Pollen-related respiratory allergies affect up to 30% of the world's population. Climate change is further exacerbating the problem. However, forecasting pollen fields is extremely difficult. PollenNet aims to provide a more accurate and up-to-date forecast of local pollen loads.
Pollen-related allergies cause high medical costs, lead to missed work and school, and result in early deaths. Due to climate change, more and more aggressive pollen is expected over longer periods in the coming years.
Using and further developing AI methods, the team led by Prof. Dr. Patrick Mäder at TU Ilmenau is pursuing four goals:
(1) accurate analysis and prediction of the distribution of allergenic plants and in particular their growth phases (phenology), (2) better characterization of pollen properties, in particular with respect to allergenicity and dispersal, by means of cytometer analyses and fluid mechanics experiments, (3) development of pollen transport and dispersal models for high-resolution local, temporal and taxonomic prediction of pollen loads, and (4) exploration of objective individual markers in the EEG for allergy sufferers in the home environment.
From the integration of these findings, we aim to develop an approach that will enable much more accurate and up-to-date prediction of local pollen exposure.