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

Linked to FindBook

Google Book

Amazon

博客來

Overcoming Data Limitation Challenges in Predicting Tropical Storm Surge with Interpretable Machine Learning Methods.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Overcoming Data Limitation Challenges in Predicting Tropical Storm Surge with Interpretable Machine Learning Methods./
Author:	Stanton, Carly Yvonne.
Description:	1 online resource (91 pages)
Notes:	Source: Masters Abstracts International, Volume: 85-03.
Contained By:	Masters Abstracts International85-03.
Subject:	Hydrologic sciences. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30568687click for full text (PQDT)
ISBN:	9798380338639

Overcoming Data Limitation Challenges in Predicting Tropical Storm Surge with Interpretable Machine Learning Methods.
Stanton, Carly Yvonne.

Overcoming Data Limitation Challenges in Predicting Tropical Storm Surge with Interpretable Machine Learning Methods. - 1 online resource (91 pages)

Source: Masters Abstracts International, Volume: 85-03.

Thesis (M.S.)--Texas A&M University - Corpus Christi, 2023.

Includes bibliographical references

The impacts of climate change have increased the risk of storm surge flooding in coastal areas. Tropical islands are especially vulnerable to the effects of sea level rise and the increase in frequency and intensity of tropical cyclones (TCs). Typically, storm surge prediction is performed using a combination of numerical forecasting models, synoptic forecasting, and statistical methods. Machine learning techniques, particularly convolutional neural networks (CNNs), have shown promise in accurately predicting storm surge levels in the short term. However, deep learning methods are computationally expensive and require large amounts of data to train their models. Often researchers must train neural network models on synthetic data generated by numerical models. The goal of this work is to study the effectiveness of simpler, interpretable models, including random forest (RF) regression, multiple linear regression (MLR), and support vector machine regression (SVR), to predict storm surge in San Juan Bay, Puerto Rico using limited local meteorological and tidal data and hurricane reanalysis data from actual storm events over the last few decades. These algorithms were used to predict surge at five different lead times from one hour to 24 hours and were trained on three different feature sets with two different types of training data windows. Models were trained using a leave-one-out cross-validation (LOOCV) approach, in which data for one TC was separated out for each model as a validation dataset. The performance of the models and different training methods was compared in terms of root mean square error (RMSE), normalized RMSE, and error at peak surge. It was found that an RF model trained on data from only eight TCs was able to predict the peak surge of Hurricane Irma to within about 0.03 m and predicted time of peak surge within three hours at lead times up to 12 hours as long as one extreme TC event, in this case Hurricane Maria, was included in the training data. However, all models failed to accurately predict surge for Hurricane Maria, even when including other high-surge storms in the training data. Other training methods achieved lower RMSE when validated against a peak surge window from the 12 hours prior to 12 hours after peak surge, but could not approach the accuracy of the RF model at predicting the time of peak surge.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798380338639Subjects--Topical Terms:

3168407
Hydrologic sciences.
Subjects--Index Terms:

Machine learningIndex Terms--Genre/Form:

542853
Electronic books.

Overcoming Data Limitation Challenges in Predicting Tropical Storm Surge with Interpretable Machine Learning Methods.
LDR:03768nmm a2200397K 4500 001 2363231
005 20231116093831.5
006 m o d
007 cr mn ---uuuuu
008 241011s2023 xx obm 000 0 eng d
020 $a 9798380338639
035 $a (MiAaPQ)AAI30568687
035 $a AAI30568687
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Stanton, Carly Yvonne. $3 3703985
245 1 0 $a Overcoming Data Limitation Challenges in Predicting Tropical Storm Surge with Interpretable Machine Learning Methods.
264 0 $c 2023
300 $a 1 online resource (91 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: 85-03.
500 $a Advisor: King, Scott.
502 $a Thesis (M.S.)--Texas A&M University - Corpus Christi, 2023.
504 $a Includes bibliographical references
520 $a The impacts of climate change have increased the risk of storm surge flooding in coastal areas. Tropical islands are especially vulnerable to the effects of sea level rise and the increase in frequency and intensity of tropical cyclones (TCs). Typically, storm surge prediction is performed using a combination of numerical forecasting models, synoptic forecasting, and statistical methods. Machine learning techniques, particularly convolutional neural networks (CNNs), have shown promise in accurately predicting storm surge levels in the short term. However, deep learning methods are computationally expensive and require large amounts of data to train their models. Often researchers must train neural network models on synthetic data generated by numerical models. The goal of this work is to study the effectiveness of simpler, interpretable models, including random forest (RF) regression, multiple linear regression (MLR), and support vector machine regression (SVR), to predict storm surge in San Juan Bay, Puerto Rico using limited local meteorological and tidal data and hurricane reanalysis data from actual storm events over the last few decades. These algorithms were used to predict surge at five different lead times from one hour to 24 hours and were trained on three different feature sets with two different types of training data windows. Models were trained using a leave-one-out cross-validation (LOOCV) approach, in which data for one TC was separated out for each model as a validation dataset. The performance of the models and different training methods was compared in terms of root mean square error (RMSE), normalized RMSE, and error at peak surge. It was found that an RF model trained on data from only eight TCs was able to predict the peak surge of Hurricane Irma to within about 0.03 m and predicted time of peak surge within three hours at lead times up to 12 hours as long as one extreme TC event, in this case Hurricane Maria, was included in the training data. However, all models failed to accurately predict surge for Hurricane Maria, even when including other high-surge storms in the training data. Other training methods achieved lower RMSE when validated against a peak surge window from the 12 hours prior to 12 hours after peak surge, but could not approach the accuracy of the RF model at predicting the time of peak surge.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Hydrologic sciences. $3 3168407
650 4 $a Meteorology. $3 542822
653 $a Machine learning
653 $a Predictive analytics
653 $a Random forests
653 $a Storm surge
653 $a Tropical cyclone
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0800
690 $a 0388
690 $a 0557
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a Texas A&M University - Corpus Christi. $b Computer Science. $3 3285562
773 0 $t Masters Abstracts International $g 85-03.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30568687 $z click for full text (PQDT)