Combining expert knowledge and neural networks to model environmental stresses in agriculture
This work addresses agricultural modeling for crop stress prediction, but it appears incremental as it builds on existing methods by integrating expert knowledge.
The authors tackled the problem of modeling environmental heat and drought stresses in agriculture by combining neural networks with expert knowledge, resulting in a method that clusters hybrids into susceptible and resistant categories through sensitivity analysis.
In 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.