東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Local Climate Zone Classification Sy...

Marques, Bruno Ricardo Jorge Martins,

Linked to FindBook

Google Book

Amazon

博客來

Local Climate Zone Classification System Using WEB GIS Approach /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Local Climate Zone Classification System Using WEB GIS Approach // Bruno Ricardo Jorge Martins Marques.
Author:	Marques, Bruno Ricardo Jorge Martins,
Description:	1 electronic resource (57 pages)
Notes:	Source: Masters Abstracts International, Volume: 86-12.
Contained By:	Masters Abstracts International86-12.
Subject:	Application programming interface. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32016440
ISBN:	9798286411757

Local Climate Zone Classification System Using WEB GIS Approach /
Marques, Bruno Ricardo Jorge Martins,

Local Climate Zone Classification System Using WEB GIS Approach /Bruno Ricardo Jorge Martins Marques. - 1 electronic resource (57 pages)

Source: Masters Abstracts International, Volume: 86-12.

Climate change along with population growth and urbanization trends across the coastal areas are pressuring our cities to become more and more resilient to the ''new normal''. Our resilience is a function of hazards' severity and probability, people's and assets' exposure and societies' sensitivity, and our ability in responding not only to a warmer climate, but also and foremost to extreme climate events will determine our resilience, in the future. Midlatitude countries such as Portugal have been experiencing warmer summers, in which heatwaves are becoming more frequent and severe, exposing an increasingly ageing population to correlated health and energy poverty issues. Part of the challenge moving forward is ensuring our ability to monitor and predict extreme heatwaves in space and time, with enough level of detail as to allow to highlight hot spots within cities and larger metropolitan areas which should be prioritized. The temporal aspect, and the spatial accuracy are something that the national and international weather services already take well care of - but there is a gap in what concerns managing cities, especially in more complex and coastal environments, where temperatures asymmetries are greater due to the complex land-sea interactions. To overcome this issue, remote sensing now offers spatially complete time series of observational data from which to derive insights into what concerns to the way we occupy these territories, as well as the thermal footprint of that land use land cover. When processed using machine learning and artificial intelligence, time series of geospatial data obtained from satellite imagery hence allows us to downscale weather and climate up to the neighborhood scale. But to do that we need to ensure consistency, precision, and standardization of processes and benchmarking of climate-relevant land use land cover data. Local Climate Zones (LCZ) is now the gold standard scheme for Land Use/Land Cover (LULC) classification; nevertheless, while the LCZ's overall criteria are well-established, the methods employed for classification are very diverse, often local-specific. Alternatively, some highly scalable satellite imagery-based classification approaches have been attempted, based on open-source data - but these lack sufficient local detail, and may lead to misleading urban climate modelling results. This thesis aims to build vii upon pre-existent attempts at transforming geospatial data products into accurate and subkilometric resolution LCZ classification maps, to optimize them in terms of precision and scalability using open-source tools and libraries and a WEB GIS interface. The GIS-based classification is implemented using Portuguese and Denmark cities for benchmark with previous works. The objective is to attain the best-performing algorithm without overfitting it to a specific location, while its usability to tackle urban climate shall be tested, particularly the predictability of the Urban Heat Island (UHI) effect using such LCZ as a predictor, but open for scientific community to use.

English

ISBN: 9798286411757Subjects--Topical Terms:

3562904
Application programming interface.

Local Climate Zone Classification System Using WEB GIS Approach /
LDR:04493nmm a22004333i 4500 001 2437424
005 20251119142812.5
006 m o d
007 cr|nu||||||||
008 261011s2025 miu||||||m |||||||eng d
020 $a 9798286411757
035 $a (MiAaPQD)AAI32016440
035 $a (MiAaPQD)RCAAP10362182169
035 $a AAI32016440
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Marques, Bruno Ricardo Jorge Martins, $e author. $3 3828392
245 1 0 $a Local Climate Zone Classification System Using WEB GIS Approach / $c Bruno Ricardo Jorge Martins Marques.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (57 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 86-12.
500 $a Advisors: da Costa Brito Cabral, Pedro; Oliveira, Ana.
502 $b M.G.I.S. $c Universidade NOVA de Lisboa (Portugal) $d 2025.
520 $a Climate change along with population growth and urbanization trends across the coastal areas are pressuring our cities to become more and more resilient to the ''new normal''. Our resilience is a function of hazards' severity and probability, people's and assets' exposure and societies' sensitivity, and our ability in responding not only to a warmer climate, but also and foremost to extreme climate events will determine our resilience, in the future. Midlatitude countries such as Portugal have been experiencing warmer summers, in which heatwaves are becoming more frequent and severe, exposing an increasingly ageing population to correlated health and energy poverty issues. Part of the challenge moving forward is ensuring our ability to monitor and predict extreme heatwaves in space and time, with enough level of detail as to allow to highlight hot spots within cities and larger metropolitan areas which should be prioritized. The temporal aspect, and the spatial accuracy are something that the national and international weather services already take well care of - but there is a gap in what concerns managing cities, especially in more complex and coastal environments, where temperatures asymmetries are greater due to the complex land-sea interactions. To overcome this issue, remote sensing now offers spatially complete time series of observational data from which to derive insights into what concerns to the way we occupy these territories, as well as the thermal footprint of that land use land cover. When processed using machine learning and artificial intelligence, time series of geospatial data obtained from satellite imagery hence allows us to downscale weather and climate up to the neighborhood scale. But to do that we need to ensure consistency, precision, and standardization of processes and benchmarking of climate-relevant land use land cover data. Local Climate Zones (LCZ) is now the gold standard scheme for Land Use/Land Cover (LULC) classification; nevertheless, while the LCZ's overall criteria are well-established, the methods employed for classification are very diverse, often local-specific. Alternatively, some highly scalable satellite imagery-based classification approaches have been attempted, based on open-source data - but these lack sufficient local detail, and may lead to misleading urban climate modelling results. This thesis aims to build vii upon pre-existent attempts at transforming geospatial data products into accurate and subkilometric resolution LCZ classification maps, to optimize them in terms of precision and scalability using open-source tools and libraries and a WEB GIS interface. The GIS-based classification is implemented using Portuguese and Denmark cities for benchmark with previous works. The objective is to attain the best-performing algorithm without overfitting it to a specific location, while its usability to tackle urban climate shall be tested, particularly the predictability of the Urban Heat Island (UHI) effect using such LCZ as a predictor, but open for scientific community to use.
546 $a English
590 $a School code: 7029
650 4 $a Application programming interface. $3 3562904
650 4 $a Urban planning. $3 2122922
650 4 $a Population density. $3 908253
650 4 $a Python. $3 3201289
650 4 $a Climate change. $2 bicssc $3 2079509
650 4 $a Landsat satellites. $3 3695193
650 4 $a Vegetation. $3 3560047
650 4 $a Geographic information systems. $3 542758
650 4 $a Rural areas. $3 3560074
650 4 $a Urban areas. $3 3546012
650 4 $a Classification schemes. $3 3695337
650 4 $a Grasslands. $3 650086
650 4 $a Urban heat islands. $3 3705078
650 4 $a Cities. $3 3544022
650 4 $a Aerospace engineering. $3 1002622
650 4 $a Geographic information science. $3 3432445
650 4 $a Information technology. $3 532993
690 $a 0404
690 $a 0999
690 $a 0538
690 $a 0800
690 $a 0370
690 $a 0489
710 2 $a Universidade NOVA de Lisboa (Portugal). $e degree granting institution. $3 3767537
720 1 $a da Costa Brito Cabral, Pedro $e degree supervisor.
720 1 $a Oliveira, Ana $e degree supervisor.
773 0 $t Masters Abstracts International $g 86-12.
790 $a 7029
791 $a M.G.I.S.
792 $a 2025
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32016440