B2. Istanbul 2004 
THE EVOLUTION STUDY OF THE NATURAL HAZARD ZONES BY THE KOHONEN 
SELF-ORGANISING MAP CLASSIFICATION 
N. Abou Dagga “, M.F Courel ”, F. Badran “, B. Anselme “ 
* PRODIG,8586 CNRS laboratory, 191 rue saint Jacques 75005 Paris, nader75(uuniv-paris l.fr 
® PRODIG, 8586 CNRS laboratory, 191 rue saint Jacques 75005 Paris courel(@univ-paris |.fr 
  
“ LODYC, Paris6, 03 place Jussieu, 75005 Paris, badran@lodyc.jussieu. fr 
4 PRODIG, 8586 CNRS laboratory, 191 rue saint Jacques 75005 Paris, brice.anselme@univ-paris |. ir 
  
  
  
Commission PS ICWGIVIV 
KEY WORDS: change detection, updating, monitoring, mapping, multitemporal, landcover, imagery 
ABSTRACT: 
ctral bands. This article consists to explain the application of a semi automatic and multi temporal method of classification of the spot images. 
The objective is to follow the evolution of the units of landscapes factors of risk in the Nouakchott area (in West Africa). In fact, it 
was proved in the literature of image processing techniques and remote sensing, that there is not a completely automatic method of 
classification, considering the complexity of the phenomena represented by a pixel and the geometrical resolution of this same pixel. 
The method used in this work allows the intervention of the expert (of validation) in certain stages of the application. The goal is to 
improve the results of classification without repeating all the calculation. 
We applied the method to chart the landscapes units of the environment of Nouakchott. The objective is to monitor the environmental 
hazards in this region characterizing the classes corresponding to landscape units present in SPOT images and to survey their 
temporal evolution. The method consists to apply the Kohonen Self-Organizing Map (SOM) algorithm on a data base of multi-dates 
images. The obtained Kohonen topological map is constituted of 100 neurons. Each neuron represents the reflectance spectrum of a 
subset of the training database. This map is thus representative of all the units of landscape present in the images of various dates. A 
Hierarchic Ascending Classification (HAC), with number of classes, is applied on the topological map to aggregate the subsets 
presenting similar reflectance, therefore to group all the local variability of the landscape. 
The classes gathering the 100 calculated subsets are labelled to make the correspondence of a given class to a landscape unit on the 
ground. These units present the factors element of risk. Once the map is validated, for each date, the image is classified automatically 
by a simple assignment of its pixels to the nearest neuron of the topological map. We thus obtain a series of classified images from 
the same map, what allows one to quantify the evolution of each class compared to its counterpart of other dates, and therefore to 
evaluate the risks evolution . 
* 
1. INTRODUCTION. is that of December 1997 and then that of June 2000 which 
required the moving of several districts (Haag, M., 1998) 
Nouakchott is a sahelian city located on the Western side of the The three factors of this risk (Courel, M.F., Leterrier, E., Le 
Atlantic (18?4 ' N, and 15?58 ' W).it’s populated moreover than Rhun, J., 1998) are, wind erosion, tablecloth salted water 
one million inhabitants, the growth rate of its population has resurgence on the level of the lagoon, the rains, and the rupture. 
increased more and more since ten year (according to of coastal dune inducing the water marine intrusion (Giresse, 
Weicheng, Wu., Courel, Le Rhun, J., 2003). These districts are 
threatened by two principal types of risks. The floods coming 
from the Atlantic Ocean on the Western side and the stranding 
due to the deposit of new dune in the East. The evaluation of 
these risks is carried out by a diachronic monitoring of the units 
of landscape constituting the environment of this area. 
P., 2000). The stranding constitutes the second major risk 
threatening Nouakchott. 
It acts especially on the East and South-east districts, as well as 
the road network of this part of the city. This phenomenon is 
due to the degradation of the dunes vegetation of Amoukrouz, 
consecutive with the drying-out of the area since 1968, which 
caused the remobilisation of sands and the appearance of sharp 
dunes (Courel, M.F., Bicheron, P., Mougin, E., 2000), so much 
at the top of the dunes than in the inters dunes. 
The town of Nouakchott is separated from the sea by a thin 
coastal dune, behind which the lagoon of Aftout Esaheli. Its 
districts are encircled by the zones of the salted water of lagoon 
in the West and by the great dunal sets in the East (Eluard, P). 
This particular situation exposes the city and his environment to To monitor the evolution of the risks we proceed by the multi 
big geomorphological changes (Weicheng, Wu., Courel, M.F., temporal study of all the landscape units constituting the 
Le Rhun, J., 2000) and two types of major risks. environment of the area of Nouakchott. We can gather these 
units in two great parts, the marine and the continental part. 
For the flood risk the marine units of landscape to direct 
influence on the coast are shore-face, the zone of breaking of 
waves and the bottom of beach.In the continental part along the 
beach, the units of landscape undergoing the floods are, the 
coastal dunes (fine and dry white sand compound), the lagoon 
(compact wetland argillaceous ground), often flooded because 
The risk of flood coming from marine water trace in particular 
the Western and North-western districts of Nouakchott, these 
districts being established in a topographic depression compared 
to the level of the ocean. Indeed these districts already 
underwent several situations of flood of which most significant 
503