In recent years great progress has been made in global mapping of phytoplankton from space. Two main trends have
emerged, the recognition of phytoplankton functional types (PFT) based on reflectance normalized to chlorophyll-a
concentration, and the recognition of phytoplankton size class (PSC) based on the relationship between cell size and
chlorophyll-a concentration. However, PFTs and PSCs are not decorrelated, and one approach can complement the other
in a recognition task. In this paper, we explore the recognition of several dominant PFTs by combining reflectance
anomalies, chlorophyll-a concentration and other environmental parameters, such as sea surface temperature and wind
speed. Remote sensing pixels are labeled thanks to coincident in-situ pigment data from GeP&CO, NOMAD and
MAREDAT datasets, covering various oceanographic environments. The recognition is made with a supervised Support
Vector Machine classifier trained on the labeled pixels. This algorithm enables a non-linear separation of the classes in the
input space and is especially adapted for small training datasets as available here. Moreover, it provides a class probability
estimate, allowing one to enhance the robustness of the classification results through the choice of a minimum probability
threshold. A greedy feature selection associated to a 10-fold cross-validation procedure is applied to select the most
discriminative input features and evaluate the classification performance. The best classifiers are finally applied on daily
remote sensing datasets (SeaWIFS, MODISA) and the resulting dominant PFT maps are compared with other studies.
Several conclusions are drawn: (1) the feature selection highlights the weight of temperature, chlorophyll-a and wind speed
variables in phytoplankton recognition; (2) the classifiers show good results and dominant PFT maps in agreement with
phytoplankton distribution knowledge; (3) classification on MODISA data seems to perform better than on SeaWIFS data,
(4) the probability threshold screens correctly the areas of smallest confidence such as the interclass regions.
We propose a statistical algorithm to assess chlorophyll-a concentration ([chl-a]) using remote sensing reflectance (Rrs)
derived from MODerate Resolution Imaging Spectroradiometer (MODIS) data. This algorithm is a combination of two
models: one for low [chl-a] (oligotrophic waters) and one for high [chl-a]. A satellite pixel is classified as low or high [chla]
according to the Rrs ratio (488 and 555 nm channels). If a pixel is considered as a low [chl-a] pixel, a log-linear model
is applied; otherwise, a more sophisticated model (Support Vector Machine) is applied. The log-linear model was
developed thanks to supervised learning on Rrs and [chl-a] data from SeaBASS and more than 15 campaigns accomplished
from 2002 to 2010 around New Caledonia. Several models to assess high [chl-a] were also tested with statistical methods.
This novel approach outperforms the standard reflectance ratio approach. Compared with algorithms such as the current
NASA OC3, Root Mean Square Error is 30% lower in New Caledonian waters.
We present data collected as part of ValHyBio- VALidation HYperspectral of a BIOgeochemical model in
the South Western Tropical Lagoon of New Caledonia, a PNTS-sponsored program dedicated to chlorophyll satellite
imaging and validation as affected by bathymetry. The specific goals of ValHyBio are to: - examine time-dependent
oceanic reflectance in relation to dynamic surface processes, - construct field/satellite reflectance-based chlorophyll
models, - investigate the feasibility of inverting the model to yield surface chlorophyll and turbidity, - validate the
biogeochemical model with field/satellite observations. In situ bio-optical parameters include absorption coefficients
by CDOM and particles, Secchi disk depth, backscattering coefficient, pigment concentration, suspended matter
concentration, and K_dPAR. They are measured every month at 5 stations, of contrasted bathymetry and bottom
reflectance, as well as at a reference station situated 4 miles offshore, and on a station over coral reefs. Remote sensing
reflectance is calculated from the absorption and backscattering coefficients and compared with satellite data.
SeaWIFS and MODIS AQUA match-ups collected over the period 1997-2010 (ValHySat-VALidation HYperspectral
SATellite database) are used. Satellite retrievals are examined as a function of bathymetry. The feasibility of a longterm
monitoring program of optical water retrieval with satellite remote sensing technique is examined in the frame of
the GOPS (South Pacific Integrated Observatory).
Due to the complexity of the tropical terrestrial environment present in Pacific islands and the lack of ground
data, remote sensing could offer an appropriate tool for obtaining a better understanding and knowledge of
the key parameters necessary to many environmental applications. Moreover, recent sensors provide high
spatial resolution and good temporal periodicity which is suitable for the study of tropical environments.
The potentiality of an oriented-object technique for land-cover mapping will be illustrated in this paper.
Unlike traditional pixel-based classification, this technique is based on object-use topology and shape features
for the differentiation of target classes. It offers a complex "knowledge base" about classes which can be
directly formulated in classification rule sets.
The first step applied to images is "segmentation" which enables the improvement of classification accuracy
as compared with that achievable using only individual spectral signature pixels.
In fact, indices based on spectral, spatial and textural or structural parameters are explored in order to reduce
the confusion between classes. The results from the segmentation are then used to produce a classification of
The oriented-object classification technique is carried out on a section of Efate Island (Vanuatu republic)
using images acquired in 2007/2008 by Formosat-2 sensor. Finally, the accuracy of the oriented-object
classification is established with the help of ground control points.