王智豪;柯长青;

• 1:南京大学地理与海洋科学学院

摘要(Abstract)：

融池对海冰融化速率估算具有重要作用。基于Sentinel-2影像，选择可见光(波段2、波段3、波段4)和近红外(波段8)作为特征波段，采用两种特征组合方式(波段2/3/4反射率、波段2/3/4反射率与波段2/3/4/8反射率差值归一化值),分别训练多层神经网络(multi-layer neural network, MNN),进行海冰、开阔水域、亮融池、暗融池识别。结果表明，基于可见光与归一化值MNN识别效果更佳，总体识别精度达到88.0%,其中亮融池生产者精度和用户精度分别为77.6%和77.1%,暗融池的生产者精度和用户精度分别为55.2%和96.1%。波段反射率差值归一化处理可增大地物间区分度，提高融池识别精度。与其他算法相比，应用MNN可实现融池准确识别，为海冰融化速率估算提供有效参考。

关键词(KeyWords)： 海冰融池识别;反射率差值归一化;多层神经网络;Sentinel-2;波弗特海

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金项目(41976212、41901129)

作者(Authors): 王智豪;柯长青;

参考文献(References)：

• [1] PEROVICH D K,GRENFELL T C,LIGHT B,et al.Seasonal evolution of the albedo of multiyear Arctic sea ice[J].Journal of geophysical research oceans,2002,107(C10):201-203.
• [2] PEROVICH D K,LIGHT B,EICKEN H,et al.Increasing solar heating of the Arctic Ocean and adjacent seas,1979-2005:attribution and role in the ice albedo feedback[J].Geophysical research letters,2007,34(19):255-268.
• [3] NICOLAUS M,HUDSON S R,GERLAND S,et al.A modern concept for autonomous and continuous measurements of spectral albedo and transmittance of sea ice[J].Cold regions science and technology,2010,62(1):14-28.
• [4] 王明锋，苏洁，李涛，等.基于无人机观测的北极冰面融池及冰面粗糙度信息提取方法研究[J].极地研究，2017,29(4):436-445.
• [5] HUNKE E C,HEBERT D A,LECOMTE O.Level-ice melt ponds in the Los Alamos sea ice model,CICE[J].Ocean modelling,2013,71(Complete):26-42.
• [6] TUCKER W B,GOW A J,MEESE D A,et al.Physical characteristics of summer sea ice across the Arctic Ocean[J].Journal of geophysical research oceans,1999,104(C1):1489-1504.
• [7] YACKEL J J,BAEBER D G,HANESIAK J M.Melt ponds on sea ice in the Canadian Archipelago:1.variability in morphological and radiative properties[J].Journal of geophysical research,2000,105(C9):22049.
• [8] MAEKUS T,CAVALIERI D J,TSCHUDI M A,et al.Comparison of aerial video and Landsat 7 data over ponded sea ice[J].Remote sensing of environment,2003,86(4):458-469.
• [9] HOWELL S E L,YACKEL J J,ABREU R D,et al.On the utility of SeaWinds/QuikSCAT data for the estimation of the thermodynamic state of first-year sea ice[J].IEEE transactions on geoscience and remote sensing,2005,43(6):1338-1350.
• [10] TSCHUDI M A,MASLANIK J A,PEROVICH D K.Derivation of melt pond coverage on Arctic sea ice using MODIS observations [J].Remote sensing of environment,2008,112(5):2605-2614.
• [11] 张干，苏洁.利用MODIS数据反演融池覆盖率及与航拍影像的比对[C]//第28届中国气象学会年会.厦门：[出版者不详],2011:186.
• [12] R?SEL A,KALESCHKE L,BIRNBAUM G.Melt ponds on Arctic sea ice determined from MODIS satellite data using an artificial neural network[J].The cryosphere,2012,6(2):431-446.
• [13] ZEGE E,MALINKA A,KATSEV I,et al.Algorithm to retrieve the melt pond fraction and the spectral albedo of Arctic summer ice from satellite optical data[J].Remote sensing of environment,2015,163:153-164.
• [14] YACKEL J J,NANDAN V,MAHMUD M,et al.A spectral mixture analysis approach to quantify Arctic first-year sea ice melt pond fraction using QuickBird and MODIS reflectance data[J].Remote sensing of environment,2018,204:704-716.
• [15] PEROVICH D K,TUCKER W B,LIGETT K A.Aerial observations of the evolution of ice surface conditions during summer[J].Journal of geophysical research oceans,2002,107(C10):14-24.
• [16] PENG L,LI Z,CHENG B,et al.Sea ice surface features in Arctic summer 2008:aerial observations[J].Remote sensing of environment,2010,114(4):693-699.
• [17] LEE S,STROEVE J,TSAMADOS M,et al.Machine learning approaches to retrieve pan-Arctic melt ponds from visible satellite imagery[J].Remote sensing of environment,2020,247:911-919.
• [18] SCHARIEN R K,SEGAL R,NASONOVA S,et al.Winter Sentinel-1 backscatter as a predictor of spring Arctic sea ice melt pond fraction[J].Geophysical research letters,2017,44(24):262-270.
• [19] WARREN S G.Optical properties of snow[J].Reviews of geophysics,1982,20(1):67-89.
• [20] 张蕊.北极夏季海冰表面融池形态分析[D].大连：大连理工大学，2010.
• [21] R?SEL A,KALESCHKE L.Comparison of different retrieval techniques for melt ponds on Arctic sea ice from Landsat and MODIS satellite data[J].Annals of glaciology,2011,52(57):185-191.
• [22] WANG M,SU J,LANDY J,et al.A new algorithm for sea ice melt pond fraction estimation from high resolution optical satellite imagery[J].Journal of geophysical research oceans,2020,125(10):157-166.
• [23] HYANGSUM H,JUNGHO I,MIAE K,et al.Retrieval of melt ponds on Arctic multiyear sea ice in summer from TerraSAR-X dual-polarization data using machine learning approaches:a case study in the Chukchi Sea with mid-incidence angle data[J].Remote sensing,2016,8(1):57.
• [24] QIN Y I,SU J,WANG M F.Melt pond retrieval based on the LinearPolar algorithm using Landsat data[J].Remote sensing,2021,13(22):4674.