scholarly journals Machine Learning-Aided Sea Ice Monitoring Using Feature Sequences Extracted from Spaceborne GNSS-Reflectometry Data

2020 ◽  
Vol 12 (22) ◽  
pp. 3751
Author(s):  
Yongchao Zhu ◽  
Tingye Tao ◽  
Kegen Yu ◽  
Xiaochuan Qu ◽  
Shuiping Li ◽  
...  
Keyword(s):  
Machine Learning ◽  
Sea Ice ◽  
Arctic Region ◽  
Satellite System ◽  
The Arctic ◽  
Monitoring Methods ◽  
Sea Ice Concentration ◽  
Monitoring Model ◽  
Input Variables ◽  
Global Navigation Satellite

Two effective machine learning-aided sea ice monitoring methods are investigated using 42 months of spaceborne Global Navigation Satellite System-Reflectometry (GNSS-R) data collected by the TechDemoSat-1 (TDS-1). The two-dimensional delay waveforms with different Doppler spread characteristics are applied to extract six features, which are combined to monitor sea ice using the decision tree (DT) and random forest (RF) algorithms. Firstly, the feature sequences are used as input variables and sea ice concentration (SIC) data from the Advanced Microwave Space Radiometer-2 (AMSR-2) are applied as targeted output to train the sea ice monitoring model. Hereafter, the performance of the proposed method is evaluated through comparing with the sea ice edge (SIE) data from the Special Sensor Microwave Imager Sounder (SSMIS) data. The DT- and RF-based methods achieve an overall accuracy of 97.51% and 98.03%, respectively, in the Arctic region and 95.46% and 95.96%, respectively, in the Antarctic region. The DT- and RF-based methods achieve similar accuracies, while the Kappa coefficient of RF-based approach is slightly larger than that of the DT-based approach, which indicates that the RF-based method outperforms the DT-based method. The results show the potential of monitoring sea ice using machine learning-aided GNSS-R approaches.

Comparison of sea ice concentrations from ASI, BT and NT2 algorithms with ERA-Interim dataset in the Arctic and Antarctic regions

2020 ◽  
Author(s):  
Shuang Liang ◽  
Jiangyuan Zeng ◽  
Zhen Li
Keyword(s):  
Sea Ice ◽  
Temporal Distribution ◽  
Arctic Region ◽  
The Arctic ◽  
Polar Regions ◽  
Significant Discrepancy ◽  
Sea Ice Concentration ◽  
Sea Ice Extent ◽  
Long Time ◽  
Mean Square Difference

<p>Evaluating the performance and consistency of passive microwave (PM) sea ice concentration (SIC) products derived from different algorithms is critical since a good knowledge of the quality of the satellite SIC products is essential for their application and improvement. To comprehensively evaluate the performance of satellite SIC in long time series and the whole polar regions (both Arctic and Antarctic), in the study we examined the spatial and temporal distribution of the discrepancy between four PM satellite SIC products with the ERA-Interim sea ice fraction dataset (ERA SIC) during the period of 2015-2018. The four PM SIC products include the DMSP SSMIS with Arctic Radiation and Turbulence Interaction Study Sea Ice (ASI) algorithm (SSMIS/ASI), the GCOM-W AMSR2 with NASA Bootstrap (BT) algorithm (AMSR2/BT), the Chinese Feng Yun-3B with enhanced NASA Team (NT2) sea ice algorithm (FY3B/NT2), and the Chinese Feng Yun-3C with NT2 (FY3C/NT2) at a spatial resolution of 12.5 km.</p><p>The results show the spatial patterns of PM SIC products are generally in good agreement with ERA SIC. The comparison of monthly and annual SIC shows that the largest bias and root mean square difference (RMSD) for the PM SIC products mainly occur in summer and the marginal ice zone, indicating that there are still many uncertainties in PM SIC products in such period and region. Meanwhile, the daily sea ice extent (SIE) and sea ice area (SIA) derived from the four PM SIC products can generally well reflect the variation trend of SIE and SIA in Arctic and Antarctic. The largest bias of SIE and SIA are above 4×10<sup>6</sup> km<sup>2</sup> when the sea ice reaches the maximum and minimum value, and the daily bias of SIE and SIA vary seasonally and regionally, which is mainly concentrated from June to October in Arctic. In general, among the four PM SIC products, the SSMIS/ASI product performs the best compared with ERA SIC though it usually underestimates SIC with a negative bias. The FY3B/NT2 and FY3C/NT2 products show more significant discrepancy with higher RMSD and bias in Arctic and Antarctic compared with the SSMIS/ASI and AMSR2/BT. The AMSR2/BT product performs much better in Antarctic than in Arctic and it always overestimates ERA SIC with a positive bias. The consistency of the four PM products concerning ERA SIC in the Antarctic region is generally superior to that in Arctic region.</p>

scholarly journals Four Paradoxes of the User–Provider Interface: A Responsible Innovation Framework for Sea Ice Services

2020 ◽  
Vol 12 (2) ◽  
pp. 448
Author(s):  
Berill Blair ◽  
Olivia A. Lee ◽  
Machiel Lamers
Keyword(s):  
Sea Ice ◽  
Service Providers ◽  
Information Service ◽  
Arctic Region ◽  
Responsible Innovation ◽  
The Arctic ◽  
Sea Ice Concentration ◽  
Spatial And Temporal Scales ◽  
Decadal Scale ◽  
Challenging Environment

In the Arctic region, sea ice retreat as a decadal-scale crisis is creating a challenging environment for navigating long-term sustainability. Innovations in sea ice services can help marine users to anticipate sea ice concentration, thickness and motion, plan ahead, as well as increase the safety and sustainability of marine operations. Increasingly however, policy makers and information service providers confront paradoxical decision-making contexts in which contradictory solutions are needed to manage uncertainties across different spatial and temporal scales. This article proposes a forward-looking sea ice services framework that acknowledges four paradoxes pressuring sea ice service provision: the paradoxes of performing, contradictory functions embedded in sea ice services, contradicting desired futures and the paradox of responsible innovation. We draw on the results from a multi-year co-production process of (sub)seasonal sea ice services structured around scoping interviews, workshops and a participatory scenario process with representatives of marine sectors, fishers, hunters, metservice providers, and policy experts. Our proposed framework identifies institutionalized coproduction processes, enhanced decision support, paradoxical thinking and dimensions of responsible innovation as tactics necessary to address existing tensions in sea ice services. We highlight the role of socio-economic scenarios in implementing these tactics in support of responsible innovation in sea ice social–ecological systems. The article concludes with a discussion of questions around equity and responsibility raised by the ultimate confirmation that enhanced information, data infrastructures, and service provisions will not benefit all actors equally.

Impact of the regional runoff Nitrogen Flux using the GFDL-TOPAZ simulation on the Arctic Ocean phytoplankton.

2020 ◽  
Author(s):  
Jung hyun Park ◽  
Baek-min Kim
Keyword(s):  
Sea Ice ◽  
Chlorophyll A ◽  
Barents Sea ◽  
Arctic Region ◽  
Arctic Sea Ice ◽  
Limiting Factors ◽  
The Arctic ◽  
Nitrogen Flux ◽  
Sea Ice Concentration ◽  
Chlorophyll A Concentration

<p>Phytoplankton is closely related to the Arctic Amplification in a future caused by the biogeophysical feedback. In particular, the increase in nutrients, which is one of the limiting factors of phytoplankton, affected by the increased inflow of rivers due to the Arctic warming in the Arctic region. Since Arctic region is sensitive to the feedback, the biological feedback is still difficult to expect an accurate simulate in the modeling simulation. This study used the GFDL-TOPAZ model by prescribing a runoff nitrogen flux in the contemporary level to simulate the phytoplankton, then prescribing the nitrogen flux over the East Siberian-Chukchi Sea. The model results underestimate chlorophyll A concentration and nutrient compared to the ARAON ship observation. But, We showed that the experiment of prescribing a regional runoff nitrogen flux by the river is well simulatinges the chlorophyll A concentration and nutrients than the CTRL experiment. Also, a  model result showed that the sea ice concentration in the Chukchi-East Siberian Sea and Kara-Barents Sea decreased, and it suggests that the regional change of the nutrient could, directly and indirectly, affect that Arctic sea ice concentrations</p>

scholarly journals Sea Ice Remote Sensing Using GNSS-R: A Review

2019 ◽  
Vol 11 (21) ◽  
pp. 2565 ◽  
Author(s):  
Qingyun Yan ◽  
Weimin Huang
Keyword(s):  
Remote Sensing ◽  
Sea Ice ◽  
Oil And Gas ◽  
Satellite System ◽  
Sea Ice Concentration ◽  
Sea Ice Thickness ◽  
Oil And Gas Exploration ◽  
Offshore Oil And Gas ◽  
Ice Detection ◽  
Global Navigation Satellite

Knowledge of sea ice is critical for offshore oil and gas exploration, global shipping industries, and climate change studies. During recent decades, Global Navigation Satellite System-Reflectometry (GNSS-R) has evolved as an efficient tool for sea ice remote sensing. In particular, thanks to the availability of the TechDemoSat-1 (TDS-1) data over high-latitude regions, remote sensing of sea ice based on spaceborne GNSS-R has been rapidly growing. The goal of this paper is to provide a review of the state-of-the-art methods for sea ice remote sensing offered by the GNSS-R technique. In this review, the fundamentals of these applications are described, and their performances are evaluated. Specifically, recent progress in sea ice sensing using TDS-1 data is highlighted including sea ice detection, sea ice concentration estimation, sea ice type classification, sea ice thickness retrieval, and sea ice altimetry. In addition, studies of sea ice sensing using airborne and ground-based data are also noted. Lastly, applications based on various platforms along with remaining challenges are summarized and possible future trends are explored. In this review, concepts, research methods, and experimental techniques of GNSS-R-based sea ice sensing are delivered, and this can benefit the scientific community by providing insights into this topic to further advance this field or transfer the relevant knowledge and practice to other studies.

scholarly journals Uncertainties in Arctic Sea Ice Thickness Associated with Different Atmospheric Reanalysis Datasets Using the CICE5 Model

Atmosphere ◽  
2019 ◽  
Vol 10 (7) ◽  
pp. 361
Author(s):  
Su-Bong Lee ◽  
Baek-Min Kim ◽  
Jinro Ukita ◽  
Joong-Bae Ahn
Keyword(s):  
Sea Ice ◽  
Arctic Region ◽  
Reanalysis Data ◽  
Arctic Sea Ice ◽  
Heat Fluxes ◽  
The Arctic ◽  
Sea Ice Concentration ◽  
Sea Ice Extent ◽  
Ice Volume ◽  
Arctic Sea

Reanalysis data are known to have relatively large uncertainties in the polar region than at lower latitudes. In this study, we used a single sea-ice model (Los Alamos’ CICE5) and three sets of reanalysis data to quantify the sensitivities of simulated Arctic sea ice area and volume to perturbed atmospheric forcings. The simulated sea ice area and thickness thus volume were clearly sensitive to the selection of atmospheric reanalysis data. Among the forcing variables, changes in radiative and sensible/latent heat fluxes caused significant amounts of sensitivities. Differences in sea-ice concentration and thickness were primarily caused by differences in downward shortwave and longwave radiations. 2-m air temperature also has a significant influence on year-to-year variability of the sea ice volume. Differences in precipitation affected the sea ice volume by causing changes in the insulation effect of snow-cover on sea ice. The diversity of sea ice extent and thickness responses due to uncertainties in atmospheric variables highlights the need to carefully evaluate reanalysis data over the Arctic region.

Inter-comparison of melt pond products with melt/freeze-up dates and sea ice concentration data

2020 ◽  
Author(s):  
Sanggyun Lee ◽  
Julienne Stroeve ◽  
Michel Tsamados
Keyword(s):  
Machine Learning ◽  
Sea Ice ◽  
Arctic Sea Ice ◽  
The Arctic ◽  
Sea Ice Concentration ◽  
Solar Heat ◽  
Melt Pond ◽  
Ice Surface ◽  
Melt Ponds ◽  
Ice Concentration

<p> Melt ponds are a dominant feature on the Arctic sea ice surface in summer, occupying up to about 50 – 60% of the sea ice surface during advanced melt. Melt ponds normally begin to form around mid-May in the marginal ice zone and expand northwards as the summer melt season progresses. Once melt ponds emerge, the scattering characteristics of the ice surface changes, dramatically lowering the sea ice albedo. Since 96% of the total annual solar heat into the ocean through sea ice occurs between May and August, the presence of melt ponds plays a significant role in this transfer of solar heat, influencing not only the sea ice energy balance, but also the amount of light available under the sea ice and ocean primary productivity. Given the importance melt ponds play in the coupled Arctic climate-ecosystem, mapping and quantification of melt pond variability on a Pan-Arctic basin scale are needed. Satellite-based observations are the only way to map melt ponds and albedo changes on a pan-Arctic scale. Rösel et al. (2012) utilized a MODIS 8-day average product to map melt ponds on a pan-Arctic scale and over several years. In another approach, melt pond fraction and surface albedo were retrieved based on the physical and optical characteristics of sea ice and melt ponds without a priori information using MERIS.Here, we propose a novel machine learning-based methodology to map Arctic melt ponds from MODIS 500m resolution data. We provide a merging procedure to create the first pan-Arctic melt pond product spanning a 20-year period at a weekly temporal resolution. Specifically, we use MODIS data together with machine learning, including multi-layer neural network and logistic regression to test our ability to map melt ponds from the start to the end of the melt season. Since sea ice reflectance is strongly dependent on the viewing and solar geometry (i.e. sensor and solar zenith and azimuth angles), we attempt to minimize this dependence by using normalized band ratios in the machine learning algorithms. Each melt pond retrieval algorithm is different and validation ways are different as well producing somewhat dissimilar melt pond results. In this study, we inter-compare melt ponds products from different institutes, including university of Hamburg, university of Bremen, and university college London. The melt pond maps are compared with melt onset and freeze-up dates data and sea ice concentration. The melt pond maps are evaluated by melt pond fraction statistics from high resolution satellite (MEDEA) images that have not been used for the evaluation in melt pond products. </p>

Prévoir les variations saisonnières de la glace de mer arctique et leurs impacts sur le climat

2020 ◽  
pp. 024
Author(s):  
Rym Msadek ◽  
Gilles Garric ◽  
Sara Fleury ◽  
Florent Garnier ◽  
Lauriane Batté ◽  
...  
Keyword(s):  
Sea Ice ◽  
Arctic Region ◽  
Arctic Sea Ice ◽  
Climate Impacts ◽  
The Arctic ◽  
Recent Effort ◽  
Sea Ice Thickness ◽  
Arctic Sea ◽  
Ice Conditions ◽  
Upper Level

L'Arctique est la région du globe qui s'est réchauffée le plus vite au cours des trente dernières années, avec une augmentation de la température de surface environ deux fois plus rapide que pour la moyenne globale. Le déclin de la banquise arctique observé depuis le début de l'ère satellitaire et attribué principalement à l'augmentation de la concentration des gaz à effet de serre aurait joué un rôle important dans cette amplification des températures au pôle. Cette fonte importante des glaces arctiques, qui devrait s'accélérer dans les décennies à venir, pourrait modifier les vents en haute altitude et potentiellement avoir un impact sur le climat des moyennes latitudes. L'étendue de la banquise arctique varie considérablement d'une saison à l'autre, d'une année à l'autre, d'une décennie à l'autre. Améliorer notre capacité à prévoir ces variations nécessite de comprendre, observer et modéliser les interactions entre la banquise et les autres composantes du système Terre, telles que l'océan, l'atmosphère ou la biosphère, à différentes échelles de temps. La réalisation de prévisions saisonnières de la banquise arctique est très récente comparée aux prévisions du temps ou aux prévisions saisonnières de paramètres météorologiques (température, précipitation). Les résultats ayant émergé au cours des dix dernières années mettent en évidence l'importance des observations de l'épaisseur de la glace de mer pour prévoir l'évolution de la banquise estivale plusieurs mois à l'avance. Surface temperatures over the Arctic region have been increasing twice as fast as global mean temperatures, a phenomenon known as arctic amplification. One main contributor to this polar warming is the large decline of Arctic sea ice observed since the beginning of satellite observations, which has been attributed to the increase of greenhouse gases. The acceleration of Arctic sea ice loss that is projected for the coming decades could modify the upper level atmospheric circulation yielding climate impacts up to the mid-latitudes. There is considerable variability in the spatial extent of ice cover on seasonal, interannual and decadal time scales. Better understanding, observing and modelling the interactions between sea ice and the other components of the climate system is key for improved predictions of Arctic sea ice in the future. Running operational-like seasonal predictions of Arctic sea ice is a quite recent effort compared to weather predictions or seasonal predictions of atmospheric fields like temperature or precipitation. Recent results stress the importance of sea ice thickness observations to improve seasonal predictions of Arctic sea ice conditions during summer.

scholarly journals Sea Ice Concentration and Sea Ice Extent Mapping with L-Band Microwave Radiometry and GNSS-R Data from the FFSCat Mission Using Neural Networks

2021 ◽  
Vol 13 (6) ◽  
pp. 1139
Author(s):  
David Llaveria ◽  
Juan Francesc Munoz-Martin ◽  
Christoph Herbert ◽  
Miriam Pablos ◽  
Hyuk Park ◽  
...  
Keyword(s):  
Sea Ice ◽  
Microwave Radiometer ◽  
Cost Effective ◽  
The Arctic ◽  
Sea Ice Concentration ◽  
Sea Ice Extent ◽  
Neural Network Approach ◽  
Ice Concentration ◽  
L Band ◽  
Moderate Cost

CubeSat-based Earth Observation missions have emerged in recent times, achieving scientifically valuable data at a moderate cost. FSSCat is a two 6U CubeSats mission, winner of the ESA S3 challenge and overall winner of the 2017 Copernicus Masters Competition, that was launched in September 2020. The first satellite, 3Cat-5/A, carries the FMPL-2 instrument, an L-band microwave radiometer and a GNSS-Reflectometer. This work presents a neural network approach for retrieving sea ice concentration and sea ice extent maps on the Arctic and the Antarctic oceans using FMPL-2 data. The results from the first months of operations are presented and analyzed, and the quality of the retrieved maps is assessed by comparing them with other existing sea ice concentration maps. As compared to OSI SAF products, the overall accuracy for the sea ice extent maps is greater than 97% using MWR data, and up to 99% when using combined GNSS-R and MWR data. In the case of Sea ice concentration, the absolute errors are lower than 5%, with MWR and lower than 3% combining it with the GNSS-R. The total extent area computed using this methodology is close, with 2.5% difference, to those computed by other well consolidated algorithms, such as OSI SAF or NSIDC. The approach presented for estimating sea ice extent and concentration maps is a cost-effective alternative, and using a constellation of CubeSats, it can be further improved.

scholarly journals NLOS Multipath Classification of GNSS Signal Correlation Output Using Machine Learning

Sensors ◽  
2021 ◽  
Vol 21 (7) ◽  
pp. 2503
Author(s):  
Taro Suzuki ◽  
Yoshiharu Amano
Keyword(s):  
Machine Learning ◽  
Satellite System ◽  
Training Data ◽  
Support Vector ◽  
Positioning Errors ◽  
Automated Method ◽  
Global Navigation Satellite ◽  
Better Than ◽  
Signal Correlation

This paper proposes a method for detecting non-line-of-sight (NLOS) multipath, which causes large positioning errors in a global navigation satellite system (GNSS). We use GNSS signal correlation output, which is the most primitive GNSS signal processing output, to detect NLOS multipath based on machine learning. The shape of the multi-correlator outputs is distorted due to the NLOS multipath. The features of the shape of the multi-correlator are used to discriminate the NLOS multipath. We implement two supervised learning methods, a support vector machine (SVM) and a neural network (NN), and compare their performance. In addition, we also propose an automated method of collecting training data for LOS and NLOS signals of machine learning. The evaluation of the proposed NLOS detection method in an urban environment confirmed that NN was better than SVM, and 97.7% of NLOS signals were correctly discriminated.

scholarly journals Retrieval of Summer Sea Ice Concentration in the Pacific Arctic Ocean from AMSR2 Observations and Numerical Weather Data Using Random Forest Regression

2021 ◽  
Vol 13 (12) ◽  
pp. 2283
Author(s):  
Hyangsun Han ◽  
Sungjae Lee ◽  
Hyun-Cheol Kim ◽  
Miae Kim
Keyword(s):  
Random Forest ◽  
Sea Ice ◽  
Arctic Ocean ◽  
Open Water ◽  
The Arctic ◽  
Atmospheric Effects ◽  
Sea Ice Concentration ◽  
Air Temperatures ◽  
The Pacific ◽  
Ice Concentration

The Arctic sea ice concentration (SIC) in summer is a key indicator of global climate change and important information for the development of a more economically valuable Northern Sea Route. Passive microwave (PM) sensors have provided information on the SIC since the 1970s by observing the brightness temperature (TB) of sea ice and open water. However, the SIC in the Arctic estimated by operational algorithms for PM observations is very inaccurate in summer because the TB values of sea ice and open water become similar due to atmospheric effects. In this study, we developed a summer SIC retrieval model for the Pacific Arctic Ocean using Advanced Microwave Scanning Radiometer 2 (AMSR2) observations and European Reanalysis Agency-5 (ERA-5) reanalysis fields based on Random Forest (RF) regression. SIC values computed from the ice/water maps generated from the Korean Multi-purpose Satellite-5 synthetic aperture radar images from July to September in 2015–2017 were used as a reference dataset. A total of 24 features including the TB values of AMSR2 channels, the ratios of TB values (the polarization ratio and the spectral gradient ratio (GR)), total columnar water vapor (TCWV), wind speed, air temperature at 2 m and 925 hPa, and the 30-day average of the air temperatures from the ERA-5 were used as the input variables for the RF model. The RF model showed greatly superior performance in retrieving summer SIC values in the Pacific Arctic Ocean to the Bootstrap (BT) and Arctic Radiation and Turbulence Interaction STudy (ARTIST) Sea Ice (ASI) algorithms under various atmospheric conditions. The root mean square error (RMSE) of the RF SIC values was 7.89% compared to the reference SIC values. The BT and ASI SIC values had three times greater values of RMSE (20.19% and 21.39%, respectively) than the RF SIC values. The air temperatures at 2 m and 925 hPa and their 30-day averages, which indicate the ice surface melting conditions, as well as the GR using the vertically polarized channels at 23 GHz and 18 GHz (GR(23V18V)), TCWV, and GR(36V18V), which accounts for atmospheric water content, were identified as the variables that contributed greatly to the RF model. These important variables allowed the RF model to retrieve unbiased and accurate SIC values by taking into account the changes in TB values of sea ice and open water caused by atmospheric effects.

Sign in / Sign up

Export Citation Format

Share Document