Leaving fields with a vegetation cover during the winter is one of the main ways to reduce water pollution, in re- stricting pollutant fluxes towards rivers. The bare soils/vegetation ratio monitoring can be carried out daily at a coarse spatial resolution with SPOT VEGETATION (1 km), and also at a higher spatial resolution with SPOT HRVIR (20 m), but with less repetitive and spatially more restricted data. Land-cover changes detected at a regional scale with this ratio can be explained by winter vegetation covering changes as well as by influence of climatic events. Therefore, observed changes have to be validated from a local scale analysis. The aim of this study is to develop a method that allows to assess high or low variations detected at a regional scale from SPOT VEGETATION images with data registered at a higher scale, SPOT HRVIR images in our case. In this study, the link between the images of the two sensors is set up from the design of an Artificial Neural Network method based on a Kohonen Self-Organizing Features Map. The originality of this method lies in the use of temporal dimension to solve such a change of scales. I. INTRODUCTION Monitoring of winter land cover is one of the most impor- tant stakes for water pollution reduction in intensive agricul- tural areas. In fact, vegetation covering fields during winters reduces pollution transfers through waterways. Thus, bare soil/vegetation ratio becomes a good farming practices indica- tor, but this ratio may represents winter land cover variations as well as climatic factor influences when it is expected from large scale remotely sensed data. A local analysis is necessary to validate the large scale estimation of the ratio. Then even if large scale pollution occurs in regions such as Brittany (in west of France), local analysis have to be engaged. Also, local and large scale are the scales of intervention of some institutions (for agriculture or water resources). Decisions of changing land use concern areas from the field to the watershed. Remote sensors induce the actual precision of winter land use monitoring. SPOT VEGETATION can offer a daily estima- tion of the ratio bare soil/vegetation at large scale - resolution is 1km a pixel. SPOT HRVIR can also offer an estimation of the ratio, but at a finer scale - 20m a pixel - for smaller regions - 60km a scene - and only once or twice a winter. Then conjonction of fine and coarse resolution has several advantages: to precise at finer scale an observation acquired at a coarse scale and then to understand changes observed at larger scale; to guaranty regular observation and prevent from missing data at key-periods. In this last case, it is necessary to simulate a higher resolution observation from the coarse acquisition, taking into consideration older data to integrate temporal behavior of land cover changes. The goal of the study is to make an estimation of the finer scale observation that would have to be acquired, giving a large scale acquisition. This local estimation is necessary to explain local abrupt or trend variations of winter land cover, while knowing the only SPOT VEGETATION observation.