CC BY 4.0Cvejoski, KostadinKostadinCvejoskiSchücker, JannisJannisSchückerMahlein, Anne-KatrinAnne-KatrinMahleinGeorgiev, BogdanBogdanGeorgiev2024-08-262024-10-282024-08-262021-10-26https://doi.org/10.24406/publica-3600https://publica.fraunhofer.de/handle/publica/47406810.24406/publica-36002111.00918v1In this work we combine representation learning capabilities of neural network with agricultural knowledge from experts to model environmental heat and drought stresses. We first design deterministic expert models which serve as a benchmark and inform the design of flexible neural-network architectures. Finally, a sensitivity analysis of the latter allows a clustering of hybrids into susceptible and resistant ones.enneural networksdeterministic expert-driven modelsinformed machine learningagriculturerepresentation learningpaper