A functional regression model to forecast the cypress pollen concentration during a given time interval, considering the air temperature in a previous interval as the input, is derived by means of a two-step procedure. This estimation is carried out by functional principal component (FPC) analysis and the residual noise is also modeled by FPC regression, taking as the explicative process the pollen concentration during the earlier interval. The prediction performance is then tested on pollen data series recorded in Granada (Spain) over a period of 10 years.