Reconstruction of Ocean Color Data Using Machine Learning Techniques in Polar Regions: Focusing on Off Cape Hallett, Ross Sea

Remote Sensing - Tập 11 Số 11 - Trang 1366
Jinku Park1, Jeong‐Hoon Kim2, Hyun‐Cheol Kim2, Bong-Kuk Kim3, Dukwon Bae1, Young‐Heon Jo1, Naeun Jo1, Sang Heon Lee1
1Department of Oceanography, Pusan National University, Geumjeong-Gu, Busan 46241, Korea
2Korea Polar Research Institute, Incheon 21990, Korea
3Underwater Survey Technology 21, Incheon 21999, Korea

Tóm tắt

The most problematic issue in the ocean color application is the presence of heavy clouds, especially in polar regions. For that reason, the demand for the ocean color application in polar regions is increased. As a way to overcome such issues, we conducted the reconstruction of the chlorophyll-a concentration (CHL) data using the machine learning-based models to raise the usability of CHL data. This analysis was first conducted on a regional scale and focused on the biologically-valued Cape Hallett, Ross Sea, Antarctica. Environmental factors and geographical information associated with phytoplankton dynamics were considered as predictors for the CHL reconstruction, which were obtained from cloud-free microwave and reanalysis data. As the machine learning models used in the present study, the ensemble-based models such as Random forest (RF) and Extremely randomized tree (ET) were selected with 10-fold cross-validation. As a result, both CHL reconstructions from the two models showed significant agreement with the standard satellite-derived CHL data. In addition, the reconstructed CHLs were close to the actual CHL value even where it was not observed by the satellites. However, there is a slight difference between the CHL reconstruction results from the RF and the ET, which is likely caused by the difference in the contribution of each predictor. In addition, we examined the variable importance for the CHL reconstruction quantitatively. As such, the sea surface and atmospheric temperature, and the photosynthetically available radiation have high contributions to the model developments. Mostly, geographic information appears to have a lower contribution relative to environmental predictors. Lastly, we estimated the partial dependences for the predictors for further study on the variable contribution and investigated the contributions to the CHL reconstruction with changes in the predictors.

Từ khóa


Tài liệu tham khảo

Maritorena, 1998, Ocean color chlorophyll algorithms for SeaWiFS, J. Geophys. Res. Ocean., 103, 24937, 10.1029/98JC02160

Gower, 2014, A review of ocean color remote sensing methods and statistical techniques for the detection, mapping and analysis of phytoplankton blooms in coastal and open oceans, Prog. Oceanogr., 123, 23

Klemas, 2011, Remote Sensing Techniques for Studying Coastal Ecosystems: An Overview, J. Coast. Res., 27, 2

Wilson, 2011, The rocky road from research to operations for satellite ocean-colour data in fishery management, ICES J. Mar. Sci., 68, 677, 10.1093/icesjms/fsq168

Shen, 2012, Satellite remote sensing of harmful algal blooms (HABs) and a potential synthesized framework, Sensors (Switzerland), 12, 7778, 10.3390/s120607778

Nechad, 2011, Reconstruction of MODIS total suspended matter time series maps by DINEOF and validation with autonomous platform data, Ocean Dyn., 61, 1205, 10.1007/s10236-011-0425-4

Liu, X., and Wang, M. (2019). Filling the Gaps of Missing Data in the Merged VIIRS SNPP/NOAA-20 Ocean Color Product Using the DINEOF Method. Remote Sens., 11.

Chen, 2019, Improving ocean color data coverage through machine learning, Remote Sens. Environ., 222, 286, 10.1016/j.rse.2018.12.023

Jouini, 2013, Reconstruction of satellite chlorophyll images under heavy cloud coverage using a neural classification method, Remote Sens. Environ., 131, 232, 10.1016/j.rse.2012.11.025

Jo, 2018, Chlorophyll Concentration Derived from Microwave Remote Sensing Measurements USING Artificial Neural Network Algorithm, J. Mar. Sci, 26, 102

Arrigo, 2004, Annual changes in sea-ice, chlorophyll a, and primary production in the Ross Sea, Antarctica, Deep. Res. Part II Top. Stud. Oceanogr., 51, 117, 10.1016/j.dsr2.2003.04.003

Marrari, 2006, Validation of SeaWiFS chlorophyll a concentrations in the Southern Ocean: A revisit, Remote Sens. Environ., 105, 367, 10.1016/j.rse.2006.07.008

Alvera-Azcárate, A., Barth, A., Beckers, J.M., and Weisberg, R.H. (2007). Multivariate reconstruction of missing data in sea surface temperature, chlorophyll, and wind satellite fields. J. Geophys. Res. Ocean., 112.

Barth, 2009, Enhancing temporal correlations in EOF expansions for the reconstruction of missing data using DINEOF, Ocean Sci., 5, 475, 10.5194/os-5-475-2009

Ruddick, 2010, Cloud filling of ocean colour and sea surface temperature remote sensing products over the Southern North Sea by the Data Interpolating Empirical Orthogonal Functions methodology, J. Sea Res., 65, 114

Volpe, 2012, Seasonal to interannual phytoplankton response to physical processes in the Mediterranean Sea from satellite observations, Remote Sens. Environ., 117, 223, 10.1016/j.rse.2011.09.020

Wang, 2014, Reconstruction of satellite chlorophyll-a data using a modified DINEOF method: A case study in the Bohai and Yellow seas, China, Int. J. Remote Sens., 35, 204, 10.1080/01431161.2013.866290

Zhao, 2012, Cloud-free sea surface temperature and colour reconstruction for the gulf of mexico: 2003–2009, Remote Sens. Lett., 3, 697, 10.1080/01431161.2012.666638

Vanhellemont, 2015, Analysis of high frequency geostationary ocean colour data using DINEOF, Estuar. Coast. Shelf Sci., 159, 28, 10.1016/j.ecss.2015.03.026

Dreano, 2015, Filtering remotely sensed chlorophyll concentrations in the Red Sea using a space-time covariance model and a Kalman filter, Spat. Stat., 13, 1, 10.1016/j.spasta.2015.04.002

Hilborn, A., and Costa, M. (2018). Applications of DINEOF to Satellite-Derived Chlorophyll-a from a Productive Coastal Region. Remote Sens., 10.

Jayaram, 2018, Analysis of gap-free chlorophyll-a data from MODIS in Arabian Sea, reconstructed using DINEOF, Int. J. Remote Sens., 39, 7506, 10.1080/01431161.2018.1471540

Liu, 2014, Spatio-temporal stability and abnormality of chlorophyll-a in the northern south china sea during 2002-2012 from MODIS images using wavelet analysis, Cont. Shelf Res., 75, 15, 10.1016/j.csr.2013.12.010

Liu, 2016, Analysis of ocean diurnal variations from the Korean Geostationary Ocean Color Imager measurements using the DINEOF method, Estuar. Coast. Shelf Sci., 180, 230, 10.1016/j.ecss.2016.07.006

Liu, 2018, Gap filling of missing data for VIIRS global ocean color products using the DINEOF Method, IEEE Trans. Geosci. Remote Sens., 56, 4464, 10.1109/TGRS.2018.2820423

Miles, 2010, Temporal and spatial variability of Chl-a and SST on the South Atlantic Bight: Revisiting with cloud-free reconstructions of MODIS satellite imagery, Cont. Shelf Res., 30, 1951, 10.1016/j.csr.2010.08.016

Krasnopolsky, V., Nadiga, S., Mehra, A., Bayler, E., and Behringer, D. (2016). Neural networks technique for filling gaps in satellite measurements: Application to ocean color observations. Comput. Intell. Neurosci., 2016.

Guisan, 2000, Predictive habitat distribution models in ecology, Ecol. Modell., 135, 147, 10.1016/S0304-3800(00)00354-9

Jane, E., Catherine, H.G., Robert, P.A., Miroslav, D., Simon, F., Antoine, G., Robert, J.H., Falk, H., John, R.L., and Anthony, L. (2006). Novel methods improve prediction of species’ distributions from occurrence data. Ecography (Cop.)., 29.

Radtke, 2017, Spatial prediction of demersal fish diversity in the Baltic Sea: Comparison of machine learning and regression-based techniques, ICES J. Mar. Sci., 74, 102, 10.1093/icesjms/fsw136

Beckers, 2003, EOF calculations and data filling from incomplete oceanographic datasets, J. Atmos. Ocean. Technol., 20, 1839, 10.1175/1520-0426(2003)020<1839:ECADFF>2.0.CO;2

Smith, 2001, The influence of phytoplankton assemblage composition on biogeochemical characteristics and cycles in the southern Ross Sea, Antarctica, Deep. Res. Part I Oceanogr. Res. Pap., 48, 137, 10.1016/S0967-0637(00)00045-5

Boyd, 2002, Environmental factors controlling phytoplankton processes in the Southern Ocean, J. Phycol., 38, 844, 10.1046/j.1529-8817.2002.t01-1-01203.x

Jones, 2017, The influence of short-term events on the hydrographic and biological structure of the southwestern Ross Sea, J. Mar. Syst., 166, 184, 10.1016/j.jmarsys.2016.09.006

Peloquin, 2007, Phytoplankton blooms in the Ross Sea, Antarctica: Interannual variability in magnitude, temporal patterns, and composition, J. Geophys. Res. Ocean., 112, 1, 10.1029/2006JC003816

DeLizo, 2017, Temporal progression of photosynthetic-strategy in phytoplankton in the Ross Sea, Antarctica, J. Mar. Syst., 166, 87, 10.1016/j.jmarsys.2016.08.014

Sedwick, 2011, Early season depletion of dissolved iron in the Ross Sea polynya: Implications for iron dynamics on the Antarctic continental shelf, J. Geophys. Res. Ocean., 116, 1, 10.1029/2010JC006553

Lynch, 2014, First global census of the Adélie Penguin, Auk Ornithol. Adv., 131, 457

Emslie, S.D., McKenzie, A., and Patterson, W.P. (2018). The rise and fall of an ancient adélie penguin ‘supercolony’ at cape adare, antarctica. R. Soc. Open Sci., 5.

Weber, 1986, The variance spectra of phytoplankton, krill and water temperature in the Antarctic Ocean south of Africa, Deep Sea Res. Part A, Oceanogr. Res. Pap., 33, 1327, 10.1016/0198-0149(86)90039-7

Kaufman, 2014, Biogeochemical variability in the southern Ross Sea as observed by a glider deployment, Deep. Res. Part I Oceanogr. Res. Pap., 92, 93, 10.1016/j.dsr.2014.06.011

Lyver, 2011, Intra-seasonal variation in foraging behavior among Adélie penguins (Pygocelis adeliae) breeding at Cape Hallett, Ross Sea, Antarctica, Polar Biol., 34, 49, 10.1007/s00300-010-0858-0

Reynolds, 2007, Daily high-resolution-blended analyses for sea surface temperature, J. Clim., 20, 5473, 10.1175/2007JCLI1824.1

EUMETSAT Ocean and Sea Ice Satelitte Application Facility (2019, June 05). Available online: http://osisaf.met.no.

Comiso, 1997, Passive microwave algorithms for sea ice concentration: A comparison of two techniques, Remote Sens. Environ., 60, 357, 10.1016/S0034-4257(96)00220-9

Dee, 2011, The ERA-Interim reanalysis: Configuration and performance of the data assimilation system, Q. J. R. Meteorol. Soc., 137, 553, 10.1002/qj.828

Fogt, 2012, The characteristic variability and connection to the underlying synoptic activity of the Amundsen-Bellingshausen Seas Low, J. Geophys. Res. Atmos., 117, 1, 10.1029/2011JD017337

Coggins, 2014, Synoptic climatology of the Ross Ice Shelf and Ross Sea region of Antarctica: K-means clustering and validation, Int. J. Climatol., 34, 2330, 10.1002/joc.3842

Dale, 2017, Atmospheric forcing of sea ice anomalies in the Ross Sea polynya region, Cryosphere, 11, 267, 10.5194/tc-11-267-2017

Buchlin, 2013, Evaluation of the antarctic surface wind climate from ERA reanalyses and RACMO2/ANT simulations based on automatic weather stations, Clim. Dyn., 40, 353, 10.1007/s00382-012-1396-y

(2009). Gebco Gridded Global Bathymetry Data, British Oceanographic Data Centre.

Becker, 2009, Global Bathymetry and Elevation Data at 30 Arc Seconds Resolution: SRTM30_PLUS, Mar. Geod., 32, 355, 10.1080/01490410903297766

GlobColour data (http://globcolour.info) used in this study has been developed, validated, and distributed by ACRI-ST, France.

Saba, 2011, An evaluation of ocean color model estimates of marine primary productivity in coastal and pelagic regions across the globe, Biogeosciences, 8, 489, 10.5194/bg-8-489-2011

Parson, T.R., Maita, Y., and Lalli, C.M. (2013). A Manual of Chemical & Biological Methods for Seawater Analysis, Pergamon Press.

Morales Maqueda, M.A., Willmott, A.J., and Biggs, N.R.T. (2004). Polynya dynamics: A review of observations and modeling. Rev. Geophys., 42.

Nihashi, 2001, Relationship between ice decay and solar heating through open water in the Antarctic sea ice zone, J. Geophys. Res. Ocean., 106, 16767, 10.1029/2000JC000399

Coale, 2003, Phytoplankton growth and biological response to iron and zinc addition in the Ross Sea and Antarctic Circumpolar Current along 170°W, Deep Sea Res. Part II Top. Stud. Oceanogr., 50, 635, 10.1016/S0967-0645(02)00588-X

Sedwick, P.N., Garcia, N.S., Riseman, S.F., Marsay, C.M., and DiTullio, G.R. (2007). Evidence for high iron requirements of colonial Phaeocystis antarctica at low irradiance. Phaeocystis Major Link Biogeochem. Cycl. Clim. Elem., 83–97.

McGillicuddy, 2015, Iron supply and demand in an Antarctic shelf ecosystem, Geophys. Res. Lett., 42, 8088, 10.1002/2015GL065727

Reddy, T.E., and Arrigo, K.R. (2006). Constraints on the extent of the Ross Sea phytoplankton bloom. J. Geophys. Res. Ocean., 111.

Arrigo, 1994, Spring phytoplankton production in the western Ross Sea, Science, 266, 261, 10.1126/science.266.5183.261

Mangoni, 2017, Phytoplankton blooms during austral summer in the Ross Sea, Antarctica: Driving factors and trophic implications, PLoS One, 12, 1, 10.1371/journal.pone.0176033

Kaufman, 2017, Climate change impacts on southern Ross Sea phytoplankton composition, productivity, and export, J. Geophys. Res. Ocean., 122, 2339, 10.1002/2016JC012514

Smith, 2007, Trophic interactions within the Ross Sea continental shelf ecosystem, Philos. Trans. R. Soc. B Biol. Sci., 362, 95, 10.1098/rstb.2006.1956

Smith, 2015, Vertical mixing, critical depths, and phytoplankton growth in the Ross Sea, ICES J. Mar. Sci., 72, 1952, 10.1093/icesjms/fsu234

2013, Bilinear interpolation theorems and applications, J. Funct. Anal., 265, 185, 10.1016/j.jfa.2013.05.001

Khoshgoftaar, 2011, Comparing boosting and bagging techniques with noisy and imbalanced data, IEEE Trans. Syst. Man Cybern. Part A Syst. Hum., 41, 552, 10.1109/TSMCA.2010.2084081

Noi, P.T., and Kappas, M. (2018). Comparison of random forest, k-nearest neighbor, and support vector machine classifiers for land cover classification using sentinel-2 imagery. Sensors (Switzerland), 18.

He, 2008, Learning from imbalanced data, Trans. Knowl. Data Eng., 21, 1263

Abraham, 2013, A Review of Class Imbalance Problem, J. Netw. Innov. Comput., 1, 332

Breiman, 2001, Random Forests, Mach. Learn., 45, 5, 10.1023/A:1010933404324

Geurts, 2006, Extremely randomized trees, Mach. Learn., 63, 3, 10.1007/s10994-006-6226-1

James, G., Witten, D., Hastie, T., and Tibshirani, R. (2013). An Introduction to Statistical Learning, Springer.

Breiman, 1996, Bagging predictors, Mach. Learn., 24, 123, 10.1007/BF00058655

Su, 2018, Retrieving Temperature Anomaly in the Global Subsurface and Deeper Ocean From Satellite Observations, J. Geophys. Res. Ocean., 123, 399, 10.1002/2017JC013631

Pinto, 2018, Hierarchical brain tumour segmentation using extremely randomized trees, Pattern Recognit., 82, 105, 10.1016/j.patcog.2018.05.006

Liaw, 2002, Classification and regression by randomForest, R News, 2, 18

Du, 2015, Random Forest and Rotation Forest for fully polarized SAR image classification using polarimetric and spatial features, ISPRS J. Photogramm. Remote Sens., 105, 38, 10.1016/j.isprsjprs.2015.03.002

Beckers, 2006, DINEOF reconstruction of clouded images including error maps application to the Sea-Surface Temperature around Corsican Island, Ocean Sci., 2, 183, 10.5194/os-2-183-2006

Ping, B., Su, F., and Meng, Y. (2016). An improved DINEOF algorithm for filling missing values in spatio-temporal sea surface temperature data. PLoS One, 11.

Mollineda, 2012, On the effectiveness of preprocessing methods when dealing with different levels of class imbalance, Knowledge-Based Syst., 25, 13, 10.1016/j.knosys.2011.06.013

Lu, 2011, Learning from imbalanced data sets with a Min-Max modular support vector machine, Front. Electr. Electron. Eng. China, 6, 56, 10.1007/s11460-011-0127-1

Smith, 2010, Phytoplankton photosynthetic pigments in the Ross Sea: Patterns and relationships among functional groups, J. Mar. Syst., 82, 177, 10.1016/j.jmarsys.2010.04.014

Arrigo, 2003, A coupled ocean-ecosystem model of the Ross Sea: 2. Iron regulation of phytoplankton taxonomic variability and primary production, J. Geophys. Res., 108, 3231, 10.1029/2001JC000856

Garrison, 2003, Development of sea ice microbial communities during autumn ice formation in the Ross Sea, Mar. Ecol. Prog. Ser., 259, 1, 10.3354/meps259001

Ji, 2010, Marine plankton phenology and life history in a changing climate: Current research and future directions, J. Plankton Res., 32, 1355, 10.1093/plankt/fbq062

Marchese, C., Albouy, C., Tremblay, J.-É., Dumont, D., D’Ortenzio, F., Vissault, S., and Bélanger, S. (2017). Changes in phytoplankton bloom phenology over the North Water (NOW) polynya: a response to changing environmental conditions. Polar Biol., 40.

Guinder, V., and Molinero, J. (2014). Climate Change Effects on Marine Phytoplankton. Mar. Ecol. a Chang. World, 68–90.

Hales, B., and Takahashi, T. (2004). High-resolution biogeochemical investigation of the Ross Sea, Antarctica, during the AESOPS (U. S. JGOFS) Program. Global Biogeochem. Cycles, 18.

Thông tin
Thông tin xuất bản

Remote Sensing

Tập 11 Số 11

1366

Thông tin tác giả