Hype-M Using HYPErspectral EnMAP Data for upscaling and long-term monitoring of Microbial activity in the phyllosphere [funded by DLR]
Project staff:
MSc Nizom Farmonov
Abstract:
The aim of the Hype-M project is, on the basis of the spatially high-resolution monitoring data from the LOEWE focus Tree-M (leaf properties, leaf microbiome, leaf hyperspectral and leaf/canopy climate), data sets of essential variables and predictors to derive machine learning models (ML) to enable upscaling of leaf microbiome activity to entire forest areas. With the underlying AI models, spatially explicit monitoring of the interaction of leaf properties and microbes in the phyllosphere would be possible for the first time. This opens up new possibilities for larger-scale, extensive monitoring of the Interaction of environmental factors, leaf properties, and microbial activity. Based on a four-year interdisciplinary research and monitoring program mainly aimed at the leaf as an interaction space (Tree-M, https://www.uni-marburg.de/de/fb17/tree-m), the aim of the HYPE-M project applied for here is to Marburg University Forest as a research and monitoring core facility to use unique monitoring data to determine essential core parameters of the leaf microbial Interaction over the phenological cycle to scale up to the forest level and thus their to enable long-term monitoring over large areas.
