Matches in SemOpenAlex for { <https://semopenalex.org/work/W4200499912> ?p ?o ?g. }
- W4200499912 endingPage "119911" @default.
- W4200499912 startingPage "119911" @default.
- W4200499912 abstract "Accurate and transparent phenological models have become a vital tool for reflecting the feedbacks and interactions between the biosphere and atmosphere and accurately predicting future phenological responses to climate change. With the rapid accumulation of ground-observed phenological data, an increasing number of studies have used process-based ecophysiological (Eco) models to predict future phenological changes. Many algorithms have been used to optimize the parameters of Eco models, but there is a lack of evaluation of different algorithms. Although no single Eco model can show obvious advantages, ensemble learning can improve model performance by combining different trained models. In this study, based on the historical observation data (leaf unfolding date and first flowering date) of more than 100 woody plants from 1962 to 2018 in Heilongjiang Forest Botanical Garden, we evaluated the performance of five Eco model parameter optimization algorithms, and compared the performance of 20 Eco models in phenological observation data prediction. Most importantly, based on the idea of ensemble learning in machine learning, we proposed improving the prediction accuracy of Eco models by applying ensemble learning methods in the trained Eco models. Our research results show that among the five optimization algorithms involved in this study, the generalized simulated annealing algorithm is more recommended for Eco model parameter optimization. Compared with the more complex three-phase and four-phase models, the simpler the model structure, the better the generalization performance of one-phase and two-phase models. The RMSEs of Eco models of many species on the test set were greater than 4 days, which indicates that the ability of Eco models to predict phenological data based on ground observations of some specific species is relatively limited. Our results highlight that the prediction accuracy of Eco models can be significantly improved by the Voting ensemble learning method. In the future, we can improve the accuracy of phenological predictions by using ensemble learning methods, so as to more accurately detect future phenological changes and their responses to climate change." @default.
- W4200499912 created "2021-12-31" @default.
- W4200499912 creator A5034281016 @default.
- W4200499912 creator A5045505240 @default.
- W4200499912 creator A5046775442 @default.
- W4200499912 creator A5052647677 @default.
- W4200499912 creator A5054081459 @default.
- W4200499912 creator A5088486032 @default.
- W4200499912 date "2022-02-01" @default.
- W4200499912 modified "2023-10-13" @default.
- W4200499912 title "Applying ensemble learning in ecophysiological models to predict spring phenology" @default.
- W4200499912 cites W1931997074 @default.
- W4200499912 cites W1970268633 @default.
- W4200499912 cites W1983047503 @default.
- W4200499912 cites W1984650181 @default.
- W4200499912 cites W1992231441 @default.
- W4200499912 cites W1999391011 @default.
- W4200499912 cites W2001448697 @default.
- W4200499912 cites W2001743134 @default.
- W4200499912 cites W2009690899 @default.
- W4200499912 cites W2017428818 @default.
- W4200499912 cites W2029411945 @default.
- W4200499912 cites W2033904036 @default.
- W4200499912 cites W2056975410 @default.
- W4200499912 cites W2064945527 @default.
- W4200499912 cites W2070938989 @default.
- W4200499912 cites W2073642568 @default.
- W4200499912 cites W2074396146 @default.
- W4200499912 cites W2079121681 @default.
- W4200499912 cites W2083702808 @default.
- W4200499912 cites W2092629213 @default.
- W4200499912 cites W2096682311 @default.
- W4200499912 cites W2097657595 @default.
- W4200499912 cites W2142094826 @default.
- W4200499912 cites W2153796196 @default.
- W4200499912 cites W2155622357 @default.
- W4200499912 cites W2156723676 @default.
- W4200499912 cites W2160275770 @default.
- W4200499912 cites W2163595580 @default.
- W4200499912 cites W2163621721 @default.
- W4200499912 cites W2164681141 @default.
- W4200499912 cites W2169686723 @default.
- W4200499912 cites W2170513691 @default.
- W4200499912 cites W2183234014 @default.
- W4200499912 cites W2211764928 @default.
- W4200499912 cites W2314366426 @default.
- W4200499912 cites W2317998620 @default.
- W4200499912 cites W2318720120 @default.
- W4200499912 cites W2318966030 @default.
- W4200499912 cites W2319879213 @default.
- W4200499912 cites W2322019790 @default.
- W4200499912 cites W2325434008 @default.
- W4200499912 cites W2337124926 @default.
- W4200499912 cites W2395364234 @default.
- W4200499912 cites W2404135380 @default.
- W4200499912 cites W2536362164 @default.
- W4200499912 cites W2558724412 @default.
- W4200499912 cites W2573131165 @default.
- W4200499912 cites W2608433761 @default.
- W4200499912 cites W2611891293 @default.
- W4200499912 cites W2625097954 @default.
- W4200499912 cites W2750408438 @default.
- W4200499912 cites W2766511823 @default.
- W4200499912 cites W2780334439 @default.
- W4200499912 cites W2788091003 @default.
- W4200499912 cites W2792442798 @default.
- W4200499912 cites W2793804454 @default.
- W4200499912 cites W2797238737 @default.
- W4200499912 cites W2903608567 @default.
- W4200499912 cites W2909801025 @default.
- W4200499912 cites W2922350609 @default.
- W4200499912 cites W2922633580 @default.
- W4200499912 cites W2935804204 @default.
- W4200499912 cites W2969816381 @default.
- W4200499912 cites W2970595972 @default.
- W4200499912 cites W2973161838 @default.
- W4200499912 cites W3000137512 @default.
- W4200499912 cites W3019280147 @default.
- W4200499912 cites W3025914776 @default.
- W4200499912 cites W3035048690 @default.
- W4200499912 cites W3109256700 @default.
- W4200499912 cites W4296177013 @default.
- W4200499912 doi "https://doi.org/10.1016/j.foreco.2021.119911" @default.
- W4200499912 hasPublicationYear "2022" @default.
- W4200499912 type Work @default.
- W4200499912 citedByCount "3" @default.
- W4200499912 countsByYear W42004999122022 @default.
- W4200499912 countsByYear W42004999122023 @default.
- W4200499912 crossrefType "journal-article" @default.
- W4200499912 hasAuthorship W4200499912A5034281016 @default.
- W4200499912 hasAuthorship W4200499912A5045505240 @default.
- W4200499912 hasAuthorship W4200499912A5046775442 @default.
- W4200499912 hasAuthorship W4200499912A5052647677 @default.
- W4200499912 hasAuthorship W4200499912A5054081459 @default.
- W4200499912 hasAuthorship W4200499912A5088486032 @default.
- W4200499912 hasConcept C11413529 @default.
- W4200499912 hasConcept C119857082 @default.
- W4200499912 hasConcept C119898033 @default.