Estimating germination of Plasmopara viticola oospores by means of neural networks

Neural networks are trained to estimate the germination percentages of Plasmopara viticola oospores, overwintered in natural conditions in two viticultural areas in northern Italy, by using climatic (temperature and rainfall) data, as well as the previous germination measurement, as input variables. The 288 available patterns consist of a set of selected independent variables associated with the corresponding germination percentage. All 12 networks investigated converge to a non-linear relationship between the selected independent variables and oospore germination. The highest correlation coefficient (equal to 0.83) between the real and estimated germination percentages is obtained by considering, as input to the network, the climatic data (both temperature and rainfall) recorded during the 40 days before sampling and the germination percentage assessed in the germination assay carried out immediately before the present sampling.