Приказ основних података о документу

Emisije gasova staklene bašte u Srbiji za period 1995-2013. godina primenom rekurentnih neuronskih mreža

dc.creatorStamenković, Lidija J.
dc.creatorAntanasijević, Davor
dc.creatorRistić, Mirjana
dc.creatorPerić-Grujić, Aleksandra
dc.creatorPocajt, Viktor
dc.date.accessioned2021-03-10T12:42:50Z
dc.date.available2021-03-10T12:42:50Z
dc.date.issued2015
dc.identifier.issn0354-3285
dc.identifier.urihttp://TechnoRep.tmf.bg.ac.rs/handle/123456789/2954
dc.description.abstractThe aim of this work was to create an ANN model for the prediction of GHG emissions in the Republic of Serbia in the period 1995-2013. Because of the lack of GHG emission data and inputs for Serbia, the ANN model was initially developed for Bulgaria, using the gross domestic product per capita (GDP) and annual energy production per capita (GPE) as inputs. The model was trained and validated with the data for Bulgaria for the period from 1990 to 2011,using Recurrent Neural Network (RNN) architecture. The results obtained for Serbia indicate a good agreement between the calculated and predicted GHG emissions in 1998, with an error of only 3%. The predicted change in the emission of GHG in the studied period is in agreement with social and economical factors that can be related to the changes in GHG emissions(e.g. emission reduction of about 10% in 1999). The RNN model predicts that the GHG emissions in 2013was above the level in 1998, but still lower than the GHG emissions calculated for the year 1990.en
dc.description.abstractCilj ovog rada je bio kreiranje modela, zasnovanog na veštačkim neuronskim mrežama, za predviđanje emisije GHG u Republici Srbiji. Zbog nedostatka podataka o GHG emisiji u Republici Srbiji, model je razvijen korišćenjem podataka za Republiku Bugarsku, a zatim je primenjen i na Republiku Srbiju. Kao ulazni parametri korišćeni su bruto d omaći proizvod po stanovniku (BDP) i godišnja proizvodnja energije po stanovniku (GPE). Model je treniran i testiran sa podacima za Bugarsku za period od 1990 do 2011. godine, pri čemu je korišćena rekurentna neuronska mreža (RNN). Rezultati za Republiku Srbiju pokazuju dobro slaganje između proračunate i modelom predviđene vrednosti emisije GHG za 1998. godinu, sa odstupanjem od svega 3%. Analiza predviđenog trenda ukazuje na promene u emisiji koje su bile posledica društvenih okolnosti (smanjenje emisije od oko 10% tokom 1999. godine). Model pokazuje da je emisija GHG-a u 2013. godini prestigla nivo iz 1998. godine, ali će i dalje biti ispod vrednosti emisije proračunate za 1990. godinu.sr
dc.publisherNaučno-stručno društvo za zaštitu životne sredine Srbije - Ecologica, Beograd
dc.relationinfo:eu-repo/grantAgreement/MESTD/Basic Research (BR or ON)/172007/RS//
dc.rightsopenAccess
dc.sourceEcologica
dc.subjectGHG emission forecasten
dc.subjectartificial neural networksen
dc.subjectSerbiaen
dc.subjectemisija gasova staklene baštesr
dc.subjectveštačke neuronske mrežesr
dc.subjectSrbijasr
dc.titleEstimation of GHG emission in Serbia for period 1995-2013 using recurent neural networksen
dc.titleEmisije gasova staklene bašte u Srbiji za period 1995-2013. godina primenom rekurentnih neuronskih mrežasr
dc.typearticle
dc.rights.licenseARR
dc.citation.epage492
dc.citation.issue79
dc.citation.other22(79): 488-492
dc.citation.rankM51
dc.citation.spage488
dc.citation.volume22
dc.identifier.fulltexthttp://TechnoRep.tmf.bg.ac.rs/bitstream/id/988/2951.pdf
dc.identifier.rcubhttps://hdl.handle.net/21.15107/rcub_technorep_2954
dc.type.versionpublishedVersion


Документи

Thumbnail

Овај документ се појављује у следећим колекцијама

Приказ основних података о документу