Early Detection of Pipeline Natural Gas Leakage from Hyperspectral Imaging by Vegetation Indicators and Deep Neural Networks
Environmental Science & Technology · 2024-07-09 · 58 (27) · 12018-12027
DOI: 10.1021/acs.est.4c03345 ↗At a glance
Journal article in Environmental Science & Technology, published online on 2024-06-14. Written by Pengfei Ma and 7 co-authors. Institution: Department of Civil, Architectural and Environmental Engineering, Missouri University of Science and Technology, Rolla, Missouri 65401, United States. Major MEDLINE topics: Neural Networks, Computer, Natural Gas. Cited 24 times so far (Crossref); 57 references. Funded by: Pipeline and Hazardous Materials Safety Administration.
Abstract (original language)
The timely detection of underground natural gas (NG) leaks in pipeline transmission systems presents a promising opportunity for reducing the potential greenhouse gas (GHG) emission. However, existing techniques face notable limitations for prompt detection. This study explores the utility of Vegetation Indicators (VIs) to reflect vegetation health deterioration, thereby representing leak-induced stress. Despite the acknowledged potential of VIs, their sensitivity and separability remain understudied. In this study, we employed ground vegetation as biosensors for detecting methane emissions from underground pipelines. Hyperspectral imaging from vegetation was collected weekly at both plant and leaf scales over two months to facilitate stress detection using VIs and Deep Neural Networks (DNNs). Our findings revealed that plant pigment-related VIs, modified chlorophyll absorption reflectance index (MCARI), exhibit commendable sensitivity but limited separability in discerning stressed grasses. A NG-specialized VI, the optimized soil-adjusted vegetation index (OSAVI), demonstrates higher sensitivity and separability in early detection of methane leaks. Notably, the OSAVI proved capable of discriminating vegetation stress 21 days after methane exposure initiation. DNNs identified the methane leaks following a 3-week methane treatment with an accuracy of 98.2%. DNN results indicated an increase in visible (VIS) and a decrease in near-infrared (NIR) in spectra due to methane exposure.
Subjects
MeSH terms (MEDLINE)
Author keywords
Substances
Authors and institutions
- Department of Civil, Architectural and Environmental Engineering, Missouri University of Science and Technology, Rolla, Missouri 65401, United States.
- School of Infrastructure, Indian Institute of Technology, Bhubaneswar, Odisha 752050, India.
- Department of Soil and Water Systems, University of Idaho, Moscow, Idaho 83844, United States.
ORCID profiles: Mohammad Hossein Afsharmovahed, Genda Chen
Funding
- Pipeline and Hazardous Materials Safety Administration
Cite
APA
Ma, P., Mondal, T. G., Shi, Z., Afsharmovahed, M. H., Romans, K., Li, L., Zhuo, Y., & Chen, G. (2024). Early Detection of Pipeline Natural Gas Leakage from Hyperspectral Imaging by Vegetation Indicators and Deep Neural Networks. Environmental Science & Technology, 58(27), 12018-12027. https://doi.org/10.1021/acs.est.4c03345
Vancouver
Ma P, Mondal TG, Shi Z, Afsharmovahed MH, Romans K, Li L, et al. Early Detection of Pipeline Natural Gas Leakage from Hyperspectral Imaging by Vegetation Indicators and Deep Neural Networks. Environmental Science & Technology. 2024;58(27):12018-12027. doi:10.1021/acs.est.4c03345
BibTeX
@article{Ma2024,
author = {Ma, Pengfei and Mondal, Tarutal Ghosh and Shi, Zhenhua and Afsharmovahed, Mohammad Hossein and Romans, Kevin and Li, Liujun and Zhuo, Ying and Chen, Genda},
title = {Early Detection of Pipeline Natural Gas Leakage from Hyperspectral Imaging by Vegetation Indicators and Deep Neural Networks},
journal = {Environmental Science & Technology},
year = {2024},
volume = {58},
number = {27},
pages = {12018--12027},
doi = {10.1021/acs.est.4c03345}
}
EUVIMED