Trupti satapathy biography of martin
•
•
Your " + userProjectSpecificShortCut + " account
Accurate mapping and monitoring of forest tree species are crucial for understanding ecosystem dynamics [1], assessing biodiversity [2], and enabling sustainable forest management [3]. Tree species adapt their morphology and phenology to the environment [4], leading to variability in spectral signatures across geographic regions. Furthermore, the spectral reflectance of a given tree species varies significantly with growth stages and seasons [5], making the classification based solely on RGB data extremely challenging. At the local level, spectral variability also closely correlates with stand structure factors such as crown size, stand density, and gap sizes. This results in varying signal reflectance from different parts of the same crown, further complicating tree species classification [6]. Thus, we proposed a spectral-spatial-temporal constrained deep learning method, an end-to-end multi-head attention-based network, to automati
•
Project-specific account required
Soil Moisture (SM) is one of the key observable variables of the hydrological cycle and therefore of high importance for many disciplines, from meteorology to agriculture. This contribution presents a comparison of different products for the mapping of SM. The aim was to identify the best available solution for the operational monitoring of SM as a drought indicator for the entire area of the European Alps, to be applied in the context of the Interreg Alpine Space project, the Alpine Drought Observatory.
The following datasets were considered: Soil Water Index (SWI) of the Copernicus Global Land Service [1]; ERA5 [2]; ERA5-Land [3]; UERRA MESCAN-SURFEX land-surface component [4]. All four datasets offer a different set of advantages and disadvantages related to their spatial resolution, update frequency and latency. As a reference, modelled SM time-series for catchments in Switzerland were used [5]. Switzerland is well suited as a test case for th