Improved Retrieval of Ice and Open Water From Sequential RADARSAT-2 Images

Komarov, Alexander S.; Buehner, Mark

doi:10.1109/tgrs.2018.2886685

Cited by 3 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In several recent studies automated algorithms have been developed for dual-polarization C-band SAR image segmentation and ice/water classification [4][5][6][7][8][9][10]; for retrieval of ice concentration [11,12]; for classification of several ice types [13][14][15]. It is emphasized in these studies that a threshold based classification of ice types on single frequency dual-polarization SAR data is not possible and more advanced methods employing either full polarization, or multi-frequency, or texture analysis are required.…”

Section: Introductionmentioning

confidence: 99%

Classification of Sea Ice Types in Sentinel-1 SAR Data Using Convolutional Neural Networks

Boulze¹,

Korosov²,

Brajard³

2020

Remote Sensing

View full text Add to dashboard Cite

A new algorithm for classification of sea ice types on Sentinel-1 Synthetic Aperture Radar (SAR) data using a convolutional neural network (CNN) is presented. The CNN is trained on reference ice charts produced by human experts and compared with an existing machine learning algorithm based on texture features and random forest classifier. The CNN is trained on two datasets in 2018 and 2020 for retrieval of four classes: ice free, young ice, first-year ice and old ice. The accuracy of our classification is 90.5% for the 2018-dataset and 91.6% for the 2020-dataset. The uncertainty is a bit higher for young ice (85%/76% accuracy in 2018/2020) and first-year ice (86%/84% accuracy in 2018/2020). Our algorithm outperforms the existing random forest product for each ice type. It has also proved to be more efficient in computing time and less sensitive to the noise in SAR data. The code is publicly available.

show abstract

Section: Introductionmentioning

confidence: 99%

Classification of Sea Ice Types in Sentinel-1 SAR Data Using Convolutional Neural Networks

Boulze¹,

Korosov²,

Brajard³

2020

Remote Sensing

View full text Add to dashboard Cite

show abstract

Generating large-scale sea ice motion from Sentinel-1 and the RADARSAT Constellation Mission using the Environment and Climate Change Canada automated sea ice tracking system

2022

Self Cite

View full text Add to dashboard Cite

Abstract. As Arctic sea ice extent continues to decline, remote sensing observations are becoming even more vital for the monitoring and understanding of sea ice. Recently, the sea ice community has entered a new era of synthetic aperture radar (SAR) satellites operating at C-band with the launch of Sentinel-1A in 2014 and Sentinel-1B (S1) in 2016 and the RADARSAT Constellation Mission (RCM) in 2019. These missions represent five spaceborne SAR sensors that together routinely cover the pan-Arctic sea ice domain. Here, we describe, apply, and validate the Environment and Climate Change Canada automated sea ice tracking system (ECCC-ASITS) that routinely generates large-scale sea ice motion (SIM) over the pan-Arctic domain using SAR images from S1 and RCM. We applied the ECCC-ASITS to the incoming image streams of S1 and RCM from March 2020 to October 2021 using a total of 135 471 SAR images and generated new SIM datasets (7 d 25 km and 3 d 6.25 km) by combining the image stream outputs of S1 and RCM (S1 + RCM). Results indicate that S1 + RCM SIM provides more coverage in the Hudson Bay, Davis Strait, Beaufort Sea, Bering Sea, and directly over the North Pole compared to SIM from S1 alone. Based on the resolvable S1 + RCM SIM grid cells, the 7 d 25 km spatiotemporal scale is able to provide the most complete picture of SIM across the pan-Arctic from SAR imagery alone, but considerable spatiotemporal coverage is also available from 3 d 6.25 SIM products. S1 + RCM SIM is resolved within the narrow channels and inlets of the Canadian Arctic Archipelago, filling a major gap from coarser-resolution sensors. Validating the ECCC-ASITS using S1 and RCM imagery against buoys indicates a root-mean-square error (RMSE) of 2.78 km for dry ice conditions and 3.43 km for melt season conditions. Higher speeds are more apparent with S1 + RCM SIM as comparison with the National Snow and Ice Data Center (NSIDC) SIM product and the Ocean and Sea Ice Satellite Application Facility (OSI SAF) SIM product indicated an RMSE of u=4.6 km d−1 and v=4.7 km d−1 for the NSIDC and u=3.9 km d−1 and v=3.9 km d−1 for OSI SAF. Overall, our results demonstrate the robustness of the ECCC-ASITS for routinely generating large-scale SIM entirely from SAR imagery across the pan-Arctic domain.

show abstract

Satellite passive microwave sea-ice concentration data set intercomparison using Landsat data

et al. 2022

View full text Add to dashboard Cite

Abstract. We report on results of an intercomparison of 10 global sea-ice concentration (SIC) data products at 12.5 to 50.0 km grid resolution from satellite passive microwave (PMW) observations. For this we use SIC estimated from >350 images acquired in the visible–near-infrared frequency range by the joint National Aeronautics and Space Administration (NASA) and United States Geological Survey (USGS) Landsat sensor during the years 2003–2011 and 2013–2015. Conditions covered are late winter/early spring in the Northern Hemisphere and from late winter through fall freeze-up in the Southern Hemisphere. Among the products investigated are the four products of the European Organisation for the Exploitation of Meteorological Satellites (EUMETSAT) Ocean and Sea Ice Satellite Application Facility (OSI SAF) and European Space Agency (ESA) Climate Change Initiative (CCI) algorithms SICCI-2 and OSI-450. We stress the importance to consider intercomparison results across the entire SIC range instead of focusing on overall mean differences and to take into account known biases in PMW SIC products, e.g., for thin ice. We find superior linear agreement between PMW SIC and Landsat SIC for the 25 and the 50 km SICCI-2 products in both hemispheres. We discuss quantitatively various uncertainty sources of the evaluation carried out. First, depending on the number of mixed ocean–ice Landsat pixels classified erroneously as ice only, our Landsat SIC is found to be biased high. This applies to some of our Southern Hemisphere data, promotes an overly large fraction of Landsat SIC underestimation by PMW SIC products, and renders PMW SIC products overestimating Landsat SIC particularly problematic. Secondly, our main results are based on SIC data truncated to the range 0 % to 100 %. We demonstrate using non-truncated SIC values, where possible, can considerably improve linear agreement between PMW and Landsat SIC. Thirdly, we investigate the impact of filters often used to clean up the final products from spurious SIC over open water due to weather effects and along coastlines due to land spillover. Benefiting from the possibility to switch on or off certain filters in the SICCI-2 and OSI-450 products, we quantify the impact land spillover filtering can have on evaluation results as shown in this paper.

show abstract

Improved Retrieval of Ice and Open Water From Sequential RADARSAT-2 Images

Cited by 3 publications

References 19 publications

Classification of Sea Ice Types in Sentinel-1 SAR Data Using Convolutional Neural Networks

Classification of Sea Ice Types in Sentinel-1 SAR Data Using Convolutional Neural Networks

Generating large-scale sea ice motion from Sentinel-1 and the RADARSAT Constellation Mission using the Environment and Climate Change Canada automated sea ice tracking system

Satellite passive microwave sea-ice concentration data set intercomparison using Landsat data

Contact Info

Product

Resources

About