2019/05/31 by Jesper Dramsch, Jesper Sören Dramsch, Mikael Lüthje +1 · 45 citations
Computer Science · Engineering · Mathematics · Physics and Astronomy · #Advanced Data Processing Techniques #Artificial intelligence #Artificial neural network #Computer science #Machine learning #Neural Networks and Applications #Time Series Analysis and Forecasting #cs.CV #cs.LG #physics.comp-ph #physics.geo-ph #stat.ML
paper · pdf · doi:10.1016/j.cageo.2020.104643
published in Computers & Geosciences 146, 104643 (Elsevier BV) · 17 pages total, 15 pages, 2 pages references, paper, 11 figures, 28 networks
arxiv created 2019/11/26 · openalex publication_date 2020/11/04 · arxiv updated 2020/11/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Deep learning has become an area of interest in most scientific areas, including physical sciences. Modern networks apply real-valued transformations on the data. Particularly, convolutions in convolutional neural networks discard phase information entirely. Many deterministic signals, such as seismic data or electrical signals, contain significant information in the phase of the signal. We explore complex-valued deep convolutional networks to leverage non-linear feature maps. Seismic data commonly has a lowcut filter applied, to attenuate noise from ocean waves and similar long wavelength contributions. Discarding the phase information leads to low-frequency aliasing analogous to the Nyquist-Shannon theorem for high frequencies. In non-stationary data, the phase content can stabilize training and improve the generalizability of neural networks. While it has been shown that phase content can be restored in deep neural networks, we show how including phase information in feature maps improves both training and inference from deterministic physical data. Furthermore, we show that the reduction of parameters in a complex network outperforms larger real-valued networks.