Results are presented from the UN/ECE ICP Vegetation (International Cooperative Programme on effects of air pollution on natural vegetation and crops) experiments in which ozone(O(3))-resistant (NC-R) and -sensitive (NC-S) clones of white clover (Trifolium repens cv. Regal) were exposed to ambient O(3) episodes at 14 sites in eight European countries in 1996, 1997 and 1998. The plants were grown according to a standard protocol, and the forage was harvested every 28 days for 4-5 months per year by excision 7 cm above the soil surface. Biomass ratio (NC-S/NC-R) was related to the climatic and pollutant conditions at each site using multiple linear regression (MLR) and artificial neural networks (ANNs). Twenty-one input parameters [e.g. AOT40, 7-h mean O(3) concentration, daylight vapour pressure deficit (VPD), daily maximum temperature] were considered individually and in combination with the aim of developing a model with high r(2) and simple structure that could be used to predict biomass change in white clover. MLR models were generally more complex, and performed less well for unseen data than non-linear ANN models. The ANN model with the best performance had five inputs with an r(2) value of 0.84 for the training data, and 0.71 for previously unseen data. Two inputs to the model described the O(3) conditions (AOT40 and 24-h mean for O(3)), two described temperature (daylight mean and 24-h mean temperature), and the fifth input appeared to be differentiating between semi-urban and rural sites (NO concentration at 17:00). Neither VPD nor harvest interval was an important component of the model. The model predicted that a 5% reduction in biomass ratio was associated with AOT40s in the range 0.9-1.7 ppm x h (microl l(-1) h) accumulated over 28 days, with plants being most sensitive in conditions of low NO(x), medium-range temperature, and high 24-h mean O(3) concentration.