prikaz prve stranice dokumenta Predviđanje mikroklimatskih parametara za primjenu u preciznoj poljoprivredi
No public access
master's thesis
Predviđanje mikroklimatskih parametara za primjenu u preciznoj poljoprivredi
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. urn:nbn:hr:168:205965
Kreković, Dora
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Kreković, D. (2021). Predviđanje mikroklimatskih parametara za primjenu u preciznoj poljoprivredi (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:205965

Kreković, Dora. "Predviđanje mikroklimatskih parametara za primjenu u preciznoj poljoprivredi." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. https://urn.nsk.hr/urn:nbn:hr:168:205965

Kreković, Dora. "Predviđanje mikroklimatskih parametara za primjenu u preciznoj poljoprivredi." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. https://urn.nsk.hr/urn:nbn:hr:168:205965

Kreković, D. (2021). 'Predviđanje mikroklimatskih parametara za primjenu u preciznoj poljoprivredi', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 23 June 2024, https://urn.nsk.hr/urn:nbn:hr:168:205965

Kreković D. Predviđanje mikroklimatskih parametara za primjenu u preciznoj poljoprivredi [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2021 [cited 2024 June 23] Available at: https://urn.nsk.hr/urn:nbn:hr:168:205965

D. Kreković, "Predviđanje mikroklimatskih parametara za primjenu u preciznoj poljoprivredi", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:168:205965

Metadata
TitlePredviđanje mikroklimatskih parametara za primjenu u preciznoj poljoprivredi
Title (english)Prediction of Microclimate Parameters for Application in Precision Agriculture
AuthorDora Kreković
MentorIvana Podnar Žarko (mentor)
Committee memberIvana Podnar Žarko (predsjednik povjerenstva)
Committee memberMario Kušek (član povjerenstva)
Committee memberPavle Skočir (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2021-07-09, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Predviđanje mikroklimatskih parametara, poput temperature, brzine vjetra i vlage, omogućuje planiranje i kontrolu poljoprivredne proizvodnje radi poboljšanja prinosa i kvalitete usjeva. U ovom radu dan je pregled metoda za predviđanje mikroklimatskih parametara koje na ulazu koriste vremenski označene tokove podataka ili tzv. vremenske serije podataka. Detaljno je objašnjen pojam vremenskih serija, kao i postupci njihove analize. Objašnjene su statističke metode prognoziranja vremenskih serija, metode prognoziranja strojnim učenjem, te metode prognoziranja neuronskim mrežama. Na studijskom slučaju su korištenjem podatka s Copernicusovog servisa CDS implementirane i evaluirane tehnike prognoze pomoću neuronske mreže LSTM te prognoze korištenjem klasičnog statističkog modela SARIMA. Dodatno, mreža je izgrađena i koristeći stvarne senzorske podatke očitane s agrometeorološke stanice Pinova nad kojima je isprobana tehnika multivarijatne prognoze. Svi dobiveni rezultati su prikazani grafički.
Abstract (english)
Forecasting microclimate parameters, such as temperature, wind speed and humidity, enables the planning and control of agricultural production to improve crop yields and quality. This paper provides an overview of methods for predicting microclimate parameters that use time series data as input. Both the concept of time series and methods for their analysis are explained in detail. Furthermore, the thesis provides insight into the methods of forecasting time series using machine learning algorithms as well as using neural networks. LSTM neural network model and statistical model SARIMA were implemented and evaluated on a case study using data from the Copernicus service CDS. Additionally, another network was built using actual sensory data streams acquired from a Pinova agrometeorological station. All results, both from analysis and forecast, were then visualized.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:205965
Study programmeTitle: Computing
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2023-01-13 12:46:07