Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385597669> ?p ?o ?g. }
- W4385597669 endingPage "133852" @default.
- W4385597669 startingPage "133852" @default.
- W4385597669 abstract "Classical problems in computational physics such as data-driven forecasting and signal reconstruction from sparse sensors have recently seen an explosion in deep neural network (DNN) based algorithmic approaches. However, most DNN models do not provide uncertainty estimates, which are crucial for establishing the trustworthiness of these techniques in downstream decision making tasks and scenarios. In recent years, ensemble-based methods have achieved significant success for the uncertainty quantification in DNNs on a number of benchmark problems. However, their performance on real-world applications remains under-explored. In this work, we present an automated approach to DNN discovery and demonstrate how this may also be utilized for ensemble-based uncertainty quantification. Specifically, we propose the use of a scalable neural and hyperparameter architecture search for discovering an ensemble of DNN models for complex dynamical systems. We highlight how the proposed method not only discovers high-performing neural network ensembles for our tasks, but also quantifies uncertainty seamlessly. This is achieved by using genetic algorithms and Bayesian optimization for sampling the search space of neural network architectures and hyperparameters. Subsequently, a model selection approach is used to identify candidate models for an ensemble set construction. Afterwards, a variance decomposition approach is used to estimate the uncertainty of the predictions from the ensemble. We demonstrate the feasibility of this framework for two tasks - forecasting from historical data and flow reconstruction from sparse sensors for the sea-surface temperature. We demonstrate superior performance from the ensemble in contrast with individual high-performing models and other benchmarks." @default.
- W4385597669 created "2023-08-05" @default.
- W4385597669 creator A5006450724 @default.
- W4385597669 creator A5030055383 @default.
- W4385597669 creator A5048243433 @default.
- W4385597669 creator A5068721920 @default.
- W4385597669 date "2023-11-01" @default.
- W4385597669 modified "2023-10-17" @default.
- W4385597669 title "Quantifying uncertainty for deep learning based forecasting and flow-reconstruction using neural architecture search ensembles" @default.
- W4385597669 cites W1723433682 @default.
- W4385597669 cites W1838478012 @default.
- W4385597669 cites W2019094351 @default.
- W4385597669 cites W2064675550 @default.
- W4385597669 cites W2066985427 @default.
- W4385597669 cites W2073594627 @default.
- W4385597669 cites W2097652335 @default.
- W4385597669 cites W2101080583 @default.
- W4385597669 cites W2120101088 @default.
- W4385597669 cites W2125634634 @default.
- W4385597669 cites W2126725034 @default.
- W4385597669 cites W2143998937 @default.
- W4385597669 cites W2156249715 @default.
- W4385597669 cites W2161155740 @default.
- W4385597669 cites W2341174028 @default.
- W4385597669 cites W2346717862 @default.
- W4385597669 cites W2529348500 @default.
- W4385597669 cites W2772709428 @default.
- W4385597669 cites W2791129043 @default.
- W4385597669 cites W2809491586 @default.
- W4385597669 cites W2889152090 @default.
- W4385597669 cites W2900304936 @default.
- W4385597669 cites W2907646486 @default.
- W4385597669 cites W2908541468 @default.
- W4385597669 cites W2921773029 @default.
- W4385597669 cites W2945976633 @default.
- W4385597669 cites W2963509795 @default.
- W4385597669 cites W2965658867 @default.
- W4385597669 cites W2981080108 @default.
- W4385597669 cites W2981433027 @default.
- W4385597669 cites W2999787543 @default.
- W4385597669 cites W3007149244 @default.
- W4385597669 cites W3016309349 @default.
- W4385597669 cites W3020274705 @default.
- W4385597669 cites W3021518412 @default.
- W4385597669 cites W3039903604 @default.
- W4385597669 cites W3046812802 @default.
- W4385597669 cites W3081067503 @default.
- W4385597669 cites W3092231855 @default.
- W4385597669 cites W3094257888 @default.
- W4385597669 cites W3097266263 @default.
- W4385597669 cites W3098633050 @default.
- W4385597669 cites W3098680501 @default.
- W4385597669 cites W3100345157 @default.
- W4385597669 cites W3102295111 @default.
- W4385597669 cites W3104291870 @default.
- W4385597669 cites W3112714421 @default.
- W4385597669 cites W3114766522 @default.
- W4385597669 cites W3125005852 @default.
- W4385597669 cites W3136004305 @default.
- W4385597669 cites W3169530841 @default.
- W4385597669 cites W3203806521 @default.
- W4385597669 cites W3206216308 @default.
- W4385597669 cites W3216107495 @default.
- W4385597669 cites W4225286424 @default.
- W4385597669 cites W4286436535 @default.
- W4385597669 cites W4312054954 @default.
- W4385597669 cites W4315628777 @default.
- W4385597669 doi "https://doi.org/10.1016/j.physd.2023.133852" @default.
- W4385597669 hasPublicationYear "2023" @default.
- W4385597669 type Work @default.
- W4385597669 citedByCount "0" @default.
- W4385597669 crossrefType "journal-article" @default.
- W4385597669 hasAuthorship W4385597669A5006450724 @default.
- W4385597669 hasAuthorship W4385597669A5030055383 @default.
- W4385597669 hasAuthorship W4385597669A5048243433 @default.
- W4385597669 hasAuthorship W4385597669A5068721920 @default.
- W4385597669 hasBestOaLocation W43855976692 @default.
- W4385597669 hasConcept C107673813 @default.
- W4385597669 hasConcept C108583219 @default.
- W4385597669 hasConcept C119857082 @default.
- W4385597669 hasConcept C13280743 @default.
- W4385597669 hasConcept C154945302 @default.
- W4385597669 hasConcept C185798385 @default.
- W4385597669 hasConcept C205649164 @default.
- W4385597669 hasConcept C32230216 @default.
- W4385597669 hasConcept C41008148 @default.
- W4385597669 hasConcept C45942800 @default.
- W4385597669 hasConcept C48044578 @default.
- W4385597669 hasConcept C50644808 @default.
- W4385597669 hasConcept C77088390 @default.
- W4385597669 hasConcept C8642999 @default.
- W4385597669 hasConceptScore W4385597669C107673813 @default.
- W4385597669 hasConceptScore W4385597669C108583219 @default.
- W4385597669 hasConceptScore W4385597669C119857082 @default.
- W4385597669 hasConceptScore W4385597669C13280743 @default.
- W4385597669 hasConceptScore W4385597669C154945302 @default.
- W4385597669 hasConceptScore W4385597669C185798385 @default.
- W4385597669 hasConceptScore W4385597669C205649164 @default.