We discuss the possibility of forecasting earthquakes by means of (anti)neutrino tomography. An- tineutrinos emitted from reactors are used as a probe. As the antineutrinos traverse through a region prone to earthquakes, observable variations in the matter effect on the antineutrino oscillation would provide a tomog- raphy of the vicinity of the region. In this preliminary work, we adopt a simplified model for the geometrical profile and matter density in a fault zone. We calculate the survival probability of electron antineutrinos for cases without and with an anomalous accumulation of electrons which can be considered as a clear signal of the coming earthquake, at the geological region with a fault zone, and find that the variation may reach as much as 3% for ν emitted from a reactor. The case for a ν beam from a neutrino factory is also investigated, and it is noted that, because of the typically high energy associated with such neutrinos, the oscillation length is too large and the resultant variation is not practically observable. Our conclusion is that with the present reactor facilities and detection techniques, it is still a difficult task to make an earthquake forecast using such a scheme, though it seems to be possible from a theoretical point of view while ignoring some uncertainties. However, with the development of the geology, especially the knowledge about the fault zone, and with the improvement of the detection techniques, etc., there is hope that a medium-term earthquake forecast would be feasible.