Identification of non-linear influences on the seasonal ozone dose–response of sensitive and resistant clover clones using artificial neural networks

Ozone is a commonly occurring pollutant that has a large impact on the yield of agricultural crops. The dose–response of crops in the field is complex, with influences from numerous biotic and abiotic factors, including microclimatic variables. This paper presents results of a number of analysis methods of artificial neural network (ANN) models, developed on biomonitoring data from 12 countries, to identify the importance of interacting influences on the biomass response of sensitive (NC-S) and resistant (NC-R) clones of white clover (Trifolium repens L. cv. Regal). These methods of analysis were also used to identify the importance of influences on a subset of the data. Empirical equations were extracted from the ANN model with the best performance and these were analysed to determine their performance and to indicate the nature of microclimatic influences. Analysis indicated that combinations of VPD and the number of raindays were strong influences on the ozone dose–response and that temperature and the number of raindays had a secondary influence on the NC-S/NC-R biomass ratio irrespective of the ozone dose. Analysis of derived empirical equations indicated they compared well with the ANN model and that only a small loss in accuracy occurred.