Counterfactual Explanations of Nitrogen Response Curves

In precision agriculture, fertilizer responsivity can be characterized using nitrogen fertilizer-yield response (N-response) curves. These curves exhibit the estimated crop yield values corresponding to a specific field site in response to all admissible fertilizer rate. The shape of response curves generated for a selected input feature might depend on the values of the other input features. We consider the case of systems whose response is approximated using regression neural networks. In this talk, I explained the use of counterfactual explanations (CFEs) for the identification of the features with the highest relevance on the shape of response curves generated by neural network black boxes. Results obtained on the yield prediction datasets revealed that the impact on fertilizer responsivity of passive features depends on the terrain characteristics of each field.

Jan 11, 2024 —