Common Ragweed (Ambrosia artemisiifolia) is a plant that constitutes an important and growing public health concern worldwide as it is probably expanding with climate change, which brings forward the need for improved mapping tools. Our final purpose is to operationalize the use of optical remote sensing for the automated mapping and surveillance of Ambrosia artemisiifolia. Analyses considering the probable spectral instability originating from the variability of the urban landscape and from that of sensors characteristics were developed. Worldview 2, Rapid Eye and SPOT 4 HRVIR sensors were used together with geolocalized surveys of Common Ragweed in Montréal and Valleyfield (Quebec, Canada). Images were standardized and various derivatives variables such as multiple vegetation indexes were created. Spectral confusion, statistical analyses, object-oriented technology and Fuzzy-logic functions were used to develop predictive risks maps of Common Ragweed potential presence. The results showed that the green bands (510-590 nm) of higher spatial resolutions sensors had a higher potential to cope with spectral confusions and changing landscape characteristics and to predict the likelihood of Ambrosia artemisiifolia presence with a recurrent stability. The good agreement between observed and predicted ragweed revealed an important potential for the operationalization of this method.