[Previous Article]
[Next Article]
Neural Network to Predict AShort Rains at the Coast of East Africa
for Boreal Autumn 1996
contributed by Larry Greischar and Stefan Hastenrath
University of Wisconsin, Madison, Wisconsin
The coastal region of East Africa has its Ashort rains@
season in boreal autumn, and its Along rains@ period in boreal spring.
The diagnostics of East African rainfall anomalies have been discussed
in Hastenrath et al. (1993). In particular, the autumnal rains were shown
to have a strong relationship with concurrent equatorial zonal winds. The
predictand here is a 7-station average of the normalized departures from
the 1931-60 mean for Sep-Oct-Nov-Dec (SOND) and for Oct-Nov (ON). The stations
are Lamu, Malindi, Mombasa and Voi in Kenya; and Dar Es Salaam, Tanga and
Bagamoyo in Tanzania. The predictors are simply the values of the predictand
itself for the 7 years immediately preceding the forecast year, averaged
over the respective target seasons (SOND or ON). That the most recent predictor
data is nearly a year prior to the beginning of the target period provides
the opportunity for multiseason lead times for these forecasts. Thus, once
the data for December 1995 became available, this forecast for fall 1996
Ashort rains@ could be made.
The methodology used to relate the 7-station mean rainfall
anomaly over the prior 7 years to that of the following year is a neural
network, as described in Hastenrath et al. (1995) in the context of South
African summer rainfall prediction. Neural nets have been found more successful
in predicting East Africa=s Ashort rains@ than multiple regression, especially
when the predictor is a series of values of the predictand itself for previous
years. This success was found in forecasts for South Africa as well, although
multiple regression also produced a reasonably skillful forecast (see the
Greischar and Hastenrath presentation on p. 24 of the December 1994, and
p. 27 of the December 1995, issues of this Bulletin).
The neural network models were developed over the training
period of 1928-78, and tested on the independent verification period of
1979-94 for realistic skill estimation. Resulting skills are expressed
in a correlation framework: For the SOND period 45% of the predictand variance
is explained, and for ON 38% is explained.
The standardized rainfall anomalies over the last 7 years
have been as follows:
1989 |
1990 |
1991 |
1992 |
1993 |
1994 |
1995 |
|
SOND |
0.89 |
0.54 |
-0.01 |
0.65 |
0.08 |
2.04 |
0.34 |
ON |
0.96 |
0.46 |
-0.09 |
0.44 |
0.16 |
1.49 |
0.72 |
Because the neural net models have an intermediate (hidden) layer of 3 nodes, the weighting formula applied to the past 7 years is not readily apparent from the system weights.
The neural-based forecast for boreal autumn 1996 is shown
in the following table:
Forecast |
Mean/SD |
Best |
|
Standardized |
Rainfall (mm) |
Analog |
|
Anomaly |
1931-60 |
Years |
|
SOND |
+0.04 |
238 / 126 |
1969,80,91,93 |
ON |
+0.06 |
124 / 95 |
1973,86,91,93 |
The 1995 predictions of -0.95 for SOND and -0.37 for ON
performed less well than expected by the model statistics over the verification
period. A diagnostic reason for this low performance cannot be identified
from this purely statistical technique. For boreal autumn 1996, rainfall
is expected to be close to the long-term mean.
Hastenrath, S., A. Nicklis and L. Greischar, 1993: Atmospheric-hydrospheric
mechanisms of climate anomalies in the western equatorial Indian Ocean.
J. Geophys. Res. (oceans), 98 (C11), 20219-20235.
Hastenrath, S., L. Greischar and J. Van Heerden, 1995:
Prediction of the summer rainfall over South Africa. J. Climate,
8, 1511-1518.