Matches in SemOpenAlex for { <https://semopenalex.org/work/W2948265475> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2948265475 endingPage "14" @default.
- W2948265475 startingPage "3" @default.
- W2948265475 abstract "In the last years, deep learning has solved seemingly intractable problems, boosting the hope to find (approximate) solutions to problems that now are considered unsolvable. Earthquake prediction - a recognized moonshot challenge - is obviously worthwhile exploring with deep learning. Although encouraging results have been obtained recently, deep neural networks (DNN) may sometimes create the illusion that patterns hidden in data are complex when this is not necessarily the case. We investigate the results of De Vries et al. [Nature, vol. 560, 2018] who defined a DNN of 6 hidden layers with 50 nodes each, and with an input layer of 12 stress features, to predict aftershock patterns in space. The performance of their DNN was assessed using ROC with AUC = 0.85 obtained. We first show that a simple artificial neural network (ANN) of 1 hidden layer yields a similar performance, suggesting that aftershock patterns are not necessarily highly abstract objects. Following first principle guidance, we then bypass the elastic stress change tensor computation, making profit of the tensorial nature of neural networks. AUC = 0.85 is again reached with an ANN, now with only two geometric and kinematic features. Not only seems deep learning to be “excessive” in the present case, the simpler ANN streamlines the process of aftershock forecasting, limits model bias, and provides better insights into aftershock physics and possible model improvement. Complexification is a controversial trend in all of Science and first principles should be applied wherever possible to gain physical interpretations of neural networks." @default.
- W2948265475 created "2019-06-14" @default.
- W2948265475 creator A5033437426 @default.
- W2948265475 creator A5083128846 @default.
- W2948265475 date "2019-01-01" @default.
- W2948265475 modified "2023-09-24" @default.
- W2948265475 title "A Deeper Look into ‘Deep Learning of Aftershock Patterns Following Large Earthquakes’: Illustrating First Principles in Neural Network Physical Interpretability" @default.
- W2948265475 cites W1901616594 @default.
- W2948265475 cites W1934758505 @default.
- W2948265475 cites W1974415988 @default.
- W2948265475 cites W1980014734 @default.
- W2948265475 cites W1994425869 @default.
- W2948265475 cites W2020516950 @default.
- W2948265475 cites W2045264869 @default.
- W2948265475 cites W2048439777 @default.
- W2948265475 cites W2050127080 @default.
- W2948265475 cites W2050273408 @default.
- W2948265475 cites W2066437717 @default.
- W2948265475 cites W2069703366 @default.
- W2948265475 cites W2078721389 @default.
- W2948265475 cites W2086958198 @default.
- W2948265475 cites W2090503999 @default.
- W2948265475 cites W2106017075 @default.
- W2948265475 cites W2124799255 @default.
- W2948265475 cites W2133411430 @default.
- W2948265475 cites W2155263022 @default.
- W2948265475 cites W2221458827 @default.
- W2948265475 cites W2272629573 @default.
- W2948265475 cites W2298347151 @default.
- W2948265475 cites W2419175238 @default.
- W2948265475 cites W2762410434 @default.
- W2948265475 cites W2770754971 @default.
- W2948265475 cites W2782714865 @default.
- W2948265475 cites W2798828763 @default.
- W2948265475 cites W2799565130 @default.
- W2948265475 cites W2803629276 @default.
- W2948265475 cites W2888770834 @default.
- W2948265475 cites W2907292342 @default.
- W2948265475 cites W2919115771 @default.
- W2948265475 cites W2944868510 @default.
- W2948265475 cites W3100672003 @default.
- W2948265475 cites W3104319098 @default.
- W2948265475 cites W3104495034 @default.
- W2948265475 cites W3122457105 @default.
- W2948265475 cites W3124928229 @default.
- W2948265475 cites W4214518794 @default.
- W2948265475 cites W4243763178 @default.
- W2948265475 cites W4244487241 @default.
- W2948265475 doi "https://doi.org/10.1007/978-3-030-20521-8_1" @default.
- W2948265475 hasPublicationYear "2019" @default.
- W2948265475 type Work @default.
- W2948265475 sameAs 2948265475 @default.
- W2948265475 citedByCount "4" @default.
- W2948265475 countsByYear W29482654752020 @default.
- W2948265475 countsByYear W29482654752022 @default.
- W2948265475 countsByYear W29482654752023 @default.
- W2948265475 crossrefType "book-chapter" @default.
- W2948265475 hasAuthorship W2948265475A5033437426 @default.
- W2948265475 hasAuthorship W2948265475A5083128846 @default.
- W2948265475 hasConcept C108583219 @default.
- W2948265475 hasConcept C127313418 @default.
- W2948265475 hasConcept C154945302 @default.
- W2948265475 hasConcept C156801008 @default.
- W2948265475 hasConcept C165205528 @default.
- W2948265475 hasConcept C2781067378 @default.
- W2948265475 hasConcept C41008148 @default.
- W2948265475 hasConcept C50644808 @default.
- W2948265475 hasConceptScore W2948265475C108583219 @default.
- W2948265475 hasConceptScore W2948265475C127313418 @default.
- W2948265475 hasConceptScore W2948265475C154945302 @default.
- W2948265475 hasConceptScore W2948265475C156801008 @default.
- W2948265475 hasConceptScore W2948265475C165205528 @default.
- W2948265475 hasConceptScore W2948265475C2781067378 @default.
- W2948265475 hasConceptScore W2948265475C41008148 @default.
- W2948265475 hasConceptScore W2948265475C50644808 @default.
- W2948265475 hasLocation W29482654751 @default.
- W2948265475 hasOpenAccess W2948265475 @default.
- W2948265475 hasPrimaryLocation W29482654751 @default.
- W2948265475 hasRelatedWork W2605281151 @default.
- W2948265475 hasRelatedWork W2787767549 @default.
- W2948265475 hasRelatedWork W2902302341 @default.
- W2948265475 hasRelatedWork W3006943036 @default.
- W2948265475 hasRelatedWork W3191046242 @default.
- W2948265475 hasRelatedWork W3208423683 @default.
- W2948265475 hasRelatedWork W4206493799 @default.
- W2948265475 hasRelatedWork W4213225422 @default.
- W2948265475 hasRelatedWork W4299487748 @default.
- W2948265475 hasRelatedWork W4310880831 @default.
- W2948265475 isParatext "false" @default.
- W2948265475 isRetracted "false" @default.
- W2948265475 magId "2948265475" @default.
- W2948265475 workType "book-chapter" @default.