FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4306168412> ?p ?o ?g. }

• W4306168412 endingPage "5184" @default.
• W4306168412 startingPage "5163" @default.
• W4306168412 abstract "Abstract. Rivers and river habitats around the world are under sustained pressure from human activities and the changing global environment. Our ability to quantify and manage the river states in a timely manner is critical for protecting the public safety and natural resources. In recent years, vector-based river network models have enabled modeling of large river basins at increasingly fine resolutions, but are computationally demanding. This work presents a multistage, physics-guided, graph neural network (GNN) approach for basin-scale river network learning and streamflow forecasting. During training, we train a GNN model to approximate outputs of a high-resolution vector-based river network model; we then fine-tune the pretrained GNN model with streamflow observations. We further apply a graph-based, data-fusion step to correct prediction biases. The GNN-based framework is first demonstrated over a snow-dominated watershed in the western United States. A series of experiments are performed to test different training and imputation strategies. Results show that the trained GNN model can effectively serve as a surrogate of the process-based model with high accuracy, with median Kling–Gupta efficiency (KGE) greater than 0.97. Application of the graph-based data fusion further reduces mismatch between the GNN model and observations, with as much as 50 % KGE improvement over some cross-validation gages. To improve scalability, a graph-coarsening procedure is introduced and is demonstrated over a much larger basin. Results show that graph coarsening achieves comparable prediction skills at only a fraction of training cost, thus providing important insights into the degree of physical realism needed for developing large-scale GNN-based river network models." @default.
• W4306168412 created "2022-10-14" @default.
• W4306168412 creator A5011121567 @default.
• W4306168412 creator A5026692271 @default.
• W4306168412 creator A5042596205 @default.
• W4306168412 creator A5079873685 @default.
• W4306168412 creator A5090957112 @default.
• W4306168412 date "2022-10-14" @default.
• W4306168412 modified "2023-10-17" @default.
• W4306168412 title "A graph neural network (GNN) approach to basin-scale river network learning: the role of physics-based connectivity and data fusion" @default.
• W4306168412 cites W105520645 @default.
• W4306168412 cites W1724334760 @default.
• W4306168412 cites W1846570231 @default.
• W4306168412 cites W1982136884 @default.
• W4306168412 cites W2001317094 @default.
• W4306168412 cites W2016107349 @default.
• W4306168412 cites W2032587589 @default.
• W4306168412 cites W2043021402 @default.
• W4306168412 cites W2043455992 @default.
• W4306168412 cites W2043607614 @default.
• W4306168412 cites W2048314306 @default.
• W4306168412 cites W2060975319 @default.
• W4306168412 cites W2062100529 @default.
• W4306168412 cites W2063858529 @default.
• W4306168412 cites W2064675550 @default.
• W4306168412 cites W2064807406 @default.
• W4306168412 cites W2065386084 @default.
• W4306168412 cites W2078888397 @default.
• W4306168412 cites W2082137964 @default.
• W4306168412 cites W2087523516 @default.
• W4306168412 cites W2097208041 @default.
• W4306168412 cites W2103497845 @default.
• W4306168412 cites W2129974232 @default.
• W4306168412 cites W2134002412 @default.
• W4306168412 cites W2138763184 @default.
• W4306168412 cites W2151329188 @default.
• W4306168412 cites W2153576883 @default.
• W4306168412 cites W2154112865 @default.
• W4306168412 cites W2165201237 @default.
• W4306168412 cites W2173589103 @default.
• W4306168412 cites W2263824596 @default.
• W4306168412 cites W2335114787 @default.
• W4306168412 cites W2558748708 @default.
• W4306168412 cites W2593484292 @default.
• W4306168412 cites W2732936487 @default.
• W4306168412 cites W2744367050 @default.
• W4306168412 cites W2756368919 @default.
• W4306168412 cites W2765754233 @default.
• W4306168412 cites W2768000806 @default.
• W4306168412 cites W2805635228 @default.
• W4306168412 cites W2887875105 @default.
• W4306168412 cites W2887891828 @default.
• W4306168412 cites W2894238602 @default.
• W4306168412 cites W2903733180 @default.
• W4306168412 cites W2906384620 @default.
• W4306168412 cites W2908893700 @default.
• W4306168412 cites W2913323966 @default.
• W4306168412 cites W2942047515 @default.
• W4306168412 cites W2944057425 @default.
• W4306168412 cites W2954648193 @default.
• W4306168412 cites W2963255299 @default.
• W4306168412 cites W2964051675 @default.
• W4306168412 cites W2965341826 @default.
• W4306168412 cites W2973731563 @default.
• W4306168412 cites W2974527409 @default.
• W4306168412 cites W2980361537 @default.
• W4306168412 cites W2989857225 @default.
• W4306168412 cites W2994881778 @default.
• W4306168412 cites W2995149074 @default.
• W4306168412 cites W2996969697 @default.
• W4306168412 cites W3016660084 @default.
• W4306168412 cites W3017283281 @default.
• W4306168412 cites W3024402844 @default.
• W4306168412 cites W3035909655 @default.
• W4306168412 cites W3040129451 @default.
• W4306168412 cites W3080997787 @default.
• W4306168412 cites W3099909056 @default.
• W4306168412 cites W3106370744 @default.
• W4306168412 cites W3121197195 @default.
• W4306168412 cites W3127723844 @default.
• W4306168412 cites W3128881494 @default.
• W4306168412 cites W3133294546 @default.
• W4306168412 cites W3144909764 @default.
• W4306168412 cites W3152893301 @default.
• W4306168412 cites W3158774913 @default.
• W4306168412 cites W3163819433 @default.
• W4306168412 cites W3168632392 @default.
• W4306168412 cites W3174646361 @default.
• W4306168412 cites W3194680813 @default.
• W4306168412 cites W3213123713 @default.
• W4306168412 cites W4211049957 @default.
• W4306168412 cites W4213046562 @default.
• W4306168412 cites W4225747436 @default.
• W4306168412 cites W4232673032 @default.
• W4306168412 cites W4243053434 @default.
• W4306168412 doi "https://doi.org/10.5194/hess-26-5163-2022" @default.
• W4306168412 hasPublicationYear "2022" @default.
• W4306168412 type Work @default.

• next