Instance weighting-based Knowledge Transfer Network for Seismic Fault Detection

Geological Fault Detection is a crucial aspect of earthquake prediction and oil exploration. With the advancements in deep learning, the challenging task of accurate fault detection has gained popularity. While the traditional deep learning methods struggle due to the labeling process, training a model solely on synthetic data may not yield satisfactory results due to the disparities between synthetic and real seismic data. To mitigate the impact of these differences, we propose employing an instance weighting-based transfer learning. This allows the model to adapt to only the unique characteristics of the geological data. The proposed method yields satisfying results on the Indian Krishna Godavari Basin dataset.