Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ EMU DSpacearrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
EMU DSpace
Doctoral thesis . 2023
Data sources: EMU DSpace
versions View all 2 versions
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Novel approaches in multi-sensor unmanned aerial vehicles as basis for enhancing fire management frameworks

Authors: Sampaio de Lima, Raul;

Novel approaches in multi-sensor unmanned aerial vehicles as basis for enhancing fire management frameworks

Abstract

A Thesis for applying for the degree of Doctor of Philosophy in Environmental Protection. Väitekiri filosoofiadoktori kraadi taotlemiseks keskkonnakaitse erialal. Introduction. Climate changes are affecting the world, making wildfire understanding vital, and Estonia might experience an increase in the frequency of wildfires in the forthcoming years. Despite efforts to integrate fire management actions and research, many findings remain in "grey literature." This gap calls for formal research to evaluate the efficacy of these strategies. Recently, Estonian initiatives seek to foster collaboration between research and government entities. This thesis thus aims to contribute to the topic by developing knowledge on remote sensing, particularly UAV-based approaches, to improve fire management frameworks. Methods. The study involved various Estonian locations. Paper I examined how UAV flight parameters affect data quality in Lahemaa National Park. Papers II and IV estimated aboveground biomass using multispectral imagery and hyperspectral data from the Agricultural Research Centre in Kuusiku, employing diverse machine learning methods and approaches. Paper III predicted soil moisture in Lavassaare Natural Reserve using optical UAV data and partial least squares regression. Lastly, Paper V maps Rosa rugosa occurrence across Estonian coast using UAVs, integrating these findings into a satellite dataset. Results and Conclusions. The study unveiled an optimal UAV collection strategy for Estonian forests, ensuring canopy and forest floor reconstruction. Machine learning and AutoML frameworks proved effective in estimating biomass, paving the way for automated algorithms. Developing distinct models or conducting field surveys at various periods emerged as the most effective approach for accurate soil moisture modelling. Lastly, a UAV-based methods aided post-fire monitoring and species mapping, allowing assessments beyond surveyed areas. Thus, the importance of these datasets shifted across management stages. Multispectral data aided pre-fire soil moisture estimation, while post-fire used photogrammetry for exposed areas. Integrating diverse remote sensing data improved modelling results, overcoming transferability challenges. Complementary use of RS and field data enhanced modelling, particularly in complex environments. Findings underlined potential in merging remote sensing data for precise variable modelling, enhancing accuracy and agreement toward improved fire management systems. Sissejuhatus. Kliimamuutused mõjutavad maailma, muutes metsatulekahjude mõistmise hädavajalikuks, ning Eestis võib lähiaastatel sageneda metsatulekahjude esinemissagedus. Hoolimata jõupingutustest integreerida tuleohjamise meetmeid ja teadustööd, jäävad paljud uuringud "halli kirjandusse". See lünk nõuab formaalset uurimustööd nende strateegiate tõhususe hindamiseks. Hiljutised Eesti algatused püüavad edendada koostööd teadus- ja valitsusasutuste vahel. Seetõttu eesmärk ongi käesoleva doktoritööga arendada teadmisi kaugseire valdkonnas, eriti mehitamata õhusõidukite (UAV) põhiste lähenemiste kaudu, et parandada tuleohjamise raamistikke. Materjal ja metoodika. Uuring hõlmas erinevaid Eesti asukohti. Artikkel I uuris, kuidas UAV lendude parameetrid mõjutavad andmete kvaliteeti Lahemaa rahvuspargis. Artiklid II ja IV hindasid ülemise maa biomassi kasutades multispektraalseid ja hüperspektraalseid andmeid Põllumajandusuuringute Keskusest Kuusikust, rakendades mitmekesiseid masinõppe meetodeid ja lähenemisi. Artikkel III prognoosis pinnase niiskust Lavassaare looduskaitsealal, kasutades optilisi UAV andmeid ja osalist vähimruutude regressiooni. Lõpuks, artikkel V kaardistas Rosa rugosa esinemist üle Eesti rannajoone, kasutades UAV-sid ja ühendades need leiud satelliidi andmestikuga. Tulemused ja järeldused. Uuring näitas optimaalset UAV andmete kogumise strateegiat Eesti metsades, tagades krooni ja metsapõranda rekonstrueerimise võrreldes laserskaneerimise andmekvaliteediga. Masinõppe ja AutoML raamistikud osutusid tõhusaks ülemise maa biomassi hindamisel, avades tee automatiseeritud algoritmidele. Erinevate mudelite arendamine või välitööde teostamine erinevatel perioodidel osutus kõige tõhusamaks meetodiks täpse pinnase niiskuse modelleerimisel. Lõpuks aitas UAV-põhine meetod jälgida tulekahjude järelvalvet ja liikide kaardistamist, võimaldades hindamist ka välitööde piirkondade kaugemale. Seega muutus nende andmete tähtsus tuleohjamise etappide vahel. Multispektraalsed andmed aitasid ennetavalt hinnata pinnase niiskust, samas kui järeltulekahjude kontekstis kasutati fotogrammetriat paljastatud alade jaoks. Erinevate kaugseire andmete integreerimine parandas modelleerimistulemusi, ületades ülekantavuse väljakutsed. Kaugseire ja välitööde andmete komplementaarne kasutamine täiustas modelleerimist, eriti keerulistes keskkondades. Leiud rõhutasid kaugseire andmete ühendamise potentsiaali täpseks muutuva muutuja modelleerimiseks, suurendades täpsust ja kokkulepet paremate tuleohjamissüsteemide poole. Publication of this thesis is supported by the Estonian University of Life Sciences and by the Doctoral School of Earth Sciences and Ecology, created under the auspices of the European Social Fund.

Country
Estonia
Related Organizations
Keywords

Estonia, dissertations, modelleerimine (teadus), Roheline Ülikool (töö toetab EMÜ Rohelise Ülikooli põhimõtteid), dissertatsioonid, drone aircrafts, droonid, modelling (science), remote sensing, metsatulekahjud, inspection of fire prevention, Green University (thesis is related to EMÜ Green University iniciative’s aims), Eesti, forest fires, kaugseire, tuleohutusjärelevalve

  • BIP!
    Impact byBIP!
    citations
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
  • citations
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
    Powered byBIP!BIP!
Powered by OpenAIRE graph
Found an issue? Give us feedback
citations
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Related to Research communities
Assessing the socio-economic impact of digitalisation in rural areas
moresidebar

Do the share buttons not appear? Please make sure, any blocking addon is disabled, and then reload the page.