[A new prediction method for the total pollen counts of Cryptomeria japonica based on variation in annual summertime temperature].

In order to predict the total pollen counts of Cryptomeria japonica, we examined the difference of summertime temperature between the previous year and the year before the previous. Correlation coefficients of nine points throughout Japan exceeded more than r = 0.84 when compared the total pollen counts obtained from prediction and those from observation. The best correlation at four out of nine places was obtained with mean temperature of July, however, mean temperature of August or maximum temperature of August (or July) exceeded at some places. The differences, between observed values and predicted values are within 1000 grains/cm2 in 101 cases out of 135 cases (75%). Prediction errors at the year of bumper crop of male flower were less than 40% and the average is 17.5%. It is considered that our new method is useful enough for prediction, especially, the year of bumper crop of male flower.