9 January 2019 in The Cryosphere
ASAtle Macdonald Sørensen
+11
We introduce the OSI-450, the SICCI-25km and the SICCI-50km climate data records of gridded global sea-ice concentration. These three records are derived from passive microwave satellite data and offer three distinct advantages compared to existing records: first, all three records provide quantitative information on uncertainty and possibly applied filtering at every grid point and every time step. Second, they are based on dynamic tie points, which capture the time evolution of surface characteristics of the ice cover and accommodate potential calibration differences between satellite missions. Third, they are produced in the context of sustained services offering committed extension, documentation, traceability, and user support. The three records differ in the underlying satellite data (SMMR & SSM/I & SSMIS or AMSR-E & AMSR2), in the imaging frequency channels (37 GHz and either 6 or 19 GHz), in their horizontal resolution (25 or 50 km), and in the time period they cover. We introduce the underlying algorithms and provide an evaluation. We find that all three records compare well with independent estimates of sea-ice concentration both in regions with very high sea-ice concentration and in regions with very low sea-ice concentration. We hence trust that these records will prove helpful for a better understanding of the evolution of the Earth's sea-ice cover.
19 November 2024 in The Cryosphere
Arctic sea ice monitoring is a fundamental prerequisite for anticipating and mitigating the impacts of climate change. Satellite-based sea ice observations have been subject to intense attention over the last few decades, with passive microwave (PMW) radiometers being the primary sensors for retrieving pan-Arctic sea ice concentration, albeit with coarse spatial resolutions of a few or even tens of kilometers. Spaceborne synthetic aperture radar (SAR) missions, such as Sentinel-1, provide dual-polarized C-band images with < 100 m spatial resolution, which are particularly well-suited for retrieving high-resolution sea ice information. In recent years, deep-learning-based vision methodologies have emerged with promising results for SAR-based sea ice concentration retrievals. Despite recent advancements, most contributions focus on regional or local applications without empirical studies on the generalization of the algorithms to the pan-Arctic region. Furthermore, many contributions omit uncertainty quantification from the retrieval methodologies, which is a prerequisite for the integration of automated SAR-based sea ice products into the workflows of the national ice services or for assimilation into numerical ocean–sea ice coupled forecast models. Here, we present ASIP (Automated Sea Ice Products): a new and comprehensive deep-learning-based methodology to retrieve high-resolution sea ice concentration with accompanying well-calibrated uncertainties from Sentinel-1 SAR and Advanced Microwave Scanning Radiometer 2 (AMSR2) passive microwave observations at a pan-Arctic scale for all seasons. We compiled a vast matched dataset of Sentinel-1 HH/HV (horizontal transmit, horizontal/vertical receive polarizations) imagery and AMSR2 brightness temperatures to train ASIP with regional ice charts as labels. ASIP achieves an R2 score of 95 % against a held-out test dataset of regional ice charts. In a comparative study against pan-Arctic ice charts and a PMW-based sea ice product, we show that ASIP generalizes well to the pan-Arctic region. Additionally, the comparison reveals that ASIP consistently produces relatively higher sea ice concentration than the PMW-based sea ice product, with mean biases ranging from 1.45 % to 8.55 %, and that the discrepancies are primarily attributed to disparities in the marginal ice zone.
7 August 2024 in The Cryosphere
Mapping sea ice in the Arctic is essential for maritime navigation, and growing vessel traffic highlights the necessity of the timeliness and accuracy of sea ice charts. In addition, with the increased availability of satellite imagery, automation is becoming more important. The AutoICE Challenge investigates the possibility of creating deep learning models capable of mapping multiple sea ice parameters automatically from spaceborne synthetic aperture radar (SAR) imagery and assesses the current state of the automatic-sea-ice-mapping scientific field. This was achieved by providing the tools and encouraging participants to adopt the paradigm of retrieving multiple sea ice parameters rather than the current focus on single sea ice parameters, such as concentration. The paper documents the efforts and analyses, compares, and discusses the performance of the top-five participants’ submissions. Participants were tasked with the development of machine learning algorithms mapping the total sea ice concentration, stage of development, and floe size using a state-of-the-art sea ice dataset with dual-polarised Sentinel-1 SAR images and 22 other relevant variables while using professionally labelled sea ice charts from multiple national ice services as reference data. The challenge had 129 teams representing a total of 179 participants, with 34 teams delivering 494 submissions, resulting in a participation rate of 26.4 %, and it was won by a team from the University of Waterloo. Participants were successful in training models capable of retrieving multiple sea ice parameters with convolutional neural networks and vision transformer models. The top participants scored best on the total sea ice concentration and stage of development, while the floe size was more difficult. Furthermore, participants offered intriguing approaches and ideas that could help propel future research within automatic sea ice mapping, such as applying high downsampling of SAR data to improve model efficiency and produce better results.
24 February 2026 in Remote Sensing of Environment
AAAthanasios Athanasiadis
16 July 2018 in EGUsphere
ASAtle Macdonald Sørensen
+11
We introduce the OSI-450, the SICCI-25km and the SICCI-50km climate data records of gridded global sea-ice concentration. These three records are derived from passive microwave satellite data and offer three distinct advantages compared to existing records: First, all three records provide quantitative information on uncertainty and possibly applied filtering at every grid point and every time step. Second, they are based on dynamic tie points, which capture the time evolution of surface characteristics of the ice cover and accommodate potential calibration differences between satellite missions. Third, they are produced in the context of sustained services offering committed extension, documentation, traceability, and user support. The three records differ in the underlying satellite data (SMMR & SSM/I & SSMIS or AMSR-E & AMSR2), in the imaging frequency channels (37 GHz and either 6 GHz or 19 GHz), in their horizontal resolution (25 km or 50 km) and in the time period they cover. We introduce the underlying algorithms and provide an initial evaluation. We find that all three records compare well with independent estimates of sea-ice concentration both in regions with very high sea-ice concentration and in regions with very low sea-ice concentration. We hence trust that these records will prove helpful for a better understanding of the evolution of the Earth's sea-ice cover.
7 February 2024 in EGUsphere
Arctic sea ice monitoring is a fundamental prerequisite for anticipating and mitigating the impacts of climate change. Satellite-based sea ice observations have been subject to intense attention over the last few decades, with passive microwave (PMW) radiometers being the primary sensors for retrieving pan-Arctic sea ice concentration, albeit with coarse spatial resolutions of a few or even tens of kilometers. Space-borne Synthetic Aperture Radar (SAR) missions, such as Sentinel-1, provide dual-polarized C-band images with <100 meter spatial resolution, which are particularly well-suited for retrieving high-resolution sea ice information. In recent years, deep learning-based vision methodologies have emerged with promising results for SAR-based sea ice concentration retrievals. Despite recent advancements, most contributions focus on regional or local applications without empirical studies on the generalization of the algorithms to the pan-Arctic region. Furthermore, many contributions omit uncertainty quantification from the retrieval methodologies, which is a prerequisite for the integration of automated SAR-based sea ice products into the workflows of the national ice services, or for the assimilation into numerical ocean-sea-ice coupled forecast models. Here, we present ASIP (Automated Sea Ice Products): a new and comprehensive deep learning-based methodology to retrieve high-resolution sea ice concentration with accompanying well-calibrated uncertainties from Sentinel-1 SAR and Advanced Microwave Scanning Radiometer 2 (AMSR2) passive microwave observations at a pan-Arctic scale for all seasons. We compiled a vast matched dataset of Sentinel-1 HH/HV imagery and AMSR2 brightness temperatures to train ASIP with regional ice charts as labels. ASIP achieves an R2-score of 95 % against a held-out test dataset of regional ice charts. In a comparative study against pan-Arctic ice charts and PMW-based sea ice products, we show that ASIP generalizes well to the pan-Arctic region. Additionally, the comparison reveals that ASIP consistently produces relatively higher sea ice concentration than the PMW-based sea ice product, with mean biases ranging from 1.45 % to 8.55 %, and that the discrepancies are primarily attributed to disparities in the marginal ice zone.