Early Detection of Pipeline Natural Gas Leakage from Hyperspectral Imaging by Vegetation Indicators and Deep Neural Networks

Pengfei Ma; Tarutal Ghosh Mondal; Zhenhua Shi; Mohammad Hossein Afsharmovahed; Kevin Romans; Liujun Li; Ying Zhuo; Genda Chen

doi:10.1021/acs.est.4c03345

Early Detection of Pipeline Natural Gas Leakage from Hyperspectral Imaging by Vegetation Indicators and Deep Neural Networks

Pengfei Ma
, Tarutal Ghosh Mondal
, Zhenhua Shi
, Mohammad Hossein Afsharmovahed
, Kevin Romans
, Liujun Li
, Ying Zhuo
, Genda Chen

Civil, Architectural and Environmental Engineering

Missouri University of Science and Technology
Indian Institute of Technology Bhubaneswar
University of Idaho

Research output: Contribution to journal › Article › peer-review

Original language	English
Pages (from-to)	12018-12027
Number of pages	10
Journal	Environmental Science and Technology
Volume	58
Issue number	27
DOIs	https://doi.org/10.1021/acs.est.4c03345
State	Published - Jul 9 2024

ASJC Scopus Subject Areas

General Chemistry
Environmental Chemistry

Keywords

DNN
Greenhouse gas (GHG)
hyperspectral imaging
machine learning
pipeline leak detection
remote sensing
vegetation indicators

Access to Document

10.1021/acs.est.4c03345

Cite this

@article{90f42cf2c8d54ce08ad456a399405ed9,

title = "Early Detection of Pipeline Natural Gas Leakage from Hyperspectral Imaging by Vegetation Indicators and Deep Neural Networks",

keywords = "DNN, Greenhouse gas (GHG), hyperspectral imaging, machine learning, pipeline leak detection, remote sensing, vegetation indicators",

author = "Pengfei Ma and Mondal, \{Tarutal Ghosh\} and Zhenhua Shi and Afsharmovahed, \{Mohammad Hossein\} and Kevin Romans and Liujun Li and Ying Zhuo and Genda Chen",

note = "Publisher Copyright: {\textcopyright} 2024 American Chemical Society.",

year = "2024",

month = jul,

day = "9",

doi = "10.1021/acs.est.4c03345",

language = "English",

volume = "58",

pages = "12018--12027",

journal = "Environmental Science and Technology",

issn = "0013-936X",

number = "27",

}

TY - JOUR

T1 - Early Detection of Pipeline Natural Gas Leakage from Hyperspectral Imaging by Vegetation Indicators and Deep Neural Networks

AU - Ma, Pengfei

AU - Mondal, Tarutal Ghosh

AU - Shi, Zhenhua

AU - Afsharmovahed, Mohammad Hossein

AU - Romans, Kevin

AU - Li, Liujun

AU - Zhuo, Ying

AU - Chen, Genda

PY - 2024/7/9

Y1 - 2024/7/9

KW - DNN

KW - Greenhouse gas (GHG)

KW - hyperspectral imaging

KW - machine learning

KW - pipeline leak detection

KW - remote sensing

KW - vegetation indicators

UR - https://www.scopus.com/pages/publications/85196393599

UR - https://www.scopus.com/pages/publications/85196393599#tab=citedBy

U2 - 10.1021/acs.est.4c03345

DO - 10.1021/acs.est.4c03345

M3 - Article

C2 - 38875010

AN - SCOPUS:85196393599

SN - 0013-936X

VL - 58

SP - 12018

EP - 12027

JO - Environmental Science and Technology

JF - Environmental Science and Technology

IS - 27

ER -

Early Detection of Pipeline Natural Gas Leakage from Hyperspectral Imaging by Vegetation Indicators and Deep Neural Networks

ASJC Scopus Subject Areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this