Titel:
"Development of Continuous AMSR-E/2 Soil Moisture Time Series by Hybrid Deep Learning Model"
Description:
We developed a hybrid deep learning model to generate a seamless, 21-year (2003–2023) European soil moisture dataset using AMSR-E/2 data. Our method fills spatio-temporal gaps in the dataset, improving accuracy by 26%. This data can support data assimilation and hydrological studies. You can access it via the following link: https://doi.org/10.1109/JSTARS.2025.3557956
In the series “My paper in 140s”, scientists from the Collaborative Research Center 1502 'DETECT' present syntheses of their project work that have been published in peer-reviewed papers.
