The auxiliary function method for waveform based earthquake location
For seismologists, AFM provides a faster and simpler alternative to iterative methods for earthquake location, though it is domain-specific and not a general ML/AI breakthrough.
The paper introduces the auxiliary function method (AFM) for waveform-based earthquake location, which constructs a function whose zero set contains the true hypocenter and origin time, achieving fast and accurate results even with large noise, with significantly lower computational cost than iterative methods.
This paper introduces the auxiliary function method (AFM), a novel, fast and simple approach for waveform based earthquake location. From any initial hypocenter and origin time, we can construct the auxiliary function, whose zero set contains the real earthquake hypocenter and the origin time. In most of situations, there are very few elements in this set. The overall computational cost of the AFM is significantly less than that of the iterative methods. According to our numerical tests, even for large noise, the method can still achieve good location results. These allow us to determine the earthquake hypocenter and the origin time extremely fast and accurate.