Evrendilek, FatihDenizli, HalukYetiş, HakanKarakaya, Nusret2021-06-232021-06-2320130167-63691573-2959https://doi.org/10.1007/s10661-012-2968-3https://hdl.handle.net/20.500.12491/7531Concentrations of outdoor radon-222 (Rn-222) in temperate grazed peatland and deciduous forest in northwestern Turkey were measured, compared, and modeled using artificial neural networks (ANNs) and multiple nonlinear regression (MNLR) models. The best-performing multilayer perceptron model selected out of 28 ANNs considerably enhanced accuracy metrics in emulating Rn-222 concentrations relative to the MNLR model. The two ecosystems had similar diel patterns with the lowest Rn-222 concentrations in the afternoon and the highest ones near dawn. Mean level (5.1 + 2.5 Bq m(-3) h(-1)) of Rn-222 in the forest was three times smaller than that (15.8 + 9.7 Bq m(-3)) of Rn-222 in the peatland. Mean Rn-222 level had negative and positive relationships with air temperature and relative humidity, respectively.eninfo:eu-repo/semantics/closedAccessForestModelingNeural NetworksPeatlandRadon-222Article10.1007/s10661-012-2968-3185755775583230961382-s2.0-84878682952Q2WOS:000319753600018Q2