The aim of this study is to assess the potential of satellite image time series with high spatial and high temporal resolutions for the prediction of grasslands plant biodiversity. The grasslands are modeled at the object scale to be consistent with ecological measurements (one biodiversity index per grassland). A kernel regression is used to predict the biodiversity index of a grassland from its spectro-temporal reflectance. The method is applied using two intra-annual multispectral or NDVI time series of SPOT5 Take5 (18 dates) and Sentinel-2 (7 dates) to predict the Shannon and the Simpson indices of about 200 grasslands in southwest France. The best coefficient of determination for the prediction of the Shannon index is 0.13 and it is 0.17 for the Simpson index prediction. The unsatisfactory results suggest that a high temporal resolution combined with a high spatial resolution and multispectral bands are not sufficient to estimate grassland biodiversity at the grassland scale.