FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3027393011> ?p ?o ?g. }

• W3027393011 abstract "In biomedical engineering, earthquake prediction, and underground energy harvesting, it is crucial to indirectly estimate the physical properties of porous media since the direct measurement of those are usually impractical/prohibitive. Here we apply the physics-informed neural networks to solve the inverse problem with regard to the nonlinear Biot's equations. Specifically, we consider batch training and explore the effect of different batch sizes. The results show that training with small batch sizes, i.e., a few examples per batch, provides better approximations (lower percentage error) of the physical parameters than using large batches or the full batch. The increased accuracy of the physical parameters, comes at the cost of longer training time. Specifically, we find the size should not be too small since a very small batch size requires a very long training time without a corresponding improvement in estimation accuracy. We find that a batch size of 8 or 32 is a good compromise, which is also robust to additive noise in the data. The learning rate also plays an important role and should be used as a hyperparameter." @default.
• W3027393011 created "2020-05-29" @default.
• W3027393011 creator A5048751702 @default.
• W3027393011 creator A5064097618 @default.
• W3027393011 creator A5074522311 @default.
• W3027393011 date "2020-05-18" @default.
• W3027393011 modified "2023-09-27" @default.
• W3027393011 title "Physics-informed Neural Networks for Solving Inverse Problems of Nonlinear Biot's Equations: Batch Training" @default.
• W3027393011 cites W1019830208 @default.
• W3027393011 cites W1522301498 @default.
• W3027393011 cites W1589221889 @default.
• W3027393011 cites W1741578612 @default.
• W3027393011 cites W1928419358 @default.
• W3027393011 cites W1977727715 @default.
• W3027393011 cites W2009420010 @default.
• W3027393011 cites W2035096829 @default.
• W3027393011 cites W2055072688 @default.
• W3027393011 cites W2074377477 @default.
• W3027393011 cites W2120548916 @default.
• W3027393011 cites W2133041109 @default.
• W3027393011 cites W2133490810 @default.
• W3027393011 cites W2141655040 @default.
• W3027393011 cites W2161023636 @default.
• W3027393011 cites W2163605009 @default.
• W3027393011 cites W2276196763 @default.
• W3027393011 cites W2338951703 @default.
• W3027393011 cites W2471838046 @default.
• W3027393011 cites W2490045648 @default.
• W3027393011 cites W2507348356 @default.
• W3027393011 cites W2533800772 @default.
• W3027393011 cites W2766179339 @default.
• W3027393011 cites W2811238296 @default.
• W3027393011 cites W2899283552 @default.
• W3027393011 cites W2904093502 @default.
• W3027393011 cites W2919115771 @default.
• W3027393011 cites W2955494838 @default.
• W3027393011 cites W2963959597 @default.
• W3027393011 cites W2964036789 @default.
• W3027393011 cites W2969933721 @default.
• W3027393011 cites W3010415407 @default.
• W3027393011 cites W3016078479 @default.
• W3027393011 cites W3021801979 @default.
• W3027393011 cites W3022923642 @default.
• W3027393011 cites W3105469151 @default.
• W3027393011 cites W3105665595 @default.
• W3027393011 cites W589949662 @default.
• W3027393011 cites W656657393 @default.
• W3027393011 cites W2086246343 @default.
• W3027393011 hasPublicationYear "2020" @default.
• W3027393011 type Work @default.
• W3027393011 sameAs 3027393011 @default.
• W3027393011 citedByCount "0" @default.
• W3027393011 crossrefType "posted-content" @default.
• W3027393011 hasAuthorship W3027393011A5048751702 @default.
• W3027393011 hasAuthorship W3027393011A5064097618 @default.
• W3027393011 hasAuthorship W3027393011A5074522311 @default.
• W3027393011 hasConcept C11413529 @default.
• W3027393011 hasConcept C115341296 @default.
• W3027393011 hasConcept C115961682 @default.
• W3027393011 hasConcept C119857082 @default.
• W3027393011 hasConcept C121332964 @default.
• W3027393011 hasConcept C126255220 @default.
• W3027393011 hasConcept C134306372 @default.
• W3027393011 hasConcept C135252773 @default.
• W3027393011 hasConcept C153294291 @default.
• W3027393011 hasConcept C154945302 @default.
• W3027393011 hasConcept C158622935 @default.
• W3027393011 hasConcept C207467116 @default.
• W3027393011 hasConcept C2524010 @default.
• W3027393011 hasConcept C2777211547 @default.
• W3027393011 hasConcept C28826006 @default.
• W3027393011 hasConcept C33923547 @default.
• W3027393011 hasConcept C41008148 @default.
• W3027393011 hasConcept C50644808 @default.
• W3027393011 hasConcept C57879066 @default.
• W3027393011 hasConcept C62520636 @default.
• W3027393011 hasConcept C8642999 @default.
• W3027393011 hasConcept C99498987 @default.
• W3027393011 hasConceptScore W3027393011C11413529 @default.
• W3027393011 hasConceptScore W3027393011C115341296 @default.
• W3027393011 hasConceptScore W3027393011C115961682 @default.
• W3027393011 hasConceptScore W3027393011C119857082 @default.
• W3027393011 hasConceptScore W3027393011C121332964 @default.
• W3027393011 hasConceptScore W3027393011C126255220 @default.
• W3027393011 hasConceptScore W3027393011C134306372 @default.
• W3027393011 hasConceptScore W3027393011C135252773 @default.
• W3027393011 hasConceptScore W3027393011C153294291 @default.
• W3027393011 hasConceptScore W3027393011C154945302 @default.
• W3027393011 hasConceptScore W3027393011C158622935 @default.
• W3027393011 hasConceptScore W3027393011C207467116 @default.
• W3027393011 hasConceptScore W3027393011C2524010 @default.
• W3027393011 hasConceptScore W3027393011C2777211547 @default.
• W3027393011 hasConceptScore W3027393011C28826006 @default.
• W3027393011 hasConceptScore W3027393011C33923547 @default.
• W3027393011 hasConceptScore W3027393011C41008148 @default.
• W3027393011 hasConceptScore W3027393011C50644808 @default.
• W3027393011 hasConceptScore W3027393011C57879066 @default.
• W3027393011 hasConceptScore W3027393011C62520636 @default.
• W3027393011 hasConceptScore W3027393011C8642999 @default.
• W3027393011 hasConceptScore W3027393011C99498987 @default.

• next