FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3210106786> ?p ?o ?g. }

• W3210106786 abstract "Parameter estimation for reactive transport models (RTMs) is important in improving their predictive capacity for accurately simulating subsurface hydrogeochemical processes. This paper introduces a deep learning approach called the tandem neural network architecture (TNNA), which consists of a forward network and a reverse network to estimate input parameters for RTMs. The TNNA approach has a limitation in that the approximation error from the forward network often results in biased inversion results. To solve this problem, we proposed to enhance TNNA using an adaptive updating strategy (AUS), which locally reduces the approximation error of the forward network. The developed framework updates the forward network by iteratively using local sampling and transfer learning. The TNNA-AUS was verified by a cation exchange example. The results show that TNNA-AUS successfully reduces the inversion bias and improves the computational efficiency and inversion accuracy, compared with the global improvement strategy of adding training samples according to the prior distribution of model parameters. After verification, the TNNA-AUS was applied to a real-world and well-documented RTM problem of the Aquia aquifer, Maryland, USA. The inversion results demonstrate that the developed TNNA-AUS algorithm is an excellent tool for us to understand the complex subsurface hydrogeochemical processes and estimate the associated reaction parameters." @default.
• W3210106786 created "2021-11-08" @default.
• W3210106786 creator A5008497258 @default.
• W3210106786 creator A5016068852 @default.
• W3210106786 creator A5036442264 @default.
• W3210106786 creator A5060162053 @default.
• W3210106786 creator A5082213642 @default.
• W3210106786 creator A5088367952 @default.
• W3210106786 creator A5091500219 @default.
• W3210106786 date "2021-11-25" @default.
• W3210106786 modified "2023-10-13" @default.
• W3210106786 title "An Improved Tandem Neural Network Architecture for Inverse Modeling of Multicomponent Reactive Transport in Porous Media" @default.
• W3210106786 cites W1528483814 @default.
• W3210106786 cites W1544278534 @default.
• W3210106786 cites W1590014004 @default.
• W3210106786 cites W1610397282 @default.
• W3210106786 cites W1668070284 @default.
• W3210106786 cites W1909649765 @default.
• W3210106786 cites W1935773568 @default.
• W3210106786 cites W1974638823 @default.
• W3210106786 cites W1982177092 @default.
• W3210106786 cites W1983156380 @default.
• W3210106786 cites W1984981661 @default.
• W3210106786 cites W1986614398 @default.
• W3210106786 cites W1991166510 @default.
• W3210106786 cites W2003273916 @default.
• W3210106786 cites W2007804207 @default.
• W3210106786 cites W2018159038 @default.
• W3210106786 cites W2018353504 @default.
• W3210106786 cites W2018524330 @default.
• W3210106786 cites W2024478138 @default.
• W3210106786 cites W2027279156 @default.
• W3210106786 cites W2036617740 @default.
• W3210106786 cites W2038538989 @default.
• W3210106786 cites W2038735558 @default.
• W3210106786 cites W2039072764 @default.
• W3210106786 cites W2040692275 @default.
• W3210106786 cites W2046320630 @default.
• W3210106786 cites W2047476280 @default.
• W3210106786 cites W2054029304 @default.
• W3210106786 cites W2056310030 @default.
• W3210106786 cites W2064235269 @default.
• W3210106786 cites W2072159113 @default.
• W3210106786 cites W2072419120 @default.
• W3210106786 cites W2078812770 @default.
• W3210106786 cites W2084367261 @default.
• W3210106786 cites W2100921809 @default.
• W3210106786 cites W2103932268 @default.
• W3210106786 cites W2104082993 @default.
• W3210106786 cites W2109806713 @default.
• W3210106786 cites W2110448863 @default.
• W3210106786 cites W2117122565 @default.
• W3210106786 cites W2118628706 @default.
• W3210106786 cites W2133944044 @default.
• W3210106786 cites W2137287199 @default.
• W3210106786 cites W2143155680 @default.
• W3210106786 cites W2146441071 @default.
• W3210106786 cites W2162811432 @default.
• W3210106786 cites W2164164045 @default.
• W3210106786 cites W2173126837 @default.
• W3210106786 cites W2194775991 @default.
• W3210106786 cites W2195005110 @default.
• W3210106786 cites W2288413795 @default.
• W3210106786 cites W2302515489 @default.
• W3210106786 cites W2319015572 @default.
• W3210106786 cites W2495574708 @default.
• W3210106786 cites W2497530411 @default.
• W3210106786 cites W2503576947 @default.
• W3210106786 cites W2528014653 @default.
• W3210106786 cites W2548313031 @default.
• W3210106786 cites W2587848016 @default.
• W3210106786 cites W2602518026 @default.
• W3210106786 cites W2605806332 @default.
• W3210106786 cites W2606758277 @default.
• W3210106786 cites W2636356257 @default.
• W3210106786 cites W2743730588 @default.
• W3210106786 cites W2761758814 @default.
• W3210106786 cites W2766162919 @default.
• W3210106786 cites W2769060130 @default.
• W3210106786 cites W2777449599 @default.
• W3210106786 cites W2786232134 @default.
• W3210106786 cites W2788465381 @default.
• W3210106786 cites W2788851490 @default.
• W3210106786 cites W2808571274 @default.
• W3210106786 cites W2810524380 @default.
• W3210106786 cites W2888243387 @default.
• W3210106786 cites W2895509799 @default.
• W3210106786 cites W2895570830 @default.
• W3210106786 cites W2896781855 @default.
• W3210106786 cites W2896999814 @default.
• W3210106786 cites W2899283552 @default.
• W3210106786 cites W2901669004 @default.
• W3210106786 cites W2905245562 @default.
• W3210106786 cites W2907730234 @default.
• W3210106786 cites W2908893700 @default.
• W3210106786 cites W2909984890 @default.
• W3210106786 cites W2917785432 @default.
• W3210106786 cites W2919115771 @default.
• W3210106786 cites W2919958648 @default.
• W3210106786 cites W2922360136 @default.

• next