Matches in SemOpenAlex for { <https://semopenalex.org/work/W3128528073> ?p ?o ?g. }
Showing items 1 to 62 of
62
with 100 items per page.
- W3128528073 abstract "Summary Inversion of geophysical data is often challenging and time-consuming, particularly for large scale surveys. The solution of the inverse problem requires numerous calculations of the forward problem, especially when calculating partial derivatives required for most linearized inversion schemes. The forward model is usually calculated numerically using accurate equations, but often less accurate and faster equations are used. In recent years, neural networks have become increasingly popular to replace the numerical forward modelling, as this may lead to a significant speed-up. Data normalization, prior to the training of neural networks, is crucial to obtain good results and faster convergence rate. This is especially true for geophysical data, as numerical data values may span over several orders of magnitude. In this abstract, we investigate several normalization approaches for TEM data, with a special focus on towed TEM data. Through extensive experimentations, we show that data normalization substantially affects the performance of neural networks when surrogating forward models. We also demonstrate the effect of normalized data variation on neural network’s performance and provide insights into which normalization approaches may be better than others. A significant improvement in performance accuracy is achieved when the appropriate data normalization technique is employed." @default.
- W3128528073 created "2021-02-15" @default.
- W3128528073 creator A5050489763 @default.
- W3128528073 creator A5057504959 @default.
- W3128528073 creator A5060536093 @default.
- W3128528073 creator A5067986636 @default.
- W3128528073 creator A5076681344 @default.
- W3128528073 date "2020-01-01" @default.
- W3128528073 modified "2023-09-23" @default.
- W3128528073 title "Effect of Data Normalization on Neural Networks for the Forward Modelling of Transient Electromagnetic Data" @default.
- W3128528073 doi "https://doi.org/10.3997/2214-4609.202020061" @default.
- W3128528073 hasPublicationYear "2020" @default.
- W3128528073 type Work @default.
- W3128528073 sameAs 3128528073 @default.
- W3128528073 citedByCount "0" @default.
- W3128528073 crossrefType "proceedings-article" @default.
- W3128528073 hasAuthorship W3128528073A5050489763 @default.
- W3128528073 hasAuthorship W3128528073A5057504959 @default.
- W3128528073 hasAuthorship W3128528073A5060536093 @default.
- W3128528073 hasAuthorship W3128528073A5067986636 @default.
- W3128528073 hasAuthorship W3128528073A5076681344 @default.
- W3128528073 hasConcept C11413529 @default.
- W3128528073 hasConcept C134306372 @default.
- W3128528073 hasConcept C135252773 @default.
- W3128528073 hasConcept C136886441 @default.
- W3128528073 hasConcept C144024400 @default.
- W3128528073 hasConcept C154945302 @default.
- W3128528073 hasConcept C19165224 @default.
- W3128528073 hasConcept C33923547 @default.
- W3128528073 hasConcept C41008148 @default.
- W3128528073 hasConcept C50644808 @default.
- W3128528073 hasConcept C67186912 @default.
- W3128528073 hasConcept C77088390 @default.
- W3128528073 hasConceptScore W3128528073C11413529 @default.
- W3128528073 hasConceptScore W3128528073C134306372 @default.
- W3128528073 hasConceptScore W3128528073C135252773 @default.
- W3128528073 hasConceptScore W3128528073C136886441 @default.
- W3128528073 hasConceptScore W3128528073C144024400 @default.
- W3128528073 hasConceptScore W3128528073C154945302 @default.
- W3128528073 hasConceptScore W3128528073C19165224 @default.
- W3128528073 hasConceptScore W3128528073C33923547 @default.
- W3128528073 hasConceptScore W3128528073C41008148 @default.
- W3128528073 hasConceptScore W3128528073C50644808 @default.
- W3128528073 hasConceptScore W3128528073C67186912 @default.
- W3128528073 hasConceptScore W3128528073C77088390 @default.
- W3128528073 hasLocation W31285280731 @default.
- W3128528073 hasOpenAccess W3128528073 @default.
- W3128528073 hasPrimaryLocation W31285280731 @default.
- W3128528073 hasRelatedWork W10991549 @default.
- W3128528073 hasRelatedWork W11546141 @default.
- W3128528073 hasRelatedWork W11910705 @default.
- W3128528073 hasRelatedWork W12865176 @default.
- W3128528073 hasRelatedWork W13478224 @default.
- W3128528073 hasRelatedWork W13550978 @default.
- W3128528073 hasRelatedWork W14383863 @default.
- W3128528073 hasRelatedWork W5626169 @default.
- W3128528073 hasRelatedWork W8153826 @default.
- W3128528073 hasRelatedWork W9605419 @default.
- W3128528073 isParatext "false" @default.
- W3128528073 isRetracted "false" @default.
- W3128528073 magId "3128528073" @default.
- W3128528073 workType "article" @default.