Details

Nadomeščanje manjkajočih opazovanj temperature s pomočjo meritev bližnjih postaj
ID Klobučar, Andraž (Author), ID Faganeli Pucer, Jana (Mentor) More about this mentor... This link opens in a new window

.pdfPDF - Presentation file, Download (963,68 KB)
MD5: 51C38753EEE172CBC20A833016E7CA4C

Abstract
Meteorološki modeli, ki so pomembni za vsakodnevno življenje in gospodarstvo, temeljijo na kakovostnih meritvah. Velik izziv pri obravnavi teh podatkov pa predstavljajo manjkajoče meritve, ki se pojavijo ob izpadih senzorjev vremenskih postaj. Cilj diplomske naloge je bil predstaviti in preizkusiti različne metode za nadomeščanje manjkajočih vrednosti v primeru, da pride do izpada celotne vremenske postaje. V takšnih primerih nimamo meritev drugih meteoroloških parametrov postaje, s pomočjo katerih bi lahko nadomestili manjkajoče, ampak se moramo zanesti na meritve ostalih vremenskih postaj v okolici. Kot primer smo uporabili meritve temperatur iz območja Slovenije katere nam je zagotovila Agencija Republike Slovenije za okolje. Najboljše rezultate smo dosegli z uporabo modela naključnih gozdov, ki so dosegli povprečno absolutno napako 0.6 °C in standardno deviacijo 0.1 °C. Pokazali smo tudi, da je uspešnost nadomeščanja manjkajočih meritev temperature odvisna od vremenskih značilnosti v okolici vremenske postaje in vremenskih vzorcev, ki se mesečno spreminjajo.

Language:Slovenian
Keywords:nadomeščanje manjkajočih meritev, meritve vremenskih postaj, naključni gozdovi, konvolucijske nevronske mreže
Work type:Bachelor thesis/paper
Typology:2.11 - Undergraduate Thesis
Organization:FRI - Faculty of Computer and Information Science
Year:2025
PID:20.500.12556/RUL-168005 This link opens in a new window
COBISS.SI-ID:232232963 This link opens in a new window
Publication date in RUL:24.03.2025
Views:348
Downloads:99
Metadata:XML DC-XML DC-RDF
:
Copy citation
Share:Bookmark and Share

Secondary language

Language:English
Title:Replacing missing temperature observations with measurements from nearby stations
Abstract:
Meteorological models depend on high quality meteorological measurements. However, the presence of missing measurements presents a major challenge in handling weather data. The aim of this thesis was to present and test various methods for imputing missing values in cases where the entire weather station experiences an outage. In such scenarios, there are no internal station measurements available that would help us impute the missing data, which forces us to rely on data from surrounding weather stations. We achieved the best results using Random Forest which achieved mean absolute error of 0.6 °C with a standard deviation of 0.1 °C. We also demonstrated that the accuracy of imputations was dependent on the meteorological characteristics of the location of the meteorological station, and the weather patterns that vary on a monthly basis.

Keywords:missing data imputation, weather station measurements, random forests, convolutional neural networks

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Back