Wildfires issues are part of a global problem. In Côte d'Ivoire, these phenomena are recurring and reduce, by the degradation of plant cover, crop yield. Official reports indicate each year many cases of wildfires in Zanzan with their impact on the local economy and human settlements. The present study aims to analyze the climatic conditions that trigger these lights for, identify critical thresholds of climate parameters in question to help prevent against this disaster. From data of ESA satellites ERS-1 and ENVISAT, the descriptive statistics and correlation analysis were used to conduct the study. The results show that during the year, vulnerable periods of wildfires go from december to March with an early occurrence in Bouna. They also show a strong dependence of fire with climatic conditions including high temperatures, low air and soil humidity and easterly dry wind regime. El Nino conditions are also critical for local fire occurrence in the district. Critical thresholds for triggering fires in Zanzan can be summarized by above 30 degrees Celsius for temperatures, below 40 percent for air relative humidity and less than 5 mm for the soil moisture. The analysis of the Angstrom index shows that this indicates is appropriate for characterize fire danger in the District Zanzan.

Daily rainfalls as they reach a certain threshold, induce severe flooding in some township of Abidjan district during the largest rainy season. This paper focuses on defining and identifying of heavy daily rainfall threshold linked in flooding over the Abidjan district. The heavy rainfall maximum and critical occurrence period ascertainment has been possible thanks to the likelihood occurrence (from 0 to 100%). Identifying heavy rainfall threshold related to flooding-causing started with classification and definition of precipitation recorded from 2012 to 2014 over all stations of Abidjan district with the percentile. Then, using the rainfall total sliding window technic helped finding a threshold amount inducing severe flooding. The critical period rainfall and flooding occurrence (likelihood occurrence of 75%) start from May 27th to June 22th. Rainfall total sliding and past flooding analysis revealed a threshold amount precipitation around 100 mm. Henceforth, this threshold could helped forecaster offices by issuing advisories and warnings for flooding when precipitation expected, at any location of Abidjan district, is near or exceeds the amount of 100 mm.

The aim of this in this research work is to present an innovative approach to classification of satellite images based on Markov Random Field, MRF. Markov models are used both on single-band and multi-band images and have the advantage to take into account the spatial context in the process of the classification of multispectral images. This leds to the integration of interactions between different pixels and to extract the maximum information contained in satellite images including textures. In this research work, the classification by Markov Random Fields was applied respectively on the colored composites of the first three principal components of multispectral images Landsat TM from 1986 ,ETM + from 2003 and OLI from 2014 of the department of Sinfra containing respectively 94,7% , 97,4% et 98,4 % of the information. Markov Random Field correctly discriminate the different classes of land use with a Kappa coefficient higher than 0.8 : 0.86 for TM images, 0.91 for ETM + and 0.9 for OLI images.