Artisanal and small-scale gold mining (ASGM) represents a significant economic activity for communities in developing countries. In south-eastern Senegal, this activity has increased in recent years and has become the main source of income for the local population. However, it is also associated with negative environmental and social impacts. Considering the recent development of ASGM in Senegal, and the difficulties of the government in monitoring and regulating this activity, this article proposes a method for detecting and mapping ASGM sites in Senegal using Sentinel 2 data and the Google Earth Engine. Two artisanal mining site in Eastern Senegal are selected to develop and test this approach. Detection and mapping are achieved using Principle Component Analysis (PCA), Separability and Threshold (SEaTH) and Support Vector Machine classifier (SVM). The results are validated by ground-truth observations. The PCA indicates that the best period for identifying artisanal mining sites against other types of land-use is the end of dry season, when vegetation is minimal. This result is confirmed by examining the spectral evolution over time of different types of land-use. Input variables for SVM classification are defined by the SEaTH. The classification results are presented as a map with 5 color-coded categories of land-use. The method can be used to map the evolution of mining sites as a function of time using future Sentinel acquisitions. This approach may also be extrapolated to other areas in the Sahel where authorities are also confronted with the difficult regulation of artisanal gold mining activities in remote areas.