Accurate estimation of snowfall rate is important particularly for the regions where snow is the major source of water supply, as well as for transportation safety. This study is focused on the application of satellite-based observation for estimating snowfall rate. There are not enough ground-based gauge networks and radar coverage available for the areas with heaviest precipitation for estimation. Consequently, remote sensing information will be useful for these regions by providing a better idea of the magnitude and distribution of snowfall coverage. Therefore, the main objective of this study is to develop a multi-sensor algorithm based on an artificial neural network (ANN) system for snowfall estimation using microwave (MW) frequencies from the Advanced Microwave Sounding Unit (AMSU) and infrared (IR) from geostationary GOES satellites. Accordingly, using MW information is expected to improve IR-based snowfall rate estimates because MW spectrum with longer wavelength can penetrate and provide some information related to cloud physics and properties. The ANN model in development is trained and validated with snow water equivalent depths data available from the Quality Controlled Local Climatological Data product from NCDC. Currently, this study is focused on exploring ANN parameters that will provide better results for snowfall estimation. Preliminary investigation indicates that the combination of higher frequency microwave channels, such as AMSU-150, -183±1, and -183±7 GHz are more correlated with snowfall rate, and are thus an appropriate source of model input information.