Back to search

Institutional Repository of Vilnius University

Bioliuminescencinių reiškinių vandenynų ir jūrų paviršiuose tyrimas naudojantis palydovinėmis technologijomis /

Abstract

dc:description

Satellite data and additional data is used in this work to study the milky sea phenomenon. The phenomenon is a rare natural occurrence that is observable in oceans and seas, during which a bioluminescent area forms on the water surface and emits a glow without the need for mechanical disturbances. In this work three research areas are observed with the accompanying satellite and extra data (HYCOM). The data is studied as compositions of three days during the phenomenon and before it and as the mean value of the bioluminescent area pixels during the whole study time span. A random forest machine learning algorithm is used which was applied to classify data according to a one DNB dataset from each study area and then used to classify data from other days. The results of the work showed that it is difficult to match the used data values (except the DNB data) to the bioluminescent area, although in certain cases NDWI and POC data can potentially be usefull. The machine learning based classification of data showed that it is possible to distinguish the occurrence areas automatically with minimal effort, but it is important to note the frequent classification errors.

Degree

thesis:*
Grantor dc:publisher
Institutional Repository of Vilnius University
Year dc:date
2024

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Tumėnas, Justas,

Rights

dc:rights
Statement dc:rights
  • info:eu-repo/semantics/openAccess
Language dc:language
lit

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
Vilnius University
Base URL
epublications.vu.lt/oai
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Tumėnas, Justas,. Bioliuminescencinių reiškinių vandenynų ir jūrų paviršiuose tyrimas naudojantis palydovinėmis technologijomis /. Institutional Repository of Vilnius University, 2024. https://repository.vu.lt/VU:ELABAETD210643335&prefLang=en_US