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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Autoencoders are neural network formulations where the input and output ofthe network are identical and the goal is to identify the hidden representationin the provided datasets. Generally, autoencoders project the data nonlinearlyonto a lower dimensional hidden space, where the important features gethighlighted and interpretation of the data becomes easier. Recent studies haveshown that even in the presence of noise in the input data, autoencoders can betrained to reconstruct the noisefree component of the data from thereduced-dimensional hidden space.  In this paper, we explore the application of autoencoders within the scope ofdenoising geophysical datasets using a data-driven methodology. The autoencoderformulation is discussed, and a stacked variant of deep autoencoders isproposed. The proposed method involves locally training the weights first usingbasic autoencoders, each comprising a single hidden layer. Using theseinitialized weights as starting points in the optimization model, the fullautoencoder network is then trained in the second step. The applicability ofdenoising autoencoders has been demonstrated on a basic mathematical exampleand several geophysical examples. For all the cases, autoencoders are found tosignificantly reduce the noise in the input data.

Stacked autoencoders based machine learning for noise reduction and signal reconstruction in geophysical data