Explore >> Select a destination


You are here

egqsj.copernicus.org
| | www.earth-system-dynamics.net
2.6 parsecs away

Travel
| |
| | gmd.copernicus.org
2.6 parsecs away

Travel
| |
| | www.atmos-chem-phys.net
2.5 parsecs away

Travel
| |
| | gmd.copernicus.org
30.2 parsecs away

Travel
| Abstract. Forecasting heavy precipitation accurately is a challenging task for most deep learning (DL)-based models. To address this, we present a novel DL architecture called multi-scale feature fusion (MFF) that can forecast precipitation with a lead time of up to 3?h. The MFF model uses convolution kernels with varying sizes to create multi-scale receptive fields. This helps to capture the movement features of precipitation systems, such as their shape, movement direction, and speed. Additionally, the...