Deep learning based retrieval algorithm for Arctic sea ice concentration from AMSR2 passive microwave and MODIS optical data

2019 ◽  
Vol 231 ◽  
pp. 111204 ◽  
Author(s):  
Junhwa Chi ◽  
Hyun-cheol Kim ◽  
Sungjae Lee ◽  
Melba M. Crawford
2020 ◽  
Author(s):  
Junhwa Chi ◽  
Hyun-Cheol Kim ◽  
Sung Jae Lee

<p>Changes in Arctic sea ice cover represent one of the most visible indicators of climate change. While changes in sea ice extent affect the albedo, changes in sea ice volume explain changes in the heat budget and the exchange of fresh water between ice and the ocean. Global climate simulations predict that Arctic sea ice will exhibit a more significant change in volume than extent. Satellite observations show a long-term negative trend in Arctic sea ice  during all seasons, particularly in summer. Sea ice volume has been estimated by ICESat and CryoSat-2 satellites, and then NASA’s second-generation spaceborne lidar mission, ICESat-2 has successfully been launched in 2018.  Although these sensors can measure sea ice freeboard precisely, long revisit cycles and narrow swaths are problematic for monitoring of the freeboard in the entire of Arctic ocean effectively. Passive microwave sensors are widely used in retrieval of sea ice concentration. Because of the capability of high temporal resolution and wider swaths, these sensors enable to produce daily sea ice concentration maps over the entire Arctic ocean. Brightness temperatures from passive microwave sensors are often used to estimate sea ice freeboard for first-year ice, but it is difficult to associate with physical characteristics related to sea ice height of multi-year ice. In machine learning community, deep learning has gained attention and notable success in addressing more complicated decision making using multiple hidden layers. In this study, we propose a deep learning based Arctic sea ice freeboard retrieval algorithm incorporating the brightness temperature data from the AMSR2 passive microwave data and sea ice freeboard data from the ICESat-2. The proposed retrieval algorithm enables to estimate daily freeboard for both first- and multi-year ice over the entire Arctic ocean. The estimated freeboard values from the AMSR2 are then quantitatively and qualitatively compared with other sea ice freeboard or thickness products.  </p>


2020 ◽  
Author(s):  
Tom Andersson ◽  
Fruzsina Agocs ◽  
Scott Hosking ◽  
María Pérez-Ortiz ◽  
Brooks Paige ◽  
...  

<p>Over recent decades, the Arctic has warmed faster than any region on Earth. The rapid decline in Arctic sea ice extent (SIE) is often highlighted as a key indicator of anthropogenic climate change. Changes in sea ice disrupt Arctic wildlife and indigenous communities, and influence weather patterns as far as the mid-latitudes. Furthermore, melting sea ice attenuates the albedo effect by replacing the white, reflective ice with dark, heat-absorbing melt ponds and open sea, increasing the Sun’s radiative heat input to the Arctic and amplifying global warming through a positive feedback loop. Thus, the reliable prediction of sea ice under a changing climate is of both regional and global importance. However, Arctic sea ice presents severe modelling challenges due to its complex coupled interactions with the ocean and atmosphere, leading to high levels of uncertainty in numerical sea ice forecasts.</p><p>Deep learning (a subset of machine learning) is a family of algorithms that use multiple nonlinear processing layers to extract increasingly high-level features from raw input data. Recent advances in deep learning techniques have enabled widespread success in diverse areas where significant volumes of data are available, such as image recognition, genetics, and online recommendation systems. Despite this success, and the presence of large climate datasets, applications of deep learning in climate science have been scarce until recent years. For example, few studies have posed the prediction of Arctic sea ice in a deep learning framework. We investigate the potential of a fully data-driven, neural network sea ice prediction system based on satellite observations of the Arctic. In particular, we use inputs of monthly-averaged sea ice concentration (SIC) maps since 1979 from the National Snow and Ice Data Centre, as well as climatological variables (such as surface pressure and temperature) from the European Centre for Medium-Range Weather Forecasts reanalysis (ERA5) dataset. Past deep learning-based Arctic sea ice prediction systems tend to overestimate sea ice in recent years - we investigate the potential to learn the non-stationarity induced by climate change with the inclusion of multi-decade global warming indicators (such as average Arctic air temperature). We train the networks to predict SIC maps one month into the future, evaluating network prediction uncertainty by ensembling independent networks with different random weight initialisations. Our model accounts for seasonal variations in the drivers of sea ice by controlling for the month of the year being predicted. We benchmark our prediction system against persistence, linear extrapolation and autoregressive models, as well as September minimum SIE predictions from submissions to the Sea Ice Prediction Network's Sea Ice Outlook. Performance is evaluated quantitatively using the root mean square error and qualitatively by analysing maps of prediction error and uncertainty.</p>


2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Tom R. Andersson ◽  
J. Scott Hosking ◽  
María Pérez-Ortiz ◽  
Brooks Paige ◽  
Andrew Elliott ◽  
...  

AbstractAnthropogenic warming has led to an unprecedented year-round reduction in Arctic sea ice extent. This has far-reaching consequences for indigenous and local communities, polar ecosystems, and global climate, motivating the need for accurate seasonal sea ice forecasts. While physics-based dynamical models can successfully forecast sea ice concentration several weeks ahead, they struggle to outperform simple statistical benchmarks at longer lead times. We present a probabilistic, deep learning sea ice forecasting system, IceNet. The system has been trained on climate simulations and observational data to forecast the next 6 months of monthly-averaged sea ice concentration maps. We show that IceNet advances the range of accurate sea ice forecasts, outperforming a state-of-the-art dynamical model in seasonal forecasts of summer sea ice, particularly for extreme sea ice events. This step-change in sea ice forecasting ability brings us closer to conservation tools that mitigate risks associated with rapid sea ice loss.


Author(s):  
Y. Chen ◽  
X. Zhao ◽  
M. Qu ◽  
Z. Cheng ◽  
X. Pang ◽  
...  

Abstract. Passive microwave (PM) sensors on satellite can monitor sea ice distribution with their strengths of daylight- and weather-independent observations. Microwave Radiation Imager (MWRI) sensor aboard on the Chinese FengYun-3D (FY-3D) satellites was launched in 2017 and provides continuous observation for Arctic sea ice since then. In this study, sea ice concentration (SIC) product is derived from brightness temperature (TB) data of MWRI, based on an Arctic Radiation and Turbulence Interaction Study Sea Ice (ASI) dynamic tie points algorithm. Our product is inter-compared with a published MWRI SIC product by the Enhanced NASA Team (NT2) algorithm, and three Advanced Microwave Scanning Radiometer 2 (AMSR2) SIC products by the ASI, Bootstrap (BST) and NT2 algorithm. Results show that MWRI SIC are generally higher than AMSR2 SIC and the median of monthly SIC differences are larger in summer. Regional analysis indicates that the smaller differences between AMSR2 SIC and MWRI-ASI SIC occur in the higher SIC areas, and the biases are within ±5% in the Beaufort Sea, Chukchi Sea, East Siberian Sea, Canadian Archipelago Sea and Central Arctic Sea. There is the smallest SIC difference in the Central Arctic Sea with the biases of −0.77%, −0.60%, and 0.19% for AMSR2-ASI, AMSR2-BST and AMSR2-NT2, respectively. The trends of MWRI and AMSR2 sea ice extent and sea ice area are consistent with correlation coefficients all greater than 0.997. Besides, mean SIC, sea ice extent and sea ice area of MWRI-ASI are closer to those of AMSR2 than those of MWRI-NT2.


2021 ◽  
Author(s):  
Harry Heorton ◽  
Michel Tsamados ◽  
Paul Holland ◽  
Jack Landy

<p><span>We combine satellite-derived observations of sea ice concentration, drift, and thickness to provide the first observational decomposition of the dynamic (advection/divergence) and thermodynamic (melt/growth) drivers of wintertime Arctic sea ice volume change. Ten winter growth seasons are analyzed over the CryoSat-2 period between October 2010 and April 2020. Sensitivity to several observational products is performed to provide an estimated uncertainty of the budget calculations. The total thermodynamic ice volume growth and dynamic ice losses are calculated with marked seasonal, inter-annual and regional variations</span><span>. Ice growth is fastest during Autumn, in the Marginal Seas and over first year ice</span><span>. Our budget decomposition methodology can help diagnose the processes confounding climate model predictions of sea ice. We make our product and code available to the community in monthly pan-Arctic netcdft files for the entire October 2010 to April 2020 period.</span></p>


2021 ◽  
Author(s):  
Vladimir Semenov ◽  
Tatiana Matveeva

<p>Global warming in the recent decades has been accompanied by a rapid recline of the Arctic sea ice area most pronounced in summer (10% per decade). To understand the relative contribution of external forcing and natural variability to the modern and future sea ice area changes, it is necessary to evaluate a range of long-term variations of the Arctic sea ice area in the period before a significant increase in anthropogenic emissions of greenhouse gases into the atmosphere. Available observational data on the spatiotemporal dynamics of Arctic sea ice until 1950s are characterized by significant gaps and uncertainties. In the recent years, there have appeared several reconstructions of the early 20<sup>th</sup> century Arctic sea ice area that filled the gaps by analogue methods or utilized combined empirical data and climate model’s output. All of them resulted in a stronger that earlier believed negative sea ice area anomaly in the 1940s concurrent with the early 20<sup>th</sup> century warming (ETCW) peak. In this study, we reconstruct the monthly average gridded sea ice concentration (SIC) in the first half of the 20th century using the relationship between the spatiotemporal features of SIC variability, surface air temperature over the Northern Hemisphere extratropical continents, sea surface temperature in the North Atlantic and North Pacific, and sea level pressure. In agreement with a few previous results, our reconstructed data also show a significant negative anomaly of the Arctic sea ice area in the middle of the 20th century, however with some 15% to 30% stronger amplitude, about 1.5 million km<sup>2</sup> in September and 0.7 million km<sup>2</sup> in March. The reconstruction demonstrates a good agreement with regional Arctic sea ice area data when available and suggests that ETWC in the Arctic has been accompanied by a concurrent sea ice area decline of a magnitude that have been exceeded only in the beginning of the 21<sup>st</sup> century.</p>


Sign in / Sign up

Export Citation Format

Share Document