Improved impedance inversion by deep learning and iterated graph Laplacian

arXiv:2404.16324v1 Announce Type: cross
Abstract: Deep learning techniques have shown significant potential in many applications through recent years. The achieved results often outperform traditional techniques. However, the quality of a neural network highly depends on the used training data. Noisy, insufficient, or biased training data leads to suboptimal results.
We present a hybrid method that combines deep learning with iterated graph Laplacian and show its application in acoustic impedance inversion which is a routine procedure in seismic explorations. A neural …

abstract applications arxiv cs.lg cs.na data deep learning deep learning techniques eess.sp graph however leads math.na network neural network quality results through training training data type