To meet the growing demands from public and private stakeholders for early yield estimates, a high-resolution (2 km × 2 km) rice yield forecasting system based on the integration of the WARM model and remote sensing (RS) technologies was developed. RS was used to identify rice-cropped area and to derive spatially distributed sowing dates, and for the dynamic assimilation of RS-derived leaf area index (LAI) data within the crop model. The system—tested for the main European rice production districts in Italy, Greece, and Spain—performed satisfactorily; >66% of the inter-annual yield variability was explained in six out of eight combinations of ecotype × district, with a maximum of 89% of the variability explained for the ‘Tropical Japonica’ cultivars in the Vercelli district (Italy). In seven out of eight cases, the assimilation of RS-derived LAI improved the forecasting capability, with minor differences due to the assimilation technology used (updating or recalibration). In particular, RS data reduced uncertainty by capturing factors that were not properly reproduced by the simulation model (given the uncertainty due to large-area simulations). The system, which is an extension of the one used for rice within the EC-JRC-MARS forecasting system, was used pre-operationally in 2015 and 2016 to provide early yield estimates to private companies and institutional stakeholders within the EU-FP7 ERMES project.