A comparison of change detection approaches for flooded area mapping using Synthetic Aperture Radar (SAR) images is provided. The aim was to assess the usefulness of fuzzy and neuro-fuzzy techniques for classification of SAR data. The work addresses both options of data-level fusion and decision-level fusion. The former is realized with multitemporal fuzzy or neural classification and the latter by combining classifications or fuzzy memberships for the pre- and post-event images. Highest overall accuracy values and flooded area accuracy values (90.3% producer's, 71.9% user's) were obtained from the neuro-fuzzy approach.