| dc.description.abstract | Rainfall extremes which cause floods or droughts are known to have
capacity to destroy many years of national economic investments on roads,
industries, energy, agriculture and other social economic infrastructures.
Efforts have thus been carried out in this study to address the space-time .
characteristics of wet and dry spells, which causes extremes to minimize
The study narrowed down to a number of specific objectives. They
various risks that are associated with negative impacts of rainfall and climate
extremes.included examination of the characteristics of the wet/dry spells in terms of
frequency/probability distribution,. modeling occurrence of rain and daily
amounts during the major rainfall seasons. Others were examination of trend
and cyclical characteristics of the weUdry spells to detect any significant inter
annual changes. The thitd involved examination of the differences in the
patterns of dry/wet spells during some years with unique atmospheric
circulation like during the\periods with strong Indian Ocean Dipole and EI Nino
Southern Oscillation. The last was on potential to derive projection scenarios
of the weUdry spells based on Indian Ocean Dipole and EI Nino Southern
Oscillation evolutions.
The datasets used in this study included daily rainfall from 22 locations
in Tanzania, sea surface temperature over the tropical Indian Ocean from
which Indian Ocean Dipole indices were derived and Southern Oscillation
Indices from the Pacific Ocean. The period of data was for the period 1960 -
2000. Methods of analyses included residual mass curves for data quality;
frequency/probability analyses; fitting of Markov chain models to occurrence
of rain; fitting of gamma models to daily rainfall amount; composite analyses;
trend, spectral and wavelet analyses together with correlation and regression
methods.
Residual mass curves indicated that data used was of good quality for
sound statistical inferences. Mean duration of seasons for the bimodal
locations observed to last for about 73 and 61 days during March-May and
October-December seasons respectively and for about 168 days on unimodal
stations during October-May season. As for the frequency of wet/dry spells,
the longest run of 28 days of wet spells was observed on the highland stations
while the longest run of dry spells of 249 days was observed in 1999 in central
Tanzania.
Markov chain models simulated wet/dry spells using first order Markov
chain models quite realistically and compared well with the observed
especially in the wetter parts of Tanzania. Gamma distribution on the other
hand, fitted the deily amount of rainfall best with the shape parameter (k) for
the' fitted gamma distri~ution rangihg from 0.59 to 0.98 an indication of large
coefficient of variations that increased from wetter high grounds to the semi
arid parts of Tanzania.
Rainfall trends were noted to be localized over most parts of Tanzania.
Positive trends were observed over parts of Lake Victoria basin during March,
April and May and October, November and December seasons and south
eastern highland~of Tanzania during the October to May single season.
Negative trends were common over the western parts of southern Tanzania
around Lake Tanganyika and north eastern highlands of the country. Spectral
and wavelet analyses indicated spectral bands of 5 to 7 days, 10 to 15 days
and 20 to 30 days at most locations in Tanzania. Dominance of wavelet bands
of more than 20 days over bimodal locations in northern Tanzania during
October -December wet season may indicate sensitivity of the phases of MJO
in the region. Composite analyses showed that the number of wet (dry) spells
was greatly enhanced at most of locations during the years of strong positive
(negative) ENSO and 100 events. It was also shown that some simple time
lagged regression equations based on 100 and SOl predictors could be used
to build some scenarios of the expected wet/dry spells.
The study has hence identified some unique space-time characteristics
of the wet/dry spells in Tanzania that are quite useful in the monitoring,
building expectation scenarios, planning and management of many
weather/climate sensitive activities including agriculture and water resources.
The findings could also be useful for the policy makers to address some of the
climate risk management challenges to various climate sensitive sectors and
enhance the national disaster management, poverty reduction and national
sustainable development efforts | en |
