A drop of ink falls into moving water.
If we know the ink particles are concentrated in a small area, there are much less possible states the system can occupy under this restriction than if all places in the liquid are allowed for ink particles.
So, if you wait some time, the states where all ink particles are
gathered in that small space are just a very very minute part of all
accessible states.
They are very very improbable , and this accounts for the empirical fact that they don't come back by themselves.
For that to happen, all ink particles had to move in the
correct direction by chance. This is very unlikely! It might happen if
there was a little person kicking them all in the correct way... But
that would be an intervention from outside. It does not happen by
itself.
[auf deutsch]