FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3001900529> ?p ?o ?g. }

• W3001900529 endingPage "845" @default.
• W3001900529 startingPage "819" @default.
• W3001900529 abstract "The bulk elemental composition of soil subsurface (B) horizons is influenced by environmental, biological, geological, and climatic factors. Because fossil soils (paleosols) are common in the geologic record, quantitative models that link climate to paleosol geochemistry are highly desirable in the paleoclimate community. Error associated with these models is typically reported as the root mean square error (RMSE) of a regression analysis and reflects the variability imparted by non-climatic influences on soil formation and the uncertainty associated with model fitting. However, for prediction purposes, the RMSE is well known to underestimate model uncertainty. In this work we re-evaluate a widely used transfer function for mean annual precipitation (MAP) based on the chemical index of alteration minus potassium (CIA-K) using data science best practices on two continental-scale soil data sets. Data set inter-comparisons and cross-validation of exponential regression models indicate that the root mean square prediction error (RMSPE) between CIA-K and MAP for soils representative of climates across the continental United States is around 299 mm, significantly higher than the currently accepted 182 mm RMSE. Further, CIA-K is unable to predict perhumid (>2000 mm MAP) climate zones. We show that transitioning from a simple regression framework to one of recursive partitioning via random forests can significantly increase prediction accuracy while automating variable selection. We introduce two new, widely applicable random forest models for MAP (RF-MAP) that use 10 elemental oxides as input variables and were calibrated on the Baylor University Soil Informatics (BU-SI) data set. RF-MAP version 1.0 (RF-MAP~1.0~) was generated using the entire BU-SI data set (n = 685) and can predict MAP values up to 6865 mm with a RMSPE of 395 mm. RF-MAP version 2.0 (RF-MAP~2.0~) was generated using a modification of the BU-SI data set (n = 642) and can predict MAP values up to ∼1600 mm with a RMSPE of 209 mm. Pruned regression trees provide insight into the mechanisms driving the random forest models and demonstrate the first empirical confirmation of the sensitivity of soil elemental responses to global climate zones. The RF-MAP~1.0~ and RF-MAP~2.0~ models predict MAP values comparable to independent proxy estimates for a range of deep-time paleosols. We advocate for application of RF-MAP~1.0~ in settings where no *a priori* information on paleoclimate is available, and encourage the use of either RF-MAP~1.0~ or RF-MAP~2.0~ if users have independent constraints that paleo-MAP was below 1600 mm." @default.
• W3001900529 created "2020-01-30" @default.
• W3001900529 creator A5026154664 @default.
• W3001900529 creator A5043714064 @default.
• W3001900529 creator A5044224247 @default.
• W3001900529 creator A5053946422 @default.
• W3001900529 creator A5082497563 @default.
• W3001900529 creator A5085286953 @default.
• W3001900529 date "2019-12-01" @default.
• W3001900529 modified "2023-10-16" @default.
• W3001900529 title "Recursive partitioning improves paleosol proxies for rainfall" @default.
• W3001900529 cites W1480376833 @default.
• W3001900529 cites W1491002046 @default.
• W3001900529 cites W1511862322 @default.
• W3001900529 cites W1565970033 @default.
• W3001900529 cites W1832876375 @default.
• W3001900529 cites W1971132622 @default.
• W3001900529 cites W1985380464 @default.
• W3001900529 cites W1989875747 @default.
• W3001900529 cites W2003879650 @default.
• W3001900529 cites W2010150056 @default.
• W3001900529 cites W2017046687 @default.
• W3001900529 cites W2026568767 @default.
• W3001900529 cites W2029401070 @default.
• W3001900529 cites W2032086472 @default.
• W3001900529 cites W2032186739 @default.
• W3001900529 cites W2032518966 @default.
• W3001900529 cites W2035549557 @default.
• W3001900529 cites W2036057044 @default.
• W3001900529 cites W2037247541 @default.
• W3001900529 cites W2042125540 @default.
• W3001900529 cites W2045518282 @default.
• W3001900529 cites W2053769525 @default.
• W3001900529 cites W2056944488 @default.
• W3001900529 cites W2059727820 @default.
• W3001900529 cites W2061870593 @default.
• W3001900529 cites W2068431090 @default.
• W3001900529 cites W2074004306 @default.
• W3001900529 cites W2074352423 @default.
• W3001900529 cites W2078734959 @default.
• W3001900529 cites W2082750542 @default.
• W3001900529 cites W2086290274 @default.
• W3001900529 cites W2087513600 @default.
• W3001900529 cites W2088610763 @default.
• W3001900529 cites W2089717705 @default.
• W3001900529 cites W2097346411 @default.
• W3001900529 cites W2101068785 @default.
• W3001900529 cites W2104224684 @default.
• W3001900529 cites W2111713949 @default.
• W3001900529 cites W2117236901 @default.
• W3001900529 cites W2122011746 @default.
• W3001900529 cites W2122014250 @default.
• W3001900529 cites W2122960116 @default.
• W3001900529 cites W2129899248 @default.
• W3001900529 cites W2132424470 @default.
• W3001900529 cites W2137247922 @default.
• W3001900529 cites W2139086914 @default.
• W3001900529 cites W2147383478 @default.
• W3001900529 cites W2160019699 @default.
• W3001900529 cites W2161185276 @default.
• W3001900529 cites W2161548576 @default.
• W3001900529 cites W2169616729 @default.
• W3001900529 cites W2176478590 @default.
• W3001900529 cites W2195345140 @default.
• W3001900529 cites W2219016031 @default.
• W3001900529 cites W2269733749 @default.
• W3001900529 cites W2283398122 @default.
• W3001900529 cites W2325730487 @default.
• W3001900529 cites W2326399519 @default.
• W3001900529 cites W2529307277 @default.
• W3001900529 cites W2553548740 @default.
• W3001900529 cites W2731600852 @default.
• W3001900529 cites W273955616 @default.
• W3001900529 cites W2765292396 @default.
• W3001900529 cites W2765656142 @default.
• W3001900529 cites W278712781 @default.
• W3001900529 cites W2787390971 @default.
• W3001900529 cites W2793013045 @default.
• W3001900529 cites W2803923412 @default.
• W3001900529 cites W2911964244 @default.
• W3001900529 cites W2912934387 @default.
• W3001900529 cites W2915949169 @default.
• W3001900529 cites W2946134324 @default.
• W3001900529 cites W3085162807 @default.
• W3001900529 cites W3121452939 @default.
• W3001900529 cites W571652462 @default.
• W3001900529 cites W636762014 @default.
• W3001900529 doi "https://doi.org/10.2475/10.2019.01" @default.
• W3001900529 hasPublicationYear "2019" @default.
• W3001900529 type Work @default.
• W3001900529 sameAs 3001900529 @default.
• W3001900529 citedByCount "14" @default.
• W3001900529 countsByYear W30019005292020 @default.
• W3001900529 countsByYear W30019005292021 @default.
• W3001900529 countsByYear W30019005292022 @default.
• W3001900529 countsByYear W30019005292023 @default.
• W3001900529 crossrefType "journal-article" @default.
• W3001900529 hasAuthorship W3001900529A5026154664 @default.

• next