M. Crepon
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
M. Crepon has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
F. Badran
3 shared publicationsS. Thiria
3 shared publicationsA. Bentamy
1 shared publicationA. Ngan
Dakar Univ., Senegal
1 shared publicationC. Mejia
1 shared publicationC. Mejía
1 shared publication
Latest Publications
- 9 November 2010
- Published by IOP Publishing in Inverse Problems
- Vol. 26 (12)
A global optimization method using a random walk on a topological map and local variational inversions
- 9 November 2010
- Published by IOP Publishing in Inverse Problems
- Vol. 26 (12)
A global optimization method using a random walk on a topological map and local variational inversions
- 22 March 2004
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 146-148
Clustering and classification based on expert knowledge propagation using probabilistic self-organizing map(PRSOM): application to the classification of satellite ocean color TOA observations
The Kohonen map with PRSOM was used to analyze a time sequence of SeaWifs images These images were observed on the Mediterranean Sea from the 6/sup th/ of August to the 12/sup th/. We processed the normalized reflectance of full TOA spectrum by first using a 20/spl times/20 Kohonen map and then we aggregated these 400 classes into 50 classes by using the PRSOM algorithm. The classifier was trained on a one year (1999) Mediterranean SeaWifs images using a temporal homogeneity. (2 images/month). We have developed an automatic labeling procedure based on the SeaWifs LUT used to invert the TOA signal. The labeling procedure allows us to identify four different aerosol type (Coastal, Maritime, Tropospheric Dust, Oceanic) and their corresponding optical thickness. We clearly see an important event of Saharian dust coming from the Sahara, crossing the Mediterranean Sea and invading North of the Mediterranean. A meteorological map taken the 10/sup th/ of August shows a strong South West wind supporting the above interpretation. This study clearly shows the possibility to use the above algorithm for automatically classify the aerosols at the Top of the Atmosphere.
- 22 March 2004
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 146-148
Clustering and classification based on expert knowledge propagation using probabilistic self-organizing map(PRSOM): application to the classification of satellite ocean color TOA observations
The Kohonen map with PRSOM was used to analyze a time sequence of SeaWifs images These images were observed on the Mediterranean Sea from the 6/sup th/ of August to the 12/sup th/. We processed the normalized reflectance of full TOA spectrum by first using a 20/spl times/20 Kohonen map and then we aggregated these 400 classes into 50 classes by using the PRSOM algorithm. The classifier was trained on a one year (1999) Mediterranean SeaWifs images using a temporal homogeneity. (2 images/month). We have developed an automatic labeling procedure based on the SeaWifs LUT used to invert the TOA signal. The labeling procedure allows us to identify four different aerosol type (Coastal, Maritime, Tropospheric Dust, Oceanic) and their corresponding optical thickness. We clearly see an important event of Saharian dust coming from the Sahara, crossing the Mediterranean Sea and invading North of the Mediterranean. A meteorological map taken the 10/sup th/ of August shows a strong South West wind supporting the above interpretation. This study clearly shows the possibility to use the above algorithm for automatically classify the aerosols at the Top of the Atmosphere.
- 15 April 2000
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Oceans
- Vol. 105 (C4) , 8737-8751
Neural network wind retrieval from ERS‐1 scatterometer data
- 15 April 2000
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Oceans
- Vol. 105 (C4) , 8737-8751
Neural network wind retrieval from ERS‐1 scatterometer data
- Open Access
- 15 May 1999
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Oceans
- Vol. 104 (C5) , 11539-11556
Determination of the geophysical model function of NSCAT and its corresponding variance by the use of neural networks
- 15 May 1999
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Oceans
- Vol. 104 (C5) , 11539-11556
Open AccessDetermination of the geophysical model function of NSCAT and its corresponding variance by the use of neural networks