Articles | Volume 14, issue 3
Research article 25 Mar 2020
Research article | 25 Mar 2020
Prediction of monthly Arctic sea ice concentrations using satellite and reanalysis data based on convolutional neural networks
Young Jun Kim et al.
No articles found.
Jeong-Won Park, Anton Andreevich Korosov, Mohamed Babiker, Joong-Sun Won, Morten Wergeland Hansen, and Hyun-Cheol Kim
The Cryosphere, 14, 2629–2645,Short summary
A new Sentinel-1 radar-based sea ice classification algorithm is proposed. We show that the readily available ice charts from operational ice services can reduce the amount of manual work in preparation of large amounts of training/testing data and feed highly reliable data to the trainer in an efficient way. Test results showed that the classifier is capable of retrieving three generalized cover types with overall accuracy of 87 % and 67 % in the winter and summer seasons, respectively.
Marco Meloni, Jerome Bouffard, Tommaso Parrinello, Geoffrey Dawson, Florent Garnier, Veit Helm, Alessandro Di Bella, Stefan Hendricks, Robert Ricker, Erica Webb, Ben Wright, Karina Nielsen, Sanggyun Lee, Marcello Passaro, Michele Scagliola, Sebastian Bjerregaard Simonsen, Louise Sandberg Sørensen, David Brockley, Steven Baker, Sara Fleury, Jonathan Bamber, Luca Maestri, Henriette Skourup, René Forsberg, and Loretta Mizzi
The Cryosphere, 14, 1889–1907,Short summary
This manuscript aims to describe the evolutions which have been implemented in the new CryoSat Ice processing chain Baseline-D and the validation activities carried out in different domains such as sea ice, land ice and hydrology. This new CryoSat processing Baseline-D will maximise the uptake and use of CryoSat data by scientific users since it offers improved capability for monitoring the complex and multiscale changes over the cryosphere.
Seohui Park, Minso Shin, Jungho Im, Chang-Keun Song, Myungje Choi, Jhoon Kim, Seungun Lee, Rokjin Park, Jiyoung Kim, Dong-Won Lee, and Sang-Kyun Kim
Atmos. Chem. Phys., 19, 1097–1113,Short summary
This study proposed machine-learning-based models to estimate ground-level particulate matter concentrations using satellite observations and numerical model-derived data. Aerosol optical depth was identified as the most significant for estimating ground-level PM concentrations, followed by wind speed and solar radiation. The results show that the proposed models produced better performance than the existing approaches, particularly in improving on the biases of the process-based models.
Joo-Eun Yoon, Kyu-Cheul Yoo, Alison M. Macdonald, Ho-Il Yoon, Ki-Tae Park, Eun Jin Yang, Hyun-Cheol Kim, Jae Il Lee, Min Kyung Lee, Jinyoung Jung, Jisoo Park, Jiyoung Lee, Soyeon Kim, Seong-Su Kim, Kitae Kim, and Il-Nam Kim
Biogeosciences, 15, 5847–5889,Short summary
Our paper provides an intensive overview of the artificial ocean iron fertilization (aOIF) experiments conducted over the last 25 years to test Martin’s hypothesis, discusses aOIF-related important unanswered open questions, suggests considerations for the design of future aOIF experiments to maximize their effectiveness, and introduces design guidelines for a future Korean Iron Fertilization Experiment in the Southern Ocean.
C. U. Hyun and H. C. Kim
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-1, 211–215,
J.-I. Kim and H.-C. Kim
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2, 501–505,
Sanggyun Lee, Hyun-cheol Kim, and Jungho Im
The Cryosphere, 12, 1665–1679,Short summary
Arctic sea ice leads play a major role in exchanging heat and momentum between the Arctic atmosphere and ocean. In this study, we propose a novel lead detection approach based on waveform mixture analysis. The performance of the proposed approach in detecting leads was promising when compared to the existing methods. The robustness of the proposed approach also lies in the fact that it does not require the rescaling of parameters, as it directly uses L1B waveform data.
Sanggyun Lee, Hyangsun Han, Jungho Im, Eunna Jang, and Myong-In Lee
Atmos. Meas. Tech., 10, 1859–1874,Short summary
Deterministic and probabilistic CI detection models based on decision trees (DT), random forest (RF), and logistic regression (LR) were developed using Himawari-8 AHI data obtained over the Korean Peninsula. We used a total of 12 interest fields including time trends to develop the models. We identified contributing variables for CI detection. DT showed a higher hit rate, while RF produced a higher critical success index. The mean lead times by the four models were in the range of 20–40 min.
Dongmin Kim, Myong-In Lee, Su-Jong Jeong, Jungho Im, Dong Hyun Cha, and Sanggyun Lee
Manuscript not accepted for further reviewShort summary
This study compares historical simulations of the terrestrial carbon cycle produced by 10 ESMs that participated in the CMIP5. The models show noticeable deficiencies compared to the MODIS data and large differences among the simulations, although the MME mean provides a realistic global mean value and spatial distributions. MME is reflected by the systematic biases of simulated biogeochemical processes which depends on temperature conditions strongly in every plant functional types.
H. M. Park, M. A. Kim, and J. Im
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLI-B7, 325–327,
S. Park and J. Im
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLI-B7, 703–704,
Related subject area
Discipline: Sea ice | Subject: Sea IceAn inter-comparison of the mass budget of the Arctic sea ice in CMIP6 modelsRefining the sea surface identification approach for determining freeboards in the ICESat-2 sea ice productsSurface-based Ku- and Ka-band polarimetric radar for sea ice studiesStatistical predictability of the Arctic sea ice volume anomaly: identifying predictors and optimal sampling locationsSatellite-based sea ice thickness changes in the Laptev Sea from 2002 to 2017: comparison to mooring observationsModeling the annual cycle of daily Antarctic sea ice extentChanges of the Arctic marginal ice zone during the satellite eraAn enhancement to sea ice motion and age products at the National Snow and Ice Data Center (NSIDC)Accuracy and inter-analyst agreement of visually estimated sea ice concentrations in Canadian Ice Service ice charts using single-polarization RADARSAT-2Variability scaling and consistency in airborne and satellite altimetry measurements of Arctic sea iceSea ice volume variability and water temperature in the Greenland SeaSea ice export through the Fram Strait derived from a combined model and satellite data setEstimating early-winter Antarctic sea ice thickness from deformed ice morphologyOn the multi-fractal scaling properties of sea ice deformationBrief communication: Pancake ice floe size distribution during the winter expansion of the Antarctic marginal ice zoneWhat historical landfast ice observations tell us about projected ice conditions in Arctic archipelagoes and marginal seas under anthropogenic forcingInterannual sea ice thickness variability in the Bay of BothniaImproving Met Office seasonal predictions of Arctic sea ice using assimilation of CryoSat-2 thicknessBrief communication: Solar radiation management not as effective as CO2 mitigation for Arctic sea ice loss in hitting the 1.5 and 2 °C COP climate targetsReflective properties of melt ponds on sea iceThe color of melt ponds on Arctic sea ice
Ann Keen, Ed Blockley, David A. Bailey, Jens Boldingh Debernard, Mitchell Bushuk, Steve Delhaye, David Docquier, Daniel Feltham, François Massonnet, Siobhan O'Farrell, Leandro Ponsoni, José M. Rodriguez, David Schroeder, Neil Swart, Takahiro Toyoda, Hiroyuki Tsujino, Martin Vancoppenolle, and Klaus Wyser
The Cryosphere, 15, 951–982,Short summary
We compare the mass budget of the Arctic sea ice in a number of the latest climate models. New output has been defined that allows us to compare the processes of sea ice growth and loss in a more detailed way than has previously been possible. We find that that the models are strikingly similar in terms of the major processes causing the annual growth and loss of Arctic sea ice and that the budget terms respond in a broadly consistent way as the climate warms during the 21st century.
Ron Kwok, Alek A. Petty, Marco Bagnardi, Nathan T. Kurtz, Glenn F. Cunningham, Alvaro Ivanoff, and Sahra Kacimi
The Cryosphere, 15, 821–833,
Julienne Stroeve, Vishnu Nandan, Rosemary Willatt, Rasmus Tonboe, Stefan Hendricks, Robert Ricker, James Mead, Robbie Mallett, Marcus Huntemann, Polona Itkin, Martin Schneebeli, Daniela Krampe, Gunnar Spreen, Jeremy Wilkinson, Ilkka Matero, Mario Hoppmann, and Michel Tsamados
The Cryosphere, 14, 4405–4426,Short summary
This study provides a first look at the data collected by a new dual-frequency Ka- and Ku-band in situ radar over winter sea ice in the Arctic Ocean. The instrument shows potential for using both bands to retrieve snow depth over sea ice, as well as sensitivity of the measurements to changing snow and atmospheric conditions.
Leandro Ponsoni, François Massonnet, David Docquier, Guillian Van Achter, and Thierry Fichefet
The Cryosphere, 14, 2409–2428,Short summary
The continuous melting of the Arctic sea ice observed in the last decades has a significant impact at global and regional scales. To understand the amplitude and consequences of this impact, the monitoring of the total sea ice volume is crucial. However, in situ monitoring in such a harsh environment is hard to perform and far too expensive. This study shows that four well-placed sampling locations are sufficient to explain about 70 % of the inter-annual changes in the pan-Arctic sea ice volume.
H. Jakob Belter, Thomas Krumpen, Stefan Hendricks, Jens Hoelemann, Markus A. Janout, Robert Ricker, and Christian Haas
The Cryosphere, 14, 2189–2203,Short summary
The validation of satellite sea ice thickness (SIT) climate data records with newly acquired moored sonar SIT data shows that satellite products provide modal rather than mean SIT in the Laptev Sea region. This tendency of satellite-based SIT products to underestimate mean SIT needs to be considered for investigations of sea ice volume transports. Validation of satellite SIT in the first-year-ice-dominated Laptev Sea will support algorithm development for more reliable SIT records in the Arctic.
Mark S. Handcock and Marilyn N. Raphael
The Cryosphere, 14, 2159–2172,Short summary
Traditional methods of calculating the annual cycle of sea ice extent disguise the variation of amplitude and timing (phase) of the advance and retreat of the ice. We present a multiscale model that explicitly allows them to vary, resulting in a much improved representation of the cycle. We show that phase is the dominant contributor to the variability in the cycle and that the anomalous decay of Antarctic sea ice in 2016 was due largely to a change of phase.
Rebecca J. Rolph, Daniel L. Feltham, and David Schröder
The Cryosphere, 14, 1971–1984,Short summary
It is well known that the Arctic sea ice extent is declining, and it is often assumed that the marginal ice zone (MIZ), the area of partial sea ice cover, is consequently increasing. However, we find no trend in the MIZ extent during the last 40 years from observations that is consistent with a widening of the MIZ as it moves northward. Differences of MIZ extent between different satellite retrievals are too large to provide a robust basis to verify model simulations of MIZ extent.
Mark A. Tschudi, Walter N. Meier, and J. Scott Stewart
The Cryosphere, 14, 1519–1536,Short summary
A new version of a set of data products that contain the velocity of sea ice and the age of this ice has been developed. We provide a history of the product development and discuss the improvements to the algorithms that create these products. We find that changes in sea ice motion and age show a significant shift in the Arctic ice cover, from a pack with a high concentration of older ice to a sea ice cover dominated by younger ice, which is more susceptible to summer melt.
Angela Cheng, Barbara Casati, Adrienne Tivy, Tom Zagon, Jean-François Lemieux, and L. Bruno Tremblay
The Cryosphere, 14, 1289–1310,Short summary
Sea ice charts by the Canadian Ice Service (CIS) contain visually estimated ice concentration produced by analysts. The accuracy of manually derived ice concentrations is not well understood. The subsequent uncertainty of ice charts results in downstream uncertainties for ice charts users, such as models and climatology studies, and when used as a verification source for automated sea ice classifiers. This study quantifies the level of accuracy and inter-analyst agreement for ice charts by CIS.
Shiming Xu, Lu Zhou, and Bin Wang
The Cryosphere, 14, 751–767,Short summary
Sea ice thickness parameters are key to polar climate change studies and forecasts. Airborne and satellite measurements provide complementary observational capabilities. The study analyzes the variability in freeboard and snow depth measurements and its changes with scale in Operation IceBridge, CryoVEx, CryoSat-2 and ICESat. Consistency between airborne and satellite data is checked. Analysis calls for process-oriented attribution of variability and covariability features of these parameters.
Valeria Selyuzhenok, Igor Bashmachnikov, Robert Ricker, Anna Vesman, and Leonid Bobylev
The Cryosphere, 14, 477–495,Short summary
This study explores a link between the long-term variations in the integral sea ice volume in the Greenland Sea and oceanic processes. We link the changes in the Pan-Arctic Ice Ocean Modeling and Assimilation System (PIOMAS) regional sea ice volume with the mixed layer, depth and upper-ocean heat content derived using the ARMOR dataset.
Chao Min, Longjiang Mu, Qinghua Yang, Robert Ricker, Qian Shi, Bo Han, Renhao Wu, and Jiping Liu
The Cryosphere, 13, 3209–3224,Short summary
Sea ice volume export through the Fram Strait has been studied using varied methods, however, mostly in winter months. Here we report sea ice volume estimates that extend over summer seasons. A recent developed sea ice thickness dataset, in which CryoSat-2 and SMOS sea ice thickness together with SSMI/SSMIS sea ice concentration are assimilated, is used and evaluated in the paper. Results show our estimate is more reasonable than that calculated by satellite data only.
M. Jeffrey Mei, Ted Maksym, Blake Weissling, and Hanumant Singh
The Cryosphere, 13, 2915–2934,Short summary
Sea ice thickness is hard to measure directly, and current datasets are very limited to sporadically conducted drill lines. However, surface elevation is much easier to measure. Converting surface elevation to ice thickness requires making assumptions about snow depth and density, which leads to large errors (and may not generalize to new datasets). A deep learning method is presented that uses the surface morphology as a direct predictor of sea ice thickness, with testing errors of < 20 %.
Pierre Rampal, Véronique Dansereau, Einar Olason, Sylvain Bouillon, Timothy Williams, Anton Korosov, and Abdoulaye Samaké
The Cryosphere, 13, 2457–2474,Short summary
In this article, we look at how the Arctic sea ice cover, as a solid body, behaves on different temporal and spatial scales. We show that the numerical model neXtSIM uses a new approach to simulate the mechanics of sea ice and reproduce the characteristics of how sea ice deforms, as observed by satellite. We discuss the importance of this model performance in the context of simulating climate processes taking place in polar regions, like the exchange of energy between the ocean and atmosphere.
Alberto Alberello, Miguel Onorato, Luke Bennetts, Marcello Vichi, Clare Eayrs, Keith MacHutchon, and Alessandro Toffoli
The Cryosphere, 13, 41–48,Short summary
Existing observations do not provide quantitative descriptions of the floe size distribution for pancake ice floes. This is important during the Antarctic winter sea ice expansion, when hundreds of kilometres of ice cover around the Antarctic continent are composed of pancake floes (D = 0.3–3 m). Here, a new set of images from the Antarctic marginal ice zone is used to measure the shape of individual pancakes for the first time and to infer their size distribution.
Frédéric Laliberté, Stephen E. L. Howell, Jean-François Lemieux, Frédéric Dupont, and Ji Lei
The Cryosphere, 12, 3577–3588,Short summary
Ice that forms over marginal seas often gets anchored and becomes landfast. Landfast ice is fundamental to the local ecosystems, is of economic importance as it leads to hazardous seafaring conditions and is also a choice hunting ground for both the local population and large predators. Using observations and climate simulations, this study shows that, especially in the Canadian Arctic, landfast ice might be more resilient to climate change than is generally thought.
Iina Ronkainen, Jonni Lehtiranta, Mikko Lensu, Eero Rinne, Jari Haapala, and Christian Haas
The Cryosphere, 12, 3459–3476,Short summary
We quantify the sea ice thickness variability in the Bay of Bothnia using various observational data sets. For the first time we use helicopter and shipborne electromagnetic soundings to study changes in drift ice of the Bay of Bothnia. Our results show that the interannual variability of ice thickness is larger in the drift ice zone than in the fast ice zone. Furthermore, the mean thickness of heavily ridged ice near the coast can be several times larger than that of fast ice.
Edward W. Blockley and K. Andrew Peterson
The Cryosphere, 12, 3419–3438,Short summary
Arctic sea-ice prediction on seasonal time scales is becoming increasingly more relevant to society but the predictive capability of forecasting systems is low. Several studies suggest initialization of sea-ice thickness (SIT) could improve the skill of seasonal prediction systems. Here for the first time we test the impact of SIT initialization in the Met Office's GloSea coupled prediction system using CryoSat-2 data. We show significant improvements to Arctic extent and ice edge location.
Jeff K. Ridley and Edward W. Blockley
The Cryosphere, 12, 3355–3360,Short summary
The climate change conference held in Paris in 2016 made a commitment to limiting global-mean warming since the pre-industrial era to well below 2 °C and to pursue efforts to limit the warming to 1.5 °C. Since global warming is already at 1 °C, the 1.5 °C can only be achieved at considerable cost. It is thus important to assess the risks associated with the higher target. This paper shows that the decline of Arctic sea ice, and associated impacts, can only be halted with the 1.5 °C target.
Aleksey Malinka, Eleonora Zege, Larysa Istomina, Georg Heygster, Gunnar Spreen, Donald Perovich, and Chris Polashenski
The Cryosphere, 12, 1921–1937,Short summary
Melt ponds occupy a large part of the Arctic sea ice in summer and strongly affect the radiative budget of the atmosphere–ice–ocean system. The melt pond reflectance is modeled in the framework of the radiative transfer theory and validated with field observations. It improves understanding of melting sea ice and enables better parameterization of the surface in Arctic atmospheric remote sensing (clouds, aerosols, trace gases) and re-evaluating Arctic climatic feedbacks at a new accuracy level.
Peng Lu, Matti Leppäranta, Bin Cheng, Zhijun Li, Larysa Istomina, and Georg Heygster
The Cryosphere, 12, 1331–1345,Short summary
It is the first time that the color of melt ponds on Arctic sea ice was quantitatively and thoroughly investigated. We answer the question of why the color of melt ponds can change and what the physical and optical reasons are that lead to such changes. More importantly, melt-pond color was provided as potential data in determining ice thickness, especially under the summer conditions when other methods such as remote sensing are unavailable.
Archer, K. J. and Kimes, R. V.: Empirical characterization of random forest variable importance measures, Comput. Stat. Data. An., 52, 2249–2260, https://doi.org/10.1016/j.csda.2007.08.015, 2008.
Årthun, M., Eldevik, T., Smedsrud, L. H., Skagseth, Ø., and Ingvaldsen, R. B.: Quantifying the Influence of Atlantic Heat on Barents Sea Ice Variability and Retreat, J. Climate, 25, 4736–4743, https://doi.org/10.1175/JCLI-D-11-00466.1, 2012.
Brahimi, M., Boukhalfa, K., and Moussaoui, A.: Deep learning for tomato diseases: classification and symptoms visualization, Appl. Artif. Intell., 31, 299–315, 2017.
Cavalieri, D. J. and Parkinson, C. L.: Arctic sea ice variability and trends, 1979–2010, The Cryosphere, 6, 881–889, https://doi.org/10.5194/tc-6-881-2012, 2012.
Chen, K., Wang, J., Chen, L.-C., Gao, H., Xu, W., and Nevatia, R.: Abc-cnn: An attention based convolutional neural network for visual question answering, arXiv Prepr. arXiv1511.05960, 2015.
Chevallier, M., Salas y Mélia, D., Voldoire, A., Déqué, M., and Garric, G.: Seasonal forecasts of the pan-Arctic sea ice extent using a GCM-based seasonal prediction system, J. Climate, 26, 6092–6104, 2013.
Chi, J. and Kim, H.: Prediction of Arctic Sea Ice Concentration Using a Fully Data Driven Deep Neural Network, Remote Sens., 9, 1305, https://doi.org/10.3390/rs9121305, 2017.
Cohen, J., Screen, J. A., Furtado, J. C., Barlow, M., Whittleston, D., Coumou, D., Francis, J., Dethloff, K., Entekhabi, D., Overland, J., and Jones, J.: Recent Arctic amplification and extreme mid-latitude weather, Nat. Geosci., 7, 627–637, https://doi.org/10.1038/ngeo2234, 2014.
Comeau, D., Giannakis, D., Zhao, Z., and Majda, A. J.: Predicting regional and pan-Arctic sea ice anomalies with kernel analog forecasting, Clim. Dynam., 52, 5507–5525, https://doi.org/10.1007/s00382-018-4459-x, 2019.
Comiso, J. C.: Abrupt decline in the Arctic winter sea ice cover, Geophys. Res. Lett., 33, L18504, https://doi.org/10.1029/2006GL027341, 2006.
Crane, R. G.: Seasonal variations of sea ice extent in the Davis Strait-Labrador Sea area and relationships with synoptic-scale atmospheric circulation, Arctic, 31, 434–447, https://doi.org/10.14430/arctic2671, 1978.
Deser, C. and Teng, H.: Evolution of Arctic sea ice concentration trends and the role of atmospheric circulation forcing, 1979–2007, Geophys. Res. Lett., 35, 2, https://doi.org/10.1029/2007GL032023, 2008.
Devasthale, A., Sedlar, J., Koenigk, T., and Fetzer, E. J.: The thermodynamic state of the Arctic atmosphere observed by AIRS: comparisons during the record minimum sea ice extents of 2007 and 2012, Atmos. Chem. Phys., 13, 7441–7450, https://doi.org/10.5194/acp-13-7441-2013, 2013.
Doney, S. C., Ruckelshaus, M., Emmett Duffy, J., Barry, J. P., Chan, F., English, C. A., Galindo, H. M., Grebmeier, J. M., Hollowed, A. B., Knowlton, N., Polovina, J., Rabalais, N. N., Sydeman, W. J., and Talley, L. D.: Climate change impacts on marine ecosystems, Ann. Rev. Mar. Sci., 4, 11–37, https://doi.org/10.1146/annurev-marine-041911-111611, 2012.
Drobot, S.: Long-range statistical forecasting of ice severity in the Beaufort–Chukchi Sea., Weather Forecast., 18, 1161–1176, https://doi.org/10.1175/1520-0434(2003)018<1161:lsfois>2.0.co;2, 2003.
Drobot, S. D., Maslanik, J. A., and Fowler, C.: A long-range forecast of Arctic summer sea-ice minimum extent., Geophys. Res. Lett., 33, L10501, https://doi.org/10.1029/2006GL026216, 2006.
Emery, W. J., Fowler, C. W., and Maslanik, J. A.: Satellite-derived maps of Arctic and Antarctic sea ice motion: 1988 to 1994, Geophys. Res. Lett., 24, 897–900, https://doi.org/10.1029/97gl00755, 1997.
Fagua, J. and Ramsey, R.: Comparng the accuracy of MODIS data products for vegetation detection between two environmentally dissimilar ecoregions : the Choco-Darien of South America and the Great Basin of North America, GIScience Remote Sens., 56, 1046–1064, 2019.
Forkuor, G., Dimobe, K., Serme, I., and Tondoh, J. E.: Landsat-8 vs. Sentinel-2: examining the added value of sentinel-2's red-edge bands to land-use and land-cover mapping in Burkina Faso, GIScience Remote Sens., 55, 331–354, https://doi.org/10.1080/15481603.2017.1370169, 2018.
Francis, J. A. and Vavrus, S. J.: Evidence for a wavier jet stream in response to rapid Arctic warming, Environ. Res. Lett., 10, 14005, https://doi.org/10.1088/1748-9326/10/1/014005, 2015.
Grumbine, R. W.: Virtual floe ice drift forecast model intercomparison, Weather Forecast., 13, 886–890, https://doi.org/10.1175/1520-0434(1998)013<0886:VFIDFM>2.0.CO;2, 1998.
Guemas, V., Blanchard-Wrigglesworth, E., Chevallier, M., Day, J. J., Déqué, M., Doblas-Reyes, F. J., Fučkar, N. S., Germe, A., Hawkins, E., Keeley, S., Koenigk, T., Melia, D. S., and Tietsche, S.: A review on Arctic sea-ice predictability and prediction on seasonal to decadal time-scales, Q. J. Roy. Meteorol. Soc., 142, 546–561, https://doi.org/10.1002/qj.2401, 2016.
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., and Pedreschi, D.: A survey of methods for explaining black box models, ACM Comput. Surv., 51, 1–42, https://doi.org/10.1145/3236009, 2018.
Guo, Z. and Du, S.: Mining parameter information for building extraction and change detection with very high-resolution imagery and GIS data, GIScience Remote Sens., 54, 38–63, https://doi.org/10.1080/15481603.2016.1250328, 2017.
Hassol, S.: Impacts of a warming Arctic-Arctic climate impact assessment, Cambridge University Press., Hassol, S.: Impacts of a warming Arctic-Arctic climate impact assessment, available at: https://www.amap.no/documents/doc/impacts-of-a-warming-arctic-2004/786 (last access: 24 March 2020, 2004.
Holland, M. M. and Stroeve, J.: Changing seasonal sea ice predictor relationships in a changing Arctic climate, Geophys. Res. Lett., 38, L18501, https://doi.org/10.1029/2011gl049303, 2011.
Jang, E., Im, J., Park, G., and Park, Y.: Estimation of fugacity of carbon dioxide in the east sea using in situ measurements and geostationary ocean color imager satellite data, Remote Sens., 9, 821, 2017.
Johannessen, O. M., Bengtsson, L., Miles, M. W., Kuzmina, S. I., Semenov, V. A., Alekseev, G. V, Nagurnyi, A. P., Zakharov, V. F., Bobylev, L. P., Pettersson, L. H., Hasselmann, K., and Cattle, H. P.: Arctic climate change: observed and modelled temperature and sea-ice variability, Tellus A Dyn. Meteorol. Oceanogr., 56, 328–341, https://doi.org/10.3402/tellusa.v56i5.14599, 2004.
Kang, D., Im, J., Lee, M. I., and Quackenbush, L. J.: The MODIS ice surface temperature product as an indicator of sea ice minimum over the Arctic Ocean, Remote Sens. Environ., 152, 99–108, https://doi.org/10.1016/j.rse.2014.05.012, 2014.
Kauker, F., Kaminski, T., Karcher, M., Giering, R., Gerdes, R., and Voßbeck, M.: Adjoint analysis of the 2007 all time Arctic sea-ice minimum, Geophys. Res. Lett., 36, L03707, https://doi.org/10.1029/2008gl036323, 2009.
Kay, J. E., L'Ecuyer, T., Gettelman, A., Stephens, G., and O'Dell, C.: The contribution of cloud and radiation anomalies to the 2007 Arctic sea ice extent minimum, Geophys. Res. Lett., 35, L08503, https://doi.org/10.1029/2008gl033451, 2008.
Kern, S., Rösel, A., Pedersen, L. T., Ivanova, N., Saldo, R., and Tonboe, R. T.: The impact of melt ponds on summertime microwave brightness temperatures and sea-ice concentrations, The Cryosphere, 10, 2217–2239, https://doi.org/10.5194/tc-10-2217-2016, 2016.
Kim, M., Lee, J., and Im, J. : Deep learning-based monitoring of overshooting cloud tops from geostationary satellite data, GIScience Remote Sens., 55, 763–792, 2018a.
Kim, M., Lee, J., Han, D., Shin, M., Im, J., Lee, J., Quackenbush, L., and Gu, Z.: Convolutional neural network-based land cover classification using 2-D spectral reflectance curve graphs with multi-temporal satellite imagery, IEEE J. Select. Top. Appl. Earth Observ. Remote Sens., 11, 4604–4617, 2018b.
Koh, P. W. and Liang, P.: Understanding black-box predictions via influence functions, in: Proceedings of the 34th International Conference on Machine Learning, Volume 70, 1885–1894, 2017.
Kondrashov, D., Chekroun, M. D., and Ghil, M.: Data-adaptive harmonic decomposition and prediction of Arctic sea ice extent, Dynam. Stat. Clim. Syst., 3, 1, https://doi.org/10.1093/climsys/dzy001, 2018.
Krizhevsky, A., Sutskever, I., and Hinton, G. E.: Imagenet classification with deep convolutional neural networks, in: Advances in neural information processing systems, Lake Tahoe, Nevada, USA, 3–6 December 2012, 1097–1105, 2012.
Lai, S., Xu, L., Liu, K., and Zhao, J.: Recurrent convolutional neural networks for text classification, in: Twenty-ninth AAAI conference on artificial intelligence, Austin, Texas, USA, 25–30 January, 2015, 2267–2273, 2015.
LeCun, Y., Bottou, L., Bengio, Y., and Haffner, P.: Gradient-based learning applied to document recognition, Proc. IEEE, 86, 2278–2324, 1998.
Ledley, T. S.: A coupled energy balance climate-sea ice model: Impact of sea ice and leads on climate, J. Geophys. Res.-Atmos., 93, 15919–15932, https://doi.org/10.1029/jd093id12p15919, 1988.
Lee, H., Grosse, R., Ranganath, R., and Ng, A. Y.: Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations, in: Proceedings of the 26th annual international conference on machine learning, Montreal, Canada, 14–18 June, 609–616, 2009.
Lee, J., Im, J., Kim, K., and Quackenbush, L.: Machine Learning Approaches for Estimating Forest Stand Height Using Plot-Based Observations and Airborne LiDAR Data, Forests, 9, 268, 2018.
Lee, S., Im, J., Kim, J., Kim, M., Shin, M., Kim, H., and Quackenbush, L.: Arctic sea ice thickness estimation from CryoSat-2 satellite data using machine learning-based lead detection, Remote Sens., 8, 698,, 2016.
Lee, S., Han, H., Im, J., Jang, E., and Lee, M.-I.: Detection of deterministic and probabilistic convection initiation using Himawari-8 Advanced Himawari Imager data, Atmos. Meas. Tech., 10, 1859–1874, https://doi.org/10.5194/amt-10-1859-2017, 2017.
Lindsay, R. W., Zhang, J., Schweiger, A. J., and Steele, M. A.: Seasonal predictions of ice extent in the Arctic Ocean., J. Geophys. Res.-Oceans., 113, C02023, https://doi.org/10.1029/2007JC004259, 2008.
Liu, T., Im, J., and Quackenbush, L.: A novel transferable individual tree crown delineation model based on fishing net dragging and boundary classification, ISPRS J. Photogramm. Remote Sens., 110, 34–47, 2015.
Liu, T., Abd-Elrahman, A., Jon, M., and Wilhelm, V. L.: Comparing Fully Convolutional Networks, Random Forest, Support Vector Machine, and Patch-based Deep Convolutional Neural Networks for Object-based Wetland Mapping using Images from small Unmanned Aircraft System, GIScience Remote Sens., 55, 243–264, https://doi.org/10.1080/15481603.2018.1426091, 2018.
Mahajan, S., Zhang, R., and Delworth, T. L.: Impact of the Atlantic meridional overturning circulation (AMOC) on Arctic surface air temperature and sea ice variability, J. Climate, 24, 6573–6581, https://doi.org/10.1175/2011jcli4002.1, 2011.
Maslanik, J. A., Fowler, C., Stroeve, J., Drobot, S., Zwally, J., Yi, D., and Emery, W.: A younger, thinner Arctic ice cover: Increased potential for rapid, extensive sea-ice loss, Geophys. Res. Lett., 34, L24501, https://doi.org/10.1029/2007gl032043, 2007.
Melia, N., Haines, K., and Hawkins, E.: Sea ice decline and 21st century trans-Arctic shipping routes, Geophys. Res. Lett., 43, 9720–9728, https://doi.org/10.1002/2016gl069315, 2016.
Moriasi, D. N., Arnold, J. G., Van Liew, M. W., Bingner, R. L., Harmel, R. D., and Veith, T. L.: Model evaluation guidelines for systematic quantification of accuracy in watershed simulations, T. ASABE, 50, 885–900, https://doi.org/10.13031/2013.23153, 2007.
Mutowo, G., Mutanga, O., and Masocha, M.: Including shaded leaves in a sample affects the accuracy of remotely estimating foliar nitrogen, GIScience Remote Sens., 56, 1114–1127, 2019.
Nash, J. E. and Sutcliffe, J. V. : River flow forecasting through conceptual models part I – A discussion of principles, J. Hydrol., 10, 282–290, https://doi.org/10.1016/0022-1694(70)90255-6, 1970.
National Snow and Ice Data Center: All About Glaciers, available at: https://nsidc.org/cryosphere/glaciers, last access: 10 November 2018.
NSIDC: Arctic sea ice summer minimum in 2017 is eighth lowest on record, available at: https://www.carbonbrief.org/arctic-sea-ice-summer-minimum-2017-eighth-lowest-record (last access: 22 March 2020), 2017.
Parkinson, C. L. and Cavalieri, D. J.: A 21 year record of Arctic sea-ice extents and their regional, seasonal and monthly variability and trends, Ann. Glaciol., 34, 441–446, doi.org/10.3189/172756402781817725, 2002.
Parkinson, C. L. and Comiso, J. C.: On the 2012 record low Arctic sea ice cover: Combined impact of preconditioning and an August storm, Geophys. Res. Lett., 40, 1356–1361, https://doi.org/10.1002/grl.50349, 2013.
Prasad, S., Zakharov, I., McGuire, P., Power, D., and Richard, M.: Estimation of sea ice parameters from sea ice model with assimilated ice concentration and SST, The Cryosphere, 12, 3949–3965, https://doi.org/10.5194/tc-12-3949-2018, 2018.
Preller, R. H. and Posey, P. G.: The polar ice prediction system-a sea ice forecasting system, NORDA Report 212, 45 pp., Naval Oceanographic and Atmospheric Research Laboratory, Stennis Space Center, Mississippi, 1989.
Rayner, N. A. A., Parker, D. E., Horton, E. B., Folland, C. K., Alexander, L. V, Rowell, D. P., Kent, E. C., and Kaplan, A.: Global analyses of sea surface temperature, sea ice, and night marine air temperature since the late nineteenth century, J. Geophys. Res.-Atmos., 108, 4407, https://doi.org/10.1029/2002jd002670, 2003.
Ren, S., He, K., Girshick, R., and Sun, J.: Faster r-cnn: Towards real-time object detection with region proposal networks, in Advances in neural information processing systems, Montreal, Quebec, Canada, 7–12 December, 2015, 91–99, 2015.
Rodner, E., Simon, M., Fisher, R. B., and Denzler, J.: Fine-grained recognition in the noisy wild: Sensitivity analysis of convolutional neural networks approaches, arXiv Prepr. arXiv1610.06756, 2016.
Schauer, U., Loeng, H., Rudels, B., Ozhigin, V. K., and Dieck, W.: Atlantic water flow through the Barents and Kara Seas, Deep Sea Res.-Part I, 49, 2281–2298, doi.org/10.1016/s0967-0637(02)00125-5, 2002.
Schweiger, A. J. and Zhang, J.: Accuracy of short-term sea ice drift forecasts using a coupled ice-ocean model, J. Geophys. Res.-Ocean., 120, 7827–7841, https://doi.org/10.1016/s0967-0637(02)00125-5, 2015.
Schweiger, A. J., Zhang, J., Lindsay, R. W., and Steele, M.: Did unusually sunny skies help drive the record sea ice minimum of 2007?, Geophys. Res. Lett., 35, L10503, https://doi.org/10.1029/2008gl033463, 2008.
Screen, J. A. and Simmonds, I.: The central role of diminishing sea ice in recent Arctic temperature amplification, Nature, 464, 1334–1337, https://doi.org/10.1038/nature09051, 2010.
Screen, J. A., Simmonds, I., Deser, C., and Tomas, R.: The atmospheric response to three decades of observed Arctic sea ice loss, J. Climate, 26, 1230–1248, https://doi.org/10.1175/jcli-d-12-00063.1, 2013.
Shimada, K., Kamoshida, T., Itoh, M., Nishino, S., Carmack, E., McLaughlin, F., Zimmermann, S., and Proshutinsky, A.: Pacific Ocean inflow: Influence on catastrophic reduction of sea ice cover in the Arctic Ocean, Geophys. Res. Lett., 33, L08605, https://doi.org/10.1029/2005gl025624, 2006.
Steele, M., Ermold, W., and Zhang, J.: Arctic Ocean surface warming trends over the past 100 years, Geophys. Res. Lett., 35, L02614, https://doi.org/10.1029/2007gl031651, 2008.
Strobl, C., Boulesteix, A. L., Zeileis, A., and Hothorn, T.: Bias in random forest variable importance measures: Illustrations, sources and a solution, BMC bioinformatics, 8, 25, https://doi.org/10.1186/1471-2105-8-25, 2007.
Stroeve, J. C., Serreze, M. C., Holland, M. M., Kay, J. E., Malanik, J., and Barrett, A. P.: The Arctic's rapidly shrinking sea ice cover: a research synthesis, Clim. Change, 110, 1005–1027, https://doi.org/10.1007/s10584-011-0101-1, 2012.
Stroeve, J., Hamilton, L. C., Bitz, C. M., and Blanchard-Wrigglesworth, E.: Predicting September sea ice: Ensemble skill of the SEARCH sea ice outlook 2008–2013, Geophys. Res. Lett., 41, 2411–2418, https://doi.org/10.1002/2014gl059388, 2014.
Stroeve, J., Holland, M. M., Meier, W., Scambos, T., and Serreze, M.: Arctic sea ice decline: Faster than forecast, Geophys. Res. Lett., 34, L09501, https://doi.org/10.1029/2007GL029703, 2007.
Stroeve, J., Serreze, M., Drobot, S., Gearheard, S., Holland, M., Maslanik, J., Meier, W., and Scambos, T.: Arctic sea ice extent plummets in 2007, Eos, Trans. Am. Geophys. Union, 89, 13–14, doi.org/10.1029/2008eo020001, 2008.
Tieleman, T. and Hinton, G.: Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude, COURSERA Neural networks, Mach. Learn., 4, 26–31, 2012.
Tietsche, S., Notz, D., Jungclaus, J. H., and Marotzke, J.: Recovery mechanisms of Arctic summer sea ice, Geophys. Res. Lett., 38, L02707, https://doi.org/10.1029/2010gl045698, 2011.
Timmermann, R., Danilov, S., Schröter, J., Böning, C., Sidorenko, D., and Rollenhagen, K.: Ocean circulation and sea ice distribution in a finite element global sea ice–ocean model, Ocean Model., 27, 114–129, https://doi.org/10.1016/j.ocemod.2008.10.009, 2009.
Trigueros, D. S., Meng, L., and Hartnett, M.: Enhancing convolutional neural networks for face recognition with occlusion maps and batch triplet loss, Image Vision Comput., 79, 99–108, https://doi.org/10.1016/j.imavis.2018.09.011, 2018.
Wang, L., Scott, K. A., Xu, L., and Clausi, D. A.: Sea ice concentration estimation during melt from dual-pol SAR scenes using deep convolutional neural networks: A case study, IEEE Trans. Geosci. Remote Sens., 54, 4524–4533, https://doi.org/10.1109/tgrs.2016.2543660, 2016a.
Wang, L., Yuan, X., Ting, M., and Li, C.: Predicting summer Arctic sea ice concentration intraseasonal variability using a vector autoregressive model, J. Climate., 29, 1529–1543, https://doi.org/10.1175/JCLI-D-15-0313.1, 2016b.
Wang, L., Scott, K., and Clausi, D.: Sea ice concentration estimation during freeze-up from SAR imagery using a convolutional neural network, Remote Sens., 9, 408, https://doi.org/10.3390/rs9050408, 2017.
Wang, L., Yuan, X., and Li, C.: Subseasonal forecast of Arctic sea ice concentration via statistical approaches, Clim. Dynam., 52, 4953–4971, https://doi.org/10.1007/s00382-018-4426-6, 2019.
West, A., and Blockley, E.: Briefing on the 2017 Arctic sea ice melt season and Antarctic sea ice state, available at: https://www.metoffice.gov.uk/binaries/content/assets/metofficegovuk/pdf/research/sea-ice-briefs/sea_ice_season-summary_october2017.pdf (last access: 24 March 2020), 2017.
Wylie, B., Pastick, N., Picotte, J., and Deering C.: Geospatial data mining for digital raster mapping, GIScience Remote Sens., 56, 406–429, 2019.
Yoo, C., Im, J., Park, S., and Quackenbush, L. J.: Estimation of daily maximum and minimum air temperatures in urban landscapes using MODIS time series satellite data, ISPRS J. Photogramm. Remote Sens., 137, 149–162, https://doi.org/10.1016/j.isprsjprs.2018.01.018, 2018.
Yoo, C., Han, D., Im, J., and Bechtel, B.: Comparison between convolutional neural networks and random forest for local climate zone classification in mega urban areas using Landsat images, ISPRS J. Photogramm. Remote Sens., 157, 155–170, 2019.
Yu, L., Zhong, S., Winkler, J. A., Zhou, M., Lenschow, D. H., Li, B., Wang, X., and Yang, Q.: Possible connections of the opposite trends in Arctic and Antarctic sea-ice cover, Sci. Rep., 7, 45804, https://doi.org/10.1038/srep45804, 2017.
Yu, X., Wu, X., Luo, C., and Ren, P.: Deep learning in remote sensing scene classification: a data augmentation ehanced convolutional neural network framework, GIScience Remote Sens., 54, 741–758, 2017.
Yuan, X., Chen, D., Li, C., Wang, L., and Wang, W.: Arctic sea ice seasonal prediction by a linear Markov model, J. Climate, 29, 8151–8173, https://doi.org/10.1175/jcli-d-15-0858.1, 2016.
Zhang, D., Liu, X., Wu, X., Yao, Y., Wu, X., and Chen, Y.: Multiple intra-urban land use simulations and driving factors analysis: a case study in Huicheng, China, GIScience Remote Sens., 56, 282–308, 2019.
Zhang, E., Liu, L., and Huang, L.: Automatically delineating the calving front of Jakobshavn Isbræ from multitemporal TerraSAR-X images: a deep learning approach, The Cryosphere, 13, 1729–1741, https://doi.org/10.5194/tc-13-1729-2019, 2019.
Zhang, J., Lindsay, R., Steele, M., and Schweiger, A.: What drove the dramatic retreat of arctic sea ice during summer 2007?, Geophys. Res. Lett., 35, L11505, https://doi.org/10.1029/2008GL034005, 2008.
Zhang, J., Lindsay, R., Schweiger, A., and Steele, M.: The impact of an intense summer cyclone on 2012 Arctic sea ice retreat, Geophys. Res. Lett., 40, 720–726, https://doi.org/10.1002/grl.50190, 2013.
Zhao, S., Liu, X., Ding, C., Liu, S., Wu, C., and Wu, L.: Mapping rice paddies in complex landscapes with convolutional neural networks and phenological metrics, GIScience Remote Sens., 57, 37–48, 2020.
In this study, we proposed a novel 1-month sea ice concentration (SIC) prediction model with eight predictors using a deep-learning approach, convolutional neural networks (CNNs). The proposed CNN model was evaluated and compared with the two baseline approaches, random-forest and simple-regression models, resulting in better performance. This study also examined SIC predictions for two extreme cases in 2007 and 2012 in detail and the influencing factors through a sensitivity analysis.
In this study, we proposed a novel 1-month sea ice concentration (SIC) prediction model with...