/explore
|
You are here 
|
esd.copernicus.org | ||
| | | | |
gmd.copernicus.org
GMD - Metrics - Deep learning model based on multi-scale feature fusion for precipitation nowcasting 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... |
|
| | | | | ||
| | | | |
egusphere.copernicus.org
[AI summary] This preprint proposes a roadmap and manifesto for advancing pedotransfer functions (PTFs) to better predict soil hydraulic properties for hydrological and biogeochemical modeling. |
|
| | | | | ||
| | | | |
amt.copernicus.org
Abstract. Solubility of aerosol trace elements, which determines their bioavailability and reactivity, is operationally defined and strongly depends on the leaching protocol used. Ultrapure water batch leaching is one of the most widely used leaching protocols, while the specific leaching protocols used in different labs can still differ in agitation methods, contact time, and filter pore size. It is yet unclear to which extent the difference in these experimental parameters would affect the aerosol trac... |
|
| | | | | ||
| | | | |
egqsj.copernicus.org
|
|
| | | |||
