English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Among the biggest challenges we face in utilizing neural networks trained onwaveform data (i.e., seismic, electromagnetic, or ultrasound) is itsapplication to real data. The requirement for accurate labels forces us todevelop solutions using synthetic data, where labels are readily available.However, synthetic data often do not capture the reality of the field/realexperiment, and we end up with poor performance of the trained neural network(NN) at the inference stage. We describe a novel approach to enhance supervisedtraining on synthetic data with real data features (domain adaptation).Specifically, for tasks in which the absolute values of the vertical axis (timeor depth) of the input data are not crucial, like classification, or can becorrected afterward, like velocity model building using a well-log, we suggesta series of linear operations on the input so the training and application datahave similar distributions. This is accomplished by applying two operations onthe input data to the NN model: 1) The crosscorrelation of the input data(i.e., shot gather, seismic image, etc.) with a fixed reference trace from thesame dataset. 2) The convolution of the resulting data with the mean (or arandom sample) of the autocorrelated data from another domain. In the trainingstage, the input data are from the synthetic domain and the auto-correlateddata are from the real domain, and random samples from real data are drawn atevery training epoch. In the inference/application stage, the input data arefrom the real subset domain and the mean of the autocorrelated sections arefrom the synthetic data subset domain. Example applications on passive seismicdata for microseismic event source location determination and active seismicdata for predicting low frequencies are used to demonstrate the power of thisapproach in improving the applicability of trained models to real data.

MLReal: Bridging the gap between training on synthetic data and real data applications in machine learning