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

Modeling Sea Level Rise in Louisiana...

Annan, Jacob Banafo,

Linked to FindBook

Google Book

Amazon

博客來

Modeling Sea Level Rise in Louisiana Using Machine Learning Algorithms /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Modeling Sea Level Rise in Louisiana Using Machine Learning Algorithms // Jacob Banafo Annan.
Author:	Annan, Jacob Banafo,
Description:	1 electronic resource (107 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 87-05, Section: B.
Contained By:	Dissertations Abstracts International87-05B.
Subject:	Urban forestry. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32117633
ISBN:	9798297971363

Modeling Sea Level Rise in Louisiana Using Machine Learning Algorithms /
Annan, Jacob Banafo,

Modeling Sea Level Rise in Louisiana Using Machine Learning Algorithms /Jacob Banafo Annan. - 1 electronic resource (107 pages)

Source: Dissertations Abstracts International, Volume: 87-05, Section: B.

Sea level rise is an escalating global challenge, particularly for coastal regions such as Louisiana, where subsidence, extreme weather events, and climate-induced factors contribute to heightened vulnerability. This study employs advanced machine learning methodologies, specifically the ELM, XGBoost and Random Forest models, to predict sea level rise and assess the vulnerability of different parishes. The predictive performance of all models was rigorously evaluated using multiple statistical metrics. The ELM, XGBoost and Random Forest models performed well in predicting sea level according to the performance metrices, but the Extreme Learning model with MAE value of 0.75 and an R-squared value of 0.78, demonstrated comparable performance and a stronger capacity for generalization of sea level prediction. A vulnerability assessment revealed that parishes such as Terrebonne, Saint Charles, and Plaquemines exhibit the highest susceptibility to sea level rise, with vulnerability scores exceeding 0.75. In contrast, parishes including Bienville, Vernon, and Claiborne were identified as the least vulnerable, with scores below 0.20. Notably, previously considered low-risk regions such as Saint Mary and Lafayette have now been classified as highly vulnerable, emphasizing the dynamic nature of climate change impacts. It was also determined that Population growth in Louisiana has generally increased over the period considered.The findings of this study provide critical insights into the regional disparities in sea level rise vulnerability, coupled together with Land Cover Land use of the most vulnerable Parishes in Louisiana, highlighting the need for targeted mitigation strategies, infrastructure adaptation, and policy interventions. By integrating machine learning-based predictive modeling with empirical vulnerability assessments, this research contributes to the advancement of coastal resilience frameworks. The study underscores the necessity of incorporating high-accuracy predictive tools into environmental planning to enhance preparedness and minimize the socio-economic consequences of sea level rise in Louisiana and other coastal regions worldwide.

English

ISBN: 9798297971363Subjects--Topical Terms:

704817
Urban forestry.
Subjects--Index Terms:

Land cover

Modeling Sea Level Rise in Louisiana Using Machine Learning Algorithms /
LDR:03719nmm a22004573i 4500 001 2438120
005 20251130221838.5
006 m o d
007 cr|nu||||||||
008 261011s2025 miu||||||m |||||||eng d
020 $a 9798297971363
035 $a (MiAaPQD)AAI32117633
035 $a AAI32117633
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Annan, Jacob Banafo, $e author. $0 (orcid)0009-0007-1503-7980 $3 3829325
245 1 0 $a Modeling Sea Level Rise in Louisiana Using Machine Learning Algorithms / $c Jacob Banafo Annan.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (107 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: Dissertations Abstracts International, Volume: 87-05, Section: B.
500 $a Advisors: Twumasi, Yaw A. Committee members: Ning, Zhu; Ferchaud, Vanessa; Chappell, Christopher; Beshera, Kebede.
502 $b Ph.D. $c Southern University and Agricultural and Mechanical College $d 2025.
520 $a Sea level rise is an escalating global challenge, particularly for coastal regions such as Louisiana, where subsidence, extreme weather events, and climate-induced factors contribute to heightened vulnerability. This study employs advanced machine learning methodologies, specifically the ELM, XGBoost and Random Forest models, to predict sea level rise and assess the vulnerability of different parishes. The predictive performance of all models was rigorously evaluated using multiple statistical metrics. The ELM, XGBoost and Random Forest models performed well in predicting sea level according to the performance metrices, but the Extreme Learning model with MAE value of 0.75 and an R-squared value of 0.78, demonstrated comparable performance and a stronger capacity for generalization of sea level prediction. A vulnerability assessment revealed that parishes such as Terrebonne, Saint Charles, and Plaquemines exhibit the highest susceptibility to sea level rise, with vulnerability scores exceeding 0.75. In contrast, parishes including Bienville, Vernon, and Claiborne were identified as the least vulnerable, with scores below 0.20. Notably, previously considered low-risk regions such as Saint Mary and Lafayette have now been classified as highly vulnerable, emphasizing the dynamic nature of climate change impacts. It was also determined that Population growth in Louisiana has generally increased over the period considered.The findings of this study provide critical insights into the regional disparities in sea level rise vulnerability, coupled together with Land Cover Land use of the most vulnerable Parishes in Louisiana, highlighting the need for targeted mitigation strategies, infrastructure adaptation, and policy interventions. By integrating machine learning-based predictive modeling with empirical vulnerability assessments, this research contributes to the advancement of coastal resilience frameworks. The study underscores the necessity of incorporating high-accuracy predictive tools into environmental planning to enhance preparedness and minimize the socio-economic consequences of sea level rise in Louisiana and other coastal regions worldwide.
546 $a English
590 $a School code: 1218
650 4 $a Urban forestry. $3 704817
650 4 $a Ecology. $3 516476
650 4 $a Biological oceanography. $3 2122748
653 $a Land cover
653 $a Land use
653 $a Machine learning
653 $a Population decline
653 $a Population growth
653 $a Sea level
690 $a 0281
690 $a 0800
690 $a 0416
690 $a 0329
710 2 $a Southern University and Agricultural and Mechanical College. $b Urban Forestry. $e degree granting institution. $3 3765702
720 1 $a Twumasi, Yaw A. $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 87-05B.
790 $a 1218
791 $a Ph.D.
792 $a 2025
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32117633