Next Article in Journal
Behaviors and Trends toward Routine Maintenance and Major Repairs of Afridev Handpumps in Rural Malawi
Previous Article in Journal
Land Use Change Influences Ecosystem Function in Headwater Streams of the Lowland Amazon Basin
Article

Can Deep Learning Extract Useful Information about Energy Dissipation and Effective Hydraulic Conductivity from Gridded Conductivity Fields?

Department of Hydrology and Atmospheric Sciences, University of Arizona, Tucson, AZ 85721, USA
*
Author to whom correspondence should be addressed.
Academic Editors: Paweł M. Rowiński and Helena M. Ramos
Water 2021, 13(12), 1668; https://doi.org/10.3390/w13121668
Received: 14 April 2021 / Revised: 27 May 2021 / Accepted: 10 June 2021 / Published: 15 June 2021
(This article belongs to the Section Hydrology)
We confirm that energy dissipation weighting provides the most accurate approach to determining the effective hydraulic conductivity (Keff) of a binary K grid. A deep learning algorithm (UNET) can infer Keff with extremely high accuracy (R2 > 0.99). The UNET architecture could be trained to infer the energy dissipation weighting pattern from an image of the K distribution, although it was less accurate for cases with highly localized structures that controlled flow. Furthermore, the UNET architecture learned to infer the energy dissipation weighting even if it was not trained directly on this information. However, the weights were represented within the UNET in a way that was not immediately interpretable by a human user. This reiterates the idea that even if ML/DL algorithms are trained to make some hydrologic predictions accurately, they must be designed and trained to provide each user-required output if their results are to be used to improve our understanding of hydrologic systems. View Full-Text
Keywords: deep learning; machine learning; hydrogeology; effective hydraulic conductivity; energy dissipation; UNET; hidden layer representation; centered kernel alignment deep learning; machine learning; hydrogeology; effective hydraulic conductivity; energy dissipation; UNET; hidden layer representation; centered kernel alignment
Show Figures

Figure 1

MDPI and ACS Style

Moghaddam, M.A.; Ferre, P.A.T.; Ehsani, M.R.; Klakovich, J.; Gupta, H.V. Can Deep Learning Extract Useful Information about Energy Dissipation and Effective Hydraulic Conductivity from Gridded Conductivity Fields? Water 2021, 13, 1668. https://doi.org/10.3390/w13121668

AMA Style

Moghaddam MA, Ferre PAT, Ehsani MR, Klakovich J, Gupta HV. Can Deep Learning Extract Useful Information about Energy Dissipation and Effective Hydraulic Conductivity from Gridded Conductivity Fields? Water. 2021; 13(12):1668. https://doi.org/10.3390/w13121668

Chicago/Turabian Style

Moghaddam, Mohammad A., Paul A.T. Ferre, Mohammad R. Ehsani, Jeffrey Klakovich, and Hoshin V. Gupta 2021. "Can Deep Learning Extract Useful Information about Energy Dissipation and Effective Hydraulic Conductivity from Gridded Conductivity Fields?" Water 13, no. 12: 1668. https://doi.org/10.3390/w13121668

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop