Napovedovanje dinamike plazu urbas z modeli časovnih vrst in strojnim učenjem

Horvat, Štefan

| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

First page > Show document

Show document

Title:	Napovedovanje dinamike plazu urbas z modeli časovnih vrst in strojnim učenjem
Authors:	ID Horvat, Štefan (Author) ID Strnad, Damjan (Mentor) More about this mentor... ID Šegina, Ela (Comentor)
Files:	MAG_Horvat_Stefan_2022.pdf (4,33 MB) MD5: 014C20A087BD3F88F55DB447B0811A11
Language:	Slovenian
Work type:	Master's thesis/paper
Typology:	2.09 - Master's Thesis
Organization:	FERI - Faculty of Electrical Engineering and Computer Science
Abstract:	Plazovi lahko resno ogrozijo človeška življenja in povzročijo ogromno gmotno škodo. Na dinamiko plazu običajno vpliva večje število zunanjih dejavnikov, zato je napovedovanje premikov težka naloga. V sodobnem času lahko premike plazov podrobno spremljamo z natančnimi merilnimi instrumenti in tako tvorimo množico podatkov, na podlagi katere gradimo razlagalne in napovedne modele. V magistrskem delu preizkušamo različne tehnike modeliranja premikov plazu Urbas, ki spada med bolj aktivne plazove v Sloveniji. Za modeliranje dinamike plazu uporabimo modele časovnih vrst in nevronsko mrežo z dolgim kratkoročnim spominom. Najboljše prileganje je dosegla nevronska mreža z dolgin kratkoročnim spominom, katere srednja kvadratna napaka je znašala 3,37 mm. Pri napovedovanju premikov se je najbolje odrezal linearni regresijski model s srednjo kvadratno napako 0,52 mm.
Keywords:	plaz, časovne vrste, linearna regresija, dinamična regresija, nevron-ske mreže LSTM
Place of publishing:	Maribor
Publisher:	[Š. Horvat]
Year of publishing:	2022
PID:	20.500.12556/DKUM-83486
UDC:	504.4
COBISS.SI-ID:	141028355
Publication date in DKUM:	15.12.2022
Views:	942
Downloads:	153
Metadata:
Categories:	KTFMB - FERI
:	Copy citation

Average score:	(0 votes)
Your score:	Voting is allowed only for logged in users.
Share:

Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:	CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International

Link:	http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:	The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:	05.12.2022

Secondary language

Language:	English
Title:	Urbas landslide dynamics prediction using time series models and machine learning
Abstract:	Landslides can pose a serious threat to human lives and cause widespread property damage. Landslide dynamics are usually affected by numerous exogenous factors so forecasting landslide displacement can be difficult. Nowadays landslide parameters can be measured with precise instruments, and thus massive amounts of data can be gathered, which can be used to build explanatory and forecasting models. We experiment with different forecasting techniques on one of the most active landslides in Slovenia – the Urbas landslide. We use time series and long short-term memory neural network models to predict landslide displacement. Long short-term memory neural network model achieved the best fit with mean square error of 3.37 mm. Linear regression model achieved the best prediction with mean square error of 0.52 mm.
Keywords:	landslide, time series, linear regression, dynamic regression, LSTM neural networks

Comments

Leave comment

You must log in to leave a comment.

Comments (0)

0 - 0 / 0

There are no comments!

Back