Comparing the Soil Conservation Service model with new machine learning algorithms for predicting cumulative infiltration in semi-arid regions

Water infiltration into soil is an important process in hydrologic cycle; however, its measurement is difficult, time-consuming and costly. Empirical and physical models have been developed to predict cumulative infiltration (CI), but are often inaccurate. In this study, several novel standalone mac...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Pedosphere Ročník 32; číslo 5; s. 718 - 732
Hlavní autoři:	KHOSRAVI, Khabat, NGO, Phuong T.T., BARZEGAR, Rahim, QUILTY, John, AALAMI, Mohammad T., BUI, Dieu T.
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Beijing Elsevier Ltd 01.10.2022 Elsevier Science Ltd Faculty of Civil Engineering,University of Tabriz,Tabriz 51 Iran%Department of Civil and Environmental Engineering,University of Waterloo,Waterloo N2L 3G1 Canada%Faculty of Civil Engineering,University of Tabriz,Tabriz 51 Iran%Department of Business and IT,University of South-Eastern Norway,Notodden 3603 Norway Department of Watershed Management Engineering,Ferdowsi University of Mashhad,Mashhad 93 Iran Department of Earth and Environment,Florida International University,Miami 33199 USA%Institute of Research and Development,Duy Tan University,Da Nang 550000 Vietnam%Department of Bioresource Engineering,McGill University,Ste Anne de Bellevue QC H9X Canada
Témata:	additive regression Algorithms Arid regions Arid zones Bulk density clay data collection Datasets empirical model hybrid algorithms Hydrologic cycle Hydrology Infiltration Iran Learning algorithms Machine learning model validation Moisture content Moisture effects Optimization prediction Predictions Root-mean-square errors sand Semi arid areas Semiarid zones silt Soil conservation Soil density Soil moisture Soil water soil water content soil water infiltration Subgroups Time measurement USDA Water content Water infiltration weighted instances handler wrapper Iran empirical model soil water infiltration additive regression hybrid algorithms weighted instances handler wrapper
ISSN:	1002-0160, 2210-5107
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!