integrated first-year ice, old ice) with overall accuracies of 85 % and 5 cover types (ice free, new ice, young ice, first-year ice, old ice) with accuracy of 58 %. The errors are attributed both to incorrect manual classification on the ice charts and to the automated algorithm. We demonstrate the potential for near-real time service of ice type classification through an example of ice maps made from daily mosaiced images.

show abstract

“…Graphs of ice concentration in Figure 2 were read directly from maps of three different producers obtained by satellite remote sensing methods. Impact of possible terrestrial observations, applied data processing algorithms and in particular added value due to work of experienced researchers on final form of maps was different [20,21,23]. Therefore, it is difficult to make such comparisons between analyzed maps.…”

Section: Fig 4 Median Ice Concentration In the Studied Region For Amentioning

confidence: 99%

“…Nevertheless, it meets the needs of vessels that do not have ice strengthening of hull (concentration from 0% to 17%), medium and high ice class vessels without distinction (concentration from 18% to 80%), icebreakers and vessels with the highest ice classes with the support of icebreakers (concentration from 81% to 100%). An important factor indicating timeliness of information content is period of time between consecutive editions of maps [20,22,23]. The MIZ type maps are issued by the NIC in the shortest time intervals every 24 hours.…”

mentioning

confidence: 99%

Scheduling Transit Voyages of Vessels of Various Ice Classes Across the Northern Sea Route

Pastusiak¹

2019

Annual of Navigation

Self Cite

View full text Add to dashboard Cite

Main problem for scheduling vessel transit voyages through the Northern Sea Route is the difficulty in predicting distribution of ice boundaries in regions that cannot be overcome by individual ice classes of vessels. Scheduling of voyage is related to speed that vessels can develop and moment of time when vessels will be able to commence and complete passage safely through areas that are main obstacle and are blocking longest transit passage through the Northern Sea Route. This applies to voyages carried out by vessels navigating on their own and with support of icebreakers. Additional problem is lack of consistency of content of maps of ice cover, which can be used for vessels voyage planning through areas where ice cover occurs. Results of this research on influence of uncertain information related with time window of conditions favorable for navigation of vessels of different ice classes on schedule of theirs voyage on example of summer navigation season 2017 are presented in this work.

show abstract

Accuracy of Sea Ice Data from Remote Sensing Methods, its Impact on Safe Speed Determination and Planning of Voyage in Ice-Covered Areas

Cited by 6 publications

References 3 publications

Classification of sea ice types in Sentinel-1 synthetic aperture radar images

Classification of sea ice types in Sentinel-1 synthetic aperture radar images

Classification of Sea Ice Types in Sentinel-1 SAR images

Scheduling Transit Voyages of Vessels of Various Ice Classes Across the Northern Sea Route

Contact Info

Product

Resources

About