TY - GEN
T1 - Automated Underground Water Leakage Detection with Machine Learning Analysis of Satellite Imagery
AU - Arabi, Shiva
AU - Grau, David
N1 - Publisher Copyright:
© CRC 2024. All rights reserved.
PY - 2024
Y1 - 2024
N2 - Increasing water shortages, droughts, and global warming demand methods to rapidly detect underground water leaks. Conventional techniques are costly, time-consuming, and error-prone. However, remote sensing techniques can offer innovative solutions. Previous studies mostly used optical sensors. However, optical data has limitations, including noise interference, limited null subsurface penetration, and weather dependency. Therefore, the study in this paper aims at exploring the combination of radar satellite data and machine learning to automatically identify underground water leakages. Radar data offers sensitivity to soil moisture below the surface. Moreover, image texture features were leveraged from dual-polarized radar data to enhance prediction. Gray-level co-occurrence matrix texture features were combined with backscattering coefficients to create a feature space that could better train the random forest. Results indicate the ability to automatically detect 69% of underground leaks with subsurface moisture alone, which lists, tables, figures, display equations, footnotes, or references.
AB - Increasing water shortages, droughts, and global warming demand methods to rapidly detect underground water leaks. Conventional techniques are costly, time-consuming, and error-prone. However, remote sensing techniques can offer innovative solutions. Previous studies mostly used optical sensors. However, optical data has limitations, including noise interference, limited null subsurface penetration, and weather dependency. Therefore, the study in this paper aims at exploring the combination of radar satellite data and machine learning to automatically identify underground water leakages. Radar data offers sensitivity to soil moisture below the surface. Moreover, image texture features were leveraged from dual-polarized radar data to enhance prediction. Gray-level co-occurrence matrix texture features were combined with backscattering coefficients to create a feature space that could better train the random forest. Results indicate the ability to automatically detect 69% of underground leaks with subsurface moisture alone, which lists, tables, figures, display equations, footnotes, or references.
UR - http://www.scopus.com/inward/record.url?scp=85188663756&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85188663756&partnerID=8YFLogxK
U2 - 10.1061/9780784485279.074
DO - 10.1061/9780784485279.074
M3 - Conference contribution
AN - SCOPUS:85188663756
T3 - Construction Research Congress 2024, CRC 2024
SP - 741
EP - 750
BT - Sustainability, Resilience, Infrastructure Systems, and Materials Design in Construction
A2 - Shane, Jennifer S.
A2 - Madson, Katherine M.
A2 - Mo, Yunjeong
A2 - Poleacovschi, Cristina
A2 - Sturgill, Roy E.
PB - American Society of Civil Engineers (ASCE)
T2 - Construction Research Congress 2024, CRC 2024
Y2 - 20 March 2024 through 23 March 2024
ER -