FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3197307613> ?p ?o ?g. }

• W3197307613 abstract "Abstract Significant attention has recently been paid to deep learning as a method for improved catchment modeling. Compared with process‐based models, deep learning is often criticized for its lack of interpretability. One solution is to combine a process‐based hydrological model with a residual error model based on deep learning to give full scope to their respective advantages. In classical residual error models, Bayesian inference via Markov chain Monte Carlo (MCMC) is commonly used to provide an estimation of the uncertainty. However, deep neural networks tend to have excessively large numbers of parameters, making MCMC an unsuitable approach. Here, we introduce an alternative to Bayesian MCMC sampling called stochastic variational inference (SVI) which has recently been developed for Bayesian deep learning in Natural Language Processing. We implement SVI in a Long Short‐Term Memory (LSTM) network and construct residual error models in process‐based hydrological models. This approach is examined in the contrasting geographical and climatic characteristics of two catchments from China, the Tangnaihai catchment and the Shiquan catchment. Compared with the Bayesian linear regression model, the Bayesian LSTM provides better uncertainty estimates. Specifically, the proposed method improves the Continuous Ranked Probability Score (CRPS) by over 10% in both two catchments. In the Tangnaihai catchment, it provides more than 10% narrower uncertainty intervals in terms of Sharpness with slightly superior Reliability. In the Shiquan catchment, it provides comparable uncertainty intervals with better Reliability. Further, our study highlights the scalability of SVI to high‐dimensional parameter spaces in hydrological applications (e.g., distributed hydrological models, groundwater models)." @default.
• W3197307613 created "2021-09-13" @default.
• W3197307613 creator A5011403405 @default.
• W3197307613 creator A5019017581 @default.
• W3197307613 creator A5019491963 @default.
• W3197307613 creator A5050493451 @default.
• W3197307613 creator A5053383515 @default.
• W3197307613 date "2021-09-01" @default.
• W3197307613 modified "2023-10-17" @default.
• W3197307613 title "Bayesian LSTM With Stochastic Variational Inference for Estimating Model Uncertainty in Process‐Based Hydrological Models" @default.
• W3197307613 cites W129305155 @default.
• W3197307613 cites W1513280753 @default.
• W3197307613 cites W1516111018 @default.
• W3197307613 cites W1527594523 @default.
• W3197307613 cites W1580822624 @default.
• W3197307613 cites W1588946961 @default.
• W3197307613 cites W1679242182 @default.
• W3197307613 cites W1862292973 @default.
• W3197307613 cites W1864889125 @default.
• W3197307613 cites W1908583432 @default.
• W3197307613 cites W1911894755 @default.
• W3197307613 cites W1932499509 @default.
• W3197307613 cites W1954090063 @default.
• W3197307613 cites W1964458071 @default.
• W3197307613 cites W1965555277 @default.
• W3197307613 cites W1970707376 @default.
• W3197307613 cites W1971927512 @default.
• W3197307613 cites W1984038448 @default.
• W3197307613 cites W1995780830 @default.
• W3197307613 cites W1996476760 @default.
• W3197307613 cites W2012798012 @default.
• W3197307613 cites W2012798851 @default.
• W3197307613 cites W2014325697 @default.
• W3197307613 cites W2031292142 @default.
• W3197307613 cites W2033904036 @default.
• W3197307613 cites W2033993157 @default.
• W3197307613 cites W2037931255 @default.
• W3197307613 cites W2056760934 @default.
• W3197307613 cites W2064675550 @default.
• W3197307613 cites W2066148124 @default.
• W3197307613 cites W2071988465 @default.
• W3197307613 cites W2097002356 @default.
• W3197307613 cites W2100511908 @default.
• W3197307613 cites W2105590405 @default.
• W3197307613 cites W2112702040 @default.
• W3197307613 cites W2117681582 @default.
• W3197307613 cites W2119179880 @default.
• W3197307613 cites W2119717200 @default.
• W3197307613 cites W2123677000 @default.
• W3197307613 cites W2133837084 @default.
• W3197307613 cites W2133944044 @default.
• W3197307613 cites W2136276425 @default.
• W3197307613 cites W2138309709 @default.
• W3197307613 cites W2138763184 @default.
• W3197307613 cites W2144661611 @default.
• W3197307613 cites W2147623518 @default.
• W3197307613 cites W2153576883 @default.
• W3197307613 cites W2178242555 @default.
• W3197307613 cites W2215560032 @default.
• W3197307613 cites W2313924670 @default.
• W3197307613 cites W2584314571 @default.
• W3197307613 cites W2595649483 @default.
• W3197307613 cites W2623181128 @default.
• W3197307613 cites W2726198599 @default.
• W3197307613 cites W2769851728 @default.
• W3197307613 cites W2770322578 @default.
• W3197307613 cites W2788532262 @default.
• W3197307613 cites W2790017071 @default.
• W3197307613 cites W2792309568 @default.
• W3197307613 cites W2800819102 @default.
• W3197307613 cites W2802436364 @default.
• W3197307613 cites W2803888599 @default.
• W3197307613 cites W2898661956 @default.
• W3197307613 cites W2899430076 @default.
• W3197307613 cites W2901672512 @default.
• W3197307613 cites W2913323966 @default.
• W3197307613 cites W2935807013 @default.
• W3197307613 cites W2952905952 @default.
• W3197307613 cites W2963058055 @default.
• W3197307613 cites W2963073614 @default.
• W3197307613 cites W2966035769 @default.
• W3197307613 cites W2966377380 @default.
• W3197307613 cites W2971675004 @default.
• W3197307613 cites W2988317184 @default.
• W3197307613 cites W2997000104 @default.
• W3197307613 cites W2998268303 @default.
• W3197307613 cites W3006264628 @default.
• W3197307613 cites W3007120688 @default.
• W3197307613 cites W3022723466 @default.
• W3197307613 cites W3081635661 @default.
• W3197307613 cites W3088538572 @default.
• W3197307613 cites W3101380508 @default.
• W3197307613 cites W3102100346 @default.
• W3197307613 cites W3106370744 @default.
• W3197307613 cites W3125807057 @default.
• W3197307613 cites W3127379605 @default.
• W3197307613 cites W3138180816 @default.
• W3197307613 cites W4212863985 @default.
• W3197307613 cites W4254767066 @default.
• W3197307613 doi "https://doi.org/10.1029/2021wr029772" @default.

• next