Abstract

We present a neural network methodology for clustering large data sets into pertinent groups. We applied this methodology to analyze the phytoplankton absorption spectra data gathered by the Laboratoire d'Océanographie de Villefranche. We first partitioned the data into 100 classes by means of a self-organizing map (SOM) and then we clustered these classes into 6 significant groups. We focused our analysis on three POMME campaigns. We were able to interpret the absorption spectra of the samples taken in the first oceanic optical layer during these campaigns, in terms of seasonal variability. We showed that spectra from the PROSOPE Mediterranean campaign, which was conducted in a different region, were strongly similar to those of the POMME-3 campaign. This analysis led us to propose regional empirical relationships, linking phytoplankton absorption spectra to pigment concentrations, that perform better than the previously derived overall relation.

© 2007 Optical Society of America

Full Article  |  PDF Article

References

  • View by:
  • |
  • |
  • |

  1. M. Saraceno, C. Provost, and M. Lebbah, "Biophysical regions identification using an artificial neuronal network: a case study in the South Western Atlantic," Adv. Space Res. 37, 793-805 (2006).
    [CrossRef]
  2. Y. Liu and R. H. Weisberg, "Patterns of ocean current variability on the West Florida Shelf using the self-organizing map," J. Geophys. Res. 110, C06003, doi: (2005).
    [CrossRef]
  3. Y. Liu, R. H. Weisberg, and R. He, "Sea surface temperature patterns on the West Florida Shelf using growing hierarchical self-organizing maps," J. Atmos. Oceanic Technol. 23, 325-338 (2006).
    [CrossRef]
  4. A. Chazottes, A. Bricaud, M. Crépon, and S. Thiria, "Statistical analysis of a database of absorption spectra of phytoplankton and pigment concentrations using self-organizing maps," Appl. Opt. 45, 8102-8115 (2006).
    [CrossRef] [PubMed]
  5. T. Kohonen, Self-Organizing Maps (Springer Verlag, 1984).
  6. A. Bricaud, M. Babin, A. Morel, and H. Claustre, "Variability in the chlorophyll-specific absorption coefficients of natural phytoplankton: analysis and parameterization," J. Geophys. Res. 100, 13331-13332 (1995).
    [CrossRef]
  7. A. Bricaud, A. Morel, M. Babin, K. Allali, and H. Claustre, "Variations of light absorption by suspended particles with chlorophyll a concentration in oceanic (case 1) waters: analysis and implications for bio-optical models," J. Geophys. Res. 103, 31033-31044 (1998).
    [CrossRef]
  8. F. Vidussi, H. Claustre, J. Bustillos-Guzman, C. Cailliau, and J. C. Marty, "Rapid HPLC method for determination of phytoplankton chemotaxonomic pigments: separation of chlorophyll a from divinyl-chlorophyll-a, and zeaxanthin from lutein," J. Plankton Res. 18, 2377-2382 (1996).
    [CrossRef]
  9. A. Morel and S. Maritorena, "Bio-optical properties of oceanic waters: a reappraisal," J. Geophys. Res. 106, 7763-7780 (2001).
    [CrossRef]
  10. A. Niang, L. Gross, S. Thiria, F. Badran, and C. Moulin, "Automatic neural classification of ocean colour reflectance spectra at the top of the atmosphere with introduction of expert knowledge," Remote Sens. Environ. 86, 257-271 (2003).
    [CrossRef]
  11. Y. Liu, R. H. Weisberg, and C. N. K. Mooers, "Performance evaluation of the self-organizing map for feature extraction," J. Geophys. Res. 111, C05018, doi: (2006).
    [CrossRef]
  12. G. Dreyfus, Neural Networks: Methodology and Applications (Springer-Verlag, 2005).
  13. L. Mémery, G. Reverdin, S. Paillet, and A. Oschlies, "Introduction to the POMME special section: thermocline ventilation and biogeochemical tracer distribution in the northeast Atlantic Ocean and impact of mesoscale dynamics," J. Geophys. Res. 110, C07S01, doi: (2005).
    [CrossRef]
  14. A. Bricaud, H. Claustre, J. Ras, and K. Oubelhkeir, "Natural variability of phytoplanktonic absorption in oceanic waters: influence of the size structure of algal populations," J. Geophys. Res. 109, C11010, doi: (2004).
    [CrossRef]
  15. M. Levy, Y. Lehahn, J.-M. Andre, L. Mémery, H. Loisel and E. Heifetz, "Production regimes in the Northeast Atlantic: a study based on Sea-viewing Wide Field-of-view Sensor (SeaWiFS) chlorophyll and ocean general circulation model mixed layer depth," J. Geophys. Res. 110, C07S10, doi: (2005).
    [CrossRef]
  16. A. Paci, G. Caniaux, M. Gavart, H. Giordani, M. Lévy, L. Prieur, and G. Reverdin, "A high-resolution simulation of the ocean during the POMME experiment: simulation results and comparison with observations," J. Geophys. Res. 110, C07S09, doi: (2005).
    [CrossRef]
  17. S. Alvain, C. Moulin, Y. Dandonneau, H. Loisel, and F.-M. Bréon, "A species-dependent bio-optical model of case I waters for global ocean color processing," Deep-Sea Res. 153, 917-925 (2006).

2006 (5)

Y. Liu, R. H. Weisberg, and C. N. K. Mooers, "Performance evaluation of the self-organizing map for feature extraction," J. Geophys. Res. 111, C05018, doi: (2006).
[CrossRef]

S. Alvain, C. Moulin, Y. Dandonneau, H. Loisel, and F.-M. Bréon, "A species-dependent bio-optical model of case I waters for global ocean color processing," Deep-Sea Res. 153, 917-925 (2006).

M. Saraceno, C. Provost, and M. Lebbah, "Biophysical regions identification using an artificial neuronal network: a case study in the South Western Atlantic," Adv. Space Res. 37, 793-805 (2006).
[CrossRef]

Y. Liu, R. H. Weisberg, and R. He, "Sea surface temperature patterns on the West Florida Shelf using growing hierarchical self-organizing maps," J. Atmos. Oceanic Technol. 23, 325-338 (2006).
[CrossRef]

A. Chazottes, A. Bricaud, M. Crépon, and S. Thiria, "Statistical analysis of a database of absorption spectra of phytoplankton and pigment concentrations using self-organizing maps," Appl. Opt. 45, 8102-8115 (2006).
[CrossRef] [PubMed]

2005 (4)

Y. Liu and R. H. Weisberg, "Patterns of ocean current variability on the West Florida Shelf using the self-organizing map," J. Geophys. Res. 110, C06003, doi: (2005).
[CrossRef]

L. Mémery, G. Reverdin, S. Paillet, and A. Oschlies, "Introduction to the POMME special section: thermocline ventilation and biogeochemical tracer distribution in the northeast Atlantic Ocean and impact of mesoscale dynamics," J. Geophys. Res. 110, C07S01, doi: (2005).
[CrossRef]

M. Levy, Y. Lehahn, J.-M. Andre, L. Mémery, H. Loisel and E. Heifetz, "Production regimes in the Northeast Atlantic: a study based on Sea-viewing Wide Field-of-view Sensor (SeaWiFS) chlorophyll and ocean general circulation model mixed layer depth," J. Geophys. Res. 110, C07S10, doi: (2005).
[CrossRef]

A. Paci, G. Caniaux, M. Gavart, H. Giordani, M. Lévy, L. Prieur, and G. Reverdin, "A high-resolution simulation of the ocean during the POMME experiment: simulation results and comparison with observations," J. Geophys. Res. 110, C07S09, doi: (2005).
[CrossRef]

2004 (1)

A. Bricaud, H. Claustre, J. Ras, and K. Oubelhkeir, "Natural variability of phytoplanktonic absorption in oceanic waters: influence of the size structure of algal populations," J. Geophys. Res. 109, C11010, doi: (2004).
[CrossRef]

2003 (1)

A. Niang, L. Gross, S. Thiria, F. Badran, and C. Moulin, "Automatic neural classification of ocean colour reflectance spectra at the top of the atmosphere with introduction of expert knowledge," Remote Sens. Environ. 86, 257-271 (2003).
[CrossRef]

2001 (1)

A. Morel and S. Maritorena, "Bio-optical properties of oceanic waters: a reappraisal," J. Geophys. Res. 106, 7763-7780 (2001).
[CrossRef]

1998 (1)

A. Bricaud, A. Morel, M. Babin, K. Allali, and H. Claustre, "Variations of light absorption by suspended particles with chlorophyll a concentration in oceanic (case 1) waters: analysis and implications for bio-optical models," J. Geophys. Res. 103, 31033-31044 (1998).
[CrossRef]

1996 (1)

F. Vidussi, H. Claustre, J. Bustillos-Guzman, C. Cailliau, and J. C. Marty, "Rapid HPLC method for determination of phytoplankton chemotaxonomic pigments: separation of chlorophyll a from divinyl-chlorophyll-a, and zeaxanthin from lutein," J. Plankton Res. 18, 2377-2382 (1996).
[CrossRef]

1995 (1)

A. Bricaud, M. Babin, A. Morel, and H. Claustre, "Variability in the chlorophyll-specific absorption coefficients of natural phytoplankton: analysis and parameterization," J. Geophys. Res. 100, 13331-13332 (1995).
[CrossRef]

Allali, K.

A. Bricaud, A. Morel, M. Babin, K. Allali, and H. Claustre, "Variations of light absorption by suspended particles with chlorophyll a concentration in oceanic (case 1) waters: analysis and implications for bio-optical models," J. Geophys. Res. 103, 31033-31044 (1998).
[CrossRef]

Alvain, S.

S. Alvain, C. Moulin, Y. Dandonneau, H. Loisel, and F.-M. Bréon, "A species-dependent bio-optical model of case I waters for global ocean color processing," Deep-Sea Res. 153, 917-925 (2006).

Andre, J.-M.

M. Levy, Y. Lehahn, J.-M. Andre, L. Mémery, H. Loisel and E. Heifetz, "Production regimes in the Northeast Atlantic: a study based on Sea-viewing Wide Field-of-view Sensor (SeaWiFS) chlorophyll and ocean general circulation model mixed layer depth," J. Geophys. Res. 110, C07S10, doi: (2005).
[CrossRef]

Babin, M.

A. Bricaud, A. Morel, M. Babin, K. Allali, and H. Claustre, "Variations of light absorption by suspended particles with chlorophyll a concentration in oceanic (case 1) waters: analysis and implications for bio-optical models," J. Geophys. Res. 103, 31033-31044 (1998).
[CrossRef]

A. Bricaud, M. Babin, A. Morel, and H. Claustre, "Variability in the chlorophyll-specific absorption coefficients of natural phytoplankton: analysis and parameterization," J. Geophys. Res. 100, 13331-13332 (1995).
[CrossRef]

Badran, F.

A. Niang, L. Gross, S. Thiria, F. Badran, and C. Moulin, "Automatic neural classification of ocean colour reflectance spectra at the top of the atmosphere with introduction of expert knowledge," Remote Sens. Environ. 86, 257-271 (2003).
[CrossRef]

Bréon, F.-M.

S. Alvain, C. Moulin, Y. Dandonneau, H. Loisel, and F.-M. Bréon, "A species-dependent bio-optical model of case I waters for global ocean color processing," Deep-Sea Res. 153, 917-925 (2006).

Bricaud, A.

A. Chazottes, A. Bricaud, M. Crépon, and S. Thiria, "Statistical analysis of a database of absorption spectra of phytoplankton and pigment concentrations using self-organizing maps," Appl. Opt. 45, 8102-8115 (2006).
[CrossRef] [PubMed]

A. Bricaud, H. Claustre, J. Ras, and K. Oubelhkeir, "Natural variability of phytoplanktonic absorption in oceanic waters: influence of the size structure of algal populations," J. Geophys. Res. 109, C11010, doi: (2004).
[CrossRef]

A. Bricaud, A. Morel, M. Babin, K. Allali, and H. Claustre, "Variations of light absorption by suspended particles with chlorophyll a concentration in oceanic (case 1) waters: analysis and implications for bio-optical models," J. Geophys. Res. 103, 31033-31044 (1998).
[CrossRef]

A. Bricaud, M. Babin, A. Morel, and H. Claustre, "Variability in the chlorophyll-specific absorption coefficients of natural phytoplankton: analysis and parameterization," J. Geophys. Res. 100, 13331-13332 (1995).
[CrossRef]

Bustillos-Guzman, J.

F. Vidussi, H. Claustre, J. Bustillos-Guzman, C. Cailliau, and J. C. Marty, "Rapid HPLC method for determination of phytoplankton chemotaxonomic pigments: separation of chlorophyll a from divinyl-chlorophyll-a, and zeaxanthin from lutein," J. Plankton Res. 18, 2377-2382 (1996).
[CrossRef]

Cailliau, C.

F. Vidussi, H. Claustre, J. Bustillos-Guzman, C. Cailliau, and J. C. Marty, "Rapid HPLC method for determination of phytoplankton chemotaxonomic pigments: separation of chlorophyll a from divinyl-chlorophyll-a, and zeaxanthin from lutein," J. Plankton Res. 18, 2377-2382 (1996).
[CrossRef]

Caniaux, G.

A. Paci, G. Caniaux, M. Gavart, H. Giordani, M. Lévy, L. Prieur, and G. Reverdin, "A high-resolution simulation of the ocean during the POMME experiment: simulation results and comparison with observations," J. Geophys. Res. 110, C07S09, doi: (2005).
[CrossRef]

Chazottes, A.

Claustre, H.

A. Bricaud, H. Claustre, J. Ras, and K. Oubelhkeir, "Natural variability of phytoplanktonic absorption in oceanic waters: influence of the size structure of algal populations," J. Geophys. Res. 109, C11010, doi: (2004).
[CrossRef]

A. Bricaud, A. Morel, M. Babin, K. Allali, and H. Claustre, "Variations of light absorption by suspended particles with chlorophyll a concentration in oceanic (case 1) waters: analysis and implications for bio-optical models," J. Geophys. Res. 103, 31033-31044 (1998).
[CrossRef]

F. Vidussi, H. Claustre, J. Bustillos-Guzman, C. Cailliau, and J. C. Marty, "Rapid HPLC method for determination of phytoplankton chemotaxonomic pigments: separation of chlorophyll a from divinyl-chlorophyll-a, and zeaxanthin from lutein," J. Plankton Res. 18, 2377-2382 (1996).
[CrossRef]

A. Bricaud, M. Babin, A. Morel, and H. Claustre, "Variability in the chlorophyll-specific absorption coefficients of natural phytoplankton: analysis and parameterization," J. Geophys. Res. 100, 13331-13332 (1995).
[CrossRef]

Crépon, M.

Dandonneau, Y.

S. Alvain, C. Moulin, Y. Dandonneau, H. Loisel, and F.-M. Bréon, "A species-dependent bio-optical model of case I waters for global ocean color processing," Deep-Sea Res. 153, 917-925 (2006).

Dreyfus, G.

G. Dreyfus, Neural Networks: Methodology and Applications (Springer-Verlag, 2005).

Gavart, M.

A. Paci, G. Caniaux, M. Gavart, H. Giordani, M. Lévy, L. Prieur, and G. Reverdin, "A high-resolution simulation of the ocean during the POMME experiment: simulation results and comparison with observations," J. Geophys. Res. 110, C07S09, doi: (2005).
[CrossRef]

Giordani, H.

A. Paci, G. Caniaux, M. Gavart, H. Giordani, M. Lévy, L. Prieur, and G. Reverdin, "A high-resolution simulation of the ocean during the POMME experiment: simulation results and comparison with observations," J. Geophys. Res. 110, C07S09, doi: (2005).
[CrossRef]

Gross, L.

A. Niang, L. Gross, S. Thiria, F. Badran, and C. Moulin, "Automatic neural classification of ocean colour reflectance spectra at the top of the atmosphere with introduction of expert knowledge," Remote Sens. Environ. 86, 257-271 (2003).
[CrossRef]

He, R.

Y. Liu, R. H. Weisberg, and R. He, "Sea surface temperature patterns on the West Florida Shelf using growing hierarchical self-organizing maps," J. Atmos. Oceanic Technol. 23, 325-338 (2006).
[CrossRef]

Heifetz, E.

M. Levy, Y. Lehahn, J.-M. Andre, L. Mémery, H. Loisel and E. Heifetz, "Production regimes in the Northeast Atlantic: a study based on Sea-viewing Wide Field-of-view Sensor (SeaWiFS) chlorophyll and ocean general circulation model mixed layer depth," J. Geophys. Res. 110, C07S10, doi: (2005).
[CrossRef]

Kohonen, T.

T. Kohonen, Self-Organizing Maps (Springer Verlag, 1984).

Lebbah, M.

M. Saraceno, C. Provost, and M. Lebbah, "Biophysical regions identification using an artificial neuronal network: a case study in the South Western Atlantic," Adv. Space Res. 37, 793-805 (2006).
[CrossRef]

Lehahn, Y.

M. Levy, Y. Lehahn, J.-M. Andre, L. Mémery, H. Loisel and E. Heifetz, "Production regimes in the Northeast Atlantic: a study based on Sea-viewing Wide Field-of-view Sensor (SeaWiFS) chlorophyll and ocean general circulation model mixed layer depth," J. Geophys. Res. 110, C07S10, doi: (2005).
[CrossRef]

Levy, M.

M. Levy, Y. Lehahn, J.-M. Andre, L. Mémery, H. Loisel and E. Heifetz, "Production regimes in the Northeast Atlantic: a study based on Sea-viewing Wide Field-of-view Sensor (SeaWiFS) chlorophyll and ocean general circulation model mixed layer depth," J. Geophys. Res. 110, C07S10, doi: (2005).
[CrossRef]

Lévy, M.

A. Paci, G. Caniaux, M. Gavart, H. Giordani, M. Lévy, L. Prieur, and G. Reverdin, "A high-resolution simulation of the ocean during the POMME experiment: simulation results and comparison with observations," J. Geophys. Res. 110, C07S09, doi: (2005).
[CrossRef]

Liu, Y.

Y. Liu, R. H. Weisberg, and R. He, "Sea surface temperature patterns on the West Florida Shelf using growing hierarchical self-organizing maps," J. Atmos. Oceanic Technol. 23, 325-338 (2006).
[CrossRef]

Y. Liu, R. H. Weisberg, and C. N. K. Mooers, "Performance evaluation of the self-organizing map for feature extraction," J. Geophys. Res. 111, C05018, doi: (2006).
[CrossRef]

Y. Liu and R. H. Weisberg, "Patterns of ocean current variability on the West Florida Shelf using the self-organizing map," J. Geophys. Res. 110, C06003, doi: (2005).
[CrossRef]

Loisel, H.

S. Alvain, C. Moulin, Y. Dandonneau, H. Loisel, and F.-M. Bréon, "A species-dependent bio-optical model of case I waters for global ocean color processing," Deep-Sea Res. 153, 917-925 (2006).

M. Levy, Y. Lehahn, J.-M. Andre, L. Mémery, H. Loisel and E. Heifetz, "Production regimes in the Northeast Atlantic: a study based on Sea-viewing Wide Field-of-view Sensor (SeaWiFS) chlorophyll and ocean general circulation model mixed layer depth," J. Geophys. Res. 110, C07S10, doi: (2005).
[CrossRef]

Maritorena, S.

A. Morel and S. Maritorena, "Bio-optical properties of oceanic waters: a reappraisal," J. Geophys. Res. 106, 7763-7780 (2001).
[CrossRef]

Marty, J. C.

F. Vidussi, H. Claustre, J. Bustillos-Guzman, C. Cailliau, and J. C. Marty, "Rapid HPLC method for determination of phytoplankton chemotaxonomic pigments: separation of chlorophyll a from divinyl-chlorophyll-a, and zeaxanthin from lutein," J. Plankton Res. 18, 2377-2382 (1996).
[CrossRef]

Mémery, L.

M. Levy, Y. Lehahn, J.-M. Andre, L. Mémery, H. Loisel and E. Heifetz, "Production regimes in the Northeast Atlantic: a study based on Sea-viewing Wide Field-of-view Sensor (SeaWiFS) chlorophyll and ocean general circulation model mixed layer depth," J. Geophys. Res. 110, C07S10, doi: (2005).
[CrossRef]

L. Mémery, G. Reverdin, S. Paillet, and A. Oschlies, "Introduction to the POMME special section: thermocline ventilation and biogeochemical tracer distribution in the northeast Atlantic Ocean and impact of mesoscale dynamics," J. Geophys. Res. 110, C07S01, doi: (2005).
[CrossRef]

Mooers, C. N. K.

Y. Liu, R. H. Weisberg, and C. N. K. Mooers, "Performance evaluation of the self-organizing map for feature extraction," J. Geophys. Res. 111, C05018, doi: (2006).
[CrossRef]

Morel, A.

A. Morel and S. Maritorena, "Bio-optical properties of oceanic waters: a reappraisal," J. Geophys. Res. 106, 7763-7780 (2001).
[CrossRef]

A. Bricaud, A. Morel, M. Babin, K. Allali, and H. Claustre, "Variations of light absorption by suspended particles with chlorophyll a concentration in oceanic (case 1) waters: analysis and implications for bio-optical models," J. Geophys. Res. 103, 31033-31044 (1998).
[CrossRef]

A. Bricaud, M. Babin, A. Morel, and H. Claustre, "Variability in the chlorophyll-specific absorption coefficients of natural phytoplankton: analysis and parameterization," J. Geophys. Res. 100, 13331-13332 (1995).
[CrossRef]

Moulin, C.

S. Alvain, C. Moulin, Y. Dandonneau, H. Loisel, and F.-M. Bréon, "A species-dependent bio-optical model of case I waters for global ocean color processing," Deep-Sea Res. 153, 917-925 (2006).

A. Niang, L. Gross, S. Thiria, F. Badran, and C. Moulin, "Automatic neural classification of ocean colour reflectance spectra at the top of the atmosphere with introduction of expert knowledge," Remote Sens. Environ. 86, 257-271 (2003).
[CrossRef]

Niang, A.

A. Niang, L. Gross, S. Thiria, F. Badran, and C. Moulin, "Automatic neural classification of ocean colour reflectance spectra at the top of the atmosphere with introduction of expert knowledge," Remote Sens. Environ. 86, 257-271 (2003).
[CrossRef]

Oschlies, A.

L. Mémery, G. Reverdin, S. Paillet, and A. Oschlies, "Introduction to the POMME special section: thermocline ventilation and biogeochemical tracer distribution in the northeast Atlantic Ocean and impact of mesoscale dynamics," J. Geophys. Res. 110, C07S01, doi: (2005).
[CrossRef]

Oubelhkeir, K.

A. Bricaud, H. Claustre, J. Ras, and K. Oubelhkeir, "Natural variability of phytoplanktonic absorption in oceanic waters: influence of the size structure of algal populations," J. Geophys. Res. 109, C11010, doi: (2004).
[CrossRef]

Paci, A.

A. Paci, G. Caniaux, M. Gavart, H. Giordani, M. Lévy, L. Prieur, and G. Reverdin, "A high-resolution simulation of the ocean during the POMME experiment: simulation results and comparison with observations," J. Geophys. Res. 110, C07S09, doi: (2005).
[CrossRef]

Paillet, S.

L. Mémery, G. Reverdin, S. Paillet, and A. Oschlies, "Introduction to the POMME special section: thermocline ventilation and biogeochemical tracer distribution in the northeast Atlantic Ocean and impact of mesoscale dynamics," J. Geophys. Res. 110, C07S01, doi: (2005).
[CrossRef]

Prieur, L.

A. Paci, G. Caniaux, M. Gavart, H. Giordani, M. Lévy, L. Prieur, and G. Reverdin, "A high-resolution simulation of the ocean during the POMME experiment: simulation results and comparison with observations," J. Geophys. Res. 110, C07S09, doi: (2005).
[CrossRef]

Provost, C.

M. Saraceno, C. Provost, and M. Lebbah, "Biophysical regions identification using an artificial neuronal network: a case study in the South Western Atlantic," Adv. Space Res. 37, 793-805 (2006).
[CrossRef]

Ras, J.

A. Bricaud, H. Claustre, J. Ras, and K. Oubelhkeir, "Natural variability of phytoplanktonic absorption in oceanic waters: influence of the size structure of algal populations," J. Geophys. Res. 109, C11010, doi: (2004).
[CrossRef]

Reverdin, G.

A. Paci, G. Caniaux, M. Gavart, H. Giordani, M. Lévy, L. Prieur, and G. Reverdin, "A high-resolution simulation of the ocean during the POMME experiment: simulation results and comparison with observations," J. Geophys. Res. 110, C07S09, doi: (2005).
[CrossRef]

L. Mémery, G. Reverdin, S. Paillet, and A. Oschlies, "Introduction to the POMME special section: thermocline ventilation and biogeochemical tracer distribution in the northeast Atlantic Ocean and impact of mesoscale dynamics," J. Geophys. Res. 110, C07S01, doi: (2005).
[CrossRef]

Saraceno, M.

M. Saraceno, C. Provost, and M. Lebbah, "Biophysical regions identification using an artificial neuronal network: a case study in the South Western Atlantic," Adv. Space Res. 37, 793-805 (2006).
[CrossRef]

Thiria, S.

A. Chazottes, A. Bricaud, M. Crépon, and S. Thiria, "Statistical analysis of a database of absorption spectra of phytoplankton and pigment concentrations using self-organizing maps," Appl. Opt. 45, 8102-8115 (2006).
[CrossRef] [PubMed]

A. Niang, L. Gross, S. Thiria, F. Badran, and C. Moulin, "Automatic neural classification of ocean colour reflectance spectra at the top of the atmosphere with introduction of expert knowledge," Remote Sens. Environ. 86, 257-271 (2003).
[CrossRef]

Vidussi, F.

F. Vidussi, H. Claustre, J. Bustillos-Guzman, C. Cailliau, and J. C. Marty, "Rapid HPLC method for determination of phytoplankton chemotaxonomic pigments: separation of chlorophyll a from divinyl-chlorophyll-a, and zeaxanthin from lutein," J. Plankton Res. 18, 2377-2382 (1996).
[CrossRef]

Weisberg, R. H.

Y. Liu, R. H. Weisberg, and C. N. K. Mooers, "Performance evaluation of the self-organizing map for feature extraction," J. Geophys. Res. 111, C05018, doi: (2006).
[CrossRef]

Y. Liu, R. H. Weisberg, and R. He, "Sea surface temperature patterns on the West Florida Shelf using growing hierarchical self-organizing maps," J. Atmos. Oceanic Technol. 23, 325-338 (2006).
[CrossRef]

Y. Liu and R. H. Weisberg, "Patterns of ocean current variability on the West Florida Shelf using the self-organizing map," J. Geophys. Res. 110, C06003, doi: (2005).
[CrossRef]

Adv. Space Res. (1)

M. Saraceno, C. Provost, and M. Lebbah, "Biophysical regions identification using an artificial neuronal network: a case study in the South Western Atlantic," Adv. Space Res. 37, 793-805 (2006).
[CrossRef]

Appl. Opt. (1)

Deep-Sea Res. (1)

S. Alvain, C. Moulin, Y. Dandonneau, H. Loisel, and F.-M. Bréon, "A species-dependent bio-optical model of case I waters for global ocean color processing," Deep-Sea Res. 153, 917-925 (2006).

J. Atmos. Oceanic Technol. (1)

Y. Liu, R. H. Weisberg, and R. He, "Sea surface temperature patterns on the West Florida Shelf using growing hierarchical self-organizing maps," J. Atmos. Oceanic Technol. 23, 325-338 (2006).
[CrossRef]

J. Geophys. Res. (9)

Y. Liu and R. H. Weisberg, "Patterns of ocean current variability on the West Florida Shelf using the self-organizing map," J. Geophys. Res. 110, C06003, doi: (2005).
[CrossRef]

Y. Liu, R. H. Weisberg, and C. N. K. Mooers, "Performance evaluation of the self-organizing map for feature extraction," J. Geophys. Res. 111, C05018, doi: (2006).
[CrossRef]

A. Bricaud, M. Babin, A. Morel, and H. Claustre, "Variability in the chlorophyll-specific absorption coefficients of natural phytoplankton: analysis and parameterization," J. Geophys. Res. 100, 13331-13332 (1995).
[CrossRef]

A. Bricaud, A. Morel, M. Babin, K. Allali, and H. Claustre, "Variations of light absorption by suspended particles with chlorophyll a concentration in oceanic (case 1) waters: analysis and implications for bio-optical models," J. Geophys. Res. 103, 31033-31044 (1998).
[CrossRef]

A. Morel and S. Maritorena, "Bio-optical properties of oceanic waters: a reappraisal," J. Geophys. Res. 106, 7763-7780 (2001).
[CrossRef]

L. Mémery, G. Reverdin, S. Paillet, and A. Oschlies, "Introduction to the POMME special section: thermocline ventilation and biogeochemical tracer distribution in the northeast Atlantic Ocean and impact of mesoscale dynamics," J. Geophys. Res. 110, C07S01, doi: (2005).
[CrossRef]

A. Bricaud, H. Claustre, J. Ras, and K. Oubelhkeir, "Natural variability of phytoplanktonic absorption in oceanic waters: influence of the size structure of algal populations," J. Geophys. Res. 109, C11010, doi: (2004).
[CrossRef]

M. Levy, Y. Lehahn, J.-M. Andre, L. Mémery, H. Loisel and E. Heifetz, "Production regimes in the Northeast Atlantic: a study based on Sea-viewing Wide Field-of-view Sensor (SeaWiFS) chlorophyll and ocean general circulation model mixed layer depth," J. Geophys. Res. 110, C07S10, doi: (2005).
[CrossRef]

A. Paci, G. Caniaux, M. Gavart, H. Giordani, M. Lévy, L. Prieur, and G. Reverdin, "A high-resolution simulation of the ocean during the POMME experiment: simulation results and comparison with observations," J. Geophys. Res. 110, C07S09, doi: (2005).
[CrossRef]

J. Plankton Res. (1)

F. Vidussi, H. Claustre, J. Bustillos-Guzman, C. Cailliau, and J. C. Marty, "Rapid HPLC method for determination of phytoplankton chemotaxonomic pigments: separation of chlorophyll a from divinyl-chlorophyll-a, and zeaxanthin from lutein," J. Plankton Res. 18, 2377-2382 (1996).
[CrossRef]

Remote Sens. Environ. (1)

A. Niang, L. Gross, S. Thiria, F. Badran, and C. Moulin, "Automatic neural classification of ocean colour reflectance spectra at the top of the atmosphere with introduction of expert knowledge," Remote Sens. Environ. 86, 257-271 (2003).
[CrossRef]

Other (2)

G. Dreyfus, Neural Networks: Methodology and Applications (Springer-Verlag, 2005).

T. Kohonen, Self-Organizing Maps (Springer Verlag, 1984).

Cited By

OSA participates in CrossRef's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (14)

Fig. 1
Fig. 1

Clustering of the neurons on the SOM. Following the HAC, based on the maximum amplitude and the slopes of the spectra, eight groups were retained. The group number resulting from the HAC is displayed for each neuron. The SOM + HAC clustering is coherent, since the groups represent clusters of contiguous neurons.

Fig. 2
Fig. 2

Top of the dendrogram resulting from the HAC is presented for the six groups used in the present study. The number of data of L corresponding to each group is also known. The higher the node linking two groups the further apart they are in the data space.

Fig. 3
Fig. 3

Mean Tchl-a concentrations and their standard deviation with respect to the groups; the groups are ranked according to their Tchl-a concentration. The overlapping of the error bars suggests that the HAC contains some additional information on the data set.

Fig. 4
Fig. 4

Normalized pigment concentrations for the six significant groups; each group has different standardized pigment ratios. Discrepancies among the groups result from these various pigment combinations.

Fig. 5
Fig. 5

Histogram of the distribution of the surface water samples from the 12 cruises in each of the six groups. The histogram is computed as the ratio of the number of samples of a given campaign in a given group to the total number of samples in that group. Basic information on the campaigns, including their respective numbers, is given in Table 1.

Fig. 6
Fig. 6

Group clustering of absorption spectra in samples from the first optical layer. The mean absorption spectrum and its standard deviation computed from the surface learning data set are displayed for each group (open circles). The mean absorption spectra for the samples from each of the three POMME cruises (val-P1, val-P2 and val-P3) and for the PROSOPE-Med cruise (learn-Pmed) have been superposed.

Fig. 7
Fig. 7

Group clustering of the derivative of the absorption spectra in samples from the first optical layer. The mean absorption spectrum slope and its standard deviation computed from the surface learning data set are displayed for each group (open circles). The mean absorption spectrum slopes for the samples from each of the three POMME cruises (val-P1, val-P2 and val-P3) and the PROSOPE-Med cruise (learn-Pmed) have been superposed.

Fig. 8
Fig. 8

Group clustering of the mean pigment concentration in samples from the first optical layer. The mean pigment concentrations of the samples from the three POMME cruises (val-P1, val-P2 and val-P3) and the PROSOPE-Med cruise (learn-Pmed) are displayed. We have also displayed the mean pigment concentrations and their standard deviation computed from the learning data set for each group (open circles).

Fig. 9
Fig. 9

Group clustering of the mean normalized pigment concentration in samples from the first optical layer. The mean normalized pigment concentrations of the samples from the three POMME cruises (val-P1, val-P2 and val-P3) and the Prosope-Med cruise (learn-Pmed) are displayed. We have also displayed the mean normalized pigment concentrations and their standard deviation computed from the learning data set for each group (open circles).

Fig. 10
Fig. 10

Mean absorption spectrum of the group 2 surface waters (o), of the group 2 water column including deep and surface waters, (∇), of the POMME-1 (×) and POMME-2 (+) cruises. The POMME-1 spectrum is close to the mean spectrum of the group 2 which includes deep samples.

Fig. 11
Fig. 11

(a) Scatterplot of the Bricaud et al. [14] regression and (b)–(g) Bricaud et al. [14] and HAC-group relationships linking absorption to Tch1-a for the six groups.

Fig. 12
Fig. 12

Plot of the relation given by Eq. (2′) on the group 2 data for samples from the first optical layer. The group 2 data displayed are from the validation data set, V surf (POMME-1 and POMME-2).

Fig. 13
Fig. 13

Plot of the relation given by Eq. (3) on the group 2 data for samples from the first optical layer. The group 2 data displayed are from the validation data set, V surf (POMME-1 and POMME-2).

Fig. 14
Fig. 14

Histogram of the distribution of the surface-water samples from the water types in each of the six groups. The histogram is computed as the ratio of the number of samples of a given water type in a given group to the total number of samples in that group. The number of water samples is given for each group. 1, 2, and 3 stand for the different water types, respectively, oligotrophic, mesotrophic, and eutrophic.

Tables (4)

Tables Icon

Table 1 Information Concerning the Cruises on which the Different Water Samples Were Collected

Tables Icon

Table 2 Sample Repartition of the Surface Samples in the Different Data Sets and Groups

Tables Icon

Table 3 For Each Group, Performance Evaluation for the SOM + HAC Regression Lines as Well as the s2 and rmse of the Bricaud et al . [14] Regression Line

Tables Icon

Table 4 Global (on the Whole Data Set) Performance Evaluation for the SOM + HAC Regression Lines and for the Bricaud et al . [14] Regression Line

Equations (10)

Equations on this page are rendered with MathJax. Learn more.

a p h ( 440 ) = 0.0654 Tchl-a 0.728
( with   R 2 = 0.934 , N = 596 ) .
Tchl- b / Tchl- a = 0.090 ( a 650 / a 640 ) 6.838
( with   R 2 = 0.531   and   s = 0.246 ) .
Tchl- b / Tchl- a = 0.0684 ( a 650 / a 640 ) 6.624
( with   R 2 = 0.431   and   s = 0.240 ) .
Fucoxanthin / Tchl- a = 1.311 ( a 510 / a 500 ) 6.74
( w i t h R 2 = 0.46 , s = 0.264 ) .
R 2 = ( y i estimated y ¯ ) 2 ( y i observed y ¯ ) 2 ,
s = ( ( y i observed y i estimated ) 2 n 2 ) 1 / 2 .

Metrics