RESTITUTION OF ATMOSPHERIC MOISTURE FROM NEURAL NETWORKS AND USING SATELLITE DATA

In the Sahelian region of West Africa most of the population lives agro-pastoral activities. The air trafficking, which is a source of sustainable development of countries which constitute this climatic zone develops. Hence the need for a weather forecast in the short and medium term. In this work, it is a question of trying to restore the humidity of the atmosphere using neural networks. The model of liebe associated modtran 6 with us allowed to establish profiles of radiances. These structures are compared to those of the satellite. We obtained satisfactory results on the humidity profiles.