20.500.12556/DKUM-70483 Radon anomalies in soil gas caused by seismic activity Anomalije radona v talnem zraku, povzročene s seizmično aktivnostjo At the Orlica fault in the Krško basin, combined barasol detectors were buried in six boreholes, two along the fault itself and four on either side of it, to measure and record radon activity, temperature and pressure in soil gas every 60 minutes for four years. Data collected have been analysed in a manner aimed at distinguishing radon anomalies resulting from environmental parameters (air and soil temperature, barometric pressure, rainfall) from those caused solely by seismic events. The following approaches have been used to identify anomalies: (i) ± 2σ deviation of radon concentration from the seasonal average, (ii) correlation between time gradients of radon concentration and barometric pressure, and (iii) prediction with regression trees within a machine learning program. In this paper results obtained with regression trees are presented. A model has been built in which the program was taught to predict radon concentration from the data collected during the seismically inactive periods when radon is presumably influenced only by environmental parameters. A correlation coefficient of 0.83 between measured and predicted values was obtained. Then, the whole data time series was included and a significantly lowered correlation was observed during the seismically active periods. This reduced correlation is thus an indicator of seismic effect. Vzdolž preloma Orlica v Krški kotlini merimo koncentracijo radona v talnem zraku z avtonomnimi kombiniranimi instrumenti barasoli. Na šestih lokacijah, dve na samem prelomu in po dve na vsaki strani preloma, merimo aktivnost radona, temperaturo in zračni tlak štiri leta vsakih 60 minut. Rezultate meritev smo analizirali z namenom, da bi razlikovali med anomalijami radona, ki jih povzročajo hidrometeorološki vplivi (temperatura zraka in tal, zračni tlak in količina padavin) in tistimi, ki jih povzroča seizmična aktivnost. Za identifikacijo anomalij smo uporabili naslednje metode: (i) ± 2σ odklon koncentracije radona od sezonskih povprečnih vrednosti, (ii) korelacijo med časovnim gradientom koncentracije radona in časovnim gradientom zračnega tlaka, in (iii) regresijska drevesa s programi strojnega učenja. V tem članku predstavljamo rezultate, ki smo jih dobili z regresijskimi drevesi. Model je bil zgrajen v času seizmične neaktivnosti, v času, ko na koncentracijo radona vplivajo le hidrometeorološki parametri. Na podlagi tega lahko model napove koncentracijo radona za neseizmično obdobje s korelacijskim koeficientom 0,83. V času seizmične aktivnosti je napoved koncentracije radona veliko slabša. To znižanje korelacijskega koeficienta kaže na vpliv seizmične aktivnosti. radon in soil gas environmental parameters earthquakes correlation regression trees forecasting radon talni zrak okoljski parametri potresi korelacija regresijska drevesa napovedovanje true false true Angleški jezik Slovenski jezik Fakulteta za gradbeništvo, prometno inženirstvo in arhitekturo Univerze v Mariboru Znanstveno delo 2018-05-15 09:53:08 2018-05-15 09:54:42 2022-08-01 19:23:43 2019-07-11 18:08:52 2004 0 0 str. 12-19 št. 1 Letn. 1 2004 0000-00-00 Zaloznikova Objavljeno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 1854-0171 546.79:004.8 215987712 18701351 1854-0171 URN:SI:UM:DK:PEW1ITSP Acta_geotechnica_Slovenica_2004_Zmazek_et_al._Radon_anomalies_in_soil_gas_caused_by_seismic_activity.pdf Acta_geotechnica_Slovenica_2004_Zmazek_et_al._Radon_anomalies_in_soil_gas_caused_by_seismic_activity.pdf 1 65D8C2B72DD137B1361ADA3320BFD5C7 0c66f9dba69a8e764c49485b78f6fe54460296f6ef3308b1747664344ec79574 f48cac41-7c0f-11eb-bb7a-00155d0001ca 20.500.12556/dkum/9ec3dac6-1a23-4737-898d-b947b2e883f9 https://dk.um.si/Dokument.php?lang=slv&id=124704 http://fgserver3.fg.um.si/journal-ags/2004/article-2.asp 1 https://dk.um.si/Dokument.php?lang=slv&id=124703 Fakulteta za gradbeništvo, prometno inženirstvo in arhitekturo Acta geotechnica Slovenica 0 0 0