PointSLA

nevronska mreža za napovedovanje manjkajočih vrednosti satelitskih meritev vodne gladine

Klemen Vovk (Author), Matej Kristan (Mentor), Matjaž Ličer (Co-mentor)

Abstract

Satelitske meritve so ključne za raziskovanje in razumevanje geofizikalnih pojavov. Kljub temu, da je okrog Zemlje utirjenih mnogo satelitov, enostavno ni mogoče hkrati pokriti in izmeriti celotnega površja. Posledično imajo satelitske meritve velike časovno-prostorske luknje kar zmanjša natančnost modelov, ki temeljijo na teh meritvah. Ena od spremenljivk, ki jih merijo sateliti je tudi anomalija višine gladine morja (ang. sea-level anomaly, SLA). Pove nam odstopanje višine morske gladine na neki točki, ob nekem času glede na referenco, ki je izračunana kot globalno povprečje preko obdobja več preteklih let. V nalogi naslavljamo problem napovedovanja manjkajočih satelitskih meritev SLA. Moderne metode ta problem rešujejo s pristopi, ki temeljijo na konvolucijah in zahtevajo meritve na regularni mreži. To pomeni, da moramo meritve predobdelati tako, da jih diskretiziramo na regularno mrežo. S tem vnesemo nenatančnost že v vhodne podatke. V tej nalogi predlagamo model PointSLA, ki za gosto napoved satelitskih meritev SLA deluje nad oblaki točk meritev in zato ne potrebuje diskretizacije vhoda. Eksperimentalni rezultati kažejo, da predlagan model doseže RMSE, ki je 5% slabši od najsodobnejše metode DIVAnd, pri tem pa omogoča večjo časovno in prostorsko fleksibilnost vhoda ter ne potrebuje diskretizacije meritev na mrežo.

Keywords

satelitske meritve;oblaki točk;transformatorji;pozornost;računalništvo in informatika;univerzitetni študij;diplomske naloge;

Data

Language:	Slovenian
Year of publishing:	2022
Typology:	2.11 - Undergraduate Thesis
Organization:	UL FRI - Faculty of Computer and Information Science
Publisher:	[K. Vovk]
UDC:	004.8:551.461(043.2)
COBISS:	123819779
Views:	40
Downloads:	20
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	PointSLA: a neural network for prediction of missing values in satelite sea-level measurements
Secondary abstract:	Satellite measurements are crucial in researching and understanding of geophysical phenomena. Even though there are many satellites orbiting Earth, it is impossible to measure the whole surface at all times. Consequentially, satellite measurements have significant gaps in space-time. One of the variables that satellites measure is sea-level anomaly (SLA). It describes the deviation of the sea surface height at some point in space-time from the global average computed over several past years. We address the problem of missing satellite measurements prediction. State-of-the-art methods solve this problem with approaches based on convolutions and therefore require measurements to be on a regular grid. To achieve this, a preprocessing step is needed to discretize the measurements onto a regular grid. However, this also introduces imprecision into the input. In this thesis, we propose PointSLA, a method that uses point clouds for dense prediction of SLA satellite measurements and therefore does not require discretization of measurements. Experimental results show the proposed model achieving RMSE 5% worse than state-of-the-art method DIVAnd while enabling greater space and time flexibility of the input and not requiring measurement discretization
Secondary keywords:	neural networks;satellite measurements;point clouds;transformers;attention;computer science;computer and information science;diploma;Nevronske mreže (računalništvo);Računalništvo;Univerzitetna in visokošolska dela;
Type (COBISS):	Bachelor thesis/paper
Study programme:	1000468
Embargo end date (OpenAIRE):	1970-01-01
Thesis comment:	Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages:	58 str.
ID:	16479226