[Paper review] Reconstruct missing traces with Deep Learning

Research papers
Missing traces can hurt seismic attribute calculation and overall seismic interpretability with state-of-the-art methods.
The paper 🔺Xintao Chai et al., 2020, Deep learning for irregularly and regularly missing data reconstruction🔺 uses mixed synthetic and field datasets to train U-net like the neural network to combat the problem of missing data. 
Once the network is fully trained, they test it on a diverse field data set and compare it with the Fourier transform interpolation method. The testing shows the effectiveness, superiority, and generalization capability of the proposed technique.

Link to the paper:
Link to the LinkedIn post