Hyppää sisältöön
    • Suomeksi
    • På svenska
    • In English
  • Suomi
  • Svenska
  • English
  • Kirjaudu
Hakuohjeet
JavaScript is disabled for your browser. Some features of this site may not work without it.
Näytä viite 
  •   Ammattikorkeakoulut
  • LAB-ammattikorkeakoulu
  • Opinnäytetyöt (Avoin kokoelma)
  • Näytä viite
  •   Ammattikorkeakoulut
  • LAB-ammattikorkeakoulu
  • Opinnäytetyöt (Avoin kokoelma)
  • Näytä viite

Quantifying the effect of anthropogenic and climate parameters on urban heat island using machine learning

Ogunfuyi, Samson Oluwafemi (2022)

Avaa tiedosto
Ogunfuyi_Samson.pdf (5.327Mt)
Lataukset: 


Ogunfuyi, Samson Oluwafemi
2022
All rights reserved. This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Näytä kaikki kuvailutiedot
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:amk-2022112824597
Tiivistelmä
The intensity of UHI in today's developed areas indicates the extent of environmental modification. Replacing natural surfaces with artificial materials has been the main difference between rural and urban areas. Therefore, creating a massive temperature variation that researchers have confirmed. Also, the detrimental effect of UHI on life and properties has called for more climate action. This study aims to analyse the distinct signatures of climate and anthropogenic factors in UHI formation and generate an urban heat risk map to aid urban planners in making policy decisions that mitigate the UHI effect. Based on existing studies, Remote sensing techniques and multicriteria decision analysis were used. Similarly, machine learning regression algorithms were used to improve traditional statistical methods adopted in literature to address these research objectives. The obtained result confirmed the existence of UHI across space and time in Glasgow. Furthermore, the result demonstrates that machine learning algorithms can predict LST, and XGBoost had the best predictive performance with an R2 value of 0.8126 compared to ANN and DT. Also, the sensitivity analysis illustrated that horizontal urban parameters such as water distance, NDVI and road network distance had more influence on LST. Though vertical urban parameters like building height and volume did not strongly influence LST, DEM illustrated a significant effect. Furthermore, socio-demographic and climate parameters fairly affect LST. The MCDA analysis showed that 3.5% of Glasgow areas fall under high-risk heat zones, 4.66% are low-risk, and 91.83% are moderate-risk. The result confirms the role of vegetation and water body in UHI reduction. Likewise, this research revealed that enhanced NDVI, used as a proxy for vegetation, can reduce heat risk. On the other hand, building height reduces vegetation's efficiency to decreasing heat risk in urban areas. On this basis, it is recommended that urban planners prioritise water bodies and vegetation during urban design. Also, policies that will protect both features should be enacted. Further research should investigate other vertical UHI properties like façade and roof material that can effectively account for its effect on UHI.
Kokoelmat
  • Opinnäytetyöt (Avoin kokoelma)
Ammattikorkeakoulujen opinnäytetyöt ja julkaisut
Yhteydenotto | Tietoa käyttöoikeuksista | Tietosuojailmoitus | Saavutettavuusseloste
 

Selaa kokoelmaa

NimekkeetTekijätJulkaisuajatKoulutusalatAsiasanatUusimmatKokoelmat

Henkilökunnalle

Ammattikorkeakoulujen opinnäytetyöt ja julkaisut
Yhteydenotto | Tietoa käyttöoikeuksista | Tietosuojailmoitus | Saavutettavuusseloste