FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201703223> ?p ?o ?g. }

• W3201703223 abstract "Species distribution modeling (SDM) is widely used in ecology and conservation. Currently, the most available data for SDM are species presence-only records (available through digital databases). There have been many studies comparing the performance of alternative algorithms for modeling presence-only data. Among these, a 2006 paper from Elith and colleagues has been particularly influential in the field, partly because they used several novel methods (at the time) on a global data set that included independent presence–absence records for model evaluation. Since its publication, some of the algorithms have been further developed and new ones have emerged. In this paper, we explore patterns in predictive performance across methods, by reanalyzing the same data set (225 species from six different regions) using updated modeling knowledge and practices. We apply well-established methods such as generalized additive models and MaxEnt, alongside others that have received attention more recently, including regularized regressions, point-process weighted regressions, random forests, XGBoost, support vector machines, and the ensemble modeling framework biomod. All the methods we use include background samples (a sample of environments in the landscape) for model fitting. We explore impacts of using weights on the presence and background points in model fitting. We introduce new ways of evaluating models fitted to these data, using the area under the precision-recall gain curve, and focusing on the rank of results. We find that the way models are fitted matters. The top method was an ensemble of tuned individual models. In contrast, ensembles built using the biomod framework with default parameters performed no better than single moderate performing models. Similarly, the second top performing method was a random forest parameterized to deal with many background samples (contrasted to relatively few presence records), which substantially outperformed other random forest implementations. We find that, in general, nonparametric techniques with the capability of controlling for model complexity outperformed traditional regression methods, with MaxEnt and boosted regression trees still among the top performing models. All the data and code with working examples are provided to make this study fully reproducible." @default.
• W3201703223 created "2021-10-11" @default.
• W3201703223 creator A5032805182 @default.
• W3201703223 creator A5052351297 @default.
• W3201703223 creator A5069640986 @default.
• W3201703223 creator A5070847668 @default.
• W3201703223 date "2021-11-16" @default.
• W3201703223 modified "2023-10-17" @default.
• W3201703223 title "Predictive performance of presence‐only species distribution models: a benchmark study with reproducible code" @default.
• W3201703223 cites W102369970 @default.
• W3201703223 cites W1494196016 @default.
• W3201703223 cites W1526319989 @default.
• W3201703223 cites W1541774929 @default.
• W3201703223 cites W1551909886 @default.
• W3201703223 cites W1568201516 @default.
• W3201703223 cites W1783101208 @default.
• W3201703223 cites W1838542636 @default.
• W3201703223 cites W1848926566 @default.
• W3201703223 cites W1909609512 @default.
• W3201703223 cites W1941659294 @default.
• W3201703223 cites W1960562915 @default.
• W3201703223 cites W1966716734 @default.
• W3201703223 cites W1972110194 @default.
• W3201703223 cites W1975652353 @default.
• W3201703223 cites W1980193681 @default.
• W3201703223 cites W1980894113 @default.
• W3201703223 cites W1994374969 @default.
• W3201703223 cites W2000288463 @default.
• W3201703223 cites W2002758482 @default.
• W3201703223 cites W2005054054 @default.
• W3201703223 cites W2006055706 @default.
• W3201703223 cites W2012035409 @default.
• W3201703223 cites W2021436645 @default.
• W3201703223 cites W2025126377 @default.
• W3201703223 cites W2027575815 @default.
• W3201703223 cites W2033686454 @default.
• W3201703223 cites W2037314599 @default.
• W3201703223 cites W2040815881 @default.
• W3201703223 cites W2041322302 @default.
• W3201703223 cites W2046577517 @default.
• W3201703223 cites W2056868695 @default.
• W3201703223 cites W2057867151 @default.
• W3201703223 cites W2060374620 @default.
• W3201703223 cites W2064965087 @default.
• W3201703223 cites W2068211709 @default.
• W3201703223 cites W2070230130 @default.
• W3201703223 cites W2070493638 @default.
• W3201703223 cites W2074074333 @default.
• W3201703223 cites W2084829927 @default.
• W3201703223 cites W2089454337 @default.
• W3201703223 cites W2092141482 @default.
• W3201703223 cites W2107108409 @default.
• W3201703223 cites W2112315008 @default.
• W3201703223 cites W2114060135 @default.
• W3201703223 cites W2118978333 @default.
• W3201703223 cites W2119202692 @default.
• W3201703223 cites W2123337039 @default.
• W3201703223 cites W2123998733 @default.
• W3201703223 cites W2127367934 @default.
• W3201703223 cites W2129435498 @default.
• W3201703223 cites W2134214590 @default.
• W3201703223 cites W2135695572 @default.
• W3201703223 cites W2139416101 @default.
• W3201703223 cites W2141070863 @default.
• W3201703223 cites W2143481518 @default.
• W3201703223 cites W2152277880 @default.
• W3201703223 cites W2155988679 @default.
• W3201703223 cites W2156632553 @default.
• W3201703223 cites W2157979460 @default.
• W3201703223 cites W2158040254 @default.
• W3201703223 cites W2158804744 @default.
• W3201703223 cites W2160486837 @default.
• W3201703223 cites W2161548576 @default.
• W3201703223 cites W2165466912 @default.
• W3201703223 cites W2168694365 @default.
• W3201703223 cites W2172138805 @default.
• W3201703223 cites W2174882701 @default.
• W3201703223 cites W2354407904 @default.
• W3201703223 cites W2464471684 @default.
• W3201703223 cites W2476764914 @default.
• W3201703223 cites W2487770199 @default.
• W3201703223 cites W2531640182 @default.
• W3201703223 cites W2537818838 @default.
• W3201703223 cites W2560136348 @default.
• W3201703223 cites W2594788739 @default.
• W3201703223 cites W2598320237 @default.
• W3201703223 cites W2614767650 @default.
• W3201703223 cites W2756692527 @default.
• W3201703223 cites W2761316039 @default.
• W3201703223 cites W2777842083 @default.
• W3201703223 cites W2787894218 @default.
• W3201703223 cites W2793845033 @default.
• W3201703223 cites W2796458509 @default.
• W3201703223 cites W2808363984 @default.
• W3201703223 cites W2896983921 @default.
• W3201703223 cites W2900221110 @default.
• W3201703223 cites W2903942159 @default.
• W3201703223 cites W2910713426 @default.
• W3201703223 cites W2912766985 @default.
• W3201703223 cites W2941774662 @default.

• next