FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4366485332> ?p ?o ?g. }

• W4366485332 endingPage "30" @default.
• W4366485332 startingPage "1" @default.
• W4366485332 abstract "Summary Constructing reliable data-driven models to predict well production performance (e.g., estimated ultimate recovery, cumulative production, production curves, etc.) for unconventional reservoirs requires large amounts of data. However, when considering unconventional reservoirs in their early stages of development, where data and the wells drilled are limited, one may benefit from leveraging available data and/or pretrained models from other more developed fields. Transfer learning, the process of storing knowledge gained while solving one problem (source data) and applying it to solve a different but related problem (target data), provides a workflow for alleviating data needs in training a data-driven model in fields with limited data. However, a pitfall in the application of transfer learning is the possibility of negative transfer, that is, transferring incorrect or irrelevant knowledge to the target data. In particular, the black-box nature of most data-driven models, e.g., neural networks, support vector machines, and random forest, makes it difficult to completely interpret the contribution of different source models used for knowledge transfer. Hence, ranking the viability of source models for transfer learning can reduce the risk of negative transfer and improve the prediction performance. In this paper, we illustrate the impact of negative transfer and how it can be identified, and present a new approach for ranking multiple source models based on their positive transfer contribution. Finally, we propose a framework to build a reliable model to predict well production performance by combining multiple sources of information into one network to be transferred and retrained with limited data in fields at their early stages of development." @default.
• W4366485332 created "2023-04-22" @default.
• W4366485332 creator A5003736943 @default.
• W4366485332 creator A5015256275 @default.
• W4366485332 creator A5030476376 @default.
• W4366485332 creator A5043459358 @default.
• W4366485332 creator A5057004904 @default.
• W4366485332 creator A5064842221 @default.
• W4366485332 date "2023-04-01" @default.
• W4366485332 modified "2023-09-29" @default.
• W4366485332 title "Transfer Learning with Prior Data-Driven Models from Multiple Unconventional Fields" @default.
• W4366485332 cites W1604131949 @default.
• W4366485332 cites W1638081485 @default.
• W4366485332 cites W1751701253 @default.
• W4366485332 cites W1871805679 @default.
• W4366485332 cites W1909286886 @default.
• W4366485332 cites W1964735120 @default.
• W4366485332 cites W1975284527 @default.
• W4366485332 cites W1983991449 @default.
• W4366485332 cites W2019801444 @default.
• W4366485332 cites W2023952181 @default.
• W4366485332 cites W2032658593 @default.
• W4366485332 cites W2033672252 @default.
• W4366485332 cites W2037265949 @default.
• W4366485332 cites W2048760145 @default.
• W4366485332 cites W2058441237 @default.
• W4366485332 cites W2075728230 @default.
• W4366485332 cites W2104094955 @default.
• W4366485332 cites W2115403315 @default.
• W4366485332 cites W2122084318 @default.
• W4366485332 cites W2124287399 @default.
• W4366485332 cites W2148143831 @default.
• W4366485332 cites W2155555303 @default.
• W4366485332 cites W2161381512 @default.
• W4366485332 cites W2162854380 @default.
• W4366485332 cites W2165698076 @default.
• W4366485332 cites W2170607218 @default.
• W4366485332 cites W2244353274 @default.
• W4366485332 cites W2282046059 @default.
• W4366485332 cites W2312004824 @default.
• W4366485332 cites W2329504164 @default.
• W4366485332 cites W2337220913 @default.
• W4366485332 cites W2385608149 @default.
• W4366485332 cites W2395579298 @default.
• W4366485332 cites W2398879410 @default.
• W4366485332 cites W2422344780 @default.
• W4366485332 cites W2469186439 @default.
• W4366485332 cites W2487770199 @default.
• W4366485332 cites W2558577979 @default.
• W4366485332 cites W2592859725 @default.
• W4366485332 cites W2618068449 @default.
• W4366485332 cites W2734256217 @default.
• W4366485332 cites W2758375579 @default.
• W4366485332 cites W2765530271 @default.
• W4366485332 cites W2770645414 @default.
• W4366485332 cites W2786511900 @default.
• W4366485332 cites W2887280559 @default.
• W4366485332 cites W2899542986 @default.
• W4366485332 cites W2910705748 @default.
• W4366485332 cites W2927471432 @default.
• W4366485332 cites W2944620330 @default.
• W4366485332 cites W2945976633 @default.
• W4366485332 cites W2948875532 @default.
• W4366485332 cites W2955109214 @default.
• W4366485332 cites W2963522845 @default.
• W4366485332 cites W2964317695 @default.
• W4366485332 cites W2965742591 @default.
• W4366485332 cites W2975872888 @default.
• W4366485332 cites W2976800897 @default.
• W4366485332 cites W2979703857 @default.
• W4366485332 cites W2980113592 @default.
• W4366485332 cites W2998429090 @default.
• W4366485332 cites W3000189979 @default.
• W4366485332 cites W3014008866 @default.
• W4366485332 cites W3015863006 @default.
• W4366485332 cites W3020873385 @default.
• W4366485332 cites W3036139134 @default.
• W4366485332 cites W3037649759 @default.
• W4366485332 cites W3041133507 @default.
• W4366485332 cites W3041247690 @default.
• W4366485332 cites W3044473380 @default.
• W4366485332 cites W3048894625 @default.
• W4366485332 cites W3129781273 @default.
• W4366485332 cites W3163452734 @default.
• W4366485332 cites W3168932992 @default.
• W4366485332 cites W3185175025 @default.
• W4366485332 cites W3191567312 @default.
• W4366485332 cites W3208677614 @default.
• W4366485332 cites W4200481400 @default.
• W4366485332 cites W4220838426 @default.
• W4366485332 cites W4220899928 @default.
• W4366485332 cites W4230077286 @default.
• W4366485332 cites W4283163619 @default.
• W4366485332 cites W4285207369 @default.
• W4366485332 cites W4293244278 @default.
• W4366485332 doi "https://doi.org/10.2118/214312-pa" @default.
• W4366485332 hasPublicationYear "2023" @default.
• W4366485332 type Work @default.

• next