Climate drift is a common and serious problem in most state-of-the-art
coupled atmosphere-ocean-sea ice models. We consider the nature of cl
imate drift in such a model, and in particular address the question of
whether or not climate drift is inherent to the model, or whether the
drift can be averted by a suitable choice of initial conditions or co
upling procedure. The ''synchronous'' approach to coupling was adopted
in which the ocean, atmosphere and sea ice models were spun-up indepe
ndently to equilibrium using climatological forcing fields. The models
were then coupled and integrated forward in time. Several experiments
were performed which were designed to assess the impact of different
coupling methodologies and changes in the initial conditions of the co
mponent models on the climate drift of the system. The results of our
experiments indicate that climate drift is a problem inherent to the c
oupled model in that systematic errors in the components lead to incom
patibilities in the surface fluxes required by the component models to
maintain realistic climatologies. We conclude that climate drift can
be averted only if the parameterizations of certain important physical
processes are improved which should have the effect of reducing or el
iminating these incompatibilities.