東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Hydrocarbon Seepage in the Gulf of Mexico : = Machine Learning Approach to Hydrocarbon Exploration.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Hydrocarbon Seepage in the Gulf of Mexico :/
其他題名:	Machine Learning Approach to Hydrocarbon Exploration.
作者:	Antwi, Ernest.
面頁冊數:	1 online resource (188 pages)
附註:	Source: Masters Abstracts International, Volume: 83-01.
Contained By:	Masters Abstracts International83-01.
標題:	Geology. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28498222click for full text (PQDT)
ISBN:	9798522906948

Hydrocarbon Seepage in the Gulf of Mexico : = Machine Learning Approach to Hydrocarbon Exploration.
Antwi, Ernest.

Hydrocarbon Seepage in the Gulf of Mexico :Machine Learning Approach to Hydrocarbon Exploration. - 1 online resource (188 pages)

Source: Masters Abstracts International, Volume: 83-01.

Thesis (M.S.)--University of Louisiana at Lafayette, 2021.

Includes bibliographical references

The Gulf of Mexico (GOM) basin is documented by researchers to hold a substantial quantity of hydrocarbon seeps. The Bureau of Energy and Ocean Management (BOEM) has mapped over 37000 amplitude anomalies of hydrocarbon seeps. Since the advent of hydrocarbon exploration, hydrocarbon seeps have been used as direct indicators for oil reservoirs.The use of data analysis and Machine Learning (ML) has been on the rise in almost every industry since they come with the advantage of employing high computing power to finding solutions to complex problems more accurately and faster.This project collected about 32000 hydrocarbon seep anomalies (positive, negative, and pockmarks) from BOEM and estimated the areas for the 404 gas and 168 oil fields using production wells coordinates in the project area provided by TGS LongBow. Only 698 of the hydrocarbon seep anomalies were contained in 69 out of the 572 estimated fields. A logistic regression model was built for the gas and oil fields in the hope that the model will utilize the seeps in making predictions on prolific oil or gas fields in the GOM basin. The prolific gas and prolific oil thresholds were set at the 50th percentile of their original reserves in the GOM Basin. The model did not select any of the hydrocarbon seeps in making predictions on both the gas and oil data. It had a prediction accuracy of 80.3% and 70.18% for the gas and oil fields respectively. There is evidence from the data analyses that the positive seep and the joint positive and negative seeps are highly correlated to the prolific gas fields while the positive seeps, positive and negative seeps and the combined positive, negative and pockmark seeps show high affinity for prolific oil fields, however, the data were not enough for the model to utilize them.

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

Mode of access: World Wide Web

ISBN: 9798522906948Subjects--Topical Terms:

516570
Geology.
Subjects--Index Terms:

Oil fieldsIndex Terms--Genre/Form:

542853
Electronic books.

Hydrocarbon Seepage in the Gulf of Mexico : = Machine Learning Approach to Hydrocarbon Exploration.
LDR:03151nmm a2200385K 4500 001 2361341
005 20231019120559.5
006 m o d
007 cr mn ---uuuuu
008 241011s2021 xx obm 000 0 eng d
020 $a 9798522906948
035 $a (MiAaPQ)AAI28498222
035 $a AAI28498222
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Antwi, Ernest. $3 3702000
245 1 0 $a Hydrocarbon Seepage in the Gulf of Mexico : $b Machine Learning Approach to Hydrocarbon Exploration.
264 0 $c 2021
300 $a 1 online resource (188 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: 83-01.
500 $a Advisor: Oppo, Davide.
502 $a Thesis (M.S.)--University of Louisiana at Lafayette, 2021.
504 $a Includes bibliographical references
520 $a The Gulf of Mexico (GOM) basin is documented by researchers to hold a substantial quantity of hydrocarbon seeps. The Bureau of Energy and Ocean Management (BOEM) has mapped over 37000 amplitude anomalies of hydrocarbon seeps. Since the advent of hydrocarbon exploration, hydrocarbon seeps have been used as direct indicators for oil reservoirs.The use of data analysis and Machine Learning (ML) has been on the rise in almost every industry since they come with the advantage of employing high computing power to finding solutions to complex problems more accurately and faster.This project collected about 32000 hydrocarbon seep anomalies (positive, negative, and pockmarks) from BOEM and estimated the areas for the 404 gas and 168 oil fields using production wells coordinates in the project area provided by TGS LongBow. Only 698 of the hydrocarbon seep anomalies were contained in 69 out of the 572 estimated fields. A logistic regression model was built for the gas and oil fields in the hope that the model will utilize the seeps in making predictions on prolific oil or gas fields in the GOM basin. The prolific gas and prolific oil thresholds were set at the 50th percentile of their original reserves in the GOM Basin. The model did not select any of the hydrocarbon seeps in making predictions on both the gas and oil data. It had a prediction accuracy of 80.3% and 70.18% for the gas and oil fields respectively. There is evidence from the data analyses that the positive seep and the joint positive and negative seeps are highly correlated to the prolific gas fields while the positive seeps, positive and negative seeps and the combined positive, negative and pockmark seeps show high affinity for prolific oil fields, however, the data were not enough for the model to utilize them.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Geology. $3 516570
650 4 $a Petroleum geology. $3 3173827
650 4 $a Artificial intelligence. $3 516317
650 4 $a Research. $3 531893
650 4 $a Oil reserves. $3 3702002
650 4 $a Datasets. $3 3541416
650 4 $a Hydrocarbons. $3 697428
650 4 $a Fault lines. $3 3642058
650 4 $a Oil fields. $3 555888
650 4 $a Decision making. $3 517204
650 4 $a Energy management. $3 3680718
650 4 $a Variables. $3 3548259
650 4 $a Algorithms. $3 536374
650 4 $a Libraries. $3 525303
650 4 $a Sedimentation & deposition. $3 3566241
650 4 $a Natural gas reserves. $3 607335
650 4 $a Polygons. $3 3252250
653 $a Oil fields
653 $a Natural gas deposits
653 $a Machine learning
653 $a Hydrocarbon exploration
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0372
690 $a 0800
690 $a 0583
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a University of Louisiana at Lafayette. $b Geology. $3 3702001
773 0 $t Masters Abstracts International $g 83-01.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28498222 $z click for full text (PQDT)