Reconstruction of regional mean sea level anomalies from tide gauges using neural networks

[1] The 20th century regional and global sea level variations are estimated based on long-term tide gauge records. For this the neural network technique is utilized that connects the coastal sea level with the regional and global mean via a nonlinear empirical relationship. Two major difficulties are overcome this way: the vertical movement of tide gauges over time and the problem of what weighting function to choose for each individual tide gauge record. Neural networks are also used to fill data gaps in the tide gauge records, which is a prerequisite for our analysis technique. A suite of different gap-filling strategies is tested which provides information about stability and variance of the results. The global mean sea level for the period January 1900 to December 2006 is estimated to rise at a rate of 1.56 ± 0.25 mm/yr which is reasonably consistent with earlier estimates, but we do not find significant acceleration. The regional mean sea level of the single ocean basins show mixed long-term behavior. While most of the basins show a sea level rise of varying strength there is an indication for a mean sea level fall in the southern Indian Ocean. Also for the the tropical Indian and the South Atlantic no significant trend can be detected. Nevertheless, the South Atlantic as well as the tropical Atlantic are the only basins that show significant acceleration. On shorter timescales, but longer than the annual cycle, the basins sea level are dominated by oscillations with periods of about 50–75 years and of about 25 years. Consequently, we find high (lagged) correlations between the single basins.

[1]  Alex J. Cannon,et al.  Robust nonlinear canonical correlation analysis: application to seasonal climate forecasting , 2008 .

[2]  Tilo Schöne,et al.  IGS Tide Gauge Benchmark Monitoring Pilot Project (TIGA): scientific benefits , 2009 .

[3]  M. Bouin,et al.  Rates of sea‐level change over the past century in a geocentric reference frame , 2009 .

[4]  P. Werbos,et al.  Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[5]  William W. Hsieh,et al.  Applying Neural Network Models to Prediction and Data Analysis in Meteorology and Oceanography. , 1998 .

[6]  Casimir C. Klimasauskas.  Neural networks for , 1996 .

[7]  Philip L. Woodworth,et al.  R. Player. . The Permanent Service for Mean Sea Level: An update to the 21st century. , 2003 .

[8]  J. Gregory,et al.  Coastal and global averaged sea level rise for 1950 to 2000 , 2005 .

[9]  G. Milne.  Space-geodetic constraints on glacial isostatic adjustment , 2001 .

[10]  S. Jevrejeva,et al.  Nonlinear trends and multiyear cycles in sea level records , 2006 .

[11]  R. Ponte.  A preliminary model study of the large‐scale seasonal cycle in bottom pressure over the global ocean , 1999 .

[12]  Sylvie Thiria,et al.  Applying artificial neural network methodology to ocean color remote sensing , 1999 .

[13]  C. Wunsch,et al.  How well does a 1/4° global circulation model simulate large-scale oceanic observations? , 1996 .

[14]  Alberto M. Mestas-Nuñez,et al.  Rotated Global Modes of Non-ENSO Sea Surface Temperature Variability , 1999 .

[15]  S. Holgate.  On the decadal rates of sea level change during the twentieth century , 2007 .

[16]  Duncan J. Wingham,et al.  Changes in Sea Level , 2001 .

[17]  Jeff Knight,et al.  Decadal to multidecadal variability and the climate change background , 2007 .

[18]  Z. Martinec,et al.  An Estimate of Global Mean Sea-level Rise Inferred from Tide-gauge Measurements Using Glacial-isostatic Models Consistent with the Relative Sea-level Record , 2007 .

[19]  N. White,et al.  A 20th century acceleration in global sea‐level rise , 2006 .

[20]  Sue Ellen Haupt,et al.  Artificial Intelligence Methods in the Environmental Sciences , 2008 .

[21]  John P. Burrows,et al.  Ozone profile retrieval from Global Ozone Monitoring Experiment (GOME) data using a neural network approach (Neural Network Ozone Retrieval System (NNORSY)) , 2003 .

[22]  K. Lambeck,et al.  The Earth's Mantle: The Viscosity of the Mantle: Evidence from Analyses of Glacial-Rebound Phenomena , 1998 .

[23]  J. Wallace,et al.  A Pacific Interdecadal Climate Oscillation with Impacts on Salmon Production , 1997 .

[24]  A H Dodson,et al.  Using continuous GPS and absolute gravity to separate vertical land movements and changes in sea-level at tide-gauges in the UK , 2006, Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[25]  S. Holgate,et al.  Evidence for enhanced coastal sea level rise during the 1990s , 2004 .

[26]  Charles Leave.  Neural Networks: Algorithms, Applications and Programming Techniques , 1992 .

[27]  Jianping Li,et al.  The relationship between the summer precipitation in the Yangtze River valley and the boreal spring Southern Hemisphere annular mode , 2003 .

[28]  Dong-Sheng Jeng,et al.  Application of artificial neural networks in tide-forecasting , 2002 .

[29]  Kimio Hanawa,et al.  Observations: Oceanic Climate Change and Sea Level , 2007 .

[30]  The surface of the ice-age Earth. , 1976, Science.

[31]  Manfred Wenzel,et al.  Neural Networks, a tool for prediction ? , 1993 .

[32]  K. Lambeck,et al.  Estimates of the Regional Distribution of Sea Level Rise over the 1950–2000 Period , 2004 .

[33]  Abdelhakim Artiba,et al.  Artificial Intelligence Methods , 1998 .

[34]  M. Bouin,et al.  Geocentric sea-level trend estimates from GPS analyses at relevant tide gauges world-wide , 2007 .

[35]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[36]  Aslak Grinsted,et al.  Recent global sea level acceleration started over 200 years ago? , 2008 .

[37]  Anny Cazenave,et al.  Is coastal mean sea level rising faster than the global mean? A comparison between tide gauges and satellite altimetry over 1993–2007 , 2009 .

[38]  J. Johansson,et al.  Space-Geodetic Constraints on Glacial Isostatic Adjustment in Fennoscandia , 2001, Science.

[39]  W. Peltier.  GLOBAL GLACIAL ISOSTASY AND THE SURFACE OF THE ICE-AGE EARTH: The ICE-5G (VM2) Model and GRACE , 2004 .

[40]  S. Jevrejeva,et al.  The Permanent Service for Mean Sea Level , 2005 .

[41]  William W. Hsieh,et al.  Forecasting regional sea surface temperatures in the tropical Pacific by neural network models, with wind stress and sea level pressure as predictors , 1998 .

[42]  C. Hughes,et al.  Propagation of signals in basin‐scale ocean bottom pressure from a barotropic model , 2006 .

[43]  C. T. Butler,et al.  Ocean surface wind retrievals from special sensor microwave imager data with neural networks , 1994 .

[44]  Jens Schröter,et al.  The Global Ocean Mass Budget in 1993-2003 Estimated from Sea Level Change , 2007 .

[45]  J. Mitrovica.  Recent controversies in predicting post-glacial sea-level change , 2003 .