FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2554014901> ?p ?o ?g. }

• W2554014901 endingPage "3545" @default.
• W2554014901 startingPage "3519" @default.
• W2554014901 abstract "Abstract. Accurate model representation of land–atmosphere carbon fluxes is essential for climate projections. However, the exact responses of carbon cycle processes to climatic drivers often remain uncertain. Presently, knowledge derived from experiments, complemented by a steadily evolving body of mechanistic theory, provides the main basis for developing such models. The strongly increasing availability of measurements may facilitate new ways of identifying suitable model structures using machine learning. Here, we explore the potential of gene expression programming (GEP) to derive relevant model formulations based solely on the signals present in data by automatically applying various mathematical transformations to potential predictors and repeatedly evolving the resulting model structures. In contrast to most other machine learning regression techniques, the GEP approach generates readable models that allow for prediction and possibly for interpretation. Our study is based on two cases: artificially generated data and real observations. Simulations based on artificial data show that GEP is successful in identifying prescribed functions, with the prediction capacity of the models comparable to four state-of-the-art machine learning methods (random forests, support vector machines, artificial neural networks, and kernel ridge regressions). Based on real observations we explore the responses of the different components of terrestrial respiration at an oak forest in south-eastern England. We find that the GEP-retrieved models are often better in prediction than some established respiration models. Based on their structures, we find previously unconsidered exponential dependencies of respiration on seasonal ecosystem carbon assimilation and water dynamics. We noticed that the GEP models are only partly portable across respiration components, the identification of a general terrestrial respiration model possibly prevented by equifinality issues. Overall, GEP is a promising tool for uncovering new model structures for terrestrial ecology in the data-rich era, complementing more traditional modelling approaches." @default.
• W2554014901 created "2016-11-30" @default.
• W2554014901 creator A5006922544 @default.
• W2554014901 creator A5008840315 @default.
• W2554014901 creator A5018987403 @default.
• W2554014901 creator A5023265994 @default.
• W2554014901 creator A5035702282 @default.
• W2554014901 creator A5038215995 @default.
• W2554014901 creator A5042836143 @default.
• W2554014901 creator A5048012435 @default.
• W2554014901 creator A5062574094 @default.
• W2554014901 creator A5088033974 @default.
• W2554014901 creator A5088518218 @default.
• W2554014901 date "2017-09-25" @default.
• W2554014901 modified "2023-09-30" @default.
• W2554014901 title "Reverse engineering model structures for soil and ecosystem respiration: the potential of gene expression programming" @default.
• W2554014901 cites W1503296932 @default.
• W2554014901 cites W1546707005 @default.
• W2554014901 cites W1576660662 @default.
• W2554014901 cites W1847201849 @default.
• W2554014901 cites W1895549337 @default.
• W2554014901 cites W1965122835 @default.
• W2554014901 cites W1975964493 @default.
• W2554014901 cites W1980844546 @default.
• W2554014901 cites W1980867191 @default.
• W2554014901 cites W1984405581 @default.
• W2554014901 cites W1989682996 @default.
• W2554014901 cites W1995875735 @default.
• W2554014901 cites W2008056655 @default.
• W2554014901 cites W2009392275 @default.
• W2554014901 cites W2014683958 @default.
• W2554014901 cites W2020088441 @default.
• W2554014901 cites W2022224360 @default.
• W2554014901 cites W2026036082 @default.
• W2554014901 cites W2030486754 @default.
• W2554014901 cites W2033852577 @default.
• W2554014901 cites W2033904036 @default.
• W2554014901 cites W2034634405 @default.
• W2554014901 cites W2040383921 @default.
• W2554014901 cites W2045106323 @default.
• W2554014901 cites W2046131409 @default.
• W2554014901 cites W2059111237 @default.
• W2554014901 cites W2060579417 @default.
• W2554014901 cites W2089940084 @default.
• W2554014901 cites W2093828424 @default.
• W2554014901 cites W2101913496 @default.
• W2554014901 cites W2104239815 @default.
• W2554014901 cites W2105699823 @default.
• W2554014901 cites W2111537121 @default.
• W2554014901 cites W2112021406 @default.
• W2554014901 cites W2114744271 @default.
• W2554014901 cites W2115775436 @default.
• W2554014901 cites W2120965873 @default.
• W2554014901 cites W2122311299 @default.
• W2554014901 cites W2124437404 @default.
• W2554014901 cites W2126192929 @default.
• W2554014901 cites W2130670721 @default.
• W2554014901 cites W2132843568 @default.
• W2554014901 cites W2135757495 @default.
• W2554014901 cites W2136963468 @default.
• W2554014901 cites W2137319595 @default.
• W2554014901 cites W2138079376 @default.
• W2554014901 cites W2138537392 @default.
• W2554014901 cites W2138999976 @default.
• W2554014901 cites W2142737108 @default.
• W2554014901 cites W2144470849 @default.
• W2554014901 cites W2145808276 @default.
• W2554014901 cites W2149160185 @default.
• W2554014901 cites W2149468258 @default.
• W2554014901 cites W2149815769 @default.
• W2554014901 cites W2149829096 @default.
• W2554014901 cites W2151328940 @default.
• W2554014901 cites W2153635508 @default.
• W2554014901 cites W2157881370 @default.
• W2554014901 cites W2158806627 @default.
• W2554014901 cites W2163558252 @default.
• W2554014901 cites W2172267151 @default.
• W2554014901 cites W2298779432 @default.
• W2554014901 cites W2463335026 @default.
• W2554014901 cites W2476340812 @default.
• W2554014901 cites W2497309206 @default.
• W2554014901 cites W2528158827 @default.
• W2554014901 cites W2911964244 @default.
• W2554014901 cites W4234698323 @default.
• W2554014901 cites W4300940299 @default.
• W2554014901 doi "https://doi.org/10.5194/gmd-10-3519-2017" @default.
• W2554014901 hasPublicationYear "2017" @default.
• W2554014901 type Work @default.
• W2554014901 sameAs 2554014901 @default.
• W2554014901 citedByCount "6" @default.
• W2554014901 countsByYear W25540149012019 @default.
• W2554014901 countsByYear W25540149012021 @default.
• W2554014901 countsByYear W25540149012022 @default.
• W2554014901 countsByYear W25540149012023 @default.
• W2554014901 crossrefType "journal-article" @default.
• W2554014901 hasAuthorship W2554014901A5006922544 @default.
• W2554014901 hasAuthorship W2554014901A5008840315 @default.
• W2554014901 hasAuthorship W2554014901A5018987403 @default.

• next