This work focuses on the contribution of modelling for the interpretation of multi- or hyperspectral optical images for the detection, characterisation and quantification of oil spills. Many parameters contribute to the spectral signature of an oil layer on the sea surface: the optical properties of the water column and of the oil, the film thickness, the surface roughness, the atmospheric radiance reaching the surface (direct and diffuse components), the geometry of observation and illumination. The number of these contributors and their combinations make the analysis of the spectral variability of oil signatures at the sea surface complex. Modelling approaches allow us to consider all those parameters and can then provide useful information to improve the interpretation of optical images. The model presented in this paper simulates the radiance of an oil layer from visible to short wave infrared spectral domains, taking into account all the above-mentioned parameters. The damping influence of the oil layer on sea surface waves is also considered. Comparisons of the simulations with in situ measurements shows a good overall agreement despite the lack of knowledge of some input parameters of the model. In combination with laboratory and in-the-field measurements, the model is then used to assess the expected contrast between water and oil and to estimate oil slick volume.