Real-time predictions of the rainfall in July--September 1997 and January--March 1998, respectively, for the Sahel and southern Africa at 1 month lead are presented. The forecast technique is based on canonical correlation analysis (CCA), a multivariate linear statistical model that relates patterns in the predictand field to patterns in the predictor field. In this CCA design, four consecutive 3 month predictor periods are followed by a lead time and a single 3 month predictand period. Cross validation is used to estimate the skill in the forecasts. The forecasts are expressed in terms of departures from climatological probabilities of three equiprobable categories for above-, near-, and below-normal rainfall. Expressing the forecasts in terms of probability anomalies communicates the level of confidence in the forecasts. Forecast verifications have been performed using the Heidke skill (S) score. For the Sahel the July--September 1997 rainfall prediction at 1 month lead showed reasonable skill. Furthermore, it is shown that the Sahel rainfall in July--September is influenced at least partly by El Nino-Southern Oscillation (ENSO). In addition, Sahel rainfall is affected by the sea surface temperature pattern in the Atlantic Ocean and perhaps the Indian Ocean. For southern Africa, the S score was +30, suggesting a moderately good forecast for the region as a whole. The results also indicate that ENSO plays an important role in modulating rainfall variations in southern Africa. ¿ 1999 American Geophysical Union