Evaluation model of crop contamination stress level based on dynamic fuzzy neural network

In this paper, the hyperspectral data, foliar chlorophyll content and heavy metal contents in foliar and soil were measured for the crop growing in three natural farmlands by measuring outdoors and indoor sample analyzing. Three indices including NDVI, TVI/MSAVI and MCARI/MSAVI, which were sensitive to crop growth circumstance, became importation parameters, with crop contamination stress level as output, in the process of crop contamination stress sensibility analysis with vegetation indices. And the dynamic fuzzy neural network model was built. The results indicated that the model had simple network structure and high function, and only six fuzzy rules could make emulation accuracy attain 90% and match an expectation request.